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
|
/*
* 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 scala.beans.BeanInfo
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}
@BeanInfo
case class NGramTestData(inputTokens: Array[String], wantedNGrams: Array[String])
class NGramSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
import org.apache.spark.ml.feature.NGramSuite._
test("default behavior yields bigram features") {
val nGram = new NGram()
.setInputCol("inputTokens")
.setOutputCol("nGrams")
val dataset = sqlContext.createDataFrame(Seq(
NGramTestData(
Array("Test", "for", "ngram", "."),
Array("Test for", "for ngram", "ngram .")
)))
testNGram(nGram, dataset)
}
test("NGramLength=4 yields length 4 n-grams") {
val nGram = new NGram()
.setInputCol("inputTokens")
.setOutputCol("nGrams")
.setN(4)
val dataset = sqlContext.createDataFrame(Seq(
NGramTestData(
Array("a", "b", "c", "d", "e"),
Array("a b c d", "b c d e")
)))
testNGram(nGram, dataset)
}
test("empty input yields empty output") {
val nGram = new NGram()
.setInputCol("inputTokens")
.setOutputCol("nGrams")
.setN(4)
val dataset = sqlContext.createDataFrame(Seq(
NGramTestData(
Array(),
Array()
)))
testNGram(nGram, dataset)
}
test("input array < n yields empty output") {
val nGram = new NGram()
.setInputCol("inputTokens")
.setOutputCol("nGrams")
.setN(6)
val dataset = sqlContext.createDataFrame(Seq(
NGramTestData(
Array("a", "b", "c", "d", "e"),
Array()
)))
testNGram(nGram, dataset)
}
test("read/write") {
val t = new NGram()
.setInputCol("myInputCol")
.setOutputCol("myOutputCol")
.setN(3)
testDefaultReadWrite(t)
}
}
object NGramSuite extends SparkFunSuite {
def testNGram(t: NGram, dataset: Dataset[_]): Unit = {
t.transform(dataset)
.select("nGrams", "wantedNGrams")
.collect()
.foreach { case Row(actualNGrams, wantedNGrams) =>
assert(actualNGrams === wantedNGrams)
}
}
}
|