com.spark.cis833.extra.SparkPageRank.java Source code

Introduction

Here is the source code for com.spark.cis833.extra.SparkPageRank.java

Source

/*
 * 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 com.spark.cis833.extra;

import scala.Tuple2;
import com.google.common.collect.Iterables;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFlatMapFunction;
import org.apache.spark.api.java.function.PairFunction;
import java.util.ArrayList;
import java.util.List;
import java.util.Iterator;
import java.util.regex.Pattern;

/**
 * Computes the PageRank of URLs from an input file. Input file should
 * be in format of:
 * URL         neighbor URL
 * URL         neighbor URL
 * URL         neighbor URL
 * ...
 * where URL and their neighbors are separated by space(s).
 */
public final class SparkPageRank {
    private static final Pattern SPACES = Pattern.compile("\\t");

    private static class Sum implements Function2<Double, Double, Double> {
        @Override
        public Double call(Double a, Double b) {
            return a + b;
        }
    }

    public static void main(String[] args) throws Exception {
        if (args.length < 2) {
            System.err.println("Usage: SparkPageRank <input> <output>");
            System.exit(1);
        }
        SparkConf sparkConf = new SparkConf().setAppName("SparkPageRank");
        JavaSparkContext ctx = new JavaSparkContext(sparkConf);
        // Loads in input file. It should be in format of:
        //     URL         neighbor URL
        //     URL         neighbor URL
        //     URL         neighbor URL
        //     ...
        JavaRDD<String> lines = ctx.textFile(args[0], 1);
        // Loads all URLs from input file and initialize their neighbors.
        JavaPairRDD<String, Iterable<String>> links = lines.mapToPair(new PairFunction<String, String, String>() {
            @Override
            public Tuple2<String, String> call(String s) {
                String[] parts = SPACES.split(s);
                return new Tuple2<String, String>(parts[0], parts[1]);
            }
        }).distinct().groupByKey().cache();
        // Loads all URLs with other URL(s) link to from input file and initialize ranks of them to one.
        JavaPairRDD<String, Double> ranks = links.mapValues(new Function<Iterable<String>, Double>() {
            @Override
            public Double call(Iterable<String> rs) {
                return 1.0;
            }
        });
        // Calculates and updates URL ranks continuously using PageRank algorithm.
        for (int current = 0; current < Integer.parseInt("10"); current++) {
            // Calculates URL contributions to the rank of other URLs.
            JavaPairRDD<String, Double> contribs = links.join(ranks).values()
                    .flatMapToPair(new PairFlatMapFunction<Tuple2<Iterable<String>, Double>, String, Double>() {
                        @Override
                        public Iterable<Tuple2<String, Double>> call(Tuple2<Iterable<String>, Double> s) {
                            int urlCount = Iterables.size(s._1);
                            List<Tuple2<String, Double>> results = new ArrayList<Tuple2<String, Double>>();
                            for (String n : s._1) {
                                results.add(new Tuple2<String, Double>(n, s._2() / urlCount));
                            }
                            return results;
                        }
                    }).sortByKey(false);
            // Re-calculates URL ranks based on neighbor contributions.
            ranks = contribs.reduceByKey(new Sum()).mapValues(new Function<Double, Double>() {
                @Override
                public Double call(Double sum) {
                    return 0.15 + sum * 0.85;
                }
            }).sortByKey(false);
        }

        // Collects all URL ranks and dump them to console.
        List<Tuple2<String, Double>> output = ranks.collect();
        for (Tuple2<?, ?> tuple : output) {
            System.out.println(tuple._1() + " has rank: " + tuple._2() + ".");
        }

        JavaPairRDD<Double, String> swap1 = ranks
                .mapToPair(new PairFunction<Tuple2<String, Double>, Double, String>() {
                    @Override
                    public Tuple2<Double, String> call(Tuple2<String, Double> item) throws Exception {
                        return item.swap();
                    }

                }).sortByKey(false);

        swap1.saveAsTextFile(args[1]);

        ctx.stop();
    }
}