org.apache.spark.examples.JavaPageRank Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of snappy-spark-examples_2.10 Show documentation
SnappyData distributed data store and execution engine
There is a newer version: 1.6.2-6
Show newest version
/*
 * 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;



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).
 *
 * This is an example implementation for learning how to use Spark. For more conventional use,
 * please refer to org.apache.spark.graphx.lib.PageRank
 */
public final class JavaPageRank {
  private static final Pattern SPACES = Pattern.compile("\\s+");

  static void showWarning() {
    String warning = "WARN: This is a naive implementation of PageRank " +
            "and is given as an example! \n" +
            "Please use the PageRank implementation found in " +
            "org.apache.spark.graphx.lib.PageRank for more conventional use.";
    System.err.println(warning);
  }

  private static class Sum implements Function2 {
    @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: JavaPageRank  ");
      System.exit(1);
    }

    showWarning();

    SparkConf sparkConf = new SparkConf().setAppName("JavaPageRank");
    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 lines = ctx.textFile(args[0], 1);

    // Loads all URLs from input file and initialize their neighbors.
    JavaPairRDD> links = lines.mapToPair(new PairFunction() {
      @Override
      public Tuple2 call(String s) {
        String[] parts = SPACES.split(s);
        return new Tuple2(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 ranks = links.mapValues(new Function, Double>() {
      @Override
      public Double call(Iterable rs) {
        return 1.0;
      }
    });

    // Calculates and updates URL ranks continuously using PageRank algorithm.
    for (int current = 0; current < Integer.parseInt(args[1]); current++) {
      // Calculates URL contributions to the rank of other URLs.
      JavaPairRDD contribs = links.join(ranks).values()
        .flatMapToPair(new PairFlatMapFunction, Double>, String, Double>() {
          @Override
          public Iterable> call(Tuple2, Double> s) {
            int urlCount = Iterables.size(s._1);
            List> results = new ArrayList>();
            for (String n : s._1) {
              results.add(new Tuple2(n, s._2() / urlCount));
            }
            return results;
          }
      });

      // Re-calculates URL ranks based on neighbor contributions.
      ranks = contribs.reduceByKey(new Sum()).mapValues(new Function() {
        @Override
        public Double call(Double sum) {
          return 0.15 + sum * 0.85;
        }
      });
    }

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

    ctx.stop();
  }
}