examples/mllib/JavaStratifiedSamplingExample.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.examples.mllib;
0019
0020 import com.google.common.collect.ImmutableMap;
0021 import org.apache.spark.SparkConf;
0022 import org.apache.spark.api.java.JavaSparkContext;
0023
0024 // $example on$
0025 import java.util.*;
0026
0027 import scala.Tuple2;
0028
0029 import org.apache.spark.api.java.JavaPairRDD;
0030 // $example off$
0031
0032 public class JavaStratifiedSamplingExample {
0033   public static void main(String[] args) {
0034
0035     SparkConf conf = new SparkConf().setAppName("JavaStratifiedSamplingExample");
0036     JavaSparkContext jsc = new JavaSparkContext(conf);
0037
0038     @SuppressWarnings("unchecked")
0039     // $example on$
0040     List<Tuple2<Integer, Character>> list = Arrays.asList(
0041         new Tuple2<>(1, 'a'),
0042         new Tuple2<>(1, 'b'),
0043         new Tuple2<>(2, 'c'),
0044         new Tuple2<>(2, 'd'),
0045         new Tuple2<>(2, 'e'),
0046         new Tuple2<>(3, 'f')
0047     );
0048
0049     JavaPairRDD<Integer, Character> data = jsc.parallelizePairs(list);
0050
0051     // specify the exact fraction desired from each key Map<K, Double>
0052     ImmutableMap<Integer, Double> fractions = ImmutableMap.of(1, 0.1, 2, 0.6, 3, 0.3);
0053
0054     // Get an approximate sample from each stratum
0055     JavaPairRDD<Integer, Character> approxSample = data.sampleByKey(false, fractions);
0056     // Get an exact sample from each stratum
0057     JavaPairRDD<Integer, Character> exactSample = data.sampleByKeyExact(false, fractions);
0058     // $example off$
0059
0060     System.out.println("approxSample size is " + approxSample.collect().size());
0061     for (Tuple2<Integer, Character> t : approxSample.collect()) {
0062       System.out.println(t._1() + " " + t._2());
0063     }
0064
0065     System.out.println("exactSample size is " + exactSample.collect().size());
0066     for (Tuple2<Integer, Character> t : exactSample.collect()) {
0067       System.out.println(t._1() + " " + t._2());
0068     }
0069
0070     jsc.stop();
0071   }
0072 }