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
|
/*
* 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.attribute.AttributeGroup
import org.apache.spark.ml.param.ParamsSuite
import org.apache.spark.ml.util.DefaultReadWriteTest
import org.apache.spark.mllib.feature.{HashingTF => MLlibHashingTF}
import org.apache.spark.mllib.linalg.{Vector, Vectors}
import org.apache.spark.mllib.util.MLlibTestSparkContext
import org.apache.spark.mllib.util.TestingUtils._
import org.apache.spark.util.Utils
class HashingTFSuite extends SparkFunSuite with MLlibTestSparkContext with DefaultReadWriteTest {
test("params") {
ParamsSuite.checkParams(new HashingTF)
}
test("hashingTF") {
val df = sqlContext.createDataFrame(Seq(
(0, "a a b b c d".split(" ").toSeq)
)).toDF("id", "words")
val n = 100
Seq("murmur3", "native").foreach { hashAlgorithm =>
val hashingTF = new HashingTF()
.setInputCol("words")
.setOutputCol("features")
.setNumFeatures(n)
.setHashAlgorithm(hashAlgorithm)
val output = hashingTF.transform(df)
val attrGroup = AttributeGroup.fromStructField(output.schema("features"))
require(attrGroup.numAttributes === Some(n))
val features = output.select("features").first().getAs[Vector](0)
// Assume perfect hash on "a", "b", "c", and "d".
def idx: Any => Int = if (hashAlgorithm == "murmur3") {
murmur3FeatureIdx(n)
} else {
nativeFeatureIdx(n)
}
val expected = Vectors.sparse(n,
Seq((idx("a"), 2.0), (idx("b"), 2.0), (idx("c"), 1.0), (idx("d"), 1.0)))
assert(features ~== expected absTol 1e-14)
}
}
test("applying binary term freqs") {
val df = sqlContext.createDataFrame(Seq(
(0, "a a b c c c".split(" ").toSeq)
)).toDF("id", "words")
val n = 100
val hashingTF = new HashingTF()
.setInputCol("words")
.setOutputCol("features")
.setNumFeatures(n)
.setBinary(true)
val output = hashingTF.transform(df)
val features = output.select("features").first().getAs[Vector](0)
def idx: Any => Int = murmur3FeatureIdx(n) // Assume perfect hash on input features
val expected = Vectors.sparse(n,
Seq((idx("a"), 1.0), (idx("b"), 1.0), (idx("c"), 1.0)))
assert(features ~== expected absTol 1e-14)
}
test("read/write") {
val t = new HashingTF()
.setInputCol("myInputCol")
.setOutputCol("myOutputCol")
.setNumFeatures(10)
testDefaultReadWrite(t)
}
private def nativeFeatureIdx(numFeatures: Int)(term: Any): Int = {
Utils.nonNegativeMod(MLlibHashingTF.nativeHash(term), numFeatures)
}
private def murmur3FeatureIdx(numFeatures: Int)(term: Any): Int = {
Utils.nonNegativeMod(MLlibHashingTF.murmur3Hash(term), numFeatures)
}
}
|