Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/7294#discussion_r34757704
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/tree/impl/RandomForest.scala ---
@@ -0,0 +1,1131 @@
+/*
+ * 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 java.io.IOException
+
+import scala.collection.mutable
+import scala.util.Random
+
+import org.apache.spark.Logging
+import org.apache.spark.ml.classification.DecisionTreeClassificationModel
+import org.apache.spark.ml.regression.DecisionTreeRegressionModel
+import org.apache.spark.ml.tree._
+import org.apache.spark.mllib.regression.LabeledPoint
+import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo,
Strategy => OldStrategy}
+import org.apache.spark.mllib.tree.impl.{BaggedPoint, DTStatsAggregator,
DecisionTreeMetadata,
+ TimeTracker}
+import org.apache.spark.mllib.tree.impurity.ImpurityCalculator
+import org.apache.spark.mllib.tree.model.{InformationGainStats, Predict}
+import org.apache.spark.rdd.RDD
+import org.apache.spark.storage.StorageLevel
+import org.apache.spark.util.random.{SamplingUtils, XORShiftRandom}
+
+
+private[ml] object RandomForest extends Logging {
+
+ /**
+ * Train a random forest.
+ * @param input Training data: RDD of
[[org.apache.spark.mllib.regression.LabeledPoint]]
+ * @return an unweighted set of trees
+ */
+ def run(
+ input: RDD[LabeledPoint],
+ strategy: OldStrategy,
+ numTrees: Int,
+ featureSubsetStrategy: String,
+ seed: Long,
+ parentUID: Option[String] = None): Array[DecisionTreeModel] = {
+
+ val timer = new TimeTracker()
+
+ timer.start("total")
+
+ timer.start("init")
+
+ val retaggedInput = input.retag(classOf[LabeledPoint])
+ val metadata =
+ DecisionTreeMetadata.buildMetadata(retaggedInput, strategy,
numTrees, featureSubsetStrategy)
+ logDebug("algo = " + strategy.algo)
+ logDebug("numTrees = " + numTrees)
+ logDebug("seed = " + seed)
+ logDebug("maxBins = " + metadata.maxBins)
+ logDebug("featureSubsetStrategy = " + featureSubsetStrategy)
+ logDebug("numFeaturesPerNode = " + metadata.numFeaturesPerNode)
+ logDebug("subsamplingRate = " + strategy.subsamplingRate)
+
+ // Find the splits and the corresponding bins (interval between the
splits) using a sample
+ // of the input data.
+ timer.start("findSplitsBins")
+ val splits = findSplits(retaggedInput, metadata)
+ timer.stop("findSplitsBins")
+ logDebug("numBins: feature: number of bins")
+ logDebug(Range(0, metadata.numFeatures).map { featureIndex =>
+ s"\t$featureIndex\t${metadata.numBins(featureIndex)}"
+ }.mkString("\n"))
+
+ // Bin feature values (TreePoint representation).
+ // Cache input RDD for speedup during multiple passes.
+ val treeInput = TreePoint.convertToTreeRDD(retaggedInput, splits,
metadata)
+
+ val withReplacement = if (numTrees > 1) true else false
+
+ val baggedInput = BaggedPoint.convertToBaggedRDD(treeInput,
strategy.subsamplingRate, numTrees,
+ withReplacement, seed).persist(StorageLevel.MEMORY_AND_DISK)
--- End diff --
Put `.persist` to a new line for readability.
~~~scala
val baggedInput = BaggedPoint.convertToBaggedRDD(
treeInput, strategy.subsamplingRate, numTrees, withReplacement, seed
).persist(StorageLevel.MEMORY_AND_DISK)
~~~
---
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]
