TFIDF文档向量化-Mahout_MapReduce

      Class<? extends Analyzer> analyzerClass = StandardAnalyzer.class;

      if (cmdLine.hasOption(analyzerNameOpt)) {
        String className = cmdLine.getValue(analyzerNameOpt).toString();
        analyzerClass = Class.forName(className).asSubclass(Analyzer.class);
        // try instantiating it, b/c there isn‘t any point in setting it if
        // you can‘t instantiate it
        AnalyzerUtils.createAnalyzer(analyzerClass);
      }

DocumentProcessor.tokenizeDocuments(inputDir, analyzerClass, tokenizedPath, conf);

 //将input documents按Analyzer进行分词，并将分得的词放在一个StringTuple中
   TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
    stream.reset();
    StringTuple document = new StringTuple();//StringTuple是一个能够被用于Hadoop Map/Reduce Job的String类型有序List
    while (stream.incrementToken()) {
      if (termAtt.length() > 0) {
        document.add(new String(termAtt.buffer(), 0, termAtt.length()));
      }
    }

        DictionaryVectorizer.createTermFrequencyVectors(tokenizedPath,
                outputDir,
                tfDirName,
                conf,
                minSupport,
                maxNGramSize,
                minLLRValue,
                -1.0f,
                false,
                reduceTasks,
                chunkSize,
                sequentialAccessOutput,
                namedVectors);

startWordCounting(input, dictionaryJobPath, baseConf, minSupport);

  //统计一个文本文档中的词频
  OpenObjectLongHashMap<String> wordCount = new OpenObjectLongHashMap<String>();
    for (String word : value.getEntries()) {
      if (wordCount.containsKey(word)) {
        wordCount.put(word, wordCount.get(word) + 1);
      } else {
        wordCount.put(word, 1);
      }
    }
    wordCount.forEachPair(new ObjectLongProcedure<String>() {
      @Override
      public boolean apply(String first, long second) {
        try {
          context.write(new Text(first), new LongWritable(second));
        } catch (IOException e) {
          context.getCounter("Exception", "Output IO Exception").increment(1);
        } catch (InterruptedException e) {
          context.getCounter("Exception", "Interrupted Exception").increment(1);
        }
        return true;
      }
    });

//汇总所有的words和单词的weights，并将同一word的权重sum
 long sum = 0;
    for (LongWritable value : values) {
      sum += value.get();
    }
    if (sum >= minSupport) {//TermCountCombiner没有这个过滤）
      context.write(key, new LongWritable(sum));
    }

 List<Path> dictionaryChunks;
      dictionaryChunks =
          createDictionaryChunks(dictionaryJobPath, output, baseConf, chunkSizeInMegabytes, maxTermDimension);

 /**
   * Read the feature frequency List which is built at the end of the Word Count Job and assign ids to them.
   * This will use constant memory and will run at the speed of your disk read
   */
  private static List<Path> createDictionaryChunks(Path wordCountPath,
                                                   Path dictionaryPathBase,
                                                   Configuration baseConf,
                                                   int chunkSizeInMegabytes,
                                                   int[] maxTermDimension) throws IOException {
    List<Path> chunkPaths = Lists.newArrayList();
    
    Configuration conf = new Configuration(baseConf);
    
    FileSystem fs = FileSystem.get(wordCountPath.toUri(), conf);

    long chunkSizeLimit = chunkSizeInMegabytes * 1024L * 1024L;//默认64M
    int chunkIndex = 0;
    Path chunkPath = new Path(dictionaryPathBase, DICTIONARY_FILE + chunkIndex);
    chunkPaths.add(chunkPath);
    
    SequenceFile.Writer dictWriter = new SequenceFile.Writer(fs, conf, chunkPath, Text.class, IntWritable.class);

    try {
      long currentChunkSize = 0;
      Path filesPattern = new Path(wordCountPath, OUTPUT_FILES_PATTERN);
      int i = 0;
      for (Pair<Writable,Writable> record
           : new SequenceFileDirIterable<Writable,Writable>(filesPattern, PathType.GLOB, null, null, true, conf)) {
        if (currentChunkSize > chunkSizeLimit) {//生成新的词典文件
          Closeables.close(dictWriter, false);
          chunkIndex++;

          chunkPath = new Path(dictionaryPathBase, DICTIONARY_FILE + chunkIndex);
          chunkPaths.add(chunkPath);

          dictWriter = new SequenceFile.Writer(fs, conf, chunkPath, Text.class, IntWritable.class);
          currentChunkSize = 0;
        }

        Writable key = record.getFirst();
        int fieldSize = DICTIONARY_BYTE_OVERHEAD + key.toString().length() * 2 + Integer.SIZE / 8;
        currentChunkSize += fieldSize;
        dictWriter.append(key, new IntWritable(i++));//指定id
      }
      maxTermDimension[0] = i;//记录最大word数目
    } finally {
      Closeables.close(dictWriter, false);
    }
    
    return chunkPaths;
  }

int partialVectorIndex = 0;
    Collection<Path> partialVectorPaths = Lists.newArrayList();
    for (Path dictionaryChunk : dictionaryChunks) {
      Path partialVectorOutputPath = new Path(output, VECTOR_OUTPUT_FOLDER + partialVectorIndex++);
      partialVectorPaths.add(partialVectorOutputPath);
      makePartialVectors(input, baseConf, maxNGramSize, dictionaryChunk, partialVectorOutputPath,
        maxTermDimension[0], sequentialAccess, namedVectors, numReducers);
    }

    //读取词典文件
//MAHOUT-1247
    Path dictionaryFile = HadoopUtil.getSingleCachedFile(conf);
    // key is word value is id
    for (Pair<Writable, IntWritable> record
            : new SequenceFileIterable<Writable, IntWritable>(dictionaryFile, true, conf)) {
      dictionary.put(record.getFirst().toString(), record.getSecond().get());
    }

//转化a document为a sparse vector
 StringTuple value = it.next();

    Vector vector = new RandomAccessSparseVector(dimension, value.length()); // guess at initial size

 for (String term : value.getEntries()) {
        if (!term.isEmpty() && dictionary.containsKey(term)) { // unigram
          int termId = dictionary.get(term);
          vector.setQuick(termId, vector.getQuick(termId) + 1);
        }
      }

    Configuration conf = new Configuration(baseConf);

    Path outputDir = new Path(output, tfVectorsFolderName);
    PartialVectorMerger.mergePartialVectors(partialVectorPaths, outputDir, conf, normPower, logNormalize,
      maxTermDimension[0], sequentialAccess, namedVectors, numReducers);

//合并partial向量为完整的TF向量
  Vector vector = new RandomAccessSparseVector(dimension, 10);
    for (VectorWritable value : values) {
      vector.assign(value.get(), Functions.PLUS);//将包含不同word的向量合并为一个
    }

      Pair<Long[], List<Path>> docFrequenciesFeatures = null;
      // Should document frequency features be processed
      if (shouldPrune || processIdf) {
        log.info("Calculating IDF");
        docFrequenciesFeatures =
                TFIDFConverter.calculateDF(new Path(outputDir, tfDirName), outputDir, conf, chunkSize);
      }

Path wordCountPath = new Path(output, WORDCOUNT_OUTPUT_FOLDER);

startDFCounting(input, wordCountPath, baseConf);

 //为一个文档中的每个word计数1、文档数1
   Vector vector = value.get();
    for (Vector.Element e : vector.nonZeroes()) {
      out.set(e.index());
      context.write(out, ONE);
    }
    context.write(TOTAL_COUNT, ONE);

   //将每个word的文档频率和文档总数sum
　　 long sum = 0;
    for (LongWritable value : values) {
      sum += value.get();
    }

 return createDictionaryChunks(wordCountPath, output, baseConf, chunkSizeInMegabytes);

  /**
   * Read the document frequency List which is built at the end of the DF Count Job. This will use constant
   * memory and will run at the speed of your disk read
   */
  private static Pair<Long[], List<Path>> createDictionaryChunks(Path featureCountPath,
                                                                 Path dictionaryPathBase,
                                                                 Configuration baseConf,
                                                                 int chunkSizeInMegabytes) throws IOException {
    List<Path> chunkPaths = Lists.newArrayList();
    Configuration conf = new Configuration(baseConf);

    FileSystem fs = FileSystem.get(featureCountPath.toUri(), conf);

    long chunkSizeLimit = chunkSizeInMegabytes * 1024L * 1024L;
    int chunkIndex = 0;
    Path chunkPath = new Path(dictionaryPathBase, FREQUENCY_FILE + chunkIndex);
    chunkPaths.add(chunkPath);
    SequenceFile.Writer freqWriter =
      new SequenceFile.Writer(fs, conf, chunkPath, IntWritable.class, LongWritable.class);

    try {
      long currentChunkSize = 0;
      long featureCount = 0;
      long vectorCount = Long.MAX_VALUE;
      Path filesPattern = new Path(featureCountPath, OUTPUT_FILES_PATTERN);
      for (Pair<IntWritable,LongWritable> record
           : new SequenceFileDirIterable<IntWritable,LongWritable>(filesPattern,
                                                                   PathType.GLOB,
                                                                   null,
                                                                   null,
                                                                   true,
                                                                   conf)) {

        if (currentChunkSize > chunkSizeLimit) {
          Closeables.close(freqWriter, false);
          chunkIndex++;

          chunkPath = new Path(dictionaryPathBase, FREQUENCY_FILE + chunkIndex);
          chunkPaths.add(chunkPath);

          freqWriter = new SequenceFile.Writer(fs, conf, chunkPath, IntWritable.class, LongWritable.class);
          currentChunkSize = 0;
        }

        int fieldSize = SEQUENCEFILE_BYTE_OVERHEAD + Integer.SIZE / 8 + Long.SIZE / 8;
        currentChunkSize += fieldSize;
        IntWritable key = record.getFirst();
        LongWritable value = record.getSecond();
        if (key.get() >= 0) {
          freqWriter.append(key, value);
        } else if (key.get() == -1) {//文档数目
          vectorCount = value.get();
        }
        featureCount = Math.max(key.get(), featureCount);

      }
      featureCount++;
      Long[] counts = {featureCount, vectorCount};//word数目、文档数目
      return new Pair<Long[], List<Path>>(counts, chunkPaths);
    } finally {
      Closeables.close(freqWriter, false);
    }
  }

        TFIDFConverter.processTfIdf(
                new Path(outputDir, DictionaryVectorizer.DOCUMENT_VECTOR_OUTPUT_FOLDER),
                outputDir, conf, docFrequenciesFeatures, minDf, maxDF, norm, logNormalize,
                sequentialAccessOutput, namedVectors, reduceTasks);

  int partialVectorIndex = 0;
    List<Path> partialVectorPaths = Lists.newArrayList();
    List<Path> dictionaryChunks = datasetFeatures.getSecond();
    for (Path dictionaryChunk : dictionaryChunks) {
      Path partialVectorOutputPath = new Path(output, VECTOR_OUTPUT_FOLDER + partialVectorIndex++);
      partialVectorPaths.add(partialVectorOutputPath);
      makePartialVectors(input,
                         baseConf,
                         datasetFeatures.getFirst()[0],
                         datasetFeatures.getFirst()[1],
                         minDf,
                         maxDF,
                         dictionaryChunk,
                         partialVectorOutputPath,
                         sequentialAccessOutput,
                         namedVector);
    }

    DistributedCache.setCacheFiles(new URI[] {dictionaryFilePath.toUri()}, conf);//缓存df分块文件

  //计算每个文档中每个word的TFIDF值
Vector value = it.next().get();
    Vector vector = new RandomAccessSparseVector((int) featureCount, value.getNumNondefaultElements());
    for (Vector.Element e : value.nonZeroes()) {
      if (!dictionary.containsKey(e.index())) {
        continue;
      }
      long df = dictionary.get(e.index());
      if (maxDf > -1 && (100.0 * df) / vectorCount > maxDf) {
        continue;
      }
      if (df < minDf) {
        df = minDf;
      }
      vector.setQuick(e.index(), tfidf.calculate((int) e.get(), (int) df, (int) featureCount, (int) vectorCount));
    }

    Configuration conf = new Configuration(baseConf);

    Path outputDir = new Path(output, DOCUMENT_VECTOR_OUTPUT_FOLDER);
    
    PartialVectorMerger.mergePartialVectors(partialVectorPaths,
                                            outputDir,
                                            baseConf,
                                            normPower,
                                            logNormalize,
                                            datasetFeatures.getFirst()[0].intValue(),
                                            sequentialAccessOutput,
                                            namedVector,
                                            numReducers);

    //汇总TFIDF向量
　　Vector vector = new RandomAccessSparseVector(dimension, 10);
    for (VectorWritable value : values) {
      vector.assign(value.get(), Functions.PLUS);
    }