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
|
/*
* 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.classification;
import java.io.File;
import java.io.Serializable;
import java.util.HashMap;
import java.util.Map;
import org.junit.After;
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.ml.impl.TreeTests;
import org.apache.spark.mllib.classification.LogisticRegressionSuite;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.util.Utils;
public class JavaDecisionTreeClassifierSuite implements Serializable {
private transient JavaSparkContext sc;
@Before
public void setUp() {
sc = new JavaSparkContext("local", "JavaDecisionTreeClassifierSuite");
}
@After
public void tearDown() {
sc.stop();
sc = null;
}
@Test
public void runDT() {
int nPoints = 20;
double A = 2.0;
double B = -1.5;
JavaRDD<LabeledPoint> data = sc.parallelize(
LogisticRegressionSuite.generateLogisticInputAsList(A, B, nPoints, 42), 2).cache();
Map<Integer, Integer> categoricalFeatures = new HashMap<Integer, Integer>();
DataFrame dataFrame = TreeTests.setMetadata(data, categoricalFeatures, 2);
// This tests setters. Training with various options is tested in Scala.
DecisionTreeClassifier dt = new DecisionTreeClassifier()
.setMaxDepth(2)
.setMaxBins(10)
.setMinInstancesPerNode(5)
.setMinInfoGain(0.0)
.setMaxMemoryInMB(256)
.setCacheNodeIds(false)
.setCheckpointInterval(10)
.setMaxDepth(2); // duplicate setMaxDepth to check builder pattern
for (int i = 0; i < DecisionTreeClassifier.supportedImpurities().length; ++i) {
dt.setImpurity(DecisionTreeClassifier.supportedImpurities()[i]);
}
DecisionTreeClassificationModel model = dt.fit(dataFrame);
model.transform(dataFrame);
model.numNodes();
model.depth();
model.toDebugString();
/*
// TODO: Add test once save/load are implemented.
File tempDir = Utils.createTempDir(System.getProperty("java.io.tmpdir"), "spark");
String path = tempDir.toURI().toString();
try {
model3.save(sc.sc(), path);
DecisionTreeClassificationModel sameModel =
DecisionTreeClassificationModel.load(sc.sc(), path);
TreeTests.checkEqual(model3, sameModel);
} finally {
Utils.deleteRecursively(tempDir);
}
*/
}
}
|