Examples of org.apache.mahout.common.FileLineIterator

org.apache.mahout.common.FileLineIterator
Iterates over the lines of a text file. This assumes the text file's lines are delimited in a manner consistent with how {@link BufferedReader} defines lines.This class will uncompress files that end in .zip or .gz accordingly, too.

  private static final Pattern SEPARATOR = Pattern.compile("[,\t]");


  private final FileLineIterator lineIterator;


  FileItemItemSimilarityIterator(File similaritiesFile) throws IOException {
    lineIterator = new FileLineIterator(similaritiesFile);
  }

View Full Code Here


    this.dataFile = dataFile.getAbsoluteFile();
    this.lastModified = dataFile.lastModified();
    this.lastUpdateFileModified = readLastUpdateFileModified();


    FileLineIterator iterator = new FileLineIterator(dataFile, false);
    String firstLine = iterator.peek();
    while ((firstLine.length() == 0) || (firstLine.charAt(0) == COMMENT_CHAR)) {
      iterator.next();
      firstLine = iterator.peek();
    }
    iterator.close();


    delimiter = determineDelimiter(firstLine);
    delimiterPattern = Pattern.compile(String.valueOf(delimiter));
    String[] firstLineSplit = delimiterPattern.split(firstLine);
    // If preference value exists and isn't empty then the file is specifying pref values

View Full Code Here

    if (hasPrefValues) {


      if (loadFreshData) {


        FastByIDMap<Collection<Preference>> data = new FastByIDMap<Collection<Preference>>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFile(iterator, data, timestamps, false);


        for (File updateFile : findUpdateFiles()) {
          processFile(new FileLineIterator(updateFile, false), data, timestamps, false);
        }


        return new GenericDataModel(GenericDataModel.toDataMap(data, true), timestamps);


      } else {


        FastByIDMap<PreferenceArray> rawData = ((GenericDataModel) delegate).getRawUserData();


        for (File updateFile : findUpdateFiles()) {
          processFile(new FileLineIterator(updateFile, false), rawData, timestamps, true);
        }


        return new GenericDataModel(rawData, timestamps);


      }


    } else {


      if (loadFreshData) {


        FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>();
        FileLineIterator iterator = new FileLineIterator(dataFile, false);
        processFileWithoutID(iterator, data, timestamps);


        for (File updateFile : findUpdateFiles()) {
          processFileWithoutID(new FileLineIterator(updateFile, false), data, timestamps);
        }


        return new GenericBooleanPrefDataModel(data, timestamps);


      } else {


        FastByIDMap<FastIDSet> rawData = ((GenericBooleanPrefDataModel) delegate).getRawUserData();


        for (File updateFile : findUpdateFiles()) {
          processFileWithoutID(new FileLineIterator(updateFile, false), rawData, timestamps);
        }


        return new GenericBooleanPrefDataModel(rawData, timestamps);


      }

View Full Code Here

    
    StringBuilder content = new StringBuilder();
    content.append(header);
    NumberFormat decimalFormatter = new DecimalFormat("0000");
    File dumpFile = new File(dumpFilePath);
    FileLineIterator it;
    if (dumpFilePath.endsWith(".bz2")) {
      // default compression format from http://download.wikimedia.org
      CompressionCodec codec = new BZip2Codec();
      it = new FileLineIterator(codec.createInputStream(new FileInputStream(dumpFile)));
    } else {
      // assume the user has previously de-compressed the dump file
      it = new FileLineIterator(dumpFile);
    }
    int filenumber = 0;
    while (it.hasNext()) {
      String thisLine = it.next();
      if (thisLine.trim().startsWith("<page>")) {
        boolean end = false;
        while (!thisLine.trim().startsWith("</page>")) {
          content.append(thisLine).append('\n');
          if (it.hasNext()) {
            thisLine = it.next();
          } else {
            end = true;
            break;
          }
        }

View Full Code Here

  }
  
  @Override
  protected DataModel buildModel() throws IOException {
    FastByIDMap<Collection<Preference>> data = new FastByIDMap<Collection<Preference>>();
    FileLineIterator iterator = new FileLineIterator(getDataFile(), false);
    FastByIDMap<FastByIDMap<Long>> timestamps = new FastByIDMap<FastByIDMap<Long>>();
    processFile(iterator, data, timestamps, false);
    return new GenericDataModel(GenericDataModel.toDataMap(data, true));
  }

View Full Code Here

   * @param path
   *          data path
   */
  public static int[] extractLabels(Dataset dataset, FileSystem fs, Path path) throws IOException {
    FSDataInputStream input = fs.open(path);
    FileLineIterator iterator = new FileLineIterator(input);
    
    int[] labels = new int[dataset.nbInstances()];
    DataConverter converter = new DataConverter(dataset);
    
    int index = 0;
    
    while (iterator.hasNext()) {
      labels[index++] = converter.convert(0, iterator.next()).getLabel();
    }
    
    iterator.close();
    
    return labels;
  }

View Full Code Here


    files = out.listFiles();
    assertEquals("files Size: " + files.length + " is not: " + WORDS.length, files.length, WORDS.length);
    for (File file : files) {
      //should only be one line in the file, and it should be label label
      Iterator<String> it = new FileLineIterator(file);
      String line = it.next().trim();
      assertFalse(it.hasNext());
      String label = "animal" + '\t' + file.getName();
      assertEquals(line + ":::: is not equal to " + label + "::::", line, label);
    }
  }

View Full Code Here

      }
    }
  }


  protected DataModel buildModel() throws IOException {
    FileLineIterator iterator = new FileLineIterator(dataFile, false);
    String firstLine = iterator.peek();
    while (firstLine.length() == 0 || firstLine.charAt(0) == COMMENT_CHAR) {
      iterator.next();
      firstLine = iterator.peek();
    }
    char delimiter = determineDelimiter(firstLine);
    boolean hasPrefValues = firstLine.indexOf(delimiter, firstLine.indexOf(delimiter) + 1) >= 0;


    if (hasPrefValues) {
      FastByIDMap<Collection<Preference>> data = new FastByIDMap<Collection<Preference>>();
      processFile(iterator, data, delimiter);
      for (File updateFile : findUpdateFiles()) {
        processFile(new FileLineIterator(updateFile, false), data, delimiter);
      }
      return new GenericDataModel(GenericDataModel.toDataMap(data, true));
    } else {
      FastByIDMap<FastIDSet> data = new FastByIDMap<FastIDSet>();
      processFileWithoutID(iterator, data, delimiter);
      for (File updateFile : findUpdateFiles()) {
        processFileWithoutID(new FileLineIterator(updateFile, false), data, delimiter);
      }
      return new GenericBooleanPrefDataModel(data);
    }
  }

View Full Code Here


    files = out.listFiles();
    assertEquals("files Size: " + files.length + " is not: " + words.length, files.length, words.length);
    for (File file : files) {
      //should only be one line in the file, and it should be label label
      FileLineIterator it = new FileLineIterator(file);
      String line = it.next().trim();
      assertFalse(it.hasNext());
      String label = "animal" + '\t' + file.getName();
      assertEquals(line + ":::: is not equal to " + label + "::::", line, label);
    }
  }

View Full Code Here

    
    return result;
  }


  private static ArrayList<String> getTermDict(String dictFile) throws IOException {
    FileLineIterator it = new FileLineIterator(new File(dictFile));


    int numEntries = Integer.parseInt(it.next());
    System.out.println(numEntries);
    ArrayList<String> result = new ArrayList<String>();
    
    for (int i = 0; i < numEntries; i++) {
      result.add("dummyentry");
    }
    
    while (it.hasNext()) {
      String line = it.next();
      if (line.startsWith("#")) {
        continue;
      }
      String[] tokens = TAB_PATTERN.split(line);
      if (tokens.length < 3) {

View Full Code Here

0 1 2

TOP

Related Classes of org.apache.mahout.common.FileLineIterator

org.apache.mahout.cf.taste.example.jester.JesterDataModel

org.apache.mahout.cf.taste.impl.model.file.FileDataModel

org.apache.mahout.cf.taste.impl.recommender.slopeone.file.FileDiffStorage

org.apache.mahout.cf.taste.impl.similarity.file.FileItemItemSimilarityIterator

org.apache.mahout.classifier.bayes.BayesFileFormatterTest

org.apache.mahout.classifier.bayes.WikipediaXmlSplitter

org.apache.mahout.clustering.lda.LDAPrintTopics

org.apache.mahout.df.data.Data

org.apache.mahout.utils.clustering.ClusterDumper

org.apache.mahout.utils.vectors.VectorHelper

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.