Example usage for org.apache.hadoop.mapred JobConf setCombinerClass

List of usage examples for org.apache.hadoop.mapred JobConf setCombinerClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setCombinerClass.

Prototype

public void setCombinerClass(Class<? extends Reducer> theClass) 

Source Link

Document

Set the user-defined combiner class used to combine map-outputs before being sent to the reducers.

Usage

From source file:buildtestproject.MyFirstMapReduce.java

public static void main(String[] args) throws Exception {
    //Configuration conf = new Configuration();
    JobConf conf = new JobConf(MyFirstMapReduce.class);
    //Job job = Job.getInstance(conf, "word-count-one");
    conf.setJobName("word-count-one");

    conf.setMapperClass(TokenizerMapper.class);
    conf.setCombinerClass(IntSumReducer.class);
    conf.setReducerClass(IntSumReducer.class);

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    //        job.setJarByClass(MyFirstMapReduce.class);
    //        job.setMapperClass(TokenizerMapper.class);
    //        job.setCombinerClass(IntSumReducer.class);
    //        job.setReducerClass(IntSumReducer.class);
    //        /*from w ww  . jav  a2s.c om*/
    //        job.setOutputKeyClass(Text.class);
    //        job.setOutputValueClass(IntWritable.class);

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    //        FileInputFormat.addInputPath(job, new Path(args[0]));
    //        FileOutputFormat.setOutputPath(job, new Path(args[1]));

    JobClient.runJob(conf);

    //        System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:cn.edu.xmu.dm.mapreduce.MultiFileWordCount.java

License:Apache License

public int run(String[] args) throws Exception {

    if (args.length < 2) {
        printUsage();/* w  ww. j  a v a2 s  .c  o  m*/
        return 1;
    }

    JobConf job = new JobConf(getConf(), MultiFileWordCount.class);
    job.setJobName("MultiFileWordCount");

    // set the InputFormat of the job to our InputFormat
    job.setInputFormat(MyInputFormat.class);

    // the keys are words (strings)
    job.setOutputKeyClass(Text.class);
    // the values are counts (ints)
    job.setOutputValueClass(LongWritable.class);

    // use the defined mapper
    job.setMapperClass(MapClass.class);
    // use the WordCount Reducer
    job.setCombinerClass(LongSumReducer.class);
    job.setReducerClass(LongSumReducer.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    JobClient.runJob(job);

    return 0;
}

From source file:com.acme.extensions.mr.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    JobConf job = new JobConf();
    String[] otherArgs = new GenericOptionsParser(job, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);/*from  ww w.  j a va2 s .co m*/
    }

    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    JobClient.runJob(job);
}

From source file:com.aerospike.hadoop.examples.wordcountinput.WordCountInput.java

License:Apache License

public int run(final String[] args) throws Exception {

    log.info("run starting");

    final Configuration conf = getConf();

    JobConf job = new JobConf(conf, WordCountInput.class);
    job.setJobName("AerospikeWordCountInput");

    job.setInputFormat(AerospikeInputFormat.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    job.setOutputFormat(TextOutputFormat.class);

    FileOutputFormat.setOutputPath(job, new Path(args[0]));

    JobClient.runJob(job);/*from   ww  w  .j a va2s. c  om*/

    log.info("finished");
    return 0;
}

From source file:com.aerospike.hadoop.examples.wordcountoutput.WordCountOutput.java

License:Apache License

public int run(final String[] args) throws Exception {

    log.info("run starting");

    final Configuration conf = getConf();

    JobConf job = new JobConf(conf, WordCountOutput.class);
    job.setJobName("AerospikeWordCountOutput");

    for (int ii = 0; ii < args.length; ++ii) {
        FileInputFormat.addInputPath(job, new Path(args[ii]));
    }/*from   w ww  . ja  v a  2  s.  c  om*/

    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setOutputFormat(MyOutputFormat.class);

    JobClient.runJob(job);

    log.info("finished");
    return 0;
}

From source file:com.benchmark.mapred.Grep.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length < 4) {
        System.out.println("Grep <inDir> <outDir> <numreduces> <regex> [<group>]");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }//from ww  w.j av  a2s .co  m

    Path tempDir = new Path("grep-temp-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));

    JobConf grepJob = new JobConf(getConf(), Grep.class);

    try {

        Date startIteration = new Date();
        grepJob.setJobName("grep-search");

        FileInputFormat.setInputPaths(grepJob, args[0]);
        grepJob.setMapperClass(RegexMapper.class);
        grepJob.set("mapred.mapper.regex", args[3]);
        if (args.length == 5)
            grepJob.set("mapred.mapper.regex.group", args[4]);

        grepJob.setCombinerClass(LongSumReducer.class);
        grepJob.setReducerClass(LongSumReducer.class);
        FileOutputFormat.setOutputPath(grepJob, new Path(args[1]));
        grepJob.setOutputKeyClass(Text.class);
        grepJob.setOutputValueClass(LongWritable.class);
        grepJob.setNumReduceTasks(Integer.parseInt(args[2]));

        JobClient.runJob(grepJob);

        Date endIteration = new Date();
        System.out.println("The iteration took " + (endIteration.getTime() - startIteration.getTime()) / 1000
                + " seconds.");
    } finally {
        FileSystem.get(grepJob).delete(tempDir, true);
    }
    return 0;
}

From source file:com.benchmark.mapred.MultiFileWordCount.java

License:Apache License

public int run(String[] args) throws Exception {

    if (args.length < 2) {
        printUsage();//from ww  w .  j a  v a2  s.  c o  m
        return 1;
    }

    JobConf job = new JobConf(getConf(), MultiFileWordCount.class);
    job.setJobName("MultiFileWordCount");

    //set the InputFormat of the job to our InputFormat
    job.setInputFormat(MyInputFormat.class);

    // the keys are words (strings)
    job.setOutputKeyClass(Text.class);
    // the values are counts (ints)
    job.setOutputValueClass(LongWritable.class);

    //use the defined mapper
    job.setMapperClass(MapClass.class);
    //use the WordCount Reducer
    job.setCombinerClass(LongSumReducer.class);
    job.setReducerClass(LongSumReducer.class);

    FileInputFormat.addInputPaths(job, args[0]);
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    JobClient.runJob(job);

    return 0;
}

From source file:com.chriscx.mapred.Driver.java

public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), Driver.class);
    conf.setJobName("wordcount");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    List<String> other_args = new ArrayList<String>();
    for (int i = 0; i < args.length; ++i) {
        if ("-skip".equals(args[i])) {
            DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf);
            conf.setBoolean("wordcount.skip.patterns", true);
        } else {//from   www .jav a2s  .  com
            other_args.add(args[i]);
        }
    }

    FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

    JobClient.runJob(conf);
    return 0;
}

From source file:com.chriscx.matching.Driver.java

public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), com.chriscx.mapred.Driver.class);
    conf.setJobName("Matching");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    List<String> other_args = new ArrayList<String>();
    for (int i = 0; i < args.length; ++i) {
        if ("-skip".equals(args[i])) {
            DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf);
            conf.setBoolean("wordcount.skip.patterns", true);
        } else {//from w  w w. j  av  a  2s.  c  o m
            other_args.add(args[i]);
        }
    }

    FileInputFormat.setInputPaths(conf, new Path(other_args.get(0)));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

    JobClient.runJob(conf);
    return 0;
}

From source file:com.cloudera.hbase.OldWordCount.java

License:Open Source License

public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(WordCount.class);
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);//  ww w. j  a va 2 s.c o  m
    }
    conf.setJobName("word count");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    FileInputFormat.setInputPaths(conf, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(conf, new Path(otherArgs[1]));
    JobClient.runJob(conf);
    return;
}