Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/5830#discussion_r29741566
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/reduction/OneVsRestClassifier.scala ---
@@ -0,0 +1,175 @@
+/*
+ * 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.reduction
+
+
+import scala.language.existentials
+
+import org.apache.spark.annotation.{AlphaComponent, DeveloperApi}
+import org.apache.spark.ml.{Estimator, Model}
+import org.apache.spark.ml.attribute.BinaryAttribute
+import org.apache.spark.ml.classification.{ClassificationModel,
Classifier, ClassifierParams}
+import org.apache.spark.ml.param.Param
+import org.apache.spark.ml.util.{MetadataUtils, SchemaUtils}
+import org.apache.spark.mllib.linalg._
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{DataFrame, Row}
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types._
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for [[OneVsRestClassifier]].
+ */
+private[ml] trait OneVsRestParams extends ClassifierParams {
+
+ type ClassifierType = Classifier[F, E, M] forSome {
+ type F ;
+ type M <: ClassificationModel[F,M];
+ type E <: Classifier[F, E,M]
+ }
+
+ /**
+ * param for the base classifier that we reduce multiclass
classification into.
+ * @group param
+ */
+ val baseClassifier: Param[ClassifierType] =
+ new Param(this, "baseClassifier", "base binary classifier/regressor ")
+
+ /** @group getParam */
+ def getBaseClassifier: ClassifierType = getOrDefault(baseClassifier)
+
+}
+
+/**
+ *
+ * @param parent
+ * @param baseClassificationModels the binary classification models for
reduction.
+ */
+@AlphaComponent
+private[ml] class OneVsRestModel(
+ override val parent: OneVsRestClassifier,
+ val baseClassificationModels: Array[Model[_]])
+ extends Model[OneVsRestModel] with OneVsRestParams {
+
+ /**
+ * Transforms the dataset with provided parameter map as additional
parameters.
+ * @param dataset input dataset
+ * @return transformed dataset
+ */
+ override def transform(dataset: DataFrame): DataFrame = {
+ // Check schema
+ val parentSchema = dataset.schema
+ transformSchema(parentSchema, logging = true)
+ val sqlCtx = dataset.sqlContext
+
+ // score each model on every data point and pick the model with
highest score
+ val predictions = baseClassificationModels.zipWithIndex.par.map { case
(model, index) =>
+ val output = model.transform(dataset)
+ output.select($(rawPredictionCol)).map { case Row(p: Vector) =>
List((index, p(1))) }
+ }.reduce[RDD[List[(Int, Double)]]] { case (x, y) =>
+ x.zip(y).map { case ((a, b)) =>
--- End diff --
We should leave a TODO here to tune performance. It would be nice if we can
use DataFrame expressions in the future to leverage on SQL performance
improvements.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
