List of usage examples for org.apache.hadoop.io IntWritable IntWritable
public IntWritable()
From source file:cc.slda.DisplayTopic.java
License:Apache License
@SuppressWarnings("unchecked") public int run(String[] args) throws Exception { Options options = new Options(); options.addOption(Settings.HELP_OPTION, false, "print the help message"); options.addOption(OptionBuilder.withArgName(Settings.PATH_INDICATOR).hasArg() .withDescription("input beta file").create(Settings.INPUT_OPTION)); options.addOption(OptionBuilder.withArgName(Settings.PATH_INDICATOR).hasArg() .withDescription("term index file").create(ParseCorpus.INDEX)); options.addOption(OptionBuilder.withArgName(Settings.INTEGER_INDICATOR).hasArg() .withDescription("display top terms only (default - 10)").create(TOP_DISPLAY_OPTION)); String betaString = null;//from w w w .j a va2 s .co m String indexString = null; int topDisplay = TOP_DISPLAY; CommandLineParser parser = new GnuParser(); HelpFormatter formatter = new HelpFormatter(); try { CommandLine line = parser.parse(options, args); if (line.hasOption(Settings.HELP_OPTION)) { formatter.printHelp(ParseCorpus.class.getName(), options); System.exit(0); } if (line.hasOption(Settings.INPUT_OPTION)) { betaString = line.getOptionValue(Settings.INPUT_OPTION); } else { throw new ParseException("Parsing failed due to " + Settings.INPUT_OPTION + " not initialized..."); } if (line.hasOption(ParseCorpus.INDEX)) { indexString = line.getOptionValue(ParseCorpus.INDEX); } else { throw new ParseException("Parsing failed due to " + ParseCorpus.INDEX + " not initialized..."); } if (line.hasOption(TOP_DISPLAY_OPTION)) { topDisplay = Integer.parseInt(line.getOptionValue(TOP_DISPLAY_OPTION)); } } catch (ParseException pe) { System.err.println(pe.getMessage()); formatter.printHelp(ParseCorpus.class.getName(), options); System.exit(0); } catch (NumberFormatException nfe) { System.err.println(nfe.getMessage()); System.exit(0); } JobConf conf = new JobConf(DisplayTopic.class); FileSystem fs = FileSystem.get(conf); Path indexPath = new Path(indexString); Preconditions.checkArgument(fs.exists(indexPath) && fs.isFile(indexPath), "Invalid index path..."); Path betaPath = new Path(betaString); Preconditions.checkArgument(fs.exists(betaPath) && fs.isFile(betaPath), "Invalid beta path..."); SequenceFile.Reader sequenceFileReader = null; try { IntWritable intWritable = new IntWritable(); Text text = new Text(); Map<Integer, String> termIndex = new HashMap<Integer, String>(); sequenceFileReader = new SequenceFile.Reader(fs, indexPath, conf); while (sequenceFileReader.next(intWritable, text)) { termIndex.put(intWritable.get(), text.toString()); } PairOfIntFloat pairOfIntFloat = new PairOfIntFloat(); // HMapIFW hmap = new HMapIFW(); HMapIDW hmap = new HMapIDW(); TreeMap<Double, Integer> treeMap = new TreeMap<Double, Integer>(); sequenceFileReader = new SequenceFile.Reader(fs, betaPath, conf); while (sequenceFileReader.next(pairOfIntFloat, hmap)) { treeMap.clear(); System.out.println("=============================="); System.out.println( "Top ranked " + topDisplay + " terms for Topic " + pairOfIntFloat.getLeftElement()); System.out.println("=============================="); Iterator<Integer> itr1 = hmap.keySet().iterator(); int temp1 = 0; while (itr1.hasNext()) { temp1 = itr1.next(); treeMap.put(-hmap.get(temp1), temp1); if (treeMap.size() > topDisplay) { treeMap.remove(treeMap.lastKey()); } } Iterator<Double> itr2 = treeMap.keySet().iterator(); double temp2 = 0; while (itr2.hasNext()) { temp2 = itr2.next(); if (termIndex.containsKey(treeMap.get(temp2))) { System.out.println(termIndex.get(treeMap.get(temp2)) + "\t\t" + -temp2); } else { System.out.println("How embarrassing! Term index not found..."); } } } } finally { IOUtils.closeStream(sequenceFileReader); } return 0; }
From source file:clustering.io.tuple.IntIntTupleWritable.java
License:Apache License
public IntIntTupleWritable() { this.left = new IntWritable(); this.right = new IntWritable(); }
From source file:clustering.io.tuple.IntIntTupleWritable.java
License:Apache License
public IntIntTupleWritable(int left, int right) { if (this.left == null) { this.left = new IntWritable(); }/* www . j a v a 2s. c om*/ if (this.right == null) { this.right = new IntWritable(); } this.left.set(left); this.right.set(right); }
From source file:clustering.link_back.io.Step1KeyWritable.java
License:Apache License
/** * Join key means the group id in mst,/*w w w . j a va 2s. c o m*/ * and tag is the secondary sort field, * 1 = group_id, 2 = content. */ public Step1KeyWritable() { this.joinKey = new IntWritable(); this.tag = new IntWritable(); }
From source file:clustering.link_back.io.Step2KeyWritable.java
License:Apache License
/** * joinKey means entry_id@@g_no,//from w w w. j ava 2 s .com * and tag is the secondary sort field, * 1 = cluster_id, 2 = content */ public Step2KeyWritable() { this.joinKey = new Text(); this.tag = new IntWritable(); }
From source file:cn.com.warlock.SequenceFilesTest.java
License:Apache License
public static void main(String[] args) throws IOException { String hdfsUri = "hdfs://hlg-2p238-fandongsheng:8020"; String pathStr = "/tmp/example/seq1"; String compressType = "1"; // ??windows? // System.setProperty("hadoop.home.dir", "E:\\tools"); Configuration conf = new Configuration(); conf.set("fs.defaultFS", hdfsUri); Path path = new Path(pathStr); IntWritable key = new IntWritable(); Text value = new Text(); SequenceFile.Writer writer = null; try {/*ww w .j a v a2s . co m*/ SequenceFile.Writer.Option pathOpt = SequenceFile.Writer.file(path); SequenceFile.Writer.Option keyClassOpt = SequenceFile.Writer.keyClass(key.getClass()); SequenceFile.Writer.Option valueClassOpt = SequenceFile.Writer.valueClass(value.getClass()); SequenceFile.Writer.Option compressionOpt = null; // compress type if (compressType.equals("1")) { System.out.println("compress none"); compressionOpt = SequenceFile.Writer.compression(CompressionType.NONE); } else if (compressType.equals("2")) { System.out.println("compress record"); compressionOpt = SequenceFile.Writer.compression(CompressionType.RECORD); } else if (compressType.equals("3")) { System.out.println("compress block"); compressionOpt = SequenceFile.Writer.compression(CompressionType.BLOCK); } else { System.out.println("Default : compress none"); compressionOpt = SequenceFile.Writer.compression(CompressionType.NONE); } writer = SequenceFile.createWriter(conf, pathOpt, keyClassOpt, valueClassOpt, compressionOpt); for (int i = 0; i < 100; i++) { key.set(100 - i); value.set(DATA[i % DATA.length]); System.out.printf("[%s]\t%s\t%s\n", writer.getLength(), key, value); writer.append(key, value); } } finally { IOUtils.closeStream(writer); } }
From source file:cn.lhfei.hadoop.ch04.MapFileWriteDemo.java
License:Apache License
public static void main(String[] args) { String uri = args[0];//from w ww . ja v a2 s . co m Configuration conf = new Configuration(); FileSystem fs = null; IntWritable key = new IntWritable(); Text value = new Text(); MapFile.Writer writer = null; try { fs = FileSystem.get(URI.create(uri), conf); /*writer = new MapFile.Writer(conf, fs, uri, key.getClass(), value.getClass());*/ writer = new MapFile.Writer(conf, new Path(uri), Writer.keyClass(key.getClass()), Writer.valueClass(value.getClass())); for (int i = 0; i < 1024; i++) { key.set(i + 1); value.set(DATA[i % DATA.length]); writer.append(key, value); } } catch (IOException e) { e.printStackTrace(); } finally { IOUtils.closeStream(writer); } }
From source file:cn.lhfei.hadoop.ch04.SequenceFileWriteDemo.java
License:Apache License
public static void main(String[] args) { String uri = args[0];/*from w w w . ja va 2 s . co m*/ Configuration conf = new Configuration(); FileSystem fs = null; SequenceFile.Writer writer = null; try { fs = FileSystem.get(URI.create(uri), conf); Path path = new Path(uri); IntWritable key = new IntWritable(); Text value = new Text(); //writer = SequenceFile.createWriter(fs, conf, path, key.getClass(), value.getClass()); writer = SequenceFile.createWriter(conf, Writer.keyClass(key.getClass()), writer.valueClass(value.getClass())); for (int i = 0; i < 100; i++) { key.set(100 - i); value.set(DATA[i % DATA.length]); System.out.printf("[%s]\t%s\t%s\n", writer.getLength(), key, value); writer.append(key, value); } } catch (IOException e) { e.printStackTrace(); } finally { IOUtils.closeStream(writer); } }
From source file:co.nubetech.hiho.testdata.SequenceFileWriteDemo.java
License:Apache License
public static void main(String[] args) throws IOException { String uri = "input2.seq"; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(URI.create(uri), conf); Path path = new Path(uri); IntWritable key = new IntWritable(); Text value = new Text(); SequenceFile.Writer writer = null; try {/* w w w. j ava 2 s .c o m*/ writer = SequenceFile.createWriter(fs, conf, path, key.getClass(), value.getClass()); for (int i = 0; i < 2; i++) { key.set(2 - i); value.set(DATA[i % DATA.length]); System.out.printf("[%s]\t%s\t%s\n", writer.getLength(), key, value); writer.append(key, value); } } catch (Exception e) { e.printStackTrace(); } finally { IOUtils.closeStream(writer); } }
From source file:com.chimpler.example.eigenface.Helper.java
License:Apache License
public static double[][] readMatrixSequenceFile(String fileName) throws Exception { Configuration configuration = new Configuration(); FileSystem fs = FileSystem.get(configuration); Reader matrixReader = new SequenceFile.Reader(fs, new Path(fileName), configuration); List<double[]> rows = new ArrayList<double[]>(); IntWritable key = new IntWritable(); VectorWritable value = new VectorWritable(); while (matrixReader.next(key, value)) { Vector vector = value.get(); double[] row = new double[vector.size()]; for (int i = 0; i < vector.getNumNondefaultElements(); i++) { Element element = vector.getElement(i); row[element.index()] = element.get(); }//from ww w .j a va 2 s . c o m rows.add(row); } return rows.toArray(new double[rows.size()][]); }