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
|
/*
* 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 breeze.linalg.{Vector => BV}
import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.param.ParamsSuite
import org.apache.spark.ml.util.DefaultReadWriteTest
import org.apache.spark.mllib.classification.NaiveBayes.{Bernoulli, Multinomial}
import org.apache.spark.mllib.classification.NaiveBayesSuite._
import org.apache.spark.mllib.linalg._
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.mllib.util.TestingUtils._
import org.apache.spark.sql.{DataFrame, Row}
class NaiveBayesSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
@transient var dataset: DataFrame = _
override def beforeAll(): Unit = {
super.beforeAll()
val pi = Array(0.5, 0.1, 0.4).map(math.log)
val theta = Array(
Array(0.70, 0.10, 0.10, 0.10), // label 0
Array(0.10, 0.70, 0.10, 0.10), // label 1
Array(0.10, 0.10, 0.70, 0.10) // label 2
).map(_.map(math.log))
dataset = sqlContext.createDataFrame(generateNaiveBayesInput(pi, theta, 100, 42))
}
def validatePrediction(predictionAndLabels: DataFrame): Unit = {
val numOfErrorPredictions = predictionAndLabels.collect().count {
case Row(prediction: Double, label: Double) =>
prediction != label
}
// At least 80% of the predictions should be on.
assert(numOfErrorPredictions < predictionAndLabels.count() / 5)
}
def validateModelFit(
piData: Vector,
thetaData: Matrix,
model: NaiveBayesModel): Unit = {
assert(Vectors.dense(model.pi.toArray.map(math.exp)) ~==
Vectors.dense(piData.toArray.map(math.exp)) absTol 0.05, "pi mismatch")
assert(model.theta.map(math.exp) ~== thetaData.map(math.exp) absTol 0.05, "theta mismatch")
}
def expectedMultinomialProbabilities(model: NaiveBayesModel, feature: Vector): Vector = {
val logClassProbs: BV[Double] = model.pi.toBreeze + model.theta.multiply(feature).toBreeze
val classProbs = logClassProbs.toArray.map(math.exp)
val classProbsSum = classProbs.sum
Vectors.dense(classProbs.map(_ / classProbsSum))
}
def expectedBernoulliProbabilities(model: NaiveBayesModel, feature: Vector): Vector = {
val negThetaMatrix = model.theta.map(v => math.log(1.0 - math.exp(v)))
val negFeature = Vectors.dense(feature.toArray.map(v => 1.0 - v))
val piTheta: BV[Double] = model.pi.toBreeze + model.theta.multiply(feature).toBreeze
val logClassProbs: BV[Double] = piTheta + negThetaMatrix.multiply(negFeature).toBreeze
val classProbs = logClassProbs.toArray.map(math.exp)
val classProbsSum = classProbs.sum
Vectors.dense(classProbs.map(_ / classProbsSum))
}
def validateProbabilities(
featureAndProbabilities: DataFrame,
model: NaiveBayesModel,
modelType: String): Unit = {
featureAndProbabilities.collect().foreach {
case Row(features: Vector, probability: Vector) => {
assert(probability.toArray.sum ~== 1.0 relTol 1.0e-10)
val expected = modelType match {
case Multinomial =>
expectedMultinomialProbabilities(model, features)
case Bernoulli =>
expectedBernoulliProbabilities(model, features)
case _ =>
throw new UnknownError(s"Invalid modelType: $modelType.")
}
assert(probability ~== expected relTol 1.0e-10)
}
}
}
test("params") {
ParamsSuite.checkParams(new NaiveBayes)
val model = new NaiveBayesModel("nb", pi = Vectors.dense(Array(0.2, 0.8)),
theta = new DenseMatrix(2, 3, Array(0.1, 0.2, 0.3, 0.4, 0.6, 0.4)))
ParamsSuite.checkParams(model)
}
test("naive bayes: default params") {
val nb = new NaiveBayes
assert(nb.getLabelCol === "label")
assert(nb.getFeaturesCol === "features")
assert(nb.getPredictionCol === "prediction")
assert(nb.getSmoothing === 1.0)
assert(nb.getModelType === "multinomial")
}
test("Naive Bayes Multinomial") {
val nPoints = 1000
val piArray = Array(0.5, 0.1, 0.4).map(math.log)
val thetaArray = Array(
Array(0.70, 0.10, 0.10, 0.10), // label 0
Array(0.10, 0.70, 0.10, 0.10), // label 1
Array(0.10, 0.10, 0.70, 0.10) // label 2
).map(_.map(math.log))
val pi = Vectors.dense(piArray)
val theta = new DenseMatrix(3, 4, thetaArray.flatten, true)
val testDataset = sqlContext.createDataFrame(generateNaiveBayesInput(
piArray, thetaArray, nPoints, 42, "multinomial"))
val nb = new NaiveBayes().setSmoothing(1.0).setModelType("multinomial")
val model = nb.fit(testDataset)
validateModelFit(pi, theta, model)
assert(model.hasParent)
val validationDataset = sqlContext.createDataFrame(generateNaiveBayesInput(
piArray, thetaArray, nPoints, 17, "multinomial"))
val predictionAndLabels = model.transform(validationDataset).select("prediction", "label")
validatePrediction(predictionAndLabels)
val featureAndProbabilities = model.transform(validationDataset)
.select("features", "probability")
validateProbabilities(featureAndProbabilities, model, "multinomial")
}
test("Naive Bayes Bernoulli") {
val nPoints = 10000
val piArray = Array(0.5, 0.3, 0.2).map(math.log)
val thetaArray = Array(
Array(0.50, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.40), // label 0
Array(0.02, 0.70, 0.10, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02), // label 1
Array(0.02, 0.02, 0.60, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.02, 0.30) // label 2
).map(_.map(math.log))
val pi = Vectors.dense(piArray)
val theta = new DenseMatrix(3, 12, thetaArray.flatten, true)
val testDataset = sqlContext.createDataFrame(generateNaiveBayesInput(
piArray, thetaArray, nPoints, 45, "bernoulli"))
val nb = new NaiveBayes().setSmoothing(1.0).setModelType("bernoulli")
val model = nb.fit(testDataset)
validateModelFit(pi, theta, model)
assert(model.hasParent)
val validationDataset = sqlContext.createDataFrame(generateNaiveBayesInput(
piArray, thetaArray, nPoints, 20, "bernoulli"))
val predictionAndLabels = model.transform(validationDataset).select("prediction", "label")
validatePrediction(predictionAndLabels)
val featureAndProbabilities = model.transform(validationDataset)
.select("features", "probability")
validateProbabilities(featureAndProbabilities, model, "bernoulli")
}
test("read/write") {
def checkModelData(model: NaiveBayesModel, model2: NaiveBayesModel): Unit = {
assert(model.pi === model2.pi)
assert(model.theta === model2.theta)
}
val nb = new NaiveBayes()
testEstimatorAndModelReadWrite(nb, dataset, NaiveBayesSuite.allParamSettings, checkModelData)
}
}
object NaiveBayesSuite {
/**
* Mapping from all Params to valid settings which differ from the defaults.
* This is useful for tests which need to exercise all Params, such as save/load.
* This excludes input columns to simplify some tests.
*/
val allParamSettings: Map[String, Any] = Map(
"predictionCol" -> "myPrediction",
"smoothing" -> 0.1
)
}
|
