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
|
/*
* 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.regression;
import java.io.Serializable;
import java.util.List;
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 static org.apache.spark.mllib.classification.LogisticRegressionSuite
.generateLogisticInputAsList;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.SQLContext;
public class JavaLinearRegressionSuite implements Serializable {
private transient JavaSparkContext jsc;
private transient SQLContext jsql;
private transient DataFrame dataset;
private transient JavaRDD<LabeledPoint> datasetRDD;
@Before
public void setUp() {
jsc = new JavaSparkContext("local", "JavaLinearRegressionSuite");
jsql = new SQLContext(jsc);
List<LabeledPoint> points = generateLogisticInputAsList(1.0, 1.0, 100, 42);
datasetRDD = jsc.parallelize(points, 2);
dataset = jsql.applySchema(datasetRDD, LabeledPoint.class);
dataset.registerTempTable("dataset");
}
@After
public void tearDown() {
jsc.stop();
jsc = null;
}
@Test
public void linearRegressionDefaultParams() {
LinearRegression lr = new LinearRegression();
assert(lr.getLabelCol().equals("label"));
LinearRegressionModel model = lr.fit(dataset);
model.transform(dataset).registerTempTable("prediction");
DataFrame predictions = jsql.sql("SELECT label, prediction FROM prediction");
predictions.collect();
// Check defaults
assert(model.getFeaturesCol().equals("features"));
assert(model.getPredictionCol().equals("prediction"));
}
@Test
public void linearRegressionWithSetters() {
// Set params, train, and check as many params as we can.
LinearRegression lr = new LinearRegression()
.setMaxIter(10)
.setRegParam(1.0);
LinearRegressionModel model = lr.fit(dataset);
assert(model.fittingParamMap().apply(lr.maxIter()).equals(10));
assert(model.fittingParamMap().apply(lr.regParam()).equals(1.0));
// Call fit() with new params, and check as many params as we can.
LinearRegressionModel model2 =
lr.fit(dataset, lr.maxIter().w(5), lr.regParam().w(0.1), lr.predictionCol().w("thePred"));
assert(model2.fittingParamMap().apply(lr.maxIter()).equals(5));
assert(model2.fittingParamMap().apply(lr.regParam()).equals(0.1));
assert(model2.getPredictionCol().equals("thePred"));
}
}
|