[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75428713
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user asfgit closed the pull request at: https://github.com/apache/spark/pull/13796 --- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- - To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75428163
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421906
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421870
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421878
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421847
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1001 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+multinomialDataset.rdd.map { case Row(label: Double, features: Vector)
=>
+ label + "," + features.toArray.mkString(",")
+
}.repartition(1).saveAsTextFile("target/tmp/LogisticRegressionSuite/multinomialDataset")
+ }
+
+test("params") {
+ ParamsSuite.checkParams(new MultinomialLogisticRegression)
+ val model = new MultinomialLogisticRegressionModel("mLogReg",
+Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ ParamsSuite.checkParams(model)
+}
+
+test("multinomial logistic regression: default params") {
+ val mlr = new MultinomialLogisticRegression
+ assert(mlr.getLabelCol === "label")
+ assert(mlr.getFeaturesCol === "features")
+ assert(mlr.getPredictionCol === "prediction")
+ assert(mlr.getRawPredictionCol === "rawPrediction")
+ assert(mlr.getProbabilityCol === "probability")
+ assert(!mlr.isDefined(mlr.weightCol))
+ assert(!mlr.isDefined(mlr.thresholds))
+ assert(mlr.getFitIntercept)
+ assert(mlr.getStandardization)
+ val model = mlr.fit(dataset)
+ model.transform(dataset)
+.select("label", "probability", "prediction", "rawPrediction")
+.collect()
+ assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421818
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421784
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421793
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421785
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75421763
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75419042
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75418682
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75418614
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75418377
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75418198
--- Diff:
mllib/src/test/scala/org/apache/spark/ml/classification/MultinomialLogisticRegressionSuite.scala
---
@@ -0,0 +1,1016 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.language.existentials
+
+import org.apache.spark.SparkFunSuite
+import org.apache.spark.ml.attribute.NominalAttribute
+import org.apache.spark.ml.classification.LogisticRegressionSuite._
+import org.apache.spark.ml.feature.LabeledPoint
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param.ParamsSuite
+import org.apache.spark.ml.util.{DefaultReadWriteTest, MLTestingUtils}
+import org.apache.spark.ml.util.TestingUtils._
+import org.apache.spark.mllib.util.MLlibTestSparkContext
+import org.apache.spark.sql.{DataFrame, Dataset, Row}
+
+class MultinomialLogisticRegressionSuite
+ extends SparkFunSuite with MLlibTestSparkContext with
DefaultReadWriteTest {
+
+ @transient var dataset: Dataset[_] = _
+ @transient var multinomialDataset: DataFrame = _
+ private val eps: Double = 1e-5
+
+ override def beforeAll(): Unit = {
+super.beforeAll()
+
+dataset = {
+ val nPoints = 100
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077,
+-0.16624, -0.84355, -0.048509)
+
+ val xMean = Array(5.843, 3.057)
+ val xVariance = Array(0.6856, 0.1899)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+
+multinomialDataset = {
+ val nPoints = 1
+ val coefficients = Array(
+-0.57997, 0.912083, -0.371077, -0.819866, 2.688191,
+-0.16624, -0.84355, -0.048509, -0.301789, 4.170682)
+
+ val xMean = Array(5.843, 3.057, 3.758, 1.199)
+ val xVariance = Array(0.6856, 0.1899, 3.116, 0.581)
+
+ val testData = generateMultinomialLogisticInput(
+coefficients, xMean, xVariance, addIntercept = true, nPoints, 42)
+
+ val df = spark.createDataFrame(sc.parallelize(testData, 4))
+ df.cache()
+ df
+}
+ }
+
+ /**
+ * Enable the ignored test to export the dataset into CSV format,
+ * so we can validate the training accuracy compared with R's glmnet
package.
+ */
+ ignore("export test data into CSV format") {
+val rdd = multinomialDataset.rdd.map { case Row(label: Double,
features: Vector) =>
+ label + "," + features.toArray.mkString(",")
+}.repartition(1)
+
rdd.saveAsTextFile("target/tmp/MultinomialLogisticRegressionSuite/multinomialDataset")
+ }
+
+ test("params") {
+ParamsSuite.checkParams(new MultinomialLogisticRegression)
+val model = new MultinomialLogisticRegressionModel("mLogReg",
+ Matrices.dense(2, 1, Array(0.0, 0.0)), Vectors.dense(0.0, 0.0), 2)
+ParamsSuite.checkParams(model)
+ }
+
+ test("multinomial logistic regression: default params") {
+val mlr = new MultinomialLogisticRegression
+assert(mlr.getLabelCol === "label")
+assert(mlr.getFeaturesCol === "features")
+assert(mlr.getPredictionCol === "prediction")
+assert(mlr.getRawPredictionCol === "rawPrediction")
+assert(mlr.getProbabilityCol === "probability")
+assert(!mlr.isDefined(mlr.weightCol))
+assert(!mlr.isDefined(mlr.thresholds))
+assert(mlr.getFitIntercept)
+assert(mlr.getStandardization)
+val model = mlr.fit(dataset)
+model.transform(dataset)
+ .select("label", "probability", "prediction", "rawPrediction")
+ .collect()
+assert(model.getFeaturesCol === "features")
+
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75417445
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75416875
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75416580
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75415117
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75414397
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75414029
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75413862
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,619 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75407900
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75407730
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75407380
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75352968
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350270
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350253
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350213
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75351207
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -952,13 +963,160 @@ private class LogisticAggregator(
val bcFeaturesStd: Broadcast[Array[Double]],
private val numFeatures: Int,
numClasses: Int,
-fitIntercept: Boolean) extends Serializable {
+fitIntercept: Boolean,
+multinomial: Boolean) extends Serializable with Logging {
+
+ private val numFeaturesPlusIntercept = if (fitIntercept) numFeatures + 1
else numFeatures
+ private val coefficientSize = bcCoefficients.value.size
+ if (multinomial) {
+require(numClasses == coefficientSize / numFeaturesPlusIntercept,
s"The number of " +
+ s"coefficients should be ${numClasses * numFeaturesPlusIntercept}
but was $coefficientSize")
+ } else {
+require(coefficientSize == numFeaturesPlusIntercept, s"Expected
$numFeaturesPlusIntercept " +
+ s"coefficients but got $coefficientSize")
+require(numClasses <= 2, s"Binary logistic aggregator requires
numClasses in {1, 2}" +
+ s" but found $numClasses.")
+ }
private var weightSum = 0.0
private var lossSum = 0.0
- private val gradientSumArray =
-Array.ofDim[Double](if (fitIntercept) numFeatures + 1 else numFeatures)
+ private val totalCoefficientLength = {
+val cols = if (fitIntercept) numFeatures + 1 else numFeatures
+val rows = if (multinomial) numClasses else 1
+rows * cols
+ }
+
+ private val gradientSumArray =
Array.ofDim[Double](totalCoefficientLength)
+
+ if (multinomial && numClasses < 2) {
+logInfo(s"Multinomial logistic regression for binary classification
yields separate " +
+ s"coefficients for positive and negative classes. When no
regularization is applied, the" +
+ s"result will be effectively the same as binary logistic regression.
When regularization" +
+ s"is applied, multinomial loss will produce a result different from
binary loss.")
+ }
+
+ /** Update gradient and loss using binary loss function. */
+ private def binaryUpdateInPlace(
+ features: Vector,
+ weight: Double,
+ label: Double,
+ coefficients: Array[Double],
+ gradient: Array[Double],
+ featuresStd: Array[Double],
+ numFeaturesPlusIntercept: Int): Unit = {
+val margin = - {
+ var sum = 0.0
+ features.foreachActive { (index, value) =>
+if (featuresStd(index) != 0.0 && value != 0.0) {
+ sum += coefficients(index) * value / featuresStd(index)
+}
+ }
+ sum + {
+if (fitIntercept) coefficients(numFeaturesPlusIntercept - 1) else
0.0
+ }
+}
+
+val multiplier = weight * (1.0 / (1.0 + math.exp(margin)) - label)
+
+features.foreachActive { (index, value) =>
+ if (featuresStd(index) != 0.0 && value != 0.0) {
+gradient(index) += multiplier * value / featuresStd(index)
+ }
+}
+
+if (fitIntercept) {
+ gradient(numFeaturesPlusIntercept - 1) += multiplier
+}
+
+if (label > 0) {
+ // The following is equivalent to log(1 + exp(margin)) but more
numerically stable.
+ lossSum += weight * MLUtils.log1pExp(margin)
+} else {
+ lossSum += weight * (MLUtils.log1pExp(margin) - margin)
+}
+ }
+
+ /** Update gradient and loss using multinomial (softmax) loss function.
*/
+ private def multinomialUpdateInPlace(
+ features: Vector,
+ weight: Double,
+ label: Double,
+ coefficients: Array[Double],
+ gradient: Array[Double],
+ featuresStd: Array[Double],
+ numFeaturesPlusIntercept: Int): Unit = {
+// TODO: use level 2 BLAS operations
+/*
+ Note: this can still be used when numClasses = 2 for binary
+ logistic regression without pivoting.
+ */
+
+// marginOfLabel is margins(label) in the formula
+var marginOfLabel = 0.0
+var maxMargin = Double.NegativeInfinity
+
+val margins = Array.tabulate(numClasses) { i =>
+ var margin = 0.0
+ features.foreachActive { (index, value) =>
+if (featuresStd(index) != 0.0 && value != 0.0) {
+ margin += coefficients(i * numFeaturesPlusIntercept + index) *
value / featuresStd(index)
+}
+ }
+
+ if (fitIntercept) {
+margin += coefficients(i * numFeaturesPlusIntercept +
features.size)
+ }
+ if (i == label.toInt) marginOfLabel = margin
+ if (margin > maxMargin) {
+maxMargin =
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75351025
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350717
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350650
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350481
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350406
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350300
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350200
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350142
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350108
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350099
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75350080
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349959
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349924
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349907
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349892
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349872
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349819
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349849
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75349832
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75329276
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75258437
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75252926
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75250973
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75250554
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75249124
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75249109
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75249096
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75249042
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248950
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248788
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248762
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248754
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248492
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248077
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248042
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75248013
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247956
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247923
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247834
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247848
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247559
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75247386
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75246901
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75246680
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75244476
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75244241
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75244154
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75242617
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75242379
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75242328
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75241700
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75241254
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75241084
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75240214
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75239975
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75239888
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75239615
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75236167
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75236065
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,611 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic (softmax) regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic (softmax) regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75233223
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+
+ setDefault(maxIter -> 100)
+
+ /**
+ * Set the convergence tolerance of iterations.
+ * Smaller value will lead to higher accuracy with the cost of more
iterations.
+ * Default is
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230355
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -933,32 +946,312 @@ class BinaryLogisticRegressionSummary
private[classification] (
}
/**
- * LogisticAggregator computes the gradient and loss for binary logistic
loss function, as used
- * in binary classification for instances in sparse or dense vector in an
online fashion.
- *
- * Note that multinomial logistic loss is not supported yet!
+ * LogisticAggregator computes the gradient and loss for binary or
multinomial logistic (softmax)
+ * loss function, as used in classification for instances in sparse or
dense vector in an online
+ * fashion.
*
- * Two LogisticAggregator can be merged together to have a summary of loss
and gradient of
+ * Two LogisticAggregators can be merged together to have a summary of
loss and gradient of
* the corresponding joint dataset.
*
+ * For improving the convergence rate during the optimization process and
also to prevent against
+ * features with very large variances exerting an overly large influence
during model training,
+ * packages like R's GLMNET perform the scaling to unit variance and
remove the mean in order to
+ * reduce the condition number. The model is then trained in this scaled
space, but returns the
+ * coefficients in the original scale. See page 9 in
+ * http://cran.r-project.org/web/packages/glmnet/glmnet.pdf
+ *
+ * However, we don't want to apply the
[[org.apache.spark.ml.feature.StandardScaler]] on the
+ * training dataset, and then cache the standardized dataset since it will
create a lot of overhead.
+ * As a result, we perform the scaling implicitly when we compute the
objective function (though
+ * we do not subtract the mean).
+ *
+ * Note that there is a difference between multinomial (softmax) and
binary loss. The binary case
+ * uses one outcome class as a "pivot" and regresses the other class
against the pivot. In the
+ * multinomial case, the softmax loss function is used to model each class
probability
+ * independently. Using softmax loss produces `K` sets of coefficients,
while using a pivot class
+ * produces `K - 1` sets of coefficients (a single coefficient vector in
the binary case). In the
+ * binary case, we can say that the coefficients are shared between the
positive and negative
+ * classes. When regularization is applied, multinomial (softmax) loss
will produce a result
+ * different from binary loss since the positive and negative don't share
the coefficients while the
+ * binary regression shares the coefficients between positive and negative.
+ *
+ * The following is a mathematical derivation for the multinomial
(softmax) loss.
+ *
+ * The probability of the multinomial outcome $y$ taking on any of the K
possible outcomes is:
+ *
+ *
+ *$$
+ *P(y_i=0|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_0}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}} \\
+ *P(y_i=1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_1}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}\\
+ *P(y_i=K-1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_{K-1}}\,}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}
+ *$$
+ *
+ *
+ * The model coefficients $\beta = (\beta_1, \beta_2, ..., \beta_{K-1})$
become a matrix
+ * which has dimension of $K \times (N+1)$ if the intercepts are added. If
the intercepts are not
+ * added, the dimension will be $K \times N$.
+ *
+ * Note that the coefficients in the model above lack identifiability.
That is, any constant scalar
+ * can be added to all of the coefficients and the probabilities remain
the same.
+ *
+ *
+ *$$
+ *\begin{align}
+ *\frac{e^{\vec{x}_i^T \left(\vec{\beta}_0 +
\vec{c}\right)}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \left(\vec{\beta}_k + \vec{c}\right)}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}e^{\vec{x}_i^T
\vec{c}}\,}{e^{\vec{x}_i^T \vec{c}}
+ * \sum_{k=0}^{K-1} e^{\vec{x}_i^T \vec{\beta}_k}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}}{\sum_{k=0}^{K-1}
e^{\vec{x}_i^T \vec{\beta}_k}}
+ *\end{align}
+ *$$
+ *
+ *
+ * However, when regularization is added to the loss function, the
coefficients are indeed
+ * identifiable because there is only one set of coefficients which
minimizes the regularization
+ * term. When no regularization is applied, we choose the coefficients
with the minimum L2
+ * penalty for consistency and reproducibility. For further discussion see:
+ *
+ * Friedman, et al. "Regularization Paths for
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230364
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -933,32 +946,312 @@ class BinaryLogisticRegressionSummary
private[classification] (
}
/**
- * LogisticAggregator computes the gradient and loss for binary logistic
loss function, as used
- * in binary classification for instances in sparse or dense vector in an
online fashion.
- *
- * Note that multinomial logistic loss is not supported yet!
+ * LogisticAggregator computes the gradient and loss for binary or
multinomial logistic (softmax)
+ * loss function, as used in classification for instances in sparse or
dense vector in an online
+ * fashion.
*
- * Two LogisticAggregator can be merged together to have a summary of loss
and gradient of
+ * Two LogisticAggregators can be merged together to have a summary of
loss and gradient of
* the corresponding joint dataset.
*
+ * For improving the convergence rate during the optimization process and
also to prevent against
+ * features with very large variances exerting an overly large influence
during model training,
+ * packages like R's GLMNET perform the scaling to unit variance and
remove the mean in order to
+ * reduce the condition number. The model is then trained in this scaled
space, but returns the
+ * coefficients in the original scale. See page 9 in
+ * http://cran.r-project.org/web/packages/glmnet/glmnet.pdf
+ *
+ * However, we don't want to apply the
[[org.apache.spark.ml.feature.StandardScaler]] on the
+ * training dataset, and then cache the standardized dataset since it will
create a lot of overhead.
+ * As a result, we perform the scaling implicitly when we compute the
objective function (though
+ * we do not subtract the mean).
+ *
+ * Note that there is a difference between multinomial (softmax) and
binary loss. The binary case
+ * uses one outcome class as a "pivot" and regresses the other class
against the pivot. In the
+ * multinomial case, the softmax loss function is used to model each class
probability
+ * independently. Using softmax loss produces `K` sets of coefficients,
while using a pivot class
+ * produces `K - 1` sets of coefficients (a single coefficient vector in
the binary case). In the
+ * binary case, we can say that the coefficients are shared between the
positive and negative
+ * classes. When regularization is applied, multinomial (softmax) loss
will produce a result
+ * different from binary loss since the positive and negative don't share
the coefficients while the
+ * binary regression shares the coefficients between positive and negative.
+ *
+ * The following is a mathematical derivation for the multinomial
(softmax) loss.
+ *
+ * The probability of the multinomial outcome $y$ taking on any of the K
possible outcomes is:
+ *
+ *
+ *$$
+ *P(y_i=0|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_0}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}} \\
+ *P(y_i=1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_1}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}\\
+ *P(y_i=K-1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_{K-1}}\,}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}
+ *$$
+ *
+ *
+ * The model coefficients $\beta = (\beta_1, \beta_2, ..., \beta_{K-1})$
become a matrix
--- End diff --
done.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230341
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -933,32 +946,312 @@ class BinaryLogisticRegressionSummary
private[classification] (
}
/**
- * LogisticAggregator computes the gradient and loss for binary logistic
loss function, as used
- * in binary classification for instances in sparse or dense vector in an
online fashion.
- *
- * Note that multinomial logistic loss is not supported yet!
+ * LogisticAggregator computes the gradient and loss for binary or
multinomial logistic (softmax)
+ * loss function, as used in classification for instances in sparse or
dense vector in an online
+ * fashion.
*
- * Two LogisticAggregator can be merged together to have a summary of loss
and gradient of
+ * Two LogisticAggregators can be merged together to have a summary of
loss and gradient of
* the corresponding joint dataset.
*
+ * For improving the convergence rate during the optimization process and
also to prevent against
+ * features with very large variances exerting an overly large influence
during model training,
+ * packages like R's GLMNET perform the scaling to unit variance and
remove the mean in order to
+ * reduce the condition number. The model is then trained in this scaled
space, but returns the
+ * coefficients in the original scale. See page 9 in
+ * http://cran.r-project.org/web/packages/glmnet/glmnet.pdf
+ *
+ * However, we don't want to apply the
[[org.apache.spark.ml.feature.StandardScaler]] on the
+ * training dataset, and then cache the standardized dataset since it will
create a lot of overhead.
+ * As a result, we perform the scaling implicitly when we compute the
objective function (though
+ * we do not subtract the mean).
+ *
+ * Note that there is a difference between multinomial (softmax) and
binary loss. The binary case
+ * uses one outcome class as a "pivot" and regresses the other class
against the pivot. In the
+ * multinomial case, the softmax loss function is used to model each class
probability
+ * independently. Using softmax loss produces `K` sets of coefficients,
while using a pivot class
+ * produces `K - 1` sets of coefficients (a single coefficient vector in
the binary case). In the
+ * binary case, we can say that the coefficients are shared between the
positive and negative
+ * classes. When regularization is applied, multinomial (softmax) loss
will produce a result
+ * different from binary loss since the positive and negative don't share
the coefficients while the
+ * binary regression shares the coefficients between positive and negative.
+ *
+ * The following is a mathematical derivation for the multinomial
(softmax) loss.
+ *
+ * The probability of the multinomial outcome $y$ taking on any of the K
possible outcomes is:
+ *
+ *
+ *$$
+ *P(y_i=0|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_0}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}} \\
+ *P(y_i=1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_1}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}\\
+ *P(y_i=K-1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_{K-1}}\,}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}
+ *$$
+ *
+ *
+ * The model coefficients $\beta = (\beta_1, \beta_2, ..., \beta_{K-1})$
become a matrix
+ * which has dimension of $K \times (N+1)$ if the intercepts are added. If
the intercepts are not
+ * added, the dimension will be $K \times N$.
+ *
+ * Note that the coefficients in the model above lack identifiability.
That is, any constant scalar
+ * can be added to all of the coefficients and the probabilities remain
the same.
+ *
+ *
+ *$$
+ *\begin{align}
+ *\frac{e^{\vec{x}_i^T \left(\vec{\beta}_0 +
\vec{c}\right)}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \left(\vec{\beta}_k + \vec{c}\right)}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}e^{\vec{x}_i^T
\vec{c}}\,}{e^{\vec{x}_i^T \vec{c}}
+ * \sum_{k=0}^{K-1} e^{\vec{x}_i^T \vec{\beta}_k}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}}{\sum_{k=0}^{K-1}
e^{\vec{x}_i^T \vec{\beta}_k}}
+ *\end{align}
+ *$$
+ *
+ *
+ * However, when regularization is added to the loss function, the
coefficients are indeed
+ * identifiable because there is only one set of coefficients which
minimizes the regularization
+ * term. When no regularization is applied, we choose the coefficients
with the minimum L2
+ * penalty for consistency and reproducibility. For further discussion see:
+ *
+ * Friedman, et al. "Regularization Paths for
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230308
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -982,45 +1275,13 @@ private class LogisticAggregator(
"coefficients only supports dense vector" +
s"but got type ${bcCoefficients.value.getClass}.")
}
- val localGradientSumArray = gradientSumArray
-
- val featuresStd = bcFeaturesStd.value
- numClasses match {
-case 2 =>
- // For Binary Logistic Regression.
- val margin = - {
-var sum = 0.0
-features.foreachActive { (index, value) =>
- if (featuresStd(index) != 0.0 && value != 0.0) {
-sum += coefficientsArray(index) * (value /
featuresStd(index))
- }
-}
-sum + {
- if (fitIntercept) coefficientsArray(numFeatures) else 0.0
-}
- }
-
- val multiplier = weight * (1.0 / (1.0 + math.exp(margin)) -
label)
-
- features.foreachActive { (index, value) =>
-if (featuresStd(index) != 0.0 && value != 0.0) {
- localGradientSumArray(index) += multiplier * (value /
featuresStd(index))
-}
- }
-
- if (fitIntercept) {
-localGradientSumArray(numFeatures) += multiplier
- }
- if (label > 0) {
-// The following is equivalent to log(1 + exp(margin)) but
more numerically stable.
-lossSum += weight * MLUtils.log1pExp(margin)
- } else {
-lossSum += weight * (MLUtils.log1pExp(margin) - margin)
- }
-case _ =>
- new NotImplementedError("LogisticRegression with ElasticNet in
ML package " +
-"only supports binary classification for now.")
+ if (multinomial) {
+multinomialUpdateInPlace(features, weight, label,
coefficientsArray, gradientSumArray,
+ bcFeaturesStd.value, numFeaturesPlusIntercept)
--- End diff --
I removed the class variables from the functions. For the performance
critical arrays, I make local copies to inside the functions.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230334
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala
---
@@ -933,32 +946,312 @@ class BinaryLogisticRegressionSummary
private[classification] (
}
/**
- * LogisticAggregator computes the gradient and loss for binary logistic
loss function, as used
- * in binary classification for instances in sparse or dense vector in an
online fashion.
- *
- * Note that multinomial logistic loss is not supported yet!
+ * LogisticAggregator computes the gradient and loss for binary or
multinomial logistic (softmax)
+ * loss function, as used in classification for instances in sparse or
dense vector in an online
+ * fashion.
*
- * Two LogisticAggregator can be merged together to have a summary of loss
and gradient of
+ * Two LogisticAggregators can be merged together to have a summary of
loss and gradient of
* the corresponding joint dataset.
*
+ * For improving the convergence rate during the optimization process and
also to prevent against
+ * features with very large variances exerting an overly large influence
during model training,
+ * packages like R's GLMNET perform the scaling to unit variance and
remove the mean in order to
+ * reduce the condition number. The model is then trained in this scaled
space, but returns the
+ * coefficients in the original scale. See page 9 in
+ * http://cran.r-project.org/web/packages/glmnet/glmnet.pdf
+ *
+ * However, we don't want to apply the
[[org.apache.spark.ml.feature.StandardScaler]] on the
+ * training dataset, and then cache the standardized dataset since it will
create a lot of overhead.
+ * As a result, we perform the scaling implicitly when we compute the
objective function (though
+ * we do not subtract the mean).
+ *
+ * Note that there is a difference between multinomial (softmax) and
binary loss. The binary case
+ * uses one outcome class as a "pivot" and regresses the other class
against the pivot. In the
+ * multinomial case, the softmax loss function is used to model each class
probability
+ * independently. Using softmax loss produces `K` sets of coefficients,
while using a pivot class
+ * produces `K - 1` sets of coefficients (a single coefficient vector in
the binary case). In the
+ * binary case, we can say that the coefficients are shared between the
positive and negative
+ * classes. When regularization is applied, multinomial (softmax) loss
will produce a result
+ * different from binary loss since the positive and negative don't share
the coefficients while the
+ * binary regression shares the coefficients between positive and negative.
+ *
+ * The following is a mathematical derivation for the multinomial
(softmax) loss.
+ *
+ * The probability of the multinomial outcome $y$ taking on any of the K
possible outcomes is:
+ *
+ *
+ *$$
+ *P(y_i=0|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_0}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}} \\
+ *P(y_i=1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_1}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}\\
+ *P(y_i=K-1|\vec{x}_i, \beta) = \frac{e^{\vec{x}_i^T
\vec{\beta}_{K-1}}\,}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \vec{\beta}_k}}
+ *$$
+ *
+ *
+ * The model coefficients $\beta = (\beta_1, \beta_2, ..., \beta_{K-1})$
become a matrix
+ * which has dimension of $K \times (N+1)$ if the intercepts are added. If
the intercepts are not
+ * added, the dimension will be $K \times N$.
+ *
+ * Note that the coefficients in the model above lack identifiability.
That is, any constant scalar
+ * can be added to all of the coefficients and the probabilities remain
the same.
+ *
+ *
+ *$$
+ *\begin{align}
+ *\frac{e^{\vec{x}_i^T \left(\vec{\beta}_0 +
\vec{c}\right)}}{\sum_{k=0}^{K-1}
+ * e^{\vec{x}_i^T \left(\vec{\beta}_k + \vec{c}\right)}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}e^{\vec{x}_i^T
\vec{c}}\,}{e^{\vec{x}_i^T \vec{c}}
+ * \sum_{k=0}^{K-1} e^{\vec{x}_i^T \vec{\beta}_k}}
+ *= \frac{e^{\vec{x}_i^T \vec{\beta}_0}}{\sum_{k=0}^{K-1}
e^{\vec{x}_i^T \vec{\beta}_k}}
+ *\end{align}
+ *$$
+ *
+ *
+ * However, when regularization is added to the loss function, the
coefficients are indeed
+ * identifiable because there is only one set of coefficients which
minimizes the regularization
+ * term. When no regularization is applied, we choose the coefficients
with the minimum L2
+ * penalty for consistency and reproducibility. For further discussion see:
+ *
+ * Friedman, et al. "Regularization Paths for
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230177
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
+
+ setDefault(elasticNetParam -> 0.0)
+
+ /**
+ * Set the maximum number of iterations.
+ * Default is 100.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setMaxIter(value: Int): this.type = set(maxIter, value)
+
--- End diff --
done.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so,
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230202
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
--- End diff --
done.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
[GitHub] spark pull request #13796: [SPARK-7159][ML] Add multiclass logistic regressi...
Github user sethah commented on a diff in the pull request:
https://github.com/apache/spark/pull/13796#discussion_r75230184
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/classification/MultinomialLogisticRegression.scala
---
@@ -0,0 +1,622 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ *http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.ml.classification
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, LBFGS => BreezeLBFGS, OWLQN =>
BreezeOWLQN}
+import org.apache.hadoop.fs.Path
+
+import org.apache.spark.SparkException
+import org.apache.spark.annotation.{Experimental, Since}
+import org.apache.spark.internal.Logging
+import org.apache.spark.ml.feature.Instance
+import org.apache.spark.ml.linalg._
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util._
+import org.apache.spark.mllib.linalg.VectorImplicits._
+import org.apache.spark.mllib.stat.MultivariateOnlineSummarizer
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Dataset, Row}
+import org.apache.spark.sql.functions.{col, lit}
+import org.apache.spark.sql.types.DoubleType
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for multinomial logistic regression.
+ */
+private[classification] trait MultinomialLogisticRegressionParams
+ extends ProbabilisticClassifierParams with HasRegParam with
HasElasticNetParam with HasMaxIter
+with HasFitIntercept with HasTol with HasStandardization with
HasWeightCol {
+
+ /**
+ * Set thresholds in multiclass (or binary) classification to adjust the
probability of
+ * predicting each class. Array must have length equal to the number of
classes, with values >= 0.
+ * The class with largest value p/t is predicted, where p is the
original probability of that
+ * class and t is the class' threshold.
+ *
+ * @group setParam
+ */
+ def setThresholds(value: Array[Double]): this.type = {
+set(thresholds, value)
+ }
+
+ /**
+ * Get thresholds for binary or multiclass classification.
+ *
+ * @group getParam
+ */
+ override def getThresholds: Array[Double] = {
+$(thresholds)
+ }
+}
+
+/**
+ * :: Experimental ::
+ * Multinomial Logistic regression.
+ */
+@Since("2.1.0")
+@Experimental
+class MultinomialLogisticRegression @Since("2.1.0") (
+@Since("2.1.0") override val uid: String)
+ extends ProbabilisticClassifier[Vector,
+MultinomialLogisticRegression, MultinomialLogisticRegressionModel]
+with MultinomialLogisticRegressionParams with DefaultParamsWritable
with Logging {
+
+ @Since("2.1.0")
+ def this() = this(Identifiable.randomUID("mlogreg"))
+
+ /**
+ * Set the regularization parameter.
+ * Default is 0.0.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setRegParam(value: Double): this.type = set(regParam, value)
+
+ setDefault(regParam -> 0.0)
+
+ /**
+ * Set the ElasticNet mixing parameter.
+ * For alpha = 0, the penalty is an L2 penalty. For alpha = 1, it is an
L1 penalty.
+ * For 0 < alpha < 1, the penalty is a combination of L1 and L2.
+ * Default is 0.0 which is an L2 penalty.
+ *
+ * @group setParam
+ */
+ @Since("2.1.0")
+ def setElasticNetParam(value: Double): this.type = set(elasticNetParam,
value)
--- End diff --
done.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
-
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For
