Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/2435#discussion_r17943424 --- Diff: mllib/src/main/scala/org/apache/spark/mllib/tree/RandomForest.scala --- @@ -0,0 +1,430 @@ +/* + * 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 scala.collection.mutable + +import org.apache.spark.Logging +import org.apache.spark.annotation.Experimental +import org.apache.spark.api.java.JavaRDD +import org.apache.spark.mllib.regression.LabeledPoint +import org.apache.spark.mllib.tree.configuration.Algo._ +import org.apache.spark.mllib.tree.configuration.QuantileStrategy._ +import org.apache.spark.mllib.tree.configuration.Strategy +import org.apache.spark.mllib.tree.impl.{BaggedPoint, TreePoint, DecisionTreeMetadata, TimeTracker} +import org.apache.spark.mllib.tree.impurity.Impurities +import org.apache.spark.mllib.tree.model._ +import org.apache.spark.rdd.RDD +import org.apache.spark.storage.StorageLevel +import org.apache.spark.util.Utils + +/** + * :: Experimental :: + * A class which implements a random forest learning algorithm for classification and regression. + * It supports both continuous and categorical features. + * + * @param strategy The configuration parameters for the random forest algorithm which specify + * the type of algorithm (classification, regression, etc.), feature type + * (continuous, categorical), depth of the tree, quantile calculation strategy, + * etc. + * @param numTrees If 1, then no bootstrapping is used. If > 1, then bootstrapping is done. + * @param featureSubsetStrategy Number of features to consider for splits at each node. + * Supported: "auto" (default), "all", "sqrt", "log2", "onethird". + * If "auto" is set, this parameter is set based on numTrees: + * if numTrees == 1, then featureSubsetStrategy = "all"; + * if numTrees > 1, then featureSubsetStrategy = "sqrt". + * @param seed Random seed for bootstrapping and choosing feature subsets. + */ +@Experimental +private class RandomForest ( + private val strategy: Strategy, + private val numTrees: Int, + featureSubsetStrategy: String, + private val seed: Int) --- End diff -- Shall we use `Long` for random seed to be consistent with Java `Random`?
--- 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