Github user manishamde commented on a diff in the pull request:
https://github.com/apache/spark/pull/2607#discussion_r19499795
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/tree/GradientBoosting.scala ---
@@ -0,0 +1,433 @@
+/*
+ * 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.mllib.tree
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.annotation.Experimental
+import org.apache.spark.api.java.JavaRDD
+import org.apache.spark.mllib.tree.configuration.BoostingStrategy
+import org.apache.spark.Logging
+import org.apache.spark.mllib.tree.impl.TimeTracker
+import org.apache.spark.mllib.tree.loss.Losses
+import org.apache.spark.rdd.RDD
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.tree.model.{WeightedEnsembleModel,
DecisionTreeModel}
+import org.apache.spark.mllib.tree.configuration.Algo._
+import org.apache.spark.storage.StorageLevel
+import
org.apache.spark.mllib.tree.configuration.EnsembleCombiningStrategy.Sum
+
+/**
+ * :: Experimental ::
+ * A class that implements gradient boosting for regression problems.
+ * @param boostingStrategy Parameters for the gradient boosting algorithm
+ */
+@Experimental
+class GradientBoosting (
+ private val boostingStrategy: BoostingStrategy) extends Serializable
with Logging {
+
+ /**
+ * Method to train a gradient boosting model
+ * @param input Training dataset: RDD of
[[org.apache.spark.mllib.regression.LabeledPoint]].
+ * @return GradientBoostingModel that can be used for prediction
+ */
+ def train(input: RDD[LabeledPoint]): WeightedEnsembleModel = {
+ val algo = boostingStrategy.algo
+ algo match {
+ case Regression => GradientBoosting.boost(input, boostingStrategy)
+ case Classification =>
+ val remappedInput = input.map(x => new LabeledPoint((x.label * 2)
- 1, x.features))
+ GradientBoosting.boost(remappedInput, boostingStrategy)
+ case _ =>
+ throw new IllegalArgumentException(s"$algo is not supported by the
gradient boosting.")
+ }
+ }
+
+}
+
+
+object GradientBoosting extends Logging {
+
+ /**
+ * Method to train a gradient boosting model.
+ *
+ * Note: Using
[[org.apache.spark.mllib.tree.GradientBoosting#trainRegressor]]
--- End diff --
Will do.
---
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]
