List of usage examples for org.apache.hadoop.util GenericOptionsParser printGenericCommandUsage
public static void printGenericCommandUsage(PrintStream out)
From source file:$.WordCount.java
License:Open Source License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println(//from w w w . j a va 2s. com "Usage: hadoop jar ${artifactId}-${version}-job.jar" + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } String inputPath = args[0]; String outputPath = args[1]; // Create an object to coordinate pipeline creation and execution. Pipeline pipeline = new MRPipeline(WordCount.class, getConf()); // Reference a given text file as a collection of Strings. PCollection<String> lines = pipeline.readTextFile(inputPath); // Define a function that splits each line in a PCollection of Strings into // a PCollection made up of the individual words in the file. // The second argument sets the serialization format. PCollection<String> words = lines.parallelDo(new Tokenizer(), Writables.strings()); // Take the collection of words and remove known stop words. PCollection<String> noStopWords = words.filter(new StopWordFilter()); // The count method applies a series of Crunch primitives and returns // a map of the unique words in the input PCollection to their counts. PTable<String, Long> counts = noStopWords.count(); // Instruct the pipeline to write the resulting counts to a text file. pipeline.writeTextFile(counts, outputPath); // Execute the pipeline as a MapReduce. PipelineResult result = pipeline.done(); return result.succeeded() ? 0 : 1; }
From source file:cn.edu.bjtu.cit.recommender.Recommender.java
License:Apache License
@SuppressWarnings("unchecked") public int run(String[] args) throws Exception { if (args.length < 2) { System.err.println();/* ww w . j a v a 2 s . c om*/ System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output [profiling] [estimation] [clustersize]"); System.err.println(); printUsage(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } OptionParser parser = new OptionParser(args); Pipeline pipeline = new MRPipeline(Recommender.class, getConf()); if (parser.hasOption(CLUSTER_SIZE)) { pipeline.getConfiguration().setInt(ClusterOracle.CLUSTER_SIZE, Integer.parseInt(parser.getOption(CLUSTER_SIZE).getValue())); } if (parser.hasOption(PROFILING)) { pipeline.getConfiguration().setBoolean(Profiler.IS_PROFILE, true); this.profileFilePath = parser.getOption(PROFILING).getValue(); } if (parser.hasOption(ESTIMATION)) { estFile = parser.getOption(ESTIMATION).getValue(); est = new Estimator(estFile, clusterSize); } if (parser.hasOption(OPT_REDUCE)) { pipeline.getConfiguration().setBoolean(OPT_REDUCE, true); } if (parser.hasOption(OPT_MSCR)) { pipeline.getConfiguration().setBoolean(OPT_MSCR, true); } if (parser.hasOption(ACTIVE_THRESHOLD)) { threshold = Integer.parseInt(parser.getOption("at").getValue()); } if (parser.hasOption(TOP)) { top = Integer.parseInt(parser.getOption("top").getValue()); } profiler = new Profiler(pipeline); /* * input node */ PCollection<String> lines = pipeline.readTextFile(args[0]); if (profiler.isProfiling() && lines.getSize() > 10 * 1024 * 1024) { lines = lines.sample(0.1); } /* * S0 + GBK */ PGroupedTable<Long, Long> userWithPrefs = lines.parallelDo(new MapFn<String, Pair<Long, Long>>() { @Override public Pair<Long, Long> map(String input) { String[] split = input.split(Estimator.DELM); long userID = Long.parseLong(split[0]); long itemID = Long.parseLong(split[1]); return Pair.of(userID, itemID); } @Override public float scaleFactor() { return est.getScaleFactor("S0").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S0").recsFactor; } }, Writables.tableOf(Writables.longs(), Writables.longs())).groupByKey(est.getClusterSize()); /* * S1 */ PTable<Long, Vector> userVector = userWithPrefs .parallelDo(new MapFn<Pair<Long, Iterable<Long>>, Pair<Long, Vector>>() { @Override public Pair<Long, Vector> map(Pair<Long, Iterable<Long>> input) { Vector userVector = new RandomAccessSparseVector(Integer.MAX_VALUE, 100); for (long itemPref : input.second()) { userVector.set((int) itemPref, 1.0f); } return Pair.of(input.first(), userVector); } @Override public float scaleFactor() { return est.getScaleFactor("S1").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S1").recsFactor; } }, Writables.tableOf(Writables.longs(), Writables.vectors())); userVector = profiler.profile("S0-S1", pipeline, userVector, ProfileConverter.long_vector(), Writables.tableOf(Writables.longs(), Writables.vectors())); /* * S2 */ PTable<Long, Vector> filteredUserVector = userVector .parallelDo(new DoFn<Pair<Long, Vector>, Pair<Long, Vector>>() { @Override public void process(Pair<Long, Vector> input, Emitter<Pair<Long, Vector>> emitter) { if (input.second().getNumNondefaultElements() > threshold) { emitter.emit(input); } } @Override public float scaleFactor() { return est.getScaleFactor("S2").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S2").recsFactor; } }, Writables.tableOf(Writables.longs(), Writables.vectors())); filteredUserVector = profiler.profile("S2", pipeline, filteredUserVector, ProfileConverter.long_vector(), Writables.tableOf(Writables.longs(), Writables.vectors())); /* * S3 + GBK */ PGroupedTable<Integer, Integer> coOccurencePairs = filteredUserVector .parallelDo(new DoFn<Pair<Long, Vector>, Pair<Integer, Integer>>() { @Override public void process(Pair<Long, Vector> input, Emitter<Pair<Integer, Integer>> emitter) { Iterator<Vector.Element> it = input.second().iterateNonZero(); while (it.hasNext()) { int index1 = it.next().index(); Iterator<Vector.Element> it2 = input.second().iterateNonZero(); while (it2.hasNext()) { int index2 = it2.next().index(); emitter.emit(Pair.of(index1, index2)); } } } @Override public float scaleFactor() { float size = est.getScaleFactor("S3").sizeFactor; return size; } @Override public float scaleFactorByRecord() { float recs = est.getScaleFactor("S3").recsFactor; return recs; } }, Writables.tableOf(Writables.ints(), Writables.ints())).groupByKey(est.getClusterSize()); /* * S4 */ PTable<Integer, Vector> coOccurenceVector = coOccurencePairs .parallelDo(new MapFn<Pair<Integer, Iterable<Integer>>, Pair<Integer, Vector>>() { @Override public Pair<Integer, Vector> map(Pair<Integer, Iterable<Integer>> input) { Vector cooccurrenceRow = new RandomAccessSparseVector(Integer.MAX_VALUE, 100); for (int itemIndex2 : input.second()) { cooccurrenceRow.set(itemIndex2, cooccurrenceRow.get(itemIndex2) + 1.0); } return Pair.of(input.first(), cooccurrenceRow); } @Override public float scaleFactor() { return est.getScaleFactor("S4").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S4").recsFactor; } }, Writables.tableOf(Writables.ints(), Writables.vectors())); coOccurenceVector = profiler.profile("S3-S4", pipeline, coOccurenceVector, ProfileConverter.int_vector(), Writables.tableOf(Writables.ints(), Writables.vectors())); /* * S5 Wrapping co-occurrence columns */ PTable<Integer, VectorOrPref> wrappedCooccurrence = coOccurenceVector .parallelDo(new MapFn<Pair<Integer, Vector>, Pair<Integer, VectorOrPref>>() { @Override public Pair<Integer, VectorOrPref> map(Pair<Integer, Vector> input) { return Pair.of(input.first(), new VectorOrPref(input.second())); } @Override public float scaleFactor() { return est.getScaleFactor("S5").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S5").recsFactor; } }, Writables.tableOf(Writables.ints(), VectorOrPref.vectorOrPrefs())); wrappedCooccurrence = profiler.profile("S5", pipeline, wrappedCooccurrence, ProfileConverter.int_vopv(), Writables.tableOf(Writables.ints(), VectorOrPref.vectorOrPrefs())); /* * S6 Splitting user vectors */ PTable<Integer, VectorOrPref> userVectorSplit = filteredUserVector .parallelDo(new DoFn<Pair<Long, Vector>, Pair<Integer, VectorOrPref>>() { @Override public void process(Pair<Long, Vector> input, Emitter<Pair<Integer, VectorOrPref>> emitter) { long userID = input.first(); Vector userVector = input.second(); Iterator<Vector.Element> it = userVector.iterateNonZero(); while (it.hasNext()) { Vector.Element e = it.next(); int itemIndex = e.index(); float preferenceValue = (float) e.get(); emitter.emit(Pair.of(itemIndex, new VectorOrPref(userID, preferenceValue))); } } @Override public float scaleFactor() { return est.getScaleFactor("S6").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S6").recsFactor; } }, Writables.tableOf(Writables.ints(), VectorOrPref.vectorOrPrefs())); userVectorSplit = profiler.profile("S6", pipeline, userVectorSplit, ProfileConverter.int_vopp(), Writables.tableOf(Writables.ints(), VectorOrPref.vectorOrPrefs())); /* * S7 Combine VectorOrPrefs */ PTable<Integer, VectorAndPrefs> combinedVectorOrPref = wrappedCooccurrence.union(userVectorSplit) .groupByKey(est.getClusterSize()) .parallelDo(new DoFn<Pair<Integer, Iterable<VectorOrPref>>, Pair<Integer, VectorAndPrefs>>() { @Override public void process(Pair<Integer, Iterable<VectorOrPref>> input, Emitter<Pair<Integer, VectorAndPrefs>> emitter) { Vector vector = null; List<Long> userIDs = Lists.newArrayList(); List<Float> values = Lists.newArrayList(); for (VectorOrPref vop : input.second()) { if (vector == null) { vector = vop.getVector(); } long userID = vop.getUserID(); if (userID != Long.MIN_VALUE) { userIDs.add(vop.getUserID()); } float value = vop.getValue(); if (!Float.isNaN(value)) { values.add(vop.getValue()); } } emitter.emit(Pair.of(input.first(), new VectorAndPrefs(vector, userIDs, values))); } @Override public float scaleFactor() { return est.getScaleFactor("S7").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S7").recsFactor; } }, Writables.tableOf(Writables.ints(), VectorAndPrefs.vectorAndPrefs())); combinedVectorOrPref = profiler.profile("S5+S6-S7", pipeline, combinedVectorOrPref, ProfileConverter.int_vap(), Writables.tableOf(Writables.ints(), VectorAndPrefs.vectorAndPrefs())); /* * S8 Computing partial recommendation vectors */ PTable<Long, Vector> partialMultiply = combinedVectorOrPref .parallelDo(new DoFn<Pair<Integer, VectorAndPrefs>, Pair<Long, Vector>>() { @Override public void process(Pair<Integer, VectorAndPrefs> input, Emitter<Pair<Long, Vector>> emitter) { Vector cooccurrenceColumn = input.second().getVector(); List<Long> userIDs = input.second().getUserIDs(); List<Float> prefValues = input.second().getValues(); for (int i = 0; i < userIDs.size(); i++) { long userID = userIDs.get(i); if (userID != Long.MIN_VALUE) { float prefValue = prefValues.get(i); Vector partialProduct = cooccurrenceColumn.times(prefValue); emitter.emit(Pair.of(userID, partialProduct)); } } } @Override public float scaleFactor() { return est.getScaleFactor("S8").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S8").recsFactor; } }, Writables.tableOf(Writables.longs(), Writables.vectors())).groupByKey(est.getClusterSize()) .combineValues(new CombineFn<Long, Vector>() { @Override public void process(Pair<Long, Iterable<Vector>> input, Emitter<Pair<Long, Vector>> emitter) { Vector partial = null; for (Vector vector : input.second()) { partial = partial == null ? vector : partial.plus(vector); } emitter.emit(Pair.of(input.first(), partial)); } @Override public float scaleFactor() { return est.getScaleFactor("combine").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("combine").recsFactor; } }); partialMultiply = profiler.profile("S8-combine", pipeline, partialMultiply, ProfileConverter.long_vector(), Writables.tableOf(Writables.longs(), Writables.vectors())); /* * S9 Producing recommendations from vectors */ PTable<Long, RecommendedItems> recommendedItems = partialMultiply .parallelDo(new DoFn<Pair<Long, Vector>, Pair<Long, RecommendedItems>>() { @Override public void process(Pair<Long, Vector> input, Emitter<Pair<Long, RecommendedItems>> emitter) { Queue<RecommendedItem> topItems = new PriorityQueue<RecommendedItem>(11, Collections.reverseOrder(BY_PREFERENCE_VALUE)); Iterator<Vector.Element> recommendationVectorIterator = input.second().iterateNonZero(); while (recommendationVectorIterator.hasNext()) { Vector.Element element = recommendationVectorIterator.next(); int index = element.index(); float value = (float) element.get(); if (topItems.size() < top) { topItems.add(new GenericRecommendedItem(index, value)); } else if (value > topItems.peek().getValue()) { topItems.add(new GenericRecommendedItem(index, value)); topItems.poll(); } } List<RecommendedItem> recommendations = new ArrayList<RecommendedItem>(topItems.size()); recommendations.addAll(topItems); Collections.sort(recommendations, BY_PREFERENCE_VALUE); emitter.emit(Pair.of(input.first(), new RecommendedItems(recommendations))); } @Override public float scaleFactor() { return est.getScaleFactor("S9").sizeFactor; } @Override public float scaleFactorByRecord() { return est.getScaleFactor("S9").recsFactor; } }, Writables.tableOf(Writables.longs(), RecommendedItems.recommendedItems())); recommendedItems = profiler.profile("S9", pipeline, recommendedItems, ProfileConverter.long_ri(), Writables.tableOf(Writables.longs(), RecommendedItems.recommendedItems())); /* * Profiling */ if (profiler.isProfiling()) { profiler.writeResultToFile(profileFilePath); profiler.cleanup(pipeline.getConfiguration()); return 0; } /* * asText */ pipeline.writeTextFile(recommendedItems, args[1]); PipelineResult result = pipeline.done(); return result.succeeded() ? 0 : 1; }
From source file:com.cloudera.castagna.crunch.AverageBytesByIP.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println();/* ww w .j ava 2s.c o m*/ System.err.println("Two and only two arguments are accepted."); System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } Pipeline pipeline = new MRPipeline(AverageBytesByIP.class, getConf()); PCollection<String> lines = pipeline.readTextFile(args[0]); Aggregator<Pair<Long, Long>> agg = pairAggregator(SUM_LONGS(), SUM_LONGS()); PTable<String, Pair<Long, Long>> remoteAddrResponseSize = lines .parallelDo(extractResponseSize, Writables.tableOf(Writables.strings(), Writables.pairs(Writables.longs(), Writables.longs()))) .groupByKey().combineValues(agg); PTable<String, Double> avgs = remoteAddrResponseSize.parallelDo(calulateAverage, Writables.tableOf(Writables.strings(), Writables.doubles())); pipeline.writeTextFile(avgs.top(100), args[1]); PipelineResult result = pipeline.done(); return result.succeeded() ? 0 : 1; }
From source file:com.cloudera.castagna.crunch.PageViews.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println();//from w w w . j av a 2 s .c o m System.err.println("Two and only two arguments are accepted."); System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } Pipeline pipeline = new MRPipeline(PageViews.class, getConf()); PCollection<String> lines = pipeline.readTextFile(args[0]); CombineFn<String, Long> longSumCombiner = CombineFn.SUM_LONGS(); PTable<String, Long> pageViews = lines .parallelDo(extractIPResponseSize, Writables.tableOf(Writables.strings(), Writables.longs())) .groupByKey().combineValues(longSumCombiner).top(200); pipeline.writeTextFile(pageViews, args[1]); PipelineResult result = pipeline.done(); return result.succeeded() ? 0 : 1; }
From source file:com.cloudera.castagna.crunch.TotalBytesByIP.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println();// ww w. j av a 2 s. com System.err.println("Two and only two arguments are accepted."); System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } Pipeline pipeline = new MRPipeline(TotalBytesByIP.class, getConf()); PCollection<String> lines = pipeline.readTextFile(args[0]); CombineFn<String, Long> longSumCombiner = CombineFn.SUM_LONGS(); PTable<String, Long> ipAddrResponseSize = lines .parallelDo(extractIPResponseSize, Writables.tableOf(Writables.strings(), Writables.longs())) .groupByKey().combineValues(longSumCombiner).top(10); pipeline.writeTextFile(ipAddrResponseSize, args[1]); PipelineResult result = pipeline.done(); return result.succeeded() ? 0 : 1; }
From source file:com.cloudera.crunch.examples.AverageBytesByIP.java
License:Open Source License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println();//from w w w. j av a 2 s . co m System.err.println("Two and only two arguments are accepted."); System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } // Create an object to coordinate pipeline creation and execution. Pipeline pipeline = new MRPipeline(AverageBytesByIP.class, getConf()); // Reference a given text file as a collection of Strings. PCollection<String> lines = pipeline.readTextFile(args[0]); // Combiner used for summing up response size and count CombineFn<String, Pair<Long, Long>> stringPairOfLongsSumCombiner = CombineFn .pairAggregator(CombineFn.SUM_LONGS, CombineFn.SUM_LONGS); // Table of (ip, sum(response size), count) PTable<String, Pair<Long, Long>> remoteAddrResponseSize = lines .parallelDo(extractResponseSize, Writables.tableOf(Writables.strings(), Writables.pairs(Writables.longs(), Writables.longs()))) .groupByKey().combineValues(stringPairOfLongsSumCombiner); // Calculate average response size by ip address PTable<String, Double> avgs = remoteAddrResponseSize.parallelDo(calulateAverage, Writables.tableOf(Writables.strings(), Writables.doubles())); // write the result to a text file pipeline.writeTextFile(avgs, args[1]); // Execute the pipeline as a MapReduce. pipeline.done(); return 0; }
From source file:com.cloudera.crunch.examples.TotalBytesByIP.java
License:Open Source License
public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println();/*from w w w .j a v a 2 s . c om*/ System.err.println("Two and only two arguments are accepted."); System.err.println("Usage: " + this.getClass().getName() + " [generic options] input output"); System.err.println(); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } // Create an object to coordinate pipeline creation and execution. Pipeline pipeline = new MRPipeline(TotalBytesByIP.class, getConf()); // Reference a given text file as a collection of Strings. PCollection<String> lines = pipeline.readTextFile(args[0]); // Combiner used for summing up response size CombineFn<String, Long> longSumCombiner = CombineFn.SUM_LONGS(); // Table of (ip, sum(response size)) PTable<String, Long> ipAddrResponseSize = lines .parallelDo(extractIPResponseSize, Writables.tableOf(Writables.strings(), Writables.longs())) .groupByKey().combineValues(longSumCombiner); pipeline.writeTextFile(ipAddrResponseSize, args[1]); // Execute the pipeline as a MapReduce. pipeline.done(); return 0; }
From source file:com.cloudera.fts.App.java
License:Open Source License
private void printUsage() { GenericOptionsParser.printGenericCommandUsage(System.err); System.err.println("Basic Usage: [avro,proto,text2pb,count] <inputdir> <outputdir>"); System.exit(1);/*from w w w .j a v a2 s .c om*/ }
From source file:com.cloudera.fts.App.java
License:Open Source License
private void printAvroUsage() { GenericOptionsParser.printGenericCommandUsage(System.err); System.err.println(/*from w w w .j av a2 s .c o m*/ "Avro requires one extra argument, the event file name: avro <inputdir> <events_file> <outputdir>"); System.exit(1); }
From source file:com.cloudera.hadoop.hdfs.nfs.nfs4.NFS4Server.java
License:Apache License
@Override public int run(String[] args) throws Exception { int port;//from w ww .ja v a 2 s .c o m try { port = Integer.parseInt(args[0]); } catch (Exception e) { System.err.println(this.getClass().getName() + " port"); GenericOptionsParser.printGenericCommandUsage(System.err); return 1; } start(null, port); while (mRPCServer.isAlive()) { Thread.sleep(10000L); } return 0; }