-
Notifications
You must be signed in to change notification settings - Fork 28k
/
MLTest.scala
158 lines (137 loc) · 5.59 KB
/
MLTest.scala
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
/*
* 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.util
import java.io.File
import org.scalatest.Suite
import org.apache.spark.{DebugFilesystem, SparkConf, SparkContext}
import org.apache.spark.ml.{PredictionModel, Transformer}
import org.apache.spark.ml.linalg.Vector
import org.apache.spark.sql.{DataFrame, Dataset, Encoder, Row}
import org.apache.spark.sql.execution.streaming.MemoryStream
import org.apache.spark.sql.functions.col
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.streaming.StreamTest
import org.apache.spark.sql.test.TestSparkSession
import org.apache.spark.util.Utils
trait MLTest extends StreamTest with TempDirectory { self: Suite =>
@transient var sc: SparkContext = _
@transient var checkpointDir: String = _
protected override def sparkConf = {
new SparkConf()
.set("spark.hadoop.fs.file.impl", classOf[DebugFilesystem].getName)
.set("spark.unsafe.exceptionOnMemoryLeak", "true")
.set(SQLConf.CODEGEN_FALLBACK.key, "false")
}
protected override def createSparkSession: TestSparkSession = {
new TestSparkSession(new SparkContext("local[2]", "MLlibUnitTest", sparkConf))
}
override def beforeAll(): Unit = {
super.beforeAll()
sc = spark.sparkContext
checkpointDir = Utils.createDirectory(tempDir.getCanonicalPath, "checkpoints").toString
sc.setCheckpointDir(checkpointDir)
}
override def afterAll() {
try {
Utils.deleteRecursively(new File(checkpointDir))
} finally {
super.afterAll()
}
}
private[util] def testTransformerOnStreamData[A : Encoder](
dataframe: DataFrame,
transformer: Transformer,
firstResultCol: String,
otherResultCols: String*)
(globalCheckFunction: Seq[Row] => Unit): Unit = {
val columnNames = dataframe.schema.fieldNames
val stream = MemoryStream[A]
val columnsWithMetadata = dataframe.schema.map { structField =>
col(structField.name).as(structField.name, structField.metadata)
}
val streamDF = stream.toDS().toDF(columnNames: _*).select(columnsWithMetadata: _*)
val data = dataframe.as[A].collect()
val streamOutput = transformer.transform(streamDF)
.select(firstResultCol, otherResultCols: _*)
testStream(streamOutput) (
AddData(stream, data: _*),
CheckAnswer(globalCheckFunction)
)
}
private[util] def testTransformerOnDF(
dataframe: DataFrame,
transformer: Transformer,
firstResultCol: String,
otherResultCols: String*)
(globalCheckFunction: Seq[Row] => Unit): Unit = {
val dfOutput = transformer.transform(dataframe)
val outputs = dfOutput.select(firstResultCol, otherResultCols: _*).collect()
globalCheckFunction(outputs)
}
def testTransformer[A : Encoder](
dataframe: DataFrame,
transformer: Transformer,
firstResultCol: String,
otherResultCols: String*)
(checkFunction: Row => Unit): Unit = {
testTransformerByGlobalCheckFunc(
dataframe,
transformer,
firstResultCol,
otherResultCols: _*) { rows: Seq[Row] => rows.foreach(checkFunction(_)) }
}
def testTransformerByGlobalCheckFunc[A : Encoder](
dataframe: DataFrame,
transformer: Transformer,
firstResultCol: String,
otherResultCols: String*)
(globalCheckFunction: Seq[Row] => Unit): Unit = {
testTransformerOnStreamData(dataframe, transformer, firstResultCol,
otherResultCols: _*)(globalCheckFunction)
testTransformerOnDF(dataframe, transformer, firstResultCol,
otherResultCols: _*)(globalCheckFunction)
}
def testTransformerByInterceptingException[A : Encoder](
dataframe: DataFrame,
transformer: Transformer,
expectedMessagePart : String,
firstResultCol: String) {
def hasExpectedMessage(exception: Throwable): Boolean =
exception.getMessage.contains(expectedMessagePart) ||
(exception.getCause != null && exception.getCause.getMessage.contains(expectedMessagePart))
withClue(s"""Expected message part "${expectedMessagePart}" is not found in DF test.""") {
val exceptionOnDf = intercept[Throwable] {
testTransformerOnDF(dataframe, transformer, firstResultCol)(_ => Unit)
}
assert(hasExpectedMessage(exceptionOnDf))
}
withClue(s"""Expected message part "${expectedMessagePart}" is not found in stream test.""") {
val exceptionOnStreamData = intercept[Throwable] {
testTransformerOnStreamData(dataframe, transformer, firstResultCol)(_ => Unit)
}
assert(hasExpectedMessage(exceptionOnStreamData))
}
}
def testPredictionModelSinglePrediction(model: PredictionModel[Vector, _],
dataset: Dataset[_]): Unit = {
model.transform(dataset).select(model.getFeaturesCol, model.getPredictionCol)
.collect().foreach {
case Row(features: Vector, prediction: Double) =>
assert(prediction === model.predict(features))
}
}
}