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:com.cloudera.recordservice.examples.mapreduce.WordCount.java

License:Apache License

public void run(String[] args) throws Exception {
    boolean useRecordService = true;
    if (args.length == 3) {
        useRecordService = Boolean.parseBoolean(args[2]);
    } else if (args.length != 2) {
        System.err.println("Usage: WordCount <input path> <output path>");
        System.exit(-1);//from   w  w  w . j  a  v  a2s . c  o m
    }
    String input = args[0].trim();
    String output = args[1];

    JobConf conf = new JobConf(WordCount.class);
    conf.setJobName("wordcount-" + (useRecordService ? "with" : "without") + "-RecordService");

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

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

    if (useRecordService) {
        conf.setInputFormat(com.cloudera.recordservice.mapred.TextInputFormat.class);
        RecordServiceConfig.setInput(conf, input);
    } else {
        conf.setInputFormat(TextInputFormat.class);
        FileInputFormat.setInputPaths(conf, new Path(input));
    }

    FileSystem fs = FileSystem.get(conf);
    Path outputPath = new Path(output);
    if (fs.exists(outputPath))
        fs.delete(outputPath, true);
    conf.setOutputFormat(TextOutputFormat.class);
    FileOutputFormat.setOutputPath(conf, outputPath);

    JobClient.runJob(conf);
    System.out.println("Done");
}

From source file:com.cloudera.recordservice.mapreduce.testapps.RecordCount.java

License:Apache License

public static long countRecords(String path) throws IOException {
    String output = TestUtil.getTempDirectory();
    Path inputPath = new Path(path);
    Path outputPath = new Path(output);

    JobConf conf = new JobConf(RecordCount.class);
    conf.setJobName("recordcount");

    conf.setOutputKeyClass(NullWritable.class);
    conf.setOutputValueClass(LongWritable.class);

    conf.setInt("mapreduce.job.reduces", 1);
    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(com.cloudera.recordservice.mapred.TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    FileInputFormat.setInputPaths(conf, inputPath);
    FileOutputFormat.setOutputPath(conf, outputPath);

    JobClient.runJob(conf);/*from  w  w  w. j  ava  2s  .  c om*/

    // Read the result and return it. Since we set the number of reducers to 1,
    // there is always just one file containing the value.
    FileSystem fs = outputPath.getFileSystem(conf);
    FSDataInputStream resultStream = fs.open(new Path(output + "/part-00000"));
    byte[] bytes = new byte[16];
    int length = resultStream.read(bytes);
    String result = new String(bytes, 0, length).trim();
    return Long.parseLong(result);
}

From source file:com.cloudera.recordservice.tests.TestMiniClusterController.java

License:Apache License

public static void fillInWordCountMRJobConf(JobConf conf) {
    String input = "select n_comment from tpch.nation";

    conf.setJobName("samplejob-wordcount");

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

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

    conf.setInputFormat(com.cloudera.recordservice.mapred.TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);
    com.cloudera.recordservice.mr.RecordServiceConfig.setInputQuery(conf, input);
    setRandomOutputDir(conf);/*from   ww w . ja  v a 2  s. c  om*/
}

From source file:com.datatorrent.demos.mroperator.LogCountsPerHour.java

License:Open Source License

public int run(String[] args) throws Exception {
    // Create a configuration
    Configuration conf = getConf();

    // Create a job from the default configuration that will use the WordCount class
    JobConf job = new JobConf(conf, LogCountsPerHour.class);

    // Define our input path as the first command line argument and our output path as the second
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);

    // Create File Input/Output formats for these paths (in the job)
    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);

    // Configure the job: name, mapper, reducer, and combiner
    job.setJobName("LogAveragePerHour");
    job.setMapperClass(LogMapClass.class);
    job.setReducerClass(LogReduce.class);
    job.setCombinerClass(LogReduce.class);

    // Configure the output
    job.setOutputFormat(TextOutputFormat.class);
    job.setOutputKeyClass(DateWritable.class);
    job.setOutputValueClass(IntWritable.class);

    // Run the job
    JobClient.runJob(job);/*  w ww  .  jav  a  2  s.co m*/
    return 0;
}

From source file:com.datatorrent.demos.mroperator.WordCount.java

License:Open Source License

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

    JobConf conf = new JobConf(this.getClass());
    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);

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

    JobClient.runJob(conf);/*ww  w  .ja v  a  2s . c  o  m*/
}

From source file:com.example.hadoop.mapreduce.test.MapReduceTest.java

License:Open Source License

public static void main(String[] args) throws IOException {
    String input = HDFS_PATH + "/input/README.txt";
    String input2 = HDFS_PATH + "/input/README2.txt";
    String output = HDFS_PATH + "/test/output";

    // ?mapreduce???
    if (HdfsClient.exists(output)) {
        HdfsClient.rm(output);/*from  ww  w. ja va 2s . co m*/
    }

    JobConf conf = new JobConf(MapReduceTest.class);
    conf.setJobName("MapReduceTest");
    conf.addResource("classpath:/hadoop/core-site.xml");
    conf.addResource("classpath:/hadoop/hdfs-site.xml");
    conf.addResource("classpath:/hadoop/mapred-site.xml");

    // mapper
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(IntWritable.class);

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

    // mapper
    conf.setMapperClass(MapperTest.class);
    // combiner?????mapper??reducer?
    conf.setCombinerClass(ReducerTest.class);
    // reducer
    conf.setReducerClass(ReducerTest.class);

    // MapReduce?
    conf.setInputFormat(TextInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    // MapReduce?
    FileInputFormat.setInputPaths(conf, new Path[] { new Path(input), new Path(input2) });
    // MapReduce?
    FileOutputFormat.setOutputPath(conf, new Path(output));

    try {
        JobClient.runJob(conf);
    } catch (IOException e) {
        e.printStackTrace();
    }
}

From source file:com.github.gaoyangthu.demo.mapred.DBCountPageView.java

License:Apache License

@Override
//Usage DBCountPageView [driverClass dburl]
public int run(String[] args) throws Exception {

    String driverClassName = DRIVER_CLASS;
    String url = DB_URL;/*from   www.  j  a v  a2s.  c o m*/

    if (args.length > 1) {
        driverClassName = args[0];
        url = args[1];
    }

    initialize(driverClassName, url);

    JobConf job = new JobConf(getConf(), DBCountPageView.class);

    job.setJobName("Count Pageviews of URLs");

    job.setMapperClass(PageviewMapper.class);
    job.setCombinerClass(LongSumReducer.class);
    job.setReducerClass(PageviewReducer.class);

    DBConfiguration.configureDB(job, driverClassName, url);

    DBInputFormat.setInput(job, AccessRecord.class, "Access", null, "url", AccessFieldNames);

    DBOutputFormat.setOutput(job, "Pageview", PageviewFieldNames);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(LongWritable.class);

    job.setOutputKeyClass(PageviewRecord.class);
    job.setOutputValueClass(NullWritable.class);

    try {
        JobClient.runJob(job);

        boolean correct = verify();
        if (!correct) {
            throw new RuntimeException("Evaluation was not correct!");
        }
    } finally {
        shutdown();
    }
    return 0;
}

From source file:com.github.gaoyangthu.demo.mapred.Grep.java

License:Apache License

public int run(String[] args) throws Exception {
    if (args.length < 3) {
        System.out.println("Grep <inDir> <outDir> <regex> [<group>]");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }/* w w w  . j av  a  2  s .  co m*/

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

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

    try {

        grepJob.setJobName("grep-search");

        FileInputFormat.setInputPaths(grepJob, args[0]);

        grepJob.setMapperClass(RegexMapper.class);
        grepJob.set("mapred.mapper.regex", args[2]);
        if (args.length == 4)
            grepJob.set("mapred.mapper.regex.group", args[3]);

        grepJob.setCombinerClass(LongSumReducer.class);
        grepJob.setReducerClass(LongSumReducer.class);

        FileOutputFormat.setOutputPath(grepJob, tempDir);
        grepJob.setOutputFormat(SequenceFileOutputFormat.class);
        grepJob.setOutputKeyClass(Text.class);
        grepJob.setOutputValueClass(LongWritable.class);

        JobClient.runJob(grepJob);

        JobConf sortJob = new JobConf(Grep.class);
        sortJob.setJobName("grep-sort");

        FileInputFormat.setInputPaths(sortJob, tempDir);
        sortJob.setInputFormat(SequenceFileInputFormat.class);

        sortJob.setMapperClass(InverseMapper.class);

        sortJob.setNumReduceTasks(1); // write a single file
        FileOutputFormat.setOutputPath(sortJob, new Path(args[1]));
        sortJob.setOutputKeyComparatorClass // sort by decreasing freq
        (LongWritable.DecreasingComparator.class);

        JobClient.runJob(sortJob);
    } finally {
        FileSystem.get(grepJob).delete(tempDir, true);
    }
    return 0;
}

From source file:com.hadoopilluminated.examples.Grep.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length < 3) {
        System.out.println("Grep <inDir> <outDir> <regex> [<group>]");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }/*  ww w .ja v  a2  s .com*/

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

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

    try {

        grepJob.setJobName("grep-search");

        FileInputFormat.setInputPaths(grepJob, args[0]);

        grepJob.setMapperClass(RegexMapper.class);
        grepJob.set("mapred.mapper.regex", args[2]);
        if (args.length == 4) {
            grepJob.set("mapred.mapper.regex.group", args[3]);
        }

        grepJob.setCombinerClass(LongSumReducer.class);
        grepJob.setReducerClass(LongSumReducer.class);

        FileOutputFormat.setOutputPath(grepJob, tempDir);
        grepJob.setOutputFormat(SequenceFileOutputFormat.class);
        grepJob.setOutputKeyClass(Text.class);
        grepJob.setOutputValueClass(LongWritable.class);

        JobClient.runJob(grepJob);

        JobConf sortJob = new JobConf(getConf(), Grep.class);
        sortJob.setJobName("grep-sort");

        FileInputFormat.setInputPaths(sortJob, tempDir);
        sortJob.setInputFormat(SequenceFileInputFormat.class);

        sortJob.setMapperClass(InverseMapper.class);

        sortJob.setNumReduceTasks(1); // write a single file
        FileOutputFormat.setOutputPath(sortJob, new Path(args[1]));
        sortJob.setOutputKeyComparatorClass // sort by decreasing freq
        (LongWritable.DecreasingComparator.class);

        JobClient.runJob(sortJob);
    } finally {
        FileSystem.get(grepJob).delete(tempDir, true);
    }
    return 0;
}

From source file:com.hp.hplc.mr.driver.WordCount.java

License:Apache License

/**
 * The main driver for word count map/reduce program.
 * Invoke this method to submit the map/reduce job.
 * @throws IOException When there is communication problems with the
 *                     job tracker.//from   w w  w .  ja  v  a2s. c om
 */
public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), WordCount.class);
    conf.setJobName("wordcount");

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

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

    List<String> other_args = new ArrayList<String>();
    for (int i = 0; i < args.length; ++i) {
        try {
            if ("-m".equals(args[i])) {
                conf.setNumMapTasks(Integer.parseInt(args[++i]));
            } else if ("-r".equals(args[i])) {
                conf.setNumReduceTasks(Integer.parseInt(args[++i]));
                System.out.println("# of reduces: " + conf.getNumReduceTasks());
            } else {
                other_args.add(args[i]);
            }
        } catch (NumberFormatException except) {
            System.out.println("ERROR: Integer expected instead of " + args[i]);
            return printUsage();
        } catch (ArrayIndexOutOfBoundsException except) {
            System.out.println("ERROR: Required parameter missing from " + args[i - 1]);
            return printUsage();
        }
    }
    // Make sure there are exactly 2 parameters left.
    if (other_args.size() != 2) {
        System.out.println("ERROR: Wrong number of parameters: " + other_args.size() + " instead of 2.");
        return printUsage();
    }
    FileInputFormat.setInputPaths(conf, other_args.get(0));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));

    JobClient.runJob(conf);

    return 0;
}