com.daleway.training.hadoop.condprob.ConditionalProbabilityPairWordExtractor.java Source code

Introduction

Here is the source code for com.daleway.training.hadoop.condprob.ConditionalProbabilityPairWordExtractor.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.daleway.training.hadoop.condprob;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Partitioner;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

/*
 * 
 * This mapper simply extracts the word pair 'for,xxx'
 *  
 */
public class ConditionalProbabilityPairWordExtractor {

    public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> {

        public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String t[] = value.toString().split("\t");
            if (t[0].startsWith("for,")) {
                context.write(new Text(t[0]), new Text(t[1] + "\t" + t[2]));
            }
        }
    }

    public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
        Job job = new Job(conf, "pair wise count");
        job.setJarByClass(ConditionalProbabilityPairWordExtractor.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);
        FileInputFormat.addInputPath(job, new Path(inputPath));
        FileOutputFormat.setOutputPath(job, new Path(outputPath));
        return job;

    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: pairwise <in> <out>");
            System.exit(2);
        }
        System.exit(createJob(conf, otherArgs[0], otherArgs[1]).waitForCompletion(true) ? 0 : 1);
    }
}