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
|
/*
* 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.impurity
import org.apache.spark.annotation.{DeveloperApi, Experimental, Since}
/**
* :: Experimental ::
* Class for calculating [[http://en.wikipedia.org/wiki/Binary_entropy_function entropy]] during
* binary classification.
*/
@Since("1.0.0")
@Experimental
object Entropy extends Impurity {
private[tree] def log2(x: Double) = scala.math.log(x) / scala.math.log(2)
/**
* :: DeveloperApi ::
* information calculation for multiclass classification
* @param counts Array[Double] with counts for each label
* @param totalCount sum of counts for all labels
* @return information value, or 0 if totalCount = 0
*/
@Since("1.1.0")
@DeveloperApi
override def calculate(counts: Array[Double], totalCount: Double): Double = {
if (totalCount == 0) {
return 0
}
val numClasses = counts.length
var impurity = 0.0
var classIndex = 0
while (classIndex < numClasses) {
val classCount = counts(classIndex)
if (classCount != 0) {
val freq = classCount / totalCount
impurity -= freq * log2(freq)
}
classIndex += 1
}
impurity
}
/**
* :: DeveloperApi ::
* variance calculation
* @param count number of instances
* @param sum sum of labels
* @param sumSquares summation of squares of the labels
* @return information value, or 0 if count = 0
*/
@Since("1.0.0")
@DeveloperApi
override def calculate(count: Double, sum: Double, sumSquares: Double): Double =
throw new UnsupportedOperationException("Entropy.calculate")
/**
* Get this impurity instance.
* This is useful for passing impurity parameters to a Strategy in Java.
*/
@Since("1.1.0")
def instance: this.type = this
}
/**
* Class for updating views of a vector of sufficient statistics,
* in order to compute impurity from a sample.
* Note: Instances of this class do not hold the data; they operate on views of the data.
* @param numClasses Number of classes for label.
*/
private[tree] class EntropyAggregator(numClasses: Int)
extends ImpurityAggregator(numClasses) with Serializable {
/**
* Update stats for one (node, feature, bin) with the given label.
* @param allStats Flat stats array, with stats for this (node, feature, bin) contiguous.
* @param offset Start index of stats for this (node, feature, bin).
*/
def update(allStats: Array[Double], offset: Int, label: Double, instanceWeight: Double): Unit = {
if (label >= statsSize) {
throw new IllegalArgumentException(s"EntropyAggregator given label $label" +
s" but requires label < numClasses (= $statsSize).")
}
if (label < 0) {
throw new IllegalArgumentException(s"EntropyAggregator given label $label" +
s"but requires label is non-negative.")
}
allStats(offset + label.toInt) += instanceWeight
}
/**
* Get an [[ImpurityCalculator]] for a (node, feature, bin).
* @param allStats Flat stats array, with stats for this (node, feature, bin) contiguous.
* @param offset Start index of stats for this (node, feature, bin).
*/
def getCalculator(allStats: Array[Double], offset: Int): EntropyCalculator = {
new EntropyCalculator(allStats.view(offset, offset + statsSize).toArray)
}
}
/**
* Stores statistics for one (node, feature, bin) for calculating impurity.
* Unlike [[EntropyAggregator]], this class stores its own data and is for a specific
* (node, feature, bin).
* @param stats Array of sufficient statistics for a (node, feature, bin).
*/
private[spark] class EntropyCalculator(stats: Array[Double]) extends ImpurityCalculator(stats) {
/**
* Make a deep copy of this [[ImpurityCalculator]].
*/
def copy: EntropyCalculator = new EntropyCalculator(stats.clone())
/**
* Calculate the impurity from the stored sufficient statistics.
*/
def calculate(): Double = Entropy.calculate(stats, stats.sum)
/**
* Number of data points accounted for in the sufficient statistics.
*/
def count: Long = stats.sum.toLong
/**
* Prediction which should be made based on the sufficient statistics.
*/
def predict: Double = if (count == 0) {
0
} else {
indexOfLargestArrayElement(stats)
}
/**
* Probability of the label given by [[predict]].
*/
override def prob(label: Double): Double = {
val lbl = label.toInt
require(lbl < stats.length,
s"EntropyCalculator.prob given invalid label: $lbl (should be < ${stats.length}")
require(lbl >= 0, "Entropy does not support negative labels")
val cnt = count
if (cnt == 0) {
0
} else {
stats(lbl) / cnt
}
}
override def toString: String = s"EntropyCalculator(stats = [${stats.mkString(", ")}])"
}
|
