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

Introduction

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

Prototype

public void setCombinerClass(Class<? extends Reducer> cls) throws IllegalStateException 

Source Link

Document

Set the combiner class for the job.

Usage

From source file:com.accumulobook.advanced.mapreduce.MapReduceFilesExample.java

License:Apache License

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

    Job job = Job.getInstance(this.getConf());
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(WordCount.WordCountMapper.class);
    job.setCombinerClass(WordCount.WordCountCombiner.class);
    job.setReducerClass(WordCount.WordCountReducer.class);

    // clone the articles table
    ZooKeeperInstance inst = new ZooKeeperInstance(args[0], args[1]);
    Connector conn = inst.getConnector(args[2], new PasswordToken(args[3]));

    conn.tableOperations().clone(WikipediaConstants.ARTICLES_TABLE, WikipediaConstants.ARTICLES_TABLE_CLONE,
            true, Collections.EMPTY_MAP, Collections.EMPTY_SET);

    // take cloned table offline, waiting until the operation is complete
    boolean wait = true;
    conn.tableOperations().offline(WikipediaConstants.ARTICLES_TABLE_CLONE, wait);

    ClientConfiguration zkiConfig = new ClientConfiguration().withInstance(args[0]).withZkHosts(args[1]);

    // input/*from w w w . j  av  a  2  s .c  o m*/
    job.setInputFormatClass(AccumuloInputFormat.class);
    AccumuloInputFormat.setInputTableName(job, WikipediaConstants.ARTICLES_TABLE_CLONE);
    List<Pair<Text, Text>> columns = new ArrayList<>();
    columns.add(new Pair(WikipediaConstants.CONTENTS_FAMILY_TEXT, new Text("")));

    AccumuloInputFormat.fetchColumns(job, columns);
    AccumuloInputFormat.setZooKeeperInstance(job, zkiConfig);
    AccumuloInputFormat.setConnectorInfo(job, args[2], new PasswordToken(args[3]));

    // configure to use underlying RFiles
    AccumuloInputFormat.setOfflineTableScan(job, true);

    // output
    job.setOutputFormatClass(AccumuloOutputFormat.class);

    BatchWriterConfig bwConfig = new BatchWriterConfig();

    AccumuloOutputFormat.setBatchWriterOptions(job, bwConfig);
    AccumuloOutputFormat.setZooKeeperInstance(job, zkiConfig);
    AccumuloOutputFormat.setConnectorInfo(job, args[2], new PasswordToken(args[3]));
    AccumuloOutputFormat.setDefaultTableName(job, WikipediaConstants.WORD_COUNT_TABLE);
    AccumuloOutputFormat.setCreateTables(job, true);

    job.setJarByClass(WordCount.class);

    job.waitForCompletion(true);
    //job.submit();

    return 0;
}

---

From source file:com.accumulobook.advanced.mapreduce.WordCount.java

License:Apache License

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

    Job job = Job.getInstance(new Configuration());
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    job.setMapperClass(WordCountMapper.class);
    job.setCombinerClass(WordCountCombiner.class);
    job.setReducerClass(WordCountReducer.class);

    // input/* www .  j a  v a  2s.c om*/
    job.setInputFormatClass(AccumuloInputFormat.class);

    ClientConfiguration zkiConfig = new ClientConfiguration().withInstance(args[0]).withZkHosts(args[1]);

    AccumuloInputFormat.setInputTableName(job, WikipediaConstants.ARTICLES_TABLE);
    List<Pair<Text, Text>> columns = new ArrayList<>();
    columns.add(new Pair(WikipediaConstants.CONTENTS_FAMILY_TEXT, new Text("")));

    AccumuloInputFormat.fetchColumns(job, columns);
    AccumuloInputFormat.setZooKeeperInstance(job, zkiConfig);
    AccumuloInputFormat.setConnectorInfo(job, args[2], new PasswordToken(args[3]));

    // output
    job.setOutputFormatClass(AccumuloOutputFormat.class);

    BatchWriterConfig config = new BatchWriterConfig();

    AccumuloOutputFormat.setBatchWriterOptions(job, config);
    AccumuloOutputFormat.setZooKeeperInstance(job, zkiConfig);
    AccumuloOutputFormat.setConnectorInfo(job, args[2], new PasswordToken(args[3]));
    AccumuloOutputFormat.setDefaultTableName(job, WikipediaConstants.WORD_COUNT_TABLE);
    AccumuloOutputFormat.setCreateTables(job, true);

    job.setJarByClass(WordCount.class);

    job.submit();
    return 0;
}

---

From source file:com.alectenharmsel.hadoop.qa.LineCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    GenericOptionsParser parse = new GenericOptionsParser(new Configuration(), args);
    Configuration conf = parse.getConfiguration();

    String[] remainingArgs = parse.getRemainingArgs();
    if (remainingArgs.length != 2) {
        System.err.println("Usage: LineCount <input> <output>");
        System.exit(-1);/*from   w  w  w  .j av  a2 s.  c  o  m*/
    }

    Job job = Job.getInstance(conf, "LineCount");
    job.setJarByClass(LineCount.class);

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

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

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

    boolean success = job.waitForCompletion(true);

    int res = success ? 0 : 1;
    System.exit(res);
}

---

From source file:com.alectenharmsel.research.hadoop.LcCounters.java

License:Apache License

public static void main(String[] args) throws Exception {
    GenericOptionsParser parse = new GenericOptionsParser(new Configuration(), args);
    Configuration conf = parse.getConfiguration();

    String[] remainingArgs = parse.getRemainingArgs();
    if (remainingArgs.length != 2) {
        System.err.println("Usage: LineCount <input> <output>");
        System.exit(-1);//from   w  w  w  .j  av  a  2 s.co m
    }

    Job job = Job.getInstance(conf, "LineCount");
    job.setJarByClass(LineCount.class);

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

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);

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

    boolean success = job.waitForCompletion(true);

    //Get the counter here and print it
    Counters counters = job.getCounters();
    long total = counters.findCounter(LcCounters.NUM_LINES).getValue();
    System.out.println(Long.toString(total));

    int res = success ? 0 : 1;
    System.exit(res);
}

---

From source file:com.aliyun.emr.example.WordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    GenericOptionsParser optionParser = new GenericOptionsParser(conf, args);
    String[] remainingArgs = optionParser.getRemainingArgs();
    if (!(remainingArgs.length == 2 || remainingArgs.length == 4)) {
        System.err.println("Usage: wordcount <in> <out> [-skip skipPatternFile]");
        System.exit(2);/*w ww  . ja va 2 s  .c o  m*/
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    List<String> otherArgs = new ArrayList<String>();
    for (int i = 0; i < remainingArgs.length; ++i) {
        if ("-skip".equals(remainingArgs[i])) {
            job.addCacheFile(new Path(EMapReduceOSSUtil.buildOSSCompleteUri(remainingArgs[++i], conf)).toUri());
            job.getConfiguration().setBoolean("wordcount.skip.patterns", true);
        } else {
            otherArgs.add(remainingArgs[i]);
        }
    }
    FileInputFormat.addInputPath(job, new Path(EMapReduceOSSUtil.buildOSSCompleteUri(otherArgs.get(0), conf)));
    FileOutputFormat.setOutputPath(job,
            new Path(EMapReduceOSSUtil.buildOSSCompleteUri(otherArgs.get(1), conf)));

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

---

From source file:com.aliyun.openservices.tablestore.hadoop.RowCounter.java

License:Apache License

public static void main(String[] args) throws Exception {
    if (!parseArgs(args)) {
        printUsage();/*from   w ww  . j av  a 2s  . com*/
        System.exit(1);
    }
    if (endpoint == null || accessKeyId == null || accessKeySecret == null || table == null
            || outputPath == null) {
        printUsage();
        System.exit(1);
    }

    Configuration conf = new Configuration();
    Job job = Job.getInstance(conf, "row count");
    job.setJarByClass(RowCounter.class);
    job.setMapperClass(RowCounterMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    job.setInputFormatClass(TableStoreInputFormat.class);

    TableStore.setCredential(job, accessKeyId, accessKeySecret, securityToken);
    TableStore.setEndpoint(job, endpoint, instance);
    TableStoreInputFormat.addCriteria(job, fetchCriteria());
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

---

From source file:com.antbrains.crf.hadoop.FeatureCounter.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 != 3) {
        System.err.println("Usage: wordcount <in> <out> <templatefile>");
        System.exit(2);//from   www .jav a 2 s .  c o  m
    }

    String[] templates = SgdCrf.readTemplates(otherArgs[2]).toArray(new String[0]);
    conf.set("templates", strArr2Str(templates));

    Job job = new Job(conf, FeatureCounter.class.getSimpleName());

    job.setJarByClass(FeatureCounter.class);
    job.setMapperClass(CounterMapper.class);
    job.setCombinerClass(SumReducer.class);
    job.setReducerClass(SumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.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:com.antbrains.crf.hadoop.FeatureStat.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   www. j  ava2s  . c  o m*/
    }

    Job job = new Job(conf, FeatureStat.class.getSimpleName());

    job.setJarByClass(FeatureStat.class);
    job.setMapperClass(CounterMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.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:com.antbrains.crf.hadoop.WordCount.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);// w ww. ja  v a  2 s. c  o m
    }
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.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:com.asakusafw.runtime.stage.AbstractStageClient.java

License:Apache License

@SuppressWarnings("rawtypes")
private void configureShuffle(Job job, VariableTable variables) {
    Class<? extends Reducer> reducer = getReducerClassOrNull();
    if (reducer != null) {
        if (LOG.isDebugEnabled()) {
            LOG.debug(MessageFormat.format("Reducer: {0}", reducer.getName())); //$NON-NLS-1$
        }/*from  w  w  w.  j a v  a  2 s  .c  o  m*/
        job.setReducerClass(reducer);
    } else {
        if (LOG.isDebugEnabled()) {
            LOG.debug("Reducer: N/A"); //$NON-NLS-1$
        }
        job.setNumReduceTasks(0);
        return;
    }

    Class<? extends Writable> outputKeyClass = or(getShuffleKeyClassOrNull(), NullWritable.class);
    Class<? extends Writable> outputValueClass = or(getShuffleValueClassOrNull(), NullWritable.class);
    if (LOG.isDebugEnabled()) {
        LOG.debug(MessageFormat.format("Shuffle: key={0}, value={1}", //$NON-NLS-1$
                outputKeyClass.getName(), outputValueClass.getName()));
    }
    job.setMapOutputKeyClass(outputKeyClass);
    job.setMapOutputValueClass(outputValueClass);

    Class<? extends Reducer> combiner = getCombinerClassOrNull();
    if (combiner != null) {
        if (LOG.isDebugEnabled()) {
            LOG.debug(MessageFormat.format("Combiner: {0}", combiner.getName())); //$NON-NLS-1$
        }
        job.setCombinerClass(combiner);
    } else {
        if (LOG.isDebugEnabled()) {
            LOG.debug("Combiner: N/A"); //$NON-NLS-1$
        }
    }

    Class<? extends Partitioner> partitioner = getPartitionerClassOrNull();
    if (partitioner != null) {
        if (LOG.isDebugEnabled()) {
            LOG.debug(MessageFormat.format("Partitioner: {0}", partitioner.getName())); //$NON-NLS-1$
        }
        job.setPartitionerClass(partitioner);
    } else {
        if (LOG.isDebugEnabled()) {
            LOG.debug("Partitioner: DEFAULT"); //$NON-NLS-1$
        }
    }

    Class<? extends RawComparator> groupingComparator = getGroupingComparatorClassOrNull();
    if (groupingComparator != null) {
        if (LOG.isDebugEnabled()) {
            LOG.debug(MessageFormat.format("GroupingComparator: {0}", groupingComparator.getName())); //$NON-NLS-1$
        }
        job.setGroupingComparatorClass(groupingComparator);
    } else {
        if (LOG.isDebugEnabled()) {
            LOG.debug("GroupingComparator: DEFAULT"); //$NON-NLS-1$
        }
    }

    Class<? extends RawComparator> sortComparator = getSortComparatorClassOrNull();
    if (sortComparator != null) {
        if (LOG.isDebugEnabled()) {
            LOG.debug(MessageFormat.format("SortComparator: {0}", sortComparator.getName())); //$NON-NLS-1$
        }
        job.setSortComparatorClass(sortComparator);
    } else {
        if (LOG.isDebugEnabled()) {
            LOG.debug("SortComparator: DEFAULT"); //$NON-NLS-1$
        }
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »