Github user sethah commented on a diff in the pull request: https://github.com/apache/spark/pull/10607#discussion_r48907328 --- Diff: mllib/src/main/scala/org/apache/spark/ml/tree/impl/GradientBoostedTrees.scala --- @@ -0,0 +1,272 @@ +/* + * 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.tree.impl + +import org.apache.spark.Logging +import org.apache.spark.mllib.impl.PeriodicRDDCheckpointer +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.ml.regression.{DecisionTreeRegressionModel, DecisionTreeRegressor} +import org.apache.spark.mllib.tree.configuration.Algo._ +import org.apache.spark.mllib.tree.configuration.BoostingStrategy +import org.apache.spark.mllib.tree.impl.TimeTracker +import org.apache.spark.mllib.tree.impurity.Variance +import org.apache.spark.mllib.tree.loss.Loss +import org.apache.spark.rdd.RDD +import org.apache.spark.storage.StorageLevel + +private[ml] object GradientBoostedTrees extends Logging { + + /** + * Method to train a gradient boosting model + * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]]. + * @return a gradient boosted trees model that can be used for prediction + */ + def run(input: RDD[LabeledPoint], + boostingStrategy: BoostingStrategy): (Array[DecisionTreeRegressionModel], Array[Double]) = { + val algo = boostingStrategy.treeStrategy.algo + algo match { + case Regression => + GradientBoostedTrees.boost(input, input, boostingStrategy, validate = false) + case Classification => + // Map labels to -1, +1 so binary classification can be treated as regression. + val remappedInput = input.map(x => new LabeledPoint((x.label * 2) - 1, x.features)) + GradientBoostedTrees.boost(remappedInput, remappedInput, boostingStrategy, validate = false) + case _ => + throw new IllegalArgumentException(s"$algo is not supported by gradient boosting.") + } + } + + /** + * Method to validate a gradient boosting model + * @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]]. + * @param validationInput Validation dataset. + * This dataset should be different from the training dataset, + * but it should follow the same distribution. + * E.g., these two datasets could be created from an original dataset + * by using [[org.apache.spark.rdd.RDD.randomSplit()]] + * @return a gradient boosted trees model that can be used for prediction + */ + def runWithValidation( + input: RDD[LabeledPoint], + validationInput: RDD[LabeledPoint], + boostingStrategy: BoostingStrategy): (Array[DecisionTreeRegressionModel], Array[Double]) = { + val algo = boostingStrategy.treeStrategy.algo + algo match { + case Regression => + GradientBoostedTrees.boost(input, validationInput, boostingStrategy, validate = true) + case Classification => + // Map labels to -1, +1 so binary classification can be treated as regression. + val remappedInput = input.map( + x => new LabeledPoint((x.label * 2) - 1, x.features)) + val remappedValidationInput = validationInput.map( + x => new LabeledPoint((x.label * 2) - 1, x.features)) + GradientBoostedTrees.boost(remappedInput, remappedValidationInput, boostingStrategy, + validate = true) + case _ => + throw new IllegalArgumentException(s"$algo is not supported by the gradient boosting.") + } + } + + /** + * Compute the initial predictions and errors for a dataset for the first + * iteration of gradient boosting. + * @param data: training data. + * @param initTreeWeight: learning rate assigned to the first tree. + * @param initTree: first DecisionTreeModel. + * @param loss: evaluation metric. + * @return a RDD with each element being a zip of the prediction and error + * corresponding to every sample. + */ + def computeInitialPredictionAndError( --- End diff -- `computeInitialPredictionAndError` and `updatePredictionError` used to be part of the developer api but are private[ml] in this implementation. I am not sure if it would be a problem to make these private[ml].
--- 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