Example usage for org.apache.hadoop.mapreduce Job setInputFormatClass

List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setInputFormatClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setInputFormatClass.

Prototype

public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException

Source Link

Document

Set the InputFormat for the job.

Usage

From source file:DateExample_Month.java

License:Apache License

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: wordcount <in> <out>");
        System.exit(2);//from  w w w .  j a va 2 s  .c o m
    }
    Job job = new Job(conf, "word count fs");
    job.setJarByClass(DateExample_Month.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    job.setInputFormatClass(IsValidKeyFormat.class);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:WordCount.java

License:Apache License

public int run(String[] args) throws Exception {
    ///start/*  w  ww  .  j  a v a 2 s.  co m*/
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }
    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";
        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);

            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);

            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }
        job.setInputFormatClass(ColumnFamilyInputFormat.class);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");

        //Change partitioner here
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);

        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row
        //Son degisiklik Super Column Support ?
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);

        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");
        job.waitForCompletion(true);
    }

    final double duration = (System.currentTimeMillis() - startTime) / 1000.0;
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:FindMaxPageRankNodes.java

License:Apache License

/**
 * Runs this tool./*from   w  w  w. jav a 2s  .c  o m*/
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("top n").create(TOP));

    CommandLine cmdline;
    CommandLineParser parser = new GnuParser();

    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        return -1;
    }

    if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT) || !cmdline.hasOption(TOP)) {
        System.out.println("args: " + Arrays.toString(args));
        HelpFormatter formatter = new HelpFormatter();
        formatter.setWidth(120);
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String inputPath = cmdline.getOptionValue(INPUT);
    String outputPath = cmdline.getOptionValue(OUTPUT);
    int n = Integer.parseInt(cmdline.getOptionValue(TOP));

    LOG.info("Tool name: " + FindMaxPageRankNodes.class.getSimpleName());
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);
    LOG.info(" - top: " + n);

    Configuration conf = getConf();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt("n", n);

    Job job = Job.getInstance(conf);
    job.setJobName(FindMaxPageRankNodes.class.getName() + ":" + inputPath);
    job.setJarByClass(FindMaxPageRankNodes.class);

    job.setNumReduceTasks(1);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(FloatWritable.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(FloatWritable.class);

    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:GetUserInfoGivenMovieId.java

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    conf.set("movieId", args[2]);
    Job job = new Job(conf, "GetUserInfoGivenMovieId");

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    job.setJarByClass(GetUserInfoGivenMovieId.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[3]));

    boolean flag1 = job.waitForCompletion(true);

    if (flag1) {/*from  ww w .ja v  a 2s.  co  m*/
        Configuration conf2 = new Configuration();
        //FileSystem fs = FileSystem.get(conf2);
        //Path Intermediate = new Path(args[1]);
        //DistributedCache.addCacheFile(Intermediate.toUri(), conf2);
        //DistributedCache.addCacheFile(new URI(args[1]),conf2);

        Job job2 = new Job(conf2, "UserInfo");
        /*Job job2 = new Job(new Configuration());
        Configuration conf2 = job.getConfiguration();
        job2.setJobName("Join with Cache");
        DistributedCache.addCacheFile(new URI(args[1]), conf2);*/
        job2.addCacheFile(new URI(args[1]));
        job2.setOutputKeyClass(Text.class);
        job2.setOutputValueClass(Text.class);
        job2.setJarByClass(GetUserInfoGivenMovieId.class);
        job2.setMapperClass(MapWithJoin.class);
        //job2.setCombinerClass(Reduce.class);
        job2.setReducerClass(ReduceFinal.class);

        job2.setInputFormatClass(TextInputFormat.class);
        job2.setOutputFormatClass(TextOutputFormat.class);

        FileInputFormat.addInputPath(job2, new Path(args[3]));
        FileOutputFormat.setOutputPath(job2, new Path(args[4]));
        job2.waitForCompletion(true);
    }
}

From source file:CrimenCasosTotales.java

public static void main(String args[]) throws Exception {

    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "casostotales");
    job.setJarByClass(WordCount.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

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

    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

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

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

From source file:DumpPageRankRecordsToPlainText.java

License:Apache License

/**
 * Runs this tool./*from w  w w  .j av  a 2  s  .c  o  m*/
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));

    CommandLine cmdline;
    CommandLineParser parser = new GnuParser();

    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        return -1;
    }

    if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) {
        System.out.println("args: " + Arrays.toString(args));
        HelpFormatter formatter = new HelpFormatter();
        formatter.setWidth(120);
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String inputPath = cmdline.getOptionValue(INPUT);
    String outputPath = cmdline.getOptionValue(OUTPUT);

    LOG.info("Tool name: " + DumpPageRankRecordsToPlainText.class.getSimpleName());
    LOG.info(" - input: " + inputPath);
    LOG.info(" - output: " + outputPath);

    Configuration conf = new Configuration();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);

    Job job = Job.getInstance(conf);
    job.setJobName(DumpPageRankRecordsToPlainText.class.getSimpleName());
    job.setJarByClass(DumpPageRankRecordsToPlainText.class);

    job.setNumReduceTasks(0);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(PageRankNode.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    return 0;
}

From source file:MaleUsersBelow7Years.java

public static void main(String args[]) throws Exception {
    Configuration configuration = new Configuration();

    Job job = new Job(configuration, "CountMaleUsersLessThan7");
    job.setJarByClass(MaleUsersBelow7Years.class);
    job.setMapperClass(Map.class);
    job.setReducerClass(Reducer.class);
    job.setCombinerClass(Reducer.class);

    //set output and input formats;mapper-input reducer-output
    job.setInputFormatClass(TextInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    FileInputFormat.addInputPath(job, new Path(args[0])); //path for input file
    FileOutputFormat.setOutputPath(job, new Path(args[1])); // Path for output file
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

From source file:WordCount.java

License:Apache License

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

    ///start// ww  w .jav  a  2  s  .c o m
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }
    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";
        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);

        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);

            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);

            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);

            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }

        job.setInputFormatClass(ColumnFamilyInputFormat.class);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);

        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row
        //Son degisiklik
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);
        //System.out.println("tessssssaaat");

        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");

        job.waitForCompletion(true);
    }
    //print
    final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:WordCount.java

License:Apache License

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

    ///start//from w w w  .  ja  v  a 2s .  c  o  m
    final long startTime = System.currentTimeMillis();
    String outputReducerType = "filesystem";
    if (args != null && args[0].startsWith(OUTPUT_REDUCER_VAR)) {
        String[] s = args[0].split("=");
        if (s != null && s.length == 2)
            outputReducerType = s[1];
    }

    logger.info("output reducer type: " + outputReducerType);

    // use a smaller page size that doesn't divide the row count evenly to exercise the paging logic better
    ConfigHelper.setRangeBatchSize(getConf(), 99);

    for (int i = 0; i < WordCountSetup.TEST_COUNT; i++) {
        String columnName = "userId";

        Job job = new Job(getConf(), "wordcount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);

        if (outputReducerType.equalsIgnoreCase("filesystem")) {
            job.setReducerClass(ReducerToFilesystem.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(Text.class);
            FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH_PREFIX + i));
        } else {
            job.setReducerClass(ReducerToCassandra.class);
            job.setMapOutputKeyClass(Text.class);
            job.setMapOutputValueClass(Text.class);
            job.setOutputKeyClass(ByteBuffer.class);
            job.setOutputValueClass(List.class);
            job.setOutputFormatClass(ColumnFamilyOutputFormat.class);
            ConfigHelper.setOutputColumnFamily(job.getConfiguration(), KEYSPACE, OUTPUT_COLUMN_FAMILY);
            job.getConfiguration().set(CONF_COLUMN_NAME, "sum");
        }
        job.setInputFormatClass(ColumnFamilyInputFormat.class);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), "9160");
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setInputPartitioner(job.getConfiguration(), "RandomPartitioner");
        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);

        SlicePredicate predicate = new SlicePredicate()
                .setColumn_names(Arrays.asList(ByteBufferUtil.bytes(columnName)));
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate);

        // this will cause the predicate to be ignored in favor of scanning everything as a wide row          
        //Son degisiklik
        // ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY, true);
        //System.out.println("tessssssaaat");

        ConfigHelper.setOutputInitialAddress(job.getConfiguration(), "localhost");
        ConfigHelper.setOutputPartitioner(job.getConfiguration(), "RandomPartitioner");

        job.waitForCompletion(true);
    }

    //print
    final double duration = (System.currentTimeMillis() - startTime) / 1000.0; // after
    System.out.println();
    System.out.println("Job Finished in " + duration + " seconds");
    System.out.println();

    return 0;
}

From source file:ExtractTopPersonalizedPageRankNodes.java

License:Apache License

/**
 * Runs this tool./*from  w w w  .jav  a 2  s  .  c o  m*/
 */
@SuppressWarnings({ "static-access" })
public int run(String[] args) throws Exception {
    Options options = new Options();

    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
    options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));
    options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("top n").create(TOP));
    options.addOption(OptionBuilder.withArgName("src").hasArg().withDescription("source node").create(SRC));

    CommandLine cmdline;
    CommandLineParser parser = new GnuParser();

    try {
        cmdline = parser.parse(options, args);
    } catch (ParseException exp) {
        System.err.println("Error parsing command line: " + exp.getMessage());
        return -1;
    }

    if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(TOP)) {
        System.out.println("args: " + Arrays.toString(args));
        HelpFormatter formatter = new HelpFormatter();
        formatter.setWidth(120);
        formatter.printHelp(this.getClass().getName(), options);
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    String inputPath = cmdline.getOptionValue(INPUT);
    String outputPath = "abc";//cmdline.getOptionValue(OUTPUT);
    int n = Integer.parseInt(cmdline.getOptionValue(TOP));

    //LOG.info("Tool name: " + ExtractTopPersonalizedPageRankNodes.class.getSimpleName());
    //LOG.info(" - input: " + inputPath);
    //LOG.info(" - output: " + outputPath);
    //LOG.info(" - top: " + n);

    Configuration conf = getConf();
    conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);
    conf.setInt(TOP_PG, n);

    Job job = Job.getInstance(conf);
    job.setJobName(ExtractTopPersonalizedPageRankNodes.class.getName() + ":" + inputPath);
    job.setJarByClass(ExtractTopPersonalizedPageRankNodes.class);

    job.setNumReduceTasks(1);

    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.setMapOutputKeyClass(PairOfIntFloat.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(FloatWritable.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(MyMapper.class);
    job.setPartitionerClass(MyPartitioner.class);
    job.setReducerClass(MyReducer.class);

    // Delete the output directory if it exists already.
    FileSystem.get(conf).delete(new Path(outputPath), true);

    job.waitForCompletion(true);

    FileSystem fileSystem = FileSystem.get(conf);
    Path path = new Path(outputPath + "/part-r-00000");
    ;
    //MapFile.Reader reader = new MapFile.Reader(new Path(outputPath+ "/part-r-00000"),conf);

    // InputStream fis=new FileInputStream(outputPath+"/part-r-00000");
    BufferedReader br = new BufferedReader(new InputStreamReader(fileSystem.open(path)));
    String s;
    float key;//=new FloatWritable();
    int value;//=new IntWritable();
    while ((s = br.readLine()) != null) {
        String[] sources = s.split("\\s+");
        key = Float.parseFloat(sources[0]);
        value = Integer.parseInt(sources[1]);
        if (key == 0.0f) {
            System.out.print("\n" + "Source: " + value + "\n");
        } else {
            System.out.print(String.format("%.5f %d", key, value) + "\n");
        }
    }
    //reader.close();
    br.close();

    //while(!SysOut.isEmpty())
    //{
    //   System.out.print(SysOut.poll());
    //}

    return 0;
}