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
|
/*
* 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.classification
import org.apache.spark.annotation.Experimental
import org.apache.spark.ml.param.ParamMap
import org.apache.spark.ml.tree.{DecisionTreeModel, DecisionTreeParams, Node, TreeClassifierParams}
import org.apache.spark.ml.tree.impl.RandomForest
import org.apache.spark.ml.util.{Identifiable, MetadataUtils}
import org.apache.spark.mllib.linalg.{DenseVector, SparseVector, Vector, Vectors}
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.tree.configuration.{Algo => OldAlgo, Strategy => OldStrategy}
import org.apache.spark.mllib.tree.model.{DecisionTreeModel => OldDecisionTreeModel}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.DataFrame
/**
* :: Experimental ::
* [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] learning algorithm
* for classification.
* It supports both binary and multiclass labels, as well as both continuous and categorical
* features.
*/
@Experimental
final class DecisionTreeClassifier(override val uid: String)
extends ProbabilisticClassifier[Vector, DecisionTreeClassifier, DecisionTreeClassificationModel]
with DecisionTreeParams with TreeClassifierParams {
def this() = this(Identifiable.randomUID("dtc"))
// Override parameter setters from parent trait for Java API compatibility.
override def setMaxDepth(value: Int): this.type = super.setMaxDepth(value)
override def setMaxBins(value: Int): this.type = super.setMaxBins(value)
override def setMinInstancesPerNode(value: Int): this.type =
super.setMinInstancesPerNode(value)
override def setMinInfoGain(value: Double): this.type = super.setMinInfoGain(value)
override def setMaxMemoryInMB(value: Int): this.type = super.setMaxMemoryInMB(value)
override def setCacheNodeIds(value: Boolean): this.type = super.setCacheNodeIds(value)
override def setCheckpointInterval(value: Int): this.type = super.setCheckpointInterval(value)
override def setImpurity(value: String): this.type = super.setImpurity(value)
override protected def train(dataset: DataFrame): DecisionTreeClassificationModel = {
val categoricalFeatures: Map[Int, Int] =
MetadataUtils.getCategoricalFeatures(dataset.schema($(featuresCol)))
val numClasses: Int = MetadataUtils.getNumClasses(dataset.schema($(labelCol))) match {
case Some(n: Int) => n
case None => throw new IllegalArgumentException("DecisionTreeClassifier was given input" +
s" with invalid label column ${$(labelCol)}, without the number of classes" +
" specified. See StringIndexer.")
// TODO: Automatically index labels: SPARK-7126
}
val oldDataset: RDD[LabeledPoint] = extractLabeledPoints(dataset)
val strategy = getOldStrategy(categoricalFeatures, numClasses)
val trees = RandomForest.run(oldDataset, strategy, numTrees = 1, featureSubsetStrategy = "all",
seed = 0L, parentUID = Some(uid))
trees.head.asInstanceOf[DecisionTreeClassificationModel]
}
/** (private[ml]) Create a Strategy instance to use with the old API. */
private[ml] def getOldStrategy(
categoricalFeatures: Map[Int, Int],
numClasses: Int): OldStrategy = {
super.getOldStrategy(categoricalFeatures, numClasses, OldAlgo.Classification, getOldImpurity,
subsamplingRate = 1.0)
}
override def copy(extra: ParamMap): DecisionTreeClassifier = defaultCopy(extra)
}
@Experimental
object DecisionTreeClassifier {
/** Accessor for supported impurities: entropy, gini */
final val supportedImpurities: Array[String] = TreeClassifierParams.supportedImpurities
}
/**
* :: Experimental ::
* [[http://en.wikipedia.org/wiki/Decision_tree_learning Decision tree]] model for classification.
* It supports both binary and multiclass labels, as well as both continuous and categorical
* features.
*/
@Experimental
final class DecisionTreeClassificationModel private[ml] (
override val uid: String,
override val rootNode: Node,
override val numClasses: Int)
extends ProbabilisticClassificationModel[Vector, DecisionTreeClassificationModel]
with DecisionTreeModel with Serializable {
require(rootNode != null,
"DecisionTreeClassificationModel given null rootNode, but it requires a non-null rootNode.")
/**
* Construct a decision tree classification model.
* @param rootNode Root node of tree, with other nodes attached.
*/
private[ml] def this(rootNode: Node, numClasses: Int) =
this(Identifiable.randomUID("dtc"), rootNode, numClasses)
override protected def predict(features: Vector): Double = {
rootNode.predictImpl(features).prediction
}
override protected def predictRaw(features: Vector): Vector = {
Vectors.dense(rootNode.predictImpl(features).impurityStats.stats.clone())
}
override protected def raw2probabilityInPlace(rawPrediction: Vector): Vector = {
rawPrediction match {
case dv: DenseVector =>
ProbabilisticClassificationModel.normalizeToProbabilitiesInPlace(dv)
dv
case sv: SparseVector =>
throw new RuntimeException("Unexpected error in DecisionTreeClassificationModel:" +
" raw2probabilityInPlace encountered SparseVector")
}
}
override def copy(extra: ParamMap): DecisionTreeClassificationModel = {
copyValues(new DecisionTreeClassificationModel(uid, rootNode, numClasses), extra)
}
override def toString: String = {
s"DecisionTreeClassificationModel of depth $depth with $numNodes nodes"
}
/** (private[ml]) Convert to a model in the old API */
private[ml] def toOld: OldDecisionTreeModel = {
new OldDecisionTreeModel(rootNode.toOld(1), OldAlgo.Classification)
}
}
private[ml] object DecisionTreeClassificationModel {
/** (private[ml]) Convert a model from the old API */
def fromOld(
oldModel: OldDecisionTreeModel,
parent: DecisionTreeClassifier,
categoricalFeatures: Map[Int, Int]): DecisionTreeClassificationModel = {
require(oldModel.algo == OldAlgo.Classification,
s"Cannot convert non-classification DecisionTreeModel (old API) to" +
s" DecisionTreeClassificationModel (new API). Algo is: ${oldModel.algo}")
val rootNode = Node.fromOld(oldModel.topNode, categoricalFeatures)
val uid = if (parent != null) parent.uid else Identifiable.randomUID("dtc")
new DecisionTreeClassificationModel(uid, rootNode, -1)
}
}
|