1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
|
/*
* 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.Since
import org.apache.spark.api.java.JavaRDD
import org.apache.spark.internal.Logging
import org.apache.spark.ml.tree.{DecisionTreeModel => NewDTModel, RandomForestParams => NewRFParams}
import org.apache.spark.ml.tree.impl.{RandomForest => NewRandomForest}
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.impurity.Impurities
import org.apache.spark.mllib.tree.model._
import org.apache.spark.rdd.RDD
import org.apache.spark.util.Utils
/**
* A class that implements a [[http://en.wikipedia.org/wiki/Random_forest Random Forest]]
* learning algorithm for classification and regression.
* It supports both continuous and categorical features.
*
* The settings for featureSubsetStrategy are based on the following references:
* - log2: tested in Breiman (2001)
* - sqrt: recommended by Breiman manual for random forests
* - The defaults of sqrt (classification) and onethird (regression) match the R randomForest
* package.
* @see [[http://www.stat.berkeley.edu/~breiman/randomforest2001.pdf Breiman (2001)]]
* @see [[http://www.stat.berkeley.edu/~breiman/Using_random_forests_V3.1.pdf Breiman manual for
* random forests]]
*
* @param strategy The configuration parameters for the random forest algorithm which specify
* the type of random forest (classification or regression), 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 values: "auto", "all", "sqrt", "log2", "onethird".
* If "auto" is set, this parameter is set based on numTrees:
* if numTrees == 1, set to "all";
* if numTrees > 1 (forest) set to "sqrt" for classification and
* to "onethird" for regression.
* @param seed Random seed for bootstrapping and choosing feature subsets.
*/
private class RandomForest (
private val strategy: Strategy,
private val numTrees: Int,
featureSubsetStrategy: String,
private val seed: Int)
extends Serializable with Logging {
strategy.assertValid()
require(numTrees > 0, s"RandomForest requires numTrees > 0, but was given numTrees = $numTrees.")
require(RandomForest.supportedFeatureSubsetStrategies.contains(featureSubsetStrategy),
s"RandomForest given invalid featureSubsetStrategy: $featureSubsetStrategy." +
s" Supported values: ${RandomForest.supportedFeatureSubsetStrategies.mkString(", ")}.")
/**
* Method to train a decision tree model over an RDD
*
* @param input Training data: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
* @return RandomForestModel that can be used for prediction.
*/
def run(input: RDD[LabeledPoint]): RandomForestModel = {
val trees: Array[NewDTModel] =
NewRandomForest.run(input, strategy, numTrees, featureSubsetStrategy, seed.toLong)
new RandomForestModel(strategy.algo, trees.map(_.toOld))
}
}
@Since("1.2.0")
object RandomForest extends Serializable with Logging {
/**
* Method to train a decision tree model for binary or multiclass classification.
*
* @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
* Labels should take values {0, 1, ..., numClasses-1}.
* @param strategy Parameters for training each tree in the forest.
* @param numTrees Number of trees in the random forest.
* @param featureSubsetStrategy Number of features to consider for splits at each node.
* Supported values: "auto", "all", "sqrt", "log2", "onethird".
* If "auto" is set, this parameter is set based on numTrees:
* if numTrees == 1, set to "all";
* if numTrees > 1 (forest) set to "sqrt".
* @param seed Random seed for bootstrapping and choosing feature subsets.
* @return RandomForestModel that can be used for prediction.
*/
@Since("1.2.0")
def trainClassifier(
input: RDD[LabeledPoint],
strategy: Strategy,
numTrees: Int,
featureSubsetStrategy: String,
seed: Int): RandomForestModel = {
require(strategy.algo == Classification,
s"RandomForest.trainClassifier given Strategy with invalid algo: ${strategy.algo}")
val rf = new RandomForest(strategy, numTrees, featureSubsetStrategy, seed)
rf.run(input)
}
/**
* Method to train a decision tree model for binary or multiclass classification.
*
* @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
* Labels should take values {0, 1, ..., numClasses-1}.
* @param numClasses Number of classes for classification.
* @param categoricalFeaturesInfo Map storing arity of categorical features. An entry (n -> k)
* indicates that feature n is categorical with k categories
* indexed from 0: {0, 1, ..., k-1}.
* @param numTrees Number of trees in the random forest.
* @param featureSubsetStrategy Number of features to consider for splits at each node.
* Supported values: "auto", "all", "sqrt", "log2", "onethird".
* If "auto" is set, this parameter is set based on numTrees:
* if numTrees == 1, set to "all";
* if numTrees > 1 (forest) set to "sqrt".
* @param impurity Criterion used for information gain calculation.
* Supported values: "gini" (recommended) or "entropy".
* @param maxDepth Maximum depth of the tree (e.g. depth 0 means 1 leaf node, depth 1 means
* 1 internal node + 2 leaf nodes).
* (suggested value: 4)
* @param maxBins Maximum number of bins used for splitting features
* (suggested value: 100)
* @param seed Random seed for bootstrapping and choosing feature subsets.
* @return RandomForestModel that can be used for prediction.
*/
@Since("1.2.0")
def trainClassifier(
input: RDD[LabeledPoint],
numClasses: Int,
categoricalFeaturesInfo: Map[Int, Int],
numTrees: Int,
featureSubsetStrategy: String,
impurity: String,
maxDepth: Int,
maxBins: Int,
seed: Int = Utils.random.nextInt()): RandomForestModel = {
val impurityType = Impurities.fromString(impurity)
val strategy = new Strategy(Classification, impurityType, maxDepth,
numClasses, maxBins, Sort, categoricalFeaturesInfo)
trainClassifier(input, strategy, numTrees, featureSubsetStrategy, seed)
}
/**
* Java-friendly API for [[org.apache.spark.mllib.tree.RandomForest$#trainClassifier]]
*/
@Since("1.2.0")
def trainClassifier(
input: JavaRDD[LabeledPoint],
numClasses: Int,
categoricalFeaturesInfo: java.util.Map[java.lang.Integer, java.lang.Integer],
numTrees: Int,
featureSubsetStrategy: String,
impurity: String,
maxDepth: Int,
maxBins: Int,
seed: Int): RandomForestModel = {
trainClassifier(input.rdd, numClasses,
categoricalFeaturesInfo.asInstanceOf[java.util.Map[Int, Int]].asScala.toMap,
numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins, seed)
}
/**
* Method to train a decision tree model for regression.
*
* @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
* Labels are real numbers.
* @param strategy Parameters for training each tree in the forest.
* @param numTrees Number of trees in the random forest.
* @param featureSubsetStrategy Number of features to consider for splits at each node.
* Supported values: "auto", "all", "sqrt", "log2", "onethird".
* If "auto" is set, this parameter is set based on numTrees:
* if numTrees == 1, set to "all";
* if numTrees > 1 (forest) set to "onethird".
* @param seed Random seed for bootstrapping and choosing feature subsets.
* @return RandomForestModel that can be used for prediction.
*/
@Since("1.2.0")
def trainRegressor(
input: RDD[LabeledPoint],
strategy: Strategy,
numTrees: Int,
featureSubsetStrategy: String,
seed: Int): RandomForestModel = {
require(strategy.algo == Regression,
s"RandomForest.trainRegressor given Strategy with invalid algo: ${strategy.algo}")
val rf = new RandomForest(strategy, numTrees, featureSubsetStrategy, seed)
rf.run(input)
}
/**
* Method to train a decision tree model for regression.
*
* @param input Training dataset: RDD of [[org.apache.spark.mllib.regression.LabeledPoint]].
* Labels are real numbers.
* @param categoricalFeaturesInfo Map storing arity of categorical features. An entry (n -> k)
* indicates that feature n is categorical with k categories
* indexed from 0: {0, 1, ..., k-1}.
* @param numTrees Number of trees in the random forest.
* @param featureSubsetStrategy Number of features to consider for splits at each node.
* Supported values: "auto", "all", "sqrt", "log2", "onethird".
* If "auto" is set, this parameter is set based on numTrees:
* if numTrees == 1, set to "all";
* if numTrees > 1 (forest) set to "onethird".
* @param impurity Criterion used for information gain calculation.
* The only supported value for regression is "variance".
* @param maxDepth Maximum depth of the tree. (e.g., depth 0 means 1 leaf node, depth 1 means
* 1 internal node + 2 leaf nodes).
* (suggested value: 4)
* @param maxBins Maximum number of bins used for splitting features.
* (suggested value: 100)
* @param seed Random seed for bootstrapping and choosing feature subsets.
* @return RandomForestModel that can be used for prediction.
*/
@Since("1.2.0")
def trainRegressor(
input: RDD[LabeledPoint],
categoricalFeaturesInfo: Map[Int, Int],
numTrees: Int,
featureSubsetStrategy: String,
impurity: String,
maxDepth: Int,
maxBins: Int,
seed: Int = Utils.random.nextInt()): RandomForestModel = {
val impurityType = Impurities.fromString(impurity)
val strategy = new Strategy(Regression, impurityType, maxDepth,
0, maxBins, Sort, categoricalFeaturesInfo)
trainRegressor(input, strategy, numTrees, featureSubsetStrategy, seed)
}
/**
* Java-friendly API for [[org.apache.spark.mllib.tree.RandomForest$#trainRegressor]]
*/
@Since("1.2.0")
def trainRegressor(
input: JavaRDD[LabeledPoint],
categoricalFeaturesInfo: java.util.Map[java.lang.Integer, java.lang.Integer],
numTrees: Int,
featureSubsetStrategy: String,
impurity: String,
maxDepth: Int,
maxBins: Int,
seed: Int): RandomForestModel = {
trainRegressor(input.rdd,
categoricalFeaturesInfo.asInstanceOf[java.util.Map[Int, Int]].asScala.toMap,
numTrees, featureSubsetStrategy, impurity, maxDepth, maxBins, seed)
}
/**
* List of supported feature subset sampling strategies.
*/
@Since("1.2.0")
val supportedFeatureSubsetStrategies: Array[String] = NewRFParams.supportedFeatureSubsetStrategies
}
|
