List of usage examples for org.apache.hadoop.mapreduce Job setMapOutputKeyClass
public void setMapOutputKeyClass(Class<?> theClass) throws IllegalStateException
From source file:clustering.link_back.step1.Driver.java
License:Apache License
public Job configJob(String[] args) throws Exception { if (args.length < 3) { System.err.printf("usage: %s mst_result_dir simhash_result_file output_dir\n", getClass().getSimpleName()); System.exit(1);//from ww w. j a va2 s . co m } Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); Job job = Job.getInstance(conf, "link back step 1 job"); job.setJarByClass(Driver.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileInputFormat.addInputPath(job, new Path(args[1])); job.setInputFormatClass(KeyValueTextInputFormat.class); job.setMapperClass(SetKeyMapper.class); job.setMapOutputKeyClass(Step1KeyWritable.class); job.setMapOutputValueClass(Text.class); job.setPartitionerClass(JoinPartitioner.class); job.setGroupingComparatorClass(Step1GroupComparator.class); job.setReducerClass(JoinReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(job, new Path(args[2])); return job; }
From source file:clustering.link_back.step2.Driver.java
License:Apache License
public Job configJob(String[] args) throws Exception { if (args.length < 3) { System.err.printf("usage: %s pre_step_result_dir step1_result_dir output_dir\n", getClass().getSimpleName()); System.exit(1);//from w ww . j a va 2 s . c o m } Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); Job job = Job.getInstance(conf, "link back step 2 job"); job.setJarByClass(Driver.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileInputFormat.addInputPath(job, new Path(args[1])); job.setInputFormatClass(KeyValueTextInputFormat.class); job.setMapperClass(clustering.link_back.step2.SetKeyMapper.class); job.setMapOutputKeyClass(Step2KeyWritable.class); job.setMapOutputValueClass(Text.class); job.setPartitionerClass(JoinPartitioner.class); job.setGroupingComparatorClass(Step2GroupComparator.class); job.setReducerClass(clustering.link_back.step2.JoinReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(job, new Path(args[2])); return job; }
From source file:clustering.mst.Driver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length < 3) { System.err.printf("usage: %s similarity_result_dir document_count_file output_dir " + "[cluster_threshold] [reduce_number] [compression]\n", getClass().getSimpleName()); System.exit(1);//from w w w. ja v a2 s. c o m } Path step1_OutputDir = new Path(args[2] + "/step1"); Path resultDir = new Path(args[2] + "/result"); URI docCntFile = new URI(args[1] + "/part-r-00000#docCnt"); Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); if (args.length > 3) { conf.setDouble("final.threshold", Double.valueOf(args[3])); } else { conf.setDouble("final.threshold", 0.2d); } if (args.length > 4) { conf.setInt("reduce.task.num", Integer.valueOf(args[4])); } else { conf.setInt("reduce.task.num", 5); } JobControl jobControl = new JobControl("mst jobs"); /* step 1, split and calculate the child msts */ Job childJob = Job.getInstance(conf, "mst child job"); childJob.setJarByClass(Driver.class); childJob.addCacheFile(docCntFile); if (args.length > 5 && args[5].equals("0")) { FileInputFormat.addInputPath(childJob, new Path(args[0])); childJob.setInputFormatClass(KeyValueTextInputFormat.class); } else { SequenceFileInputFormat.addInputPath(childJob, new Path(args[0])); childJob.setInputFormatClass(SequenceFileAsTextInputFormat.class); } FileOutputFormat.setOutputPath(childJob, step1_OutputDir); childJob.setMapperClass(ChildMapper.class); childJob.setMapOutputKeyClass(DoubleWritable.class); childJob.setMapOutputValueClass(Text.class); childJob.setPartitionerClass(ChildPartitioner.class); childJob.setReducerClass(ChildReducer.class); childJob.setNumReduceTasks(conf.getInt("reduce.task.num", 1)); childJob.setOutputKeyClass(DoubleWritable.class); childJob.setOutputValueClass(Text.class); ControlledJob controlledChildJob = new ControlledJob(conf); controlledChildJob.setJob(childJob); jobControl.addJob(controlledChildJob); /* step 2, merge step 1's output and calculate final mst */ Job finalJob = Job.getInstance(conf, "mst final job"); finalJob.setJarByClass(FinalReducer.class); finalJob.addCacheFile(docCntFile); FileInputFormat.addInputPath(finalJob, step1_OutputDir); finalJob.setInputFormatClass(KeyValueTextInputFormat.class); finalJob.setMapperClass(FinalMapper.class); finalJob.setMapOutputKeyClass(DoubleWritable.class); finalJob.setMapOutputValueClass(Text.class); finalJob.setReducerClass(FinalReducer.class); finalJob.setOutputKeyClass(IntWritable.class); finalJob.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(finalJob, resultDir); ControlledJob finalControlledJob = new ControlledJob(conf); finalControlledJob.setJob(finalJob); finalControlledJob.addDependingJob(controlledChildJob); jobControl.addJob(finalControlledJob); // run jobs MapReduceUtils.runJobs(jobControl); return finalJob.waitForCompletion(true) ? 0 : 1; }
From source file:clustering.simhash.Driver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length < 2) { System.err.printf("usage: %s init_result_dir output_dir [simhash_threshold]\n", getClass().getSimpleName()); System.exit(1);/*from w ww . java 2 s .c om*/ } Path step1_outputDir = new Path(args[1] + "/step1"); Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); if (args.length > 2) { conf.setInt("simhash.threshold", Integer.valueOf(args[2])); } else { conf.setInt("simhash.threshold", 3); } JobControl jobControl = new JobControl("simhash jobs"); Job job1 = Job.getInstance(conf, "simhash step1 job"); job1.setJarByClass(Driver.class); FileInputFormat.addInputPath(job1, new Path(args[0])); job1.setInputFormatClass(KeyValueTextInputFormat.class); job1.setMapperClass(Step1Mapper.class); job1.setMapOutputKeyClass(LongWritable.class); job1.setMapOutputValueClass(Text.class); job1.setReducerClass(Step1Reducer.class); job1.setOutputKeyClass(IntWritable.class); job1.setOutputValueClass(Text.class); FileOutputFormat.setOutputPath(job1, step1_outputDir); ControlledJob controlledJob1 = new ControlledJob(conf); controlledJob1.setJob(job1); jobControl.addJob(controlledJob1); Job job2 = Job.getInstance(conf, "simhash step2 job"); job2.setJarByClass(Driver.class); FileInputFormat.addInputPath(job2, step1_outputDir); job2.setInputFormatClass(KeyValueTextInputFormat.class); job2.setMapperClass(Step2Mapper.class); job2.setMapOutputKeyClass(IntWritable.class); job2.setMapOutputValueClass(Text.class); job2.setReducerClass(Step2Reducer.class); job2.setOutputKeyClass(IntWritable.class); job2.setOutputValueClass(Text.class); FileOutputFormat.setOutputPath(job2, new Path(args[1] + "/result")); ControlledJob controlledJob2 = new ControlledJob(conf); controlledJob2.setJob(job2); controlledJob2.addDependingJob(controlledJob1); jobControl.addJob(controlledJob2); long starttime = System.currentTimeMillis(); clustering.Utils.MapReduceUtils.runJobs(jobControl); boolean complete = job2.waitForCompletion(true); long endtime = System.currentTimeMillis(); System.out.println("simhash job finished in: " + (endtime - starttime) / 1000 + " seconds"); return complete ? 0 : 1; }
From source file:clustering.similarity.ISimDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length < 2) { System.err.printf("usage: %s simpre_dir output_dir " + "[compression_or_not] [reduce_task_number]\n", getClass().getSimpleName()); System.exit(1);//from w ww . j a va2s . c o m } Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); Job job = Job.getInstance(conf, "isim job"); job.setJarByClass(ISimDriver.class); if (args.length > 2 && args[2].equals("0")) { FileInputFormat.addInputPath(job, new Path(args[0])); job.setInputFormatClass(KeyValueTextInputFormat.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); } else { job.setInputFormatClass(SequenceFileAsTextInputFormat.class); SequenceFileInputFormat.addInputPath(job, new Path(args[0])); conf.setBoolean("mapreduce.map.output.compress", true); conf.set("mapreduce.map.output.compress.codec", "org.apache.hadoop.io.compress.GzipCodec"); job.setOutputFormatClass(SequenceFileOutputFormat.class); SequenceFileOutputFormat.setCompressOutput(job, true); SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK); SequenceFileOutputFormat.setOutputCompressorClass(job, org.apache.hadoop.io.compress.GzipCodec.class); SequenceFileOutputFormat.setOutputPath(job, new Path(args[1])); } if (args.length > 3) { conf.setInt("reduce.num", Integer.valueOf(args[3])); } else { conf.setInt("reduce.num", 5); } job.setMapperClass(ISimMapper.class); job.setMapOutputKeyClass(IntIntTupleWritable.class); job.setMapOutputValueClass(DoubleWritable.class); job.setCombinerClass(ISimCombiner.class); job.setPartitionerClass(HashPartitioner.class); job.setNumReduceTasks(conf.getInt("reduce.num", 1)); job.setReducerClass(ISimReducer.class); job.setOutputKeyClass(IntIntTupleWritable.class); job.setOutputValueClass(DoubleWritable.class); long starttime = System.currentTimeMillis(); boolean complete = job.waitForCompletion(true); long endtime = System.currentTimeMillis(); System.out.println("inverted similarity job finished in: " + (endtime - starttime) / 1000 + " seconds"); return complete ? 0 : 1; }
From source file:clustering.similarity.PreDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length < 2) { System.err.printf(/*ww w . j a va 2 s.c o m*/ "usage: %s inverted_index_result_dir output_dir" + " [compress_or_not] [reducer_number] [deci_number]\n", this.getClass().getSimpleName()); System.exit(1); } Configuration conf = getConf(); conf = MapReduceUtils.initConf(conf); conf.set("mapreduce.reduce.speculative", "false"); // TODO: 17-4-24 calculate split number from reducer number conf.setInt("split.num", 8); if (args.length > 3) { conf.setInt("reducer.num", Integer.valueOf(args[3])); } else { conf.setInt("reducer.num", 29); } if (args.length > 4) { conf.setInt("deci.number", Integer.valueOf(args[4])); } else { conf.setInt("deci.number", 3); } Job job = Job.getInstance(conf, "pre job"); job.setJarByClass(PreDriver.class); FileInputFormat.addInputPath(job, new Path(args[0])); job.setInputFormatClass(KeyValueTextInputFormat.class); job.setMapperClass(PreMapper.class); job.setMapOutputKeyClass(IntIntTupleWritable.class); job.setMapOutputValueClass(Text.class); job.setPartitionerClass(PrePartitioner.class); job.setNumReduceTasks(conf.getInt("reducer.num", 29)); job.setReducerClass(PreReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // set default compression if (args.length > 2 && args[2].equals("0")) { FileOutputFormat.setOutputPath(job, new Path(args[1])); } else { job.setOutputFormatClass(SequenceFileOutputFormat.class); SequenceFileOutputFormat.setCompressOutput(job, true); SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK); SequenceFileOutputFormat.setOutputCompressorClass(job, org.apache.hadoop.io.compress.GzipCodec.class); SequenceFileOutputFormat.setOutputPath(job, new Path(args[1])); } long starttime = System.currentTimeMillis(); boolean complete = job.waitForCompletion(true); long endtime = System.currentTimeMillis(); System.out.println("inverted similarity pre job finished in: " + (endtime - starttime) / 1000 + " seconds"); return complete ? 0 : 1; }
From source file:clustering.tf_idf.TermCntDriver.java
License:Apache License
Job configJob(String[] args) throws Exception { if (args.length < 2) { System.err.printf("usage: %s simhash_result_dir step_1_output_dir\n", getClass().getSimpleName()); System.exit(1);/*ww w .j av a 2s .co m*/ } Configuration conf = getConf(); conf = initConf(conf); Job job = Job.getInstance(conf, "tf idf step1 job"); job.setJarByClass(TermCntDriver.class); FileInputFormat.addInputPath(job, new Path(args[0])); job.setInputFormatClass(KeyValueTextInputFormat.class); job.setMapperClass(TermCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setCombinerClass(TermCountReducer.class); job.setReducerClass(TermCountReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); return job; }
From source file:cmd.sampler.java
License:Apache License
/** * Driver for InputSampler from the command line. Configures a JobConf * instance and calls {@link #writePartitionFile}. *///from w ww . ja v a 2 s . c o m public int run(String[] args) throws Exception { Job job = new Job(getConf()); ArrayList<String> otherArgs = new ArrayList<String>(); Sampler<K, V> sampler = null; for (int i = 0; i < args.length; ++i) { try { if ("-r".equals(args[i])) { job.setNumReduceTasks(Integer.parseInt(args[++i])); } else if ("-inFormat".equals(args[i])) { job.setInputFormatClass(Class.forName(args[++i]).asSubclass(InputFormat.class)); } else if ("-keyClass".equals(args[i])) { job.setMapOutputKeyClass(Class.forName(args[++i]).asSubclass(WritableComparable.class)); } else if ("-splitSample".equals(args[i])) { int numSamples = Integer.parseInt(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new SplitSampler<K, V>(numSamples, maxSplits); } else { otherArgs.add(args[i]); } } catch (NumberFormatException except) { System.out.println("ERROR: Integer expected instead of " + args[i]); return printUsage(); } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); } } if (job.getNumReduceTasks() <= 1) { System.err.println("Sampler requires more than one reducer"); return printUsage(); } if (otherArgs.size() < 2) { System.out.println("ERROR: Wrong number of parameters: "); return printUsage(); } if (null == sampler) { sampler = new SplitSampler<K, V>(1000, 10); } Path outf = new Path(otherArgs.remove(otherArgs.size() - 1)); TotalOrderPartitioner.setPartitionFile(getConf(), outf); for (String s : otherArgs) { FileInputFormat.addInputPath(job, new Path(s)); } InputSampler.<K, V>writePartitionFile(job, sampler); return 0; }
From source file:cn.edu.hfut.dmic.webcollector.crawldb.DBReader.java
public static void main(String[] args) throws Exception { Path crawlPath = new Path("task2"); Path currentPath = new Path(crawlPath, "crawldb/current"); Path output = new Path("output"); Configuration config = CrawlerConfiguration.create(); FileSystem fs = FileSystem.get(config); if (fs.exists(output)) { fs.delete(output);/* ww w . j a v a2 s . c o m*/ } Job job = new Job(config); job.setJobName("dbreader " + crawlPath.toString()); job.setMapperClass(DBReaderMapper.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, currentPath); FileOutputFormat.setOutputPath(job, output); job.waitForCompletion(true); }
From source file:cn.edu.hfut.dmic.webcollector.crawldb.Generator.java
public static String generate(Path crawlPath, Configuration conf) throws Exception { SegmentUtil.initSegments(crawlPath, conf); String segmentName = SegmentUtil.createSegment(crawlPath, conf); Path currentPath = new Path(crawlPath, "crawldb/current"); Path generatePath = new Path(crawlPath, "segments/" + segmentName + "/generate"); Job job = new Job(conf); job.setJobName("generate " + crawlPath.toString()); job.setJarByClass(Generator.class); job.setReducerClass(GeneratorReducer.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(CrawlDatum.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(CrawlDatum.class); FileInputFormat.addInputPath(job, currentPath); FileOutputFormat.setOutputPath(job, generatePath); job.waitForCompletion(true);/*from w w w .java 2 s .c o m*/ long count = job.getCounters().findCounter("generator", "count").getValue(); System.out.println("total generate:" + count); if (count == 0) { return null; } else { return segmentName; } }