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
|
/*
* 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.feature
import org.apache.spark.SparkFunSuite
import org.apache.spark.ml.util.DefaultReadWriteTest
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.sql.{DataFrame, Dataset, Row}
object StopWordsRemoverSuite extends SparkFunSuite {
def testStopWordsRemover(t: StopWordsRemover, dataset: Dataset[_]): Unit = {
t.transform(dataset)
.select("filtered", "expected")
.collect()
.foreach { case Row(tokens, wantedTokens) =>
assert(tokens === wantedTokens)
}
}
}
class StopWordsRemoverSuite
extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
import StopWordsRemoverSuite._
test("StopWordsRemover default") {
val remover = new StopWordsRemover()
.setInputCol("raw")
.setOutputCol("filtered")
val dataSet = sqlContext.createDataFrame(Seq(
(Seq("test", "test"), Seq("test", "test")),
(Seq("a", "b", "c", "d"), Seq("b", "c", "d")),
(Seq("a", "the", "an"), Seq()),
(Seq("A", "The", "AN"), Seq()),
(Seq(null), Seq(null)),
(Seq(), Seq())
)).toDF("raw", "expected")
testStopWordsRemover(remover, dataSet)
}
test("StopWordsRemover case sensitive") {
val remover = new StopWordsRemover()
.setInputCol("raw")
.setOutputCol("filtered")
.setCaseSensitive(true)
val dataSet = sqlContext.createDataFrame(Seq(
(Seq("A"), Seq("A")),
(Seq("The", "the"), Seq("The"))
)).toDF("raw", "expected")
testStopWordsRemover(remover, dataSet)
}
test("StopWordsRemover with additional words") {
val stopWords = StopWords.English ++ Array("python", "scala")
val remover = new StopWordsRemover()
.setInputCol("raw")
.setOutputCol("filtered")
.setStopWords(stopWords)
val dataSet = sqlContext.createDataFrame(Seq(
(Seq("python", "scala", "a"), Seq()),
(Seq("Python", "Scala", "swift"), Seq("swift"))
)).toDF("raw", "expected")
testStopWordsRemover(remover, dataSet)
}
test("read/write") {
val t = new StopWordsRemover()
.setInputCol("myInputCol")
.setOutputCol("myOutputCol")
.setStopWords(Array("the", "a"))
.setCaseSensitive(true)
testDefaultReadWrite(t)
}
test("StopWordsRemover output column already exists") {
val outputCol = "expected"
val remover = new StopWordsRemover()
.setInputCol("raw")
.setOutputCol(outputCol)
val dataSet = sqlContext.createDataFrame(Seq(
(Seq("The", "the", "swift"), Seq("swift"))
)).toDF("raw", outputCol)
val thrown = intercept[IllegalArgumentException] {
testStopWordsRemover(remover, dataSet)
}
assert(thrown.getMessage == s"requirement failed: Column $outputCol already exists.")
}
}
|