List of usage examples for org.apache.hadoop.mapreduce.lib.output MultipleOutputs MultipleOutputs
public MultipleOutputs(TaskInputOutputContext<?, ?, KEYOUT, VALUEOUT> context)
From source file:org.apache.mahout.fpm.bigfim.ComputeTidListReducer.java
License:Apache License
@Override public void setup(Context context) { Configuration conf = context.getConfiguration(); minSup = conf.getInt(MIN_SUP_KEY, 1); subDbSize = conf.getInt(SUBDB_SIZE, 1); int numberOfMappers = conf.getInt(NUMBER_OF_MAPPERS_KEY, 1); bucketSizes = new ArrayList<AtomicInteger>(numberOfMappers); for (int i = 0; i < numberOfMappers; i++) { bucketSizes.add(new AtomicInteger()); }/*from w w w. jav a 2 s .c o m*/ mos = new MultipleOutputs<IntArrayWritable, IntArrayWritable>(context); }
From source file:org.apache.mahout.fpm.disteclat.ItemReaderReducer.java
License:Apache License
@Override public void setup(Context context) { Configuration conf = context.getConfiguration(); mos = new MultipleOutputs<Text, Writable>(context); numberOfMappers = parseInt(conf.get(NUMBER_OF_MAPPERS_KEY, "1")); }
From source file:org.apache.mahout.fpm.disteclat.PrefixComputerReducer.java
License:Apache License
@Override public void setup(Context context) { Configuration conf = context.getConfiguration(); minSup = conf.getInt(MIN_SUP_KEY, 1); int numberOfMappers = conf.getInt(NUMBER_OF_MAPPERS_KEY, 1); bucketSizes = new ArrayList<AtomicInteger>(numberOfMappers); for (int i = 0; i < numberOfMappers; i++) { bucketSizes.add(new AtomicInteger()); }//ww w .j a v a 2 s .c o m mos = new MultipleOutputs<IntArrayWritable, IntArrayWritable>(context); }
From source file:org.apache.pirk.responder.wideskies.mapreduce.ColumnMultReducer.java
License:Apache License
@Override public void setup(Context ctx) throws IOException, InterruptedException { super.setup(ctx); outputValue = new Text(); mos = new MultipleOutputs<>(ctx); FileSystem fs = FileSystem.newInstance(ctx.getConfiguration()); String queryDir = ctx.getConfiguration().get("pirMR.queryInputDir"); query = new HadoopFileSystemStore(fs).recall(queryDir, Query.class); }
From source file:org.apache.pirk.responder.wideskies.mapreduce.ExpTableReducer.java
License:Apache License
@Override public void setup(Context ctx) throws IOException, InterruptedException { super.setup(ctx); mos = new MultipleOutputs<>(ctx); reducerID = String.format("%05d", ctx.getTaskAttemptID().getTaskID().getId()); logger.info("reducerID = " + reducerID); }
From source file:org.apache.pirk.responder.wideskies.mapreduce.FinalResponseReducer.java
License:Apache License
@Override public void setup(Context ctx) throws IOException, InterruptedException { super.setup(ctx); mos = new MultipleOutputs<>(ctx); FileSystem fs = FileSystem.newInstance(ctx.getConfiguration()); storage = new HadoopFileSystemStore(fs); String queryDir = ctx.getConfiguration().get("pirMR.queryInputDir"); Query query = storage.recall(queryDir, Query.class); QueryInfo queryInfo = query.getQueryInfo(); outputFile = ctx.getConfiguration().get("pirMR.outputFile"); response = new Response(queryInfo); }
From source file:org.apache.pirk.responder.wideskies.mapreduce.RowCalcReducer.java
License:Apache License
@Override public void setup(Context ctx) throws IOException, InterruptedException { super.setup(ctx); keyOut = new LongWritable(); valueOut = new Text(); mos = new MultipleOutputs<>(ctx); fs = FileSystem.newInstance(ctx.getConfiguration()); String queryDir = ctx.getConfiguration().get("pirMR.queryInputDir"); query = new HadoopFileSystemStore(fs).recall(queryDir, Query.class); queryInfo = query.getQueryInfo();//from www.ja v a 2s. co m try { SystemConfiguration.setProperty("data.schemas", ctx.getConfiguration().get("data.schemas")); SystemConfiguration.setProperty("query.schemas", ctx.getConfiguration().get("query.schemas")); SystemConfiguration.setProperty("pir.stopListFile", ctx.getConfiguration().get("pirMR.stopListFile")); DataSchemaLoader.initialize(true, fs); QuerySchemaLoader.initialize(true, fs); } catch (Exception e) { e.printStackTrace(); } if (ctx.getConfiguration().get("pirWL.useLocalCache").equals("true")) { useLocalCache = true; } if (ctx.getConfiguration().get("pirWL.limitHitsPerSelector").equals("true")) { limitHitsPerSelector = true; } maxHitsPerSelector = Integer.parseInt(ctx.getConfiguration().get("pirWL.maxHitsPerSelector")); logger.info("RowCalcReducer -- useLocalCache = " + useLocalCache + " limitHitsPerSelector = " + limitHitsPerSelector + " maxHitsPerSelector = " + maxHitsPerSelector); }
From source file:org.apache.rya.accumulo.mr.merge.reducers.MultipleFileReducer.java
License:Apache License
@Override protected void setup(final Context context) { mos = new MultipleOutputs<>(context); }
From source file:org.apache.sqoop.mapreduce.mainframe.MainframeDatasetImportMapper.java
License:Apache License
@Override protected void setup(Context context) throws IOException, InterruptedException { super.setup(context); inputSplit = (MainframeDatasetInputSplit) context.getInputSplit(); mos = new MultipleOutputs<Text, NullWritable>(context); numberOfRecords = 0;//from ww w . j a v a 2 s. c om outkey = new Text(); }
From source file:org.bgi.flexlab.gaea.tools.mapreduce.annotator.AnnotationReducer.java
License:Open Source License
@Override protected void setup(Context context) throws IOException, InterruptedException { long setupStart = System.currentTimeMillis(); conf = context.getConfiguration();/*from ww w .j a v a 2s . c o m*/ long start = System.currentTimeMillis(); ReferenceShare genomeShare = new ReferenceShare(); genomeShare.loadChromosomeList(); System.err.println("genomeShare" + (System.currentTimeMillis() - start) + ""); Config userConfig = new Config(conf, genomeShare); userConfig.setVerbose(conf.getBoolean("verbose", false)); userConfig.setDebug(conf.getBoolean("debug", false)); start = System.currentTimeMillis(); AnnotatorBuild annoBuild = new AnnotatorBuild(userConfig); userConfig.setSnpEffectPredictor(annoBuild.createSnpEffPredictor()); annoBuild.buildForest(); System.err.println("build SnpEffectPredictor" + (System.currentTimeMillis() - start) + ""); sampleNames = new ArrayList<>(); vcfCodecs = new HashMap<>(); Path inputPath = new Path(conf.get("inputFilePath")); FileSystem fs = inputPath.getFileSystem(conf); FileStatus[] files = fs.listStatus(inputPath); for (FileStatus file : files) { System.out.println(file.getPath()); if (file.isFile()) { SingleVCFHeader singleVcfHeader = new SingleVCFHeader(); singleVcfHeader.readHeaderFrom(file.getPath(), fs); VCFHeader vcfHeader = singleVcfHeader.getHeader(); VCFHeaderVersion vcfVersion = singleVcfHeader.getVCFVersion(vcfHeader); VCFCodec vcfcodec = new VCFCodec(); vcfcodec.setVCFHeader(vcfHeader, vcfVersion); vcfCodecs.put(file.getPath().getName(), vcfcodec); System.out.println("getname: " + file.getPath().getName()); sampleNames.addAll(vcfHeader.getSampleNamesInOrder()); System.out.println(sampleNames.toString()); } } multipleOutputs = new MultipleOutputs(context); System.err.println("getVCFHeader" + (System.currentTimeMillis() - start) + ""); vcfAnnotator = new VcfAnnotator(userConfig); start = System.currentTimeMillis(); //?? dbAnnotator = new DBAnnotator(userConfig); try { dbAnnotator.connection(); } catch (InstantiationException | IllegalAccessException | ClassNotFoundException e) { e.printStackTrace(); } System.err.println("dbAnnotator.connection" + (System.currentTimeMillis() - start) + ""); // header? resultValue.set(userConfig.getHeader()); for (int i = 0; i < sampleNames.size(); i++) { multipleOutputs.write(SampleNameModifier.modify(sampleNames.get(i)), NullWritable.get(), resultValue, sampleNames.get(i) + "/part"); } System.err.println("mapper.setup" + (System.currentTimeMillis() - setupStart) + ""); }