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
|
/*
* 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.io.Serializable;
import java.util.Arrays;
import java.util.List;
import scala.Tuple2;
import org.junit.Assert;
import org.junit.Test;
import org.apache.spark.SharedSparkSession;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.ml.linalg.Vector;
import org.apache.spark.ml.linalg.Vectors;
import org.apache.spark.mllib.linalg.Matrix;
import org.apache.spark.mllib.linalg.distributed.RowMatrix;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
public class JavaPCASuite extends SharedSparkSession {
public static class VectorPair implements Serializable {
private Vector features = Vectors.dense(0.0);
private Vector expected = Vectors.dense(0.0);
public void setFeatures(Vector features) {
this.features = features;
}
public Vector getFeatures() {
return this.features;
}
public void setExpected(Vector expected) {
this.expected = expected;
}
public Vector getExpected() {
return this.expected;
}
}
@Test
public void testPCA() {
List<Vector> points = Arrays.asList(
Vectors.sparse(5, new int[]{1, 3}, new double[]{1.0, 7.0}),
Vectors.dense(2.0, 0.0, 3.0, 4.0, 5.0),
Vectors.dense(4.0, 0.0, 0.0, 6.0, 7.0)
);
JavaRDD<Vector> dataRDD = jsc.parallelize(points, 2);
RowMatrix mat = new RowMatrix(dataRDD.map(
new Function<Vector, org.apache.spark.mllib.linalg.Vector>() {
public org.apache.spark.mllib.linalg.Vector call(Vector vector) {
return new org.apache.spark.mllib.linalg.DenseVector(vector.toArray());
}
}
).rdd());
Matrix pc = mat.computePrincipalComponents(3);
mat.multiply(pc).rows().toJavaRDD();
JavaRDD<Vector> expected = mat.multiply(pc).rows().toJavaRDD().map(
new Function<org.apache.spark.mllib.linalg.Vector, Vector>() {
public Vector call(org.apache.spark.mllib.linalg.Vector vector) {
return vector.asML();
}
}
);
JavaRDD<VectorPair> featuresExpected = dataRDD.zip(expected).map(
new Function<Tuple2<Vector, Vector>, VectorPair>() {
public VectorPair call(Tuple2<Vector, Vector> pair) {
VectorPair featuresExpected = new VectorPair();
featuresExpected.setFeatures(pair._1());
featuresExpected.setExpected(pair._2());
return featuresExpected;
}
}
);
Dataset<Row> df = spark.createDataFrame(featuresExpected, VectorPair.class);
PCAModel pca = new PCA()
.setInputCol("features")
.setOutputCol("pca_features")
.setK(3)
.fit(df);
List<Row> result = pca.transform(df).select("pca_features", "expected").toJavaRDD().collect();
for (Row r : result) {
Vector calculatedVector = (Vector) r.get(0);
Vector expectedVector = (Vector) r.get(1);
for (int i = 0; i < calculatedVector.size(); i++) {
Assert.assertEquals(calculatedVector.apply(i), expectedVector.apply(i), 1.0e-8);
}
}
}
}
|