Java Job.setReducerClass方法代码示例

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void run(Configuration conf, Path inputPath, Path output, double params) throws IOException, ClassNotFoundException, InterruptedException {
    String jobName = "calculating parameter";
    conf.set("params",String.valueOf(params));

    Job job = new Job(conf, jobName);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(indexToCountWritable.class);
    job.setOutputKeyClass(twoDimensionIndexWritable.class);
    job.setOutputValueClass(Text.class);

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

    job.setMapperClass(CalParamsMapper.class);
    job.setReducerClass(CalParamsReducer.class);

    FileInputFormat.addInputPath(job, inputPath);
    FileOutputFormat.setOutputPath(job,output);

    job.setJarByClass(LDADriver.class);
    if (!job.waitForCompletion(true)) {
        throw new InterruptedException("calculating parameter failed");
    }
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	Configuration conf = new Configuration();

	Job job = Job.getInstance(conf);
	job.setJarByClass(Multiplication.class);

	ChainMapper.addMapper(job, CooccurrenceMapper.class, LongWritable.class, Text.class, Text.class, Text.class, conf);
	ChainMapper.addMapper(job, RatingMapper.class, Text.class, Text.class, Text.class, Text.class, conf);

	job.setMapperClass(CooccurrenceMapper.class);
	job.setMapperClass(RatingMapper.class);

	job.setReducerClass(MultiplicationReducer.class);

	job.setMapOutputKeyClass(Text.class);
	job.setMapOutputValueClass(Text.class);
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(DoubleWritable.class);

	MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, CooccurrenceMapper.class);
	MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, RatingMapper.class);

	TextOutputFormat.setOutputPath(job, new Path(args[2]));
	
	job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
@Override
public int run(String[] args) throws Exception {
  if (args.length != 2) {
    System.err.println("Usage: wordmean <in> <out>");
    return 0;
  }

  Configuration conf = getConf();

  Job job = Job.getInstance(conf, "word mean");
  job.setJarByClass(WordMean.class);
  job.setMapperClass(WordMeanMapper.class);
  job.setCombinerClass(WordMeanReducer.class);
  job.setReducerClass(WordMeanReducer.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(LongWritable.class);
  FileInputFormat.addInputPath(job, new Path(args[0]));
  Path outputpath = new Path(args[1]);
  FileOutputFormat.setOutputPath(job, outputpath);
  boolean result = job.waitForCompletion(true);
  mean = readAndCalcMean(outputpath, conf);

  return (result ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(UnitMultiplication.class);

        ChainMapper.addMapper(job, TransitionMapper.class, Object.class, Text.class, Text.class, Text.class, conf);
        ChainMapper.addMapper(job, PRMapper.class, Object.class, Text.class, Text.class, Text.class, conf);

        job.setReducerClass(MultiplicationReducer.class);

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

        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, TransitionMapper.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, PRMapper.class);

        FileOutputFormat.setOutputPath(job, new Path(args[2]));
        job.waitForCompletion(true);
    }
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
private Job jobListFriends(String inputPath, String outputPath) throws IOException, InterruptedException, ClassNotFoundException{      
    Job job = new Job();
    job.setJarByClass(WordCount.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

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

    job.setInputFormatClass(KeyValueTextInputFormat.class);   // Need to change the import
    job.setOutputFormatClass(TextOutputFormat.class);

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

    job.waitForCompletion(true);

    return job;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
@Override
public int run(String[] args) throws Exception {
  if (args.length != 2) {
    System.err.println("Usage: wordstddev <in> <out>");
    return 0;
  }

  Configuration conf = getConf();

  Job job = Job.getInstance(conf, "word stddev");
  job.setJarByClass(WordStandardDeviation.class);
  job.setMapperClass(WordStandardDeviationMapper.class);
  job.setCombinerClass(WordStandardDeviationReducer.class);
  job.setReducerClass(WordStandardDeviationReducer.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(LongWritable.class);
  FileInputFormat.addInputPath(job, new Path(args[0]));
  Path outputpath = new Path(args[1]);
  FileOutputFormat.setOutputPath(job, outputpath);
  boolean result = job.waitForCompletion(true);

  // read output and calculate standard deviation
  stddev = readAndCalcStdDev(outputpath, conf);

  return (result ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static Job createJob() throws IOException {
  final Configuration conf = new Configuration();
  final Job baseJob = Job.getInstance(conf);
  baseJob.setOutputKeyClass(Text.class);
  baseJob.setOutputValueClass(IntWritable.class);
  baseJob.setMapperClass(NewMapTokenizer.class);
  baseJob.setCombinerClass(NewSummer.class);
  baseJob.setReducerClass(NewSummer.class);
  baseJob.setNumReduceTasks(1);
  baseJob.getConfiguration().setInt(JobContext.IO_SORT_MB, 1);
  baseJob.getConfiguration().set(JobContext.MAP_SORT_SPILL_PERCENT, "0.50");
  baseJob.getConfiguration().setInt(JobContext.MAP_COMBINE_MIN_SPILLS, 3);
  org.apache.hadoop.mapreduce.lib.input.FileInputFormat.setMinInputSplitSize(
      baseJob, Long.MAX_VALUE);
  return baseJob;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
private void testWithConf(Configuration conf) throws IOException,
    InterruptedException, ClassNotFoundException, URISyntaxException {
  // Create a temporary file of length 1.
  Path first = createTempFile("distributed.first", "x");
  // Create two jars with a single file inside them.
  Path second =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.second.jar"), 2);
  Path third =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.third.jar"), 3);
  Path fourth =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.fourth.jar"), 4);


  Job job = Job.getInstance(conf);
  job.setMapperClass(DistributedCacheCheckerMapper.class);
  job.setReducerClass(DistributedCacheCheckerReducer.class);
  job.setOutputFormatClass(NullOutputFormat.class);
  FileInputFormat.setInputPaths(job, first);
  // Creates the Job Configuration
  job.addCacheFile(
    new URI(first.toUri().toString() + "#distributed.first.symlink"));
  job.addFileToClassPath(second);
  job.addArchiveToClassPath(third);
  job.addCacheArchive(fourth.toUri());
  job.setMaxMapAttempts(1); // speed up failures

  job.submit();
  assertTrue(job.waitForCompletion(false));
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static Job createJob() throws IOException {
  final Job baseJob = Job.getInstance(mrCluster.getConfig());
  baseJob.setOutputKeyClass(Text.class);
  baseJob.setOutputValueClass(IntWritable.class);
  baseJob.setMapperClass(MyMapper.class);
  baseJob.setReducerClass(MyReducer.class);
  baseJob.setNumReduceTasks(1);
  return baseJob;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(UnitSum.class);
        job.setMapperClass(PassMapper.class);
        job.setReducerClass(SumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(DoubleWritable.class);
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        job.waitForCompletion(true);
    }
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Creates a simple fail job.
 * 
 * @param conf Configuration object
 * @param outdir Output directory.
 * @param indirs Comma separated input directories.
 * @return Job initialized for a simple kill job.
 * @throws Exception If an error occurs creating job configuration.
 */
public static Job createKillJob(Configuration conf, Path outdir, 
    Path... indirs) throws Exception {

  Job theJob = Job.getInstance(conf);
  theJob.setJobName("Kill-Job");

  FileInputFormat.setInputPaths(theJob, indirs);
  theJob.setMapperClass(KillMapper.class);
  theJob.setReducerClass(Reducer.class);
  theJob.setNumReduceTasks(0);
  FileOutputFormat.setOutputPath(theJob, outdir);
  theJob.setOutputKeyClass(Text.class);
  theJob.setOutputValueClass(Text.class);
  return theJob;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
private int doVerify(Path outputDir, int numReducers) throws IOException, InterruptedException,
    ClassNotFoundException {
  job = new Job(getConf());

  job.setJobName("Link Verifier");
  job.setNumReduceTasks(numReducers);
  job.setJarByClass(getClass());

  setJobScannerConf(job);

  Scan scan = new Scan();
  scan.addColumn(FAMILY_NAME, COLUMN_PREV);
  scan.setCaching(10000);
  scan.setCacheBlocks(false);
  String[] split = labels.split(COMMA);

  scan.setAuthorizations(new Authorizations(split[this.labelIndex * 2],
      split[(this.labelIndex * 2) + 1]));

  TableMapReduceUtil.initTableMapperJob(tableName.getName(), scan, VerifyMapper.class,
      BytesWritable.class, BytesWritable.class, job);
  TableMapReduceUtil.addDependencyJars(job.getConfiguration(), AbstractHBaseTool.class);

  job.getConfiguration().setBoolean("mapreduce.map.speculative", false);

  job.setReducerClass(VerifyReducer.class);
  job.setOutputFormatClass(TextOutputFormat.class);
  TextOutputFormat.setOutputPath(job, outputDir);
  boolean success = job.waitForCompletion(true);

  return success ? 0 : 1;
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
	Configuration conf = new Configuration();
	conf.set("xmlinput.start", "<page>");
	conf.set("xmlinput.end", "</page>");
			
	Job job =Job.getInstance(conf);
	job.setJobName("PageWordCount");
	job.setJarByClass(PageWordCount.class);
	
	job.setOutputKeyClass(Text.class);
	job.setOutputValueClass(IntWritable.class);
	
	job.setMapperClass(PageWordCountMap.class);
	job.setCombinerClass(PageWordCountReduce.class);
	job.setReducerClass(PageWordCountReduce.class);
	
	job.setInputFormatClass(XmlInputFormat.class);
	job.setOutputFormatClass(TextOutputFormat.class);
	
	FileInputFormat.addInputPath(job, new Path(args[0]));
	FileOutputFormat.setOutputPath(job, new Path(args[1]));
	job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Tests an MR Scan initialized from properties set in the Configuration.
 * 
 * @throws IOException
 * @throws ClassNotFoundException
 * @throws InterruptedException
 */
protected void testScanFromConfiguration(String start, String stop, String last)
throws IOException, InterruptedException, ClassNotFoundException {
  String jobName = "ScanFromConfig" + (start != null ? start.toUpperCase() : "Empty") +
    "To" + (stop != null ? stop.toUpperCase() : "Empty");
  Configuration c = new Configuration(TEST_UTIL.getConfiguration());
  c.set(TableInputFormat.INPUT_TABLE, Bytes.toString(TABLE_NAME));
  c.set(TableInputFormat.SCAN_COLUMN_FAMILY, Bytes.toString(INPUT_FAMILY));
  c.set(KEY_STARTROW, start != null ? start : "");
  c.set(KEY_LASTROW, last != null ? last : "");

  if (start != null) {
    c.set(TableInputFormat.SCAN_ROW_START, start);
  }

  if (stop != null) {
    c.set(TableInputFormat.SCAN_ROW_STOP, stop);
  }

  Job job = new Job(c, jobName);
  job.setMapperClass(ScanMapper.class);
  job.setReducerClass(ScanReducer.class);
  job.setMapOutputKeyClass(ImmutableBytesWritable.class);
  job.setMapOutputValueClass(ImmutableBytesWritable.class);
  job.setInputFormatClass(TableInputFormat.class);
  job.setNumReduceTasks(1);
  FileOutputFormat.setOutputPath(job, new Path(job.getJobName()));
  TableMapReduceUtil.addDependencyJars(job);
  assertTrue(job.waitForCompletion(true));
}
 

import org.apache.hadoop.mapreduce.Job; //导入方法依赖的package包/类
/**
 * Tests a MR scan using specific start and stop rows.
 *
 * @throws IOException
 * @throws ClassNotFoundException
 * @throws InterruptedException
 */
protected void testScan(String start, String stop, String last)
throws IOException, InterruptedException, ClassNotFoundException {
  String jobName = "Scan" + (start != null ? start.toUpperCase() : "Empty") +
    "To" + (stop != null ? stop.toUpperCase() : "Empty");
  LOG.info("Before map/reduce startup - job " + jobName);
  Configuration c = new Configuration(TEST_UTIL.getConfiguration());
  Scan scan = new Scan();
  scan.addFamily(INPUT_FAMILY);
  if (start != null) {
    scan.setStartRow(Bytes.toBytes(start));
  }
  c.set(KEY_STARTROW, start != null ? start : "");
  if (stop != null) {
    scan.setStopRow(Bytes.toBytes(stop));
  }
  c.set(KEY_LASTROW, last != null ? last : "");
  LOG.info("scan before: " + scan);
  Job job = new Job(c, jobName);
  TableMapReduceUtil.initTableMapperJob(
    Bytes.toString(TABLE_NAME), scan, ScanMapper.class,
    ImmutableBytesWritable.class, ImmutableBytesWritable.class, job);
  job.setReducerClass(ScanReducer.class);
  job.setNumReduceTasks(1); // one to get final "first" and "last" key
  FileOutputFormat.setOutputPath(job,
      new Path(TEST_UTIL.getDataTestDir(), job.getJobName()));
  LOG.info("Started " + job.getJobName());
  assertTrue(job.waitForCompletion(true));
  LOG.info("After map/reduce completion - job " + jobName);
}