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

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

Introduction

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

Prototype

public void setCompressMapOutput(boolean compress) 

Source Link

Document

Should the map outputs be compressed before transfer?

Usage

From source file:org.sf.xrime.algorithms.partitions.connected.bi.EdgeSetMinorJoin.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, EdgeSetMinorJoin.class);
    conf.setJobName("EdgeSetMinorJoin");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(EdgeSet.class);
    conf.setMapperClass(MapClass.class);
    // Combiner is permitted here.
    conf.setCombinerClass(ReduceClass.class);
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {// w  w w  .j  av  a  2  s  .  c  o m
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.bi.EdgeSetSummarize.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, EdgeSetSummarize.class);
    conf.setJobName("EdgeSetSummarize");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(EdgeSet.class);
    conf.setMapperClass(MapClass.class);
    conf.setCombinerClass(ReduceClass.class);
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {//from  w ww  .  j av  a  2 s. co  m
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.bi.SpanningTreeGenerate.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, SpanningTreeGenerate.class);
    conf.setJobName("SpanningTreeGenerate");

    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(LabeledAdjSetVertex.class);
    conf.setMapperClass(MapClass.class);
    // No combiner is permitted, since the logic of reducer depends on the completeness
    // of information.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {//w ww .j  ava 2 s.  c om
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setMapOutputCompressorClass(GzipCodec.class);
    conf.setCompressMapOutput(true);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.bi.SpanningTreeRootChoose.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, SpanningTreeRootChoose.class);
    conf.setJobName("SpanningTreeRootChoose");

    // This is necessary.
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(LabeledAdjSetVertex.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(MapClass.class);
    // Since k2,v2 is different from k3,v3. No combiner is permitted.
    conf.setReducerClass(ReduceClass.class);
    // The format of input data is generated with WritableSerialization.
    conf.setInputFormat(SequenceFileInputFormat.class);
    try {//w w w  .  j a  va  2s  .c  o m
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    // Only one reducer is permitted, or the largest value will be wrong.
    conf.setNumReduceTasks(1);
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.bi.Tree2EdgeSet.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, Tree2EdgeSet.class);
    conf.setJobName("Tree2EdgeSet");

    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(PathAsVertexesList.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(EdgeSet.class);
    conf.setMapperClass(MapClass.class);
    // No combiner is permitted, since the logic of reducer depends on the completeness
    // of information.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {// w  ww. j a  v a 2 s.  c  om
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.strongly.BackwardTrimPartB.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, BackwardTrimPartB.class);
    conf.setJobName("BackwardTrimPartB");

    // the keys are vertex identifiers (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are vertexes (Writable)
    conf.setOutputValueClass(LabeledAdjBiSetVertex.class);
    conf.setMapperClass(MapClass.class);
    // No combiner is permitted.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {// w  w  w .  j  ava2s  .  co  m
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setMapOutputCompressorClass(GzipCodec.class);
    conf.setCompressMapOutput(true);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.strongly.ExtractDescMinusSCC.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, ExtractDescMinusSCC.class);
    conf.setJobName("ExtractDescMinusSCC");

    // the keys are vertex identifiers (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are vertexes (Writable)
    conf.setOutputValueClass(LabeledAdjBiSetVertex.class);
    conf.setMapperClass(MapClass.class);
    // No combiners.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {/*  ww w  . ja  v a2 s  . c o  m*/
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setMapOutputCompressorClass(GzipCodec.class);
    conf.setCompressMapOutput(true);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.strongly.ExtractPartitions.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, ExtractPartitions.class);
    conf.setJobName("ExtractPartitions");

    // the keys are vertex identifiers (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are vertexes (Writable)
    conf.setOutputValueClass(Text.class);
    conf.setMapperClass(MapClass.class);
    // No combiners.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    try {/*from  w  w  w. j ava 2s .  com*/
        Path[] paths = new Path[1];
        FileInputFormat.setInputPaths(conf, getSource().getPaths().toArray(paths));
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setMapOutputCompressorClass(GzipCodec.class);
    conf.setCompressMapOutput(true);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.strongly.ExtractPredMinusSCC.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, ExtractPredMinusSCC.class);
    conf.setJobName("ExtractPredMinusSCC");

    // the keys are vertex identifiers (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are vertexes (Writable)
    conf.setOutputValueClass(LabeledAdjBiSetVertex.class);
    conf.setMapperClass(MapClass.class);
    // No combiners.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {/*from  www . j ava 2s. com*/
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}

From source file:org.sf.xrime.algorithms.partitions.connected.strongly.ExtractRemains.java

License:Apache License

@Override
public void execute() throws ProcessorExecutionException {
    JobConf conf = new JobConf(context, ExtractRemains.class);
    conf.setJobName("ExtractRemains");

    // the keys are vertex identifiers (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are vertexes (Writable)
    conf.setOutputValueClass(LabeledAdjBiSetVertex.class);
    conf.setMapperClass(MapClass.class);
    // No combiners.
    conf.setReducerClass(ReduceClass.class);
    // makes the file format suitable for machine processing.
    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    try {//w w  w .java2  s . c o m
        FileInputFormat.setInputPaths(conf, getSource().getPath());
        FileOutputFormat.setOutputPath(conf, getDestination().getPath());
    } catch (IllegalAccessException e1) {
        throw new ProcessorExecutionException(e1);
    }
    conf.setNumMapTasks(getMapperNum());
    conf.setNumReduceTasks(getReducerNum());
    conf.setCompressMapOutput(true);
    conf.setMapOutputCompressorClass(GzipCodec.class);

    try {
        this.runningJob = JobClient.runJob(conf);
    } catch (IOException e) {
        throw new ProcessorExecutionException(e);
    }
}