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
|
/*
* 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 org.apache.spark.ml.tree.{ContinuousSplit, Split}
import org.apache.spark.mllib.regression.LabeledPoint
import org.apache.spark.mllib.tree.impl.DecisionTreeMetadata
import org.apache.spark.rdd.RDD
/**
* Internal representation of LabeledPoint for DecisionTree.
* This bins feature values based on a subsampled of data as follows:
* (a) Continuous features are binned into ranges.
* (b) Unordered categorical features are binned based on subsets of feature values.
* "Unordered categorical features" are categorical features with low arity used in
* multiclass classification.
* (c) Ordered categorical features are binned based on feature values.
* "Ordered categorical features" are categorical features with high arity,
* or any categorical feature used in regression or binary classification.
*
* @param label Label from LabeledPoint
* @param binnedFeatures Binned feature values.
* Same length as LabeledPoint.features, but values are bin indices.
*/
private[spark] class TreePoint(val label: Double, val binnedFeatures: Array[Int])
extends Serializable {
}
private[spark] object TreePoint {
/**
* Convert an input dataset into its TreePoint representation,
* binning feature values in preparation for DecisionTree training.
* @param input Input dataset.
* @param splits Splits for features, of size (numFeatures, numSplits).
* @param metadata Learning and dataset metadata
* @return TreePoint dataset representation
*/
def convertToTreeRDD(
input: RDD[LabeledPoint],
splits: Array[Array[Split]],
metadata: DecisionTreeMetadata): RDD[TreePoint] = {
// Construct arrays for featureArity for efficiency in the inner loop.
val featureArity: Array[Int] = new Array[Int](metadata.numFeatures)
var featureIndex = 0
while (featureIndex < metadata.numFeatures) {
featureArity(featureIndex) = metadata.featureArity.getOrElse(featureIndex, 0)
featureIndex += 1
}
val thresholds: Array[Array[Double]] = featureArity.zipWithIndex.map { case (arity, idx) =>
if (arity == 0) {
splits(idx).map(_.asInstanceOf[ContinuousSplit].threshold)
} else {
Array.empty[Double]
}
}
input.map { x =>
TreePoint.labeledPointToTreePoint(x, thresholds, featureArity)
}
}
/**
* Convert one LabeledPoint into its TreePoint representation.
* @param thresholds For each feature, split thresholds for continuous features,
* empty for categorical features.
* @param featureArity Array indexed by feature, with value 0 for continuous and numCategories
* for categorical features.
*/
private def labeledPointToTreePoint(
labeledPoint: LabeledPoint,
thresholds: Array[Array[Double]],
featureArity: Array[Int]): TreePoint = {
val numFeatures = labeledPoint.features.size
val arr = new Array[Int](numFeatures)
var featureIndex = 0
while (featureIndex < numFeatures) {
arr(featureIndex) =
findBin(featureIndex, labeledPoint, featureArity(featureIndex), thresholds(featureIndex))
featureIndex += 1
}
new TreePoint(labeledPoint.label, arr)
}
/**
* Find discretized value for one (labeledPoint, feature).
*
* NOTE: We cannot use Bucketizer since it handles split thresholds differently than the old
* (mllib) tree API. We want to maintain the same behavior as the old tree API.
*
* @param featureArity 0 for continuous features; number of categories for categorical features.
*/
private def findBin(
featureIndex: Int,
labeledPoint: LabeledPoint,
featureArity: Int,
thresholds: Array[Double]): Int = {
val featureValue = labeledPoint.features(featureIndex)
if (featureArity == 0) {
val idx = java.util.Arrays.binarySearch(thresholds, featureValue)
if (idx >= 0) {
idx
} else {
-idx - 1
}
} else {
// Categorical feature bins are indexed by feature values.
if (featureValue < 0 || featureValue >= featureArity) {
throw new IllegalArgumentException(
s"DecisionTree given invalid data:" +
s" Feature $featureIndex is categorical with values in {0,...,${featureArity - 1}," +
s" but a data point gives it value $featureValue.\n" +
" Bad data point: " + labeledPoint.toString)
}
featureValue.toInt
}
}
}
|
