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
|
/*
* 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 java.util.Arrays;
import org.junit.After;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.mllib.linalg.Vector;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SQLContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
public class JavaHashingTFSuite {
private transient JavaSparkContext jsc;
private transient SQLContext jsql;
@Before
public void setUp() {
jsc = new JavaSparkContext("local", "JavaHashingTFSuite");
jsql = new SQLContext(jsc);
}
@After
public void tearDown() {
jsc.stop();
jsc = null;
}
@Test
public void hashingTF() {
JavaRDD<Row> jrdd = jsc.parallelize(Arrays.asList(
RowFactory.create(0.0, "Hi I heard about Spark"),
RowFactory.create(0.0, "I wish Java could use case classes"),
RowFactory.create(1.0, "Logistic regression models are neat")
));
StructType schema = new StructType(new StructField[]{
new StructField("label", DataTypes.DoubleType, false, Metadata.empty()),
new StructField("sentence", DataTypes.StringType, false, Metadata.empty())
});
DataFrame sentenceData = jsql.createDataFrame(jrdd, schema);
Tokenizer tokenizer = new Tokenizer()
.setInputCol("sentence")
.setOutputCol("words");
DataFrame wordsData = tokenizer.transform(sentenceData);
int numFeatures = 20;
HashingTF hashingTF = new HashingTF()
.setInputCol("words")
.setOutputCol("rawFeatures")
.setNumFeatures(numFeatures);
DataFrame featurizedData = hashingTF.transform(wordsData);
IDF idf = new IDF().setInputCol("rawFeatures").setOutputCol("features");
IDFModel idfModel = idf.fit(featurizedData);
DataFrame rescaledData = idfModel.transform(featurizedData);
for (Row r : rescaledData.select("features", "label").take(3)) {
Vector features = r.getAs(0);
Assert.assertEquals(features.size(), numFeatures);
}
}
}
|