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
|
/*
* 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.examples.ml;
// $example on$
import java.util.Arrays;
// $example off$
import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
// $example on$
import org.apache.spark.ml.classification.LogisticRegression;
import org.apache.spark.ml.classification.LogisticRegressionModel;
import org.apache.spark.ml.param.ParamMap;
import org.apache.spark.mllib.linalg.Vectors;
import org.apache.spark.mllib.regression.LabeledPoint;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
// $example off$
import org.apache.spark.sql.SQLContext;
/**
* Java example for Estimator, Transformer, and Param.
*/
public class JavaEstimatorTransformerParamExample {
public static void main(String[] args) {
SparkConf conf = new SparkConf()
.setAppName("JavaEstimatorTransformerParamExample");
SparkContext sc = new SparkContext(conf);
SQLContext sqlContext = new SQLContext(sc);
// $example on$
// Prepare training data.
// We use LabeledPoint, which is a JavaBean. Spark SQL can convert RDDs of JavaBeans into
// DataFrames, where it uses the bean metadata to infer the schema.
DataFrame training = sqlContext.createDataFrame(
Arrays.asList(
new LabeledPoint(1.0, Vectors.dense(0.0, 1.1, 0.1)),
new LabeledPoint(0.0, Vectors.dense(2.0, 1.0, -1.0)),
new LabeledPoint(0.0, Vectors.dense(2.0, 1.3, 1.0)),
new LabeledPoint(1.0, Vectors.dense(0.0, 1.2, -0.5))
), LabeledPoint.class);
// Create a LogisticRegression instance. This instance is an Estimator.
LogisticRegression lr = new LogisticRegression();
// Print out the parameters, documentation, and any default values.
System.out.println("LogisticRegression parameters:\n" + lr.explainParams() + "\n");
// We may set parameters using setter methods.
lr.setMaxIter(10).setRegParam(0.01);
// Learn a LogisticRegression model. This uses the parameters stored in lr.
LogisticRegressionModel model1 = lr.fit(training);
// Since model1 is a Model (i.e., a Transformer produced by an Estimator),
// we can view the parameters it used during fit().
// This prints the parameter (name: value) pairs, where names are unique IDs for this
// LogisticRegression instance.
System.out.println("Model 1 was fit using parameters: " + model1.parent().extractParamMap());
// We may alternatively specify parameters using a ParamMap.
ParamMap paramMap = new ParamMap()
.put(lr.maxIter().w(20)) // Specify 1 Param.
.put(lr.maxIter(), 30) // This overwrites the original maxIter.
.put(lr.regParam().w(0.1), lr.threshold().w(0.55)); // Specify multiple Params.
// One can also combine ParamMaps.
ParamMap paramMap2 = new ParamMap()
.put(lr.probabilityCol().w("myProbability")); // Change output column name
ParamMap paramMapCombined = paramMap.$plus$plus(paramMap2);
// Now learn a new model using the paramMapCombined parameters.
// paramMapCombined overrides all parameters set earlier via lr.set* methods.
LogisticRegressionModel model2 = lr.fit(training, paramMapCombined);
System.out.println("Model 2 was fit using parameters: " + model2.parent().extractParamMap());
// Prepare test documents.
DataFrame test = sqlContext.createDataFrame(Arrays.asList(
new LabeledPoint(1.0, Vectors.dense(-1.0, 1.5, 1.3)),
new LabeledPoint(0.0, Vectors.dense(3.0, 2.0, -0.1)),
new LabeledPoint(1.0, Vectors.dense(0.0, 2.2, -1.5))
), LabeledPoint.class);
// Make predictions on test documents using the Transformer.transform() method.
// LogisticRegression.transform will only use the 'features' column.
// Note that model2.transform() outputs a 'myProbability' column instead of the usual
// 'probability' column since we renamed the lr.probabilityCol parameter previously.
DataFrame results = model2.transform(test);
for (Row r : results.select("features", "label", "myProbability", "prediction").collect()) {
System.out.println("(" + r.get(0) + ", " + r.get(1) + ") -> prob=" + r.get(2)
+ ", prediction=" + r.get(3));
}
// $example off$
sc.stop();
}
}
|
