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

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

Introduction

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

Prototype

public void setOutputValueClass(Class<?> theClass) throws IllegalStateException 

Source Link

Document

Set the value class for job outputs.

Usage

From source file:Assignment3_P5_Top25Movies.Top25MovieRatingDriver.java

/**
 * @param args the command line arguments
 *//*from  w  w  w . j  a v a 2 s  .  co  m*/
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job1 = Job.getInstance(conf, "Movie Rating Count");
    job1.setJarByClass(Top25MovieRatingDriver.class);

    // the usual - get basic mapred ready
    job1.setMapperClass(Top25MovieRating_Mapper.class);
    job1.setCombinerClass(Top25MovieRating_Reducer.class);
    job1.setReducerClass(Top25MovieRating_Reducer.class);

    // this will basically out -> movieId, average rating
    job1.setOutputKeyClass(IntWritable.class);
    job1.setOutputValueClass(FloatWritable.class);

    FileInputFormat.addInputPath(job1, new Path(args[0]));
    FileOutputFormat.setOutputPath(job1, new Path(args[1]));
    boolean complete = job1.waitForCompletion(true);

    // here's where we sort
    Configuration conf2 = new Configuration();
    Job job2 = Job.getInstance(conf2, "Movie Rating Count");
    if (complete) {
        job2.setJarByClass(Top25MovieRatingDriver.class);

        // namesake fellow, take it and go types - mostly useless
        job2.setMapperClass(Top25MovieRating_Mapper1.class);
        job2.setMapOutputKeyClass(FloatWritable.class);
        job2.setMapOutputValueClass(IntWritable.class);

        // this is where we would ideally sort descendingly
        job2.setSortComparatorClass(Top25MovieRating_SortComparator.class);

        // o/p top 25, man
        job2.setNumReduceTasks(1);
        job2.setReducerClass(Top25MovieRating_Reducer1.class);
        job2.setOutputKeyClass(FloatWritable.class);
        job2.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job2, new Path(args[1]));
        FileOutputFormat.setOutputPath(job2, new Path(args[2]));
        System.exit(job2.waitForCompletion(true) ? 0 : 1);
    }
}

From source file:Assignment4_P2_StockAverageWithCombiner.StockAverageDriver.java

/**
 * @param args the command line arguments
 *//*ww  w .  j ava  2  s . c  o m*/
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Average Stock Price");
    job.setJarByClass(StockAverageDriver.class);

    job.setMapperClass(StockAverage_Mapper.class);
    job.setCombinerClass(StockAverage_Combiner.class);
    job.setReducerClass(StockAverage_Reducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(StockAverage_CompositeValueWritable.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:Assignment4_P3_InMemoryStdDeviation.MovieRatingStdDevDriver.java

/**
 * @param args the command line arguments
 *///  www .  jav a  2s  .c  o m
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Movie Rating Standard Deviation");
    job.setJarByClass(MovieRatingStdDevDriver.class);

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

    job.setReducerClass(MovieRatingStdDev_Reducer.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.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:Assignment4_P4_MemoryConscious.MovieRatingMemConsciousDriver.java

/**
 * @param args the command line arguments
 *///w w  w.  ja v a2s . c  om
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Movie Rating Mem Conscious Standard Deviation");
    job.setJarByClass(MovieRatingMemConsciousDriver.class);

    job.setMapperClass(MovieRatingMemConscious_Mapper.class);
    job.setCombinerClass(MovingRatingMemConscious_Combiner.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(SortedMapWritable.class);

    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.class);
    job.setReducerClass(MovieRatingMemConscious_Reducer.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:Assignment5_P2_DistinctIPAddress.DistinctIPAddressDriver.java

/**
 * @param args the command line arguments
 *//* w  ww  . ja v  a2  s .  co  m*/
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "IP Address Count");
    job.setJarByClass(DistinctIPAddressDriver.class);
    job.setMapperClass(DistinctIPAddress_Mapper.class);
    job.setCombinerClass(DistinctIPAddress_Reducer.class);
    job.setReducerClass(DistinctIPAddress_Reducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.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:Assignment5_P3_PartitionPattern.Partition_IPAddress_By_MonthDriver.java

/**
 * @param args the command line arguments
 *///  w  w  w. jav a2s  .c  om
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "IP Address By Date");
    job.setJarByClass(Partition_IPAddress_By_MonthDriver.class);
    job.setMapperClass(Partition_IPAddress_By_Month_Mapper.class);
    //job.setCombinerClass(Partition_IPAddress_By_Month_Reducer.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(Text.class);

    // partitioner class inclusion
    job.setPartitionerClass(Partition_IPAddress_By_Month_Partitioner.class);

    // set num of reduce tasks based on partition we need (here we need 12 cos total no.of months in a year)
    job.setNumReduceTasks(12);
    job.setReducerClass(Partition_IPAddress_By_Month_Reducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.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:Assignment5_P6_StructureToHierarchyPattern.Structure_HierarchyDriver.java

/**
 * @param args the command line arguments
 *//*  w w  w .  ja v  a2  s. c om*/
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {
    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "Structure to Hierarchy");
    job.setJarByClass(Structure_HierarchyDriver.class);

    // pass file 1 to this mapper in Text format
    MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class,
            Structure_Hierarchy_Movie_Mapper.class);

    // pass file 2 to this mapper in Text format
    MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class,
            Structure_Hierarchy_Tag_Mapper.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setReducerClass(Structure_Hierarchy_Reducer.class);

    FileOutputFormat.setOutputPath(job, new Path(args[2]));
    System.exit(job.waitForCompletion(true) ? 0 : 2);
}

From source file:at.illecker.hama.rootbeer.examples.util.RandomGraphGenerator.java

License:Apache License

public static void main(String[] args) throws Exception {
    if (args.length != 4) {
        System.out.println(/* w  ww  .  ja v a 2  s. c o m*/
                "USAGE: <Number of vertices> <Number of edges per vertex> <Number of partitions> <Outpath>");
        return;
    }
    System.out.println(Arrays.toString(args));
    Configuration conf = new Configuration();
    conf.setInt("hama.num.vertices", Integer.parseInt(args[0]));
    conf.setInt("hama.num.partitions", Integer.parseInt(args[2]));
    conf.setInt("number.edges", Integer.parseInt(args[1]));
    Job job = new Job(conf);

    Path generated = new Path(new Path(args[3]).getParent(), "generated");
    FileOutputFormat.setOutputPath(job, generated);
    FileSystem.get(conf).delete(generated, true);

    job.setJobName("RangeWriter");

    job.setJarByClass(SortGenMapper.class);
    job.setMapperClass(SortGenMapper.class);
    job.setNumReduceTasks(0);

    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(NullWritable.class);

    job.setInputFormatClass(RangeInputFormat.class);

    job.waitForCompletion(true);
    conf.setInt("max.id", Integer.valueOf(args[0]));
    job = new Job(conf);

    FileOutputFormat.setOutputPath(job, new Path(args[3]));
    FileSystem.get(conf).delete(new Path(args[3]), true);

    job.setJobName("Random Vertex Writer");

    FileInputFormat.addInputPath(job, generated);

    job.setJarByClass(RandomMapper.class);
    job.setMapperClass(RandomMapper.class);
    job.setReducerClass(Reducer.class);

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

    job.setNumReduceTasks(conf.getInt("hama.num.partitions", 2));
    job.setPartitionerClass(HashPartitioner.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    job.waitForCompletion(true);
}

From source file:AverageProj.AveragePrice.java

public int run(String[] args) throws Exception, ClassNotFoundException {
    Configuration conf = getConf();
    Job job = new Job(conf, "Avg");
    job.setJarByClass(AveragePrice.class);
    //final File f = new File(AveragePrice.class.getProtectionDomain().getCodeSource().getLocation().getPath());
    Path in = new Path(args[0]);
    Path out = new Path(args[1]);

    FileInputFormat.setInputPaths(job, in);
    FileOutputFormat.setOutputPath(job, out);

    job.setMapperClass(AvMapper.class);
    job.setMapOutputKeyClass(YearPrice.class);
    job.setMapOutputValueClass(DoubleWritable.class);

    job.setGroupingComparatorClass(YearSymComparator.class);
    // job.setCombinerClass(AvReducer.class);
    job.setReducerClass(AvReducer.class);

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

    job.setOutputKeyClass(YearPrice.class);
    job.setOutputValueClass(DoubleWritable.class);
    job.setPartitionerClass(AvgPartitioner.class);
    job.setNumReduceTasks(7);/*from w w  w.  java 2  s .  co m*/
    System.exit(job.waitForCompletion(true) ? 0 : 1);
    return 0;
}

From source file:averagerating_youtube.AverageRating_Youtube.java

/**
 * @param args the command line arguments
 *//* ww  w .  j ava  2s  . c om*/
@Override
public int run(String[] args) throws Exception {
    Job job = new Job(getConf());
    job.setJobName("AverageRating_Youtube");

    job.setJarByClass(AverageRating_Youtube.class);
    FileInputFormat.setInputPaths(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(AvgRating_CommCountMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(AverageRating_CommentCountTuple.class);
    job.setCombinerClass(AvgRating_CommCountCombiner.class);
    job.setReducerClass(AvgRating_CommCountReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(AverageRating_CommentCountTuple.class);
    boolean success = job.waitForCompletion(true);
    return success ? 0 : 1;
}