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
|
/*
* 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.regression
import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.tree.impl.TreeTests
import org.apache.spark.ml.util.MLTestingUtils
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.tree.{EnsembleTestHelper, RandomForest => OldRandomForest}
import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo}
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.DataFrame
/**
* Test suite for [[RandomForestRegressor]].
*/
class RandomForestRegressorSuite extends SparkFunSuite with MLlibTestSparkContext {
import RandomForestRegressorSuite.compareAPIs
private var orderedLabeledPoints50_1000: RDD[LabeledPoint] = _
override def beforeAll() {
super.beforeAll()
orderedLabeledPoints50_1000 =
sc.parallelize(EnsembleTestHelper.generateOrderedLabeledPoints(numFeatures = 50, 1000))
}
/////////////////////////////////////////////////////////////////////////////
// Tests calling train()
/////////////////////////////////////////////////////////////////////////////
def regressionTestWithContinuousFeatures(rf: RandomForestRegressor) {
val categoricalFeaturesInfo = Map.empty[Int, Int]
val newRF = rf
.setImpurity("variance")
.setMaxDepth(2)
.setMaxBins(10)
.setNumTrees(1)
.setFeatureSubsetStrategy("auto")
.setSeed(123)
compareAPIs(orderedLabeledPoints50_1000, newRF, categoricalFeaturesInfo)
}
test("Regression with continuous features:" +
" comparing DecisionTree vs. RandomForest(numTrees = 1)") {
val rf = new RandomForestRegressor()
regressionTestWithContinuousFeatures(rf)
}
test("Regression with continuous features and node Id cache :" +
" comparing DecisionTree vs. RandomForest(numTrees = 1)") {
val rf = new RandomForestRegressor()
.setCacheNodeIds(true)
regressionTestWithContinuousFeatures(rf)
}
test("Feature importance with toy data") {
val rf = new RandomForestRegressor()
.setImpurity("variance")
.setMaxDepth(3)
.setNumTrees(3)
.setFeatureSubsetStrategy("all")
.setSubsamplingRate(1.0)
.setSeed(123)
// In this data, feature 1 is very important.
val data: RDD[LabeledPoint] = TreeTests.featureImportanceData(sc)
val categoricalFeatures = Map.empty[Int, Int]
val df: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, 0)
val model = rf.fit(df)
val importances = model.featureImportances
val mostImportantFeature = importances.argmax
assert(mostImportantFeature === 1)
assert(importances.toArray.sum === 1.0)
assert(importances.toArray.forall(_ >= 0.0))
}
/////////////////////////////////////////////////////////////////////////////
// Tests of model save/load
/////////////////////////////////////////////////////////////////////////////
// TODO: Reinstate test once save/load are implemented SPARK-6725
/*
test("model save/load") {
val tempDir = Utils.createTempDir()
val path = tempDir.toURI.toString
val trees = Range(0, 3).map(_ => OldDecisionTreeSuite.createModel(OldAlgo.Regression)).toArray
val oldModel = new OldRandomForestModel(OldAlgo.Regression, trees)
val newModel = RandomForestRegressionModel.fromOld(oldModel)
// Save model, load it back, and compare.
try {
newModel.save(sc, path)
val sameNewModel = RandomForestRegressionModel.load(sc, path)
TreeTests.checkEqual(newModel, sameNewModel)
} finally {
Utils.deleteRecursively(tempDir)
}
}
*/
}
private object RandomForestRegressorSuite extends SparkFunSuite {
/**
* Train 2 models on the given dataset, one using the old API and one using the new API.
* Convert the old model to the new format, compare them, and fail if they are not exactly equal.
*/
def compareAPIs(
data: RDD[LabeledPoint],
rf: RandomForestRegressor,
categoricalFeatures: Map[Int, Int]): Unit = {
val numFeatures = data.first().features.size
val oldStrategy =
rf.getOldStrategy(categoricalFeatures, numClasses = 0, OldAlgo.Regression, rf.getOldImpurity)
val oldModel = OldRandomForest.trainRegressor(
data, oldStrategy, rf.getNumTrees, rf.getFeatureSubsetStrategy, rf.getSeed.toInt)
val newData: DataFrame = TreeTests.setMetadata(data, categoricalFeatures, numClasses = 0)
val newModel = rf.fit(newData)
// Use parent from newTree since this is not checked anyways.
val oldModelAsNew = RandomForestRegressionModel.fromOld(
oldModel, newModel.parent.asInstanceOf[RandomForestRegressor], categoricalFeatures)
TreeTests.checkEqual(oldModelAsNew, newModel)
assert(newModel.numFeatures === numFeatures)
}
}
|
