Examples of VectorWriter


Examples of org.apache.mahout.utils.vectors.io.VectorWriter

    Path path = new Path(tmpFile.getAbsolutePath());
    Configuration conf = new Configuration();//<co id="vec.examples.seq.conf"/>
    FileSystem fs = FileSystem.get(conf);
    SequenceFile.Writer seqWriter = SequenceFile.createWriter(fs, conf, path,
            LongWritable.class, VectorWritable.class);//<co id="vec.examples.seq.writer"/>
    VectorWriter vecWriter = new SequenceFileVectorWriter(seqWriter);//<co id="vec.examples.seq.vecwriter"/>
    List<Vector> vectors = new ArrayList<Vector>();
    vectors.add(sparse);
    vectors.add(sparseSame);
    vecWriter.write(vectors);//<co id="vec.examples.seq.write"/>
    vecWriter.close();
    /*
<calloutlist>
    <callout arearefs="vec.examples.seq.conf"><para>Create a <classname>Configuration</classname> for Hadoop</para></callout>
    <callout arearefs="vec.examples.seq.writer"><para>Create a Hadoop <classname>SequenceFile.Writer</classname> to handle the job of physically writing out the vectors to a file in HDFS</para></callout>
    <callout arearefs="vec.examples.seq.vecwriter"><para>A <classname>VectorWriter</classname> processes the <classname>Vector</classname>s and invokes the underlying write methods on the <classname>SequenceFile.Writer</classname></para></callout>
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

    ARFFModel model = new MapBackedARFFModel(arffModel.getWords(), arffModel.getWordCount() + 1, arffModel
        .getNominalMap());
    ARFFVectorIterable iteratable = new ARFFVectorIterable(file, model);
    String outFile = outDir + '/' + file.getName() + ".mvc";
   
    VectorWriter vectorWriter;
    if (outWriter != null) {
      if (outWriter.equals("file")) {
        BufferedWriter writer = new BufferedWriter(new FileWriter(outFile));
        vectorWriter = new JWriterVectorWriter(writer);
      } else {
        vectorWriter = getSeqFileWriter(outFile);
      }
    } else {
      vectorWriter = getSeqFileWriter(outFile);
    }
   
    long numDocs = vectorWriter.write(iteratable, maxDocs);
    vectorWriter.close();
    log.info("Wrote: {} vectors", numDocs);
  }
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

            iterable = new LuceneIterable(reader, idField, field, mapper, norm);
          }
          String outFile = cmdLine.getValue(outputOpt).toString();
          log.info("Output File: {}", outFile);
         
          VectorWriter vectorWriter;
          if (cmdLine.hasOption(outWriterOpt)) {
            String outWriter = cmdLine.getValue(outWriterOpt).toString();
            if (outWriter.equals("file")) {
              BufferedWriter writer = new BufferedWriter(new FileWriter(outFile));
              vectorWriter = new JWriterVectorWriter(writer);
            } else {
              vectorWriter = getSeqFileWriter(outFile);
            }
          } else {
            vectorWriter = getSeqFileWriter(outFile);
          }
         
          long numDocs = vectorWriter.write(iterable, maxDocs);
          vectorWriter.close();
          log.info("Wrote: {} vectors", numDocs);
         
          String delimiter = cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString()
              : "\t";
          File dictOutFile = new File(cmdLine.getValue(dictOutOpt).toString());
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

      iterable = new LuceneIterable(reader, idField, field, mapper, norm, maxPercentErrorDocs);
    }

    log.info("Output File: {}", outFile);

    VectorWriter vectorWriter = getSeqFileWriter(outFile);
    try {
      long numDocs = vectorWriter.write(iterable, maxDocs);
      log.info("Wrote: {} vectors", numDocs);
    } finally {
      Closeables.closeQuietly(vectorWriter);
    }
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

        }

        String outFile = cmdLine.getValue(outputOpt).toString();
        log.info("Output File: {}", outFile);

        VectorWriter vectorWriter;
        if (cmdLine.hasOption(outWriterOpt)) {
          String outWriter = cmdLine.getValue(outWriterOpt).toString();
          if ("file".equals(outWriter)) {
            BufferedWriter writer = new BufferedWriter(new FileWriter(outFile));
            vectorWriter = new JWriterVectorWriter(writer);
          } else {
            vectorWriter = getSeqFileWriter(outFile);
          }
        } else {
          vectorWriter = getSeqFileWriter(outFile);
        }

        long numDocs = vectorWriter.write(iterable, maxDocs);
        vectorWriter.close();
        log.info("Wrote: {} vectors", numDocs);

        String delimiter = cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString() : "\t";
       
        File dictOutFile = new File(cmdLine.getValue(dictOutOpt).toString());
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

    ARFFModel model = new MapBackedARFFModel(arffModel.getWords(), arffModel.getWordCount() + 1, arffModel
        .getNominalMap());
    Iterable<Vector> iteratable = new ARFFVectorIterable(file, model);
    String outFile = outDir + '/' + file.getName() + ".mvc";
   
    VectorWriter vectorWriter;
    if (outWriter == null) {
      vectorWriter = getSeqFileWriter(outFile);
    } else {
      if ("file".equals(outWriter)) {
        vectorWriter = new JWriterVectorWriter(new BufferedWriter(new FileWriter(outFile)));
      } else {
        vectorWriter = getSeqFileWriter(outFile);
      }
    }
    try {
      long numDocs = vectorWriter.write(iteratable, maxDocs);
      log.info("Wrote: {} vectors", numDocs);
    } finally {
      vectorWriter.close();
    }
  }
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

    ARFFModel model = new MapBackedARFFModel(arffModel.getWords(), arffModel.getWordCount() + 1, arffModel
        .getNominalMap());
    Iterable<Vector> iteratable = new ARFFVectorIterable(file, model);
    String outFile = outDir + '/' + file.getName() + ".mvc";
   
    VectorWriter vectorWriter = getSeqFileWriter(outFile);
    try {
      long numDocs = vectorWriter.write(iteratable, maxDocs);
      writeLabelBindings(dictOut, model, delimiter, jsonDictonary);
      log.info("Wrote: {} vectors", numDocs);
    } finally {
      Closeables.close(vectorWriter, false);
    }
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

      iterable = new LuceneIterable(reader, idField, field, termInfo, weight, norm, maxPercentErrorDocs);
    }

    log.info("Output File: {}", outFile);

    VectorWriter vectorWriter = getSeqFileWriter(outFile);
    try {
      long numDocs = vectorWriter.write(iterable, maxDocs);
      log.info("Wrote: {} vectors", numDocs);
    } finally {
      Closeables.close(vectorWriter, false);
    }
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

            iterable = new LuceneIterable(reader, idField, field, mapper, norm);
          }
          String outFile = cmdLine.getValue(outputOpt).toString();
          log.info("Output File: " + outFile);

          VectorWriter vectorWriter;
          if (cmdLine.hasOption(outWriterOpt)) {
            String outWriter = cmdLine.getValue(outWriterOpt).toString();
            if (outWriter.equals("file")) {
              BufferedWriter writer = new BufferedWriter(new FileWriter(outFile));
              vectorWriter = new JWriterVectorWriter(writer);
            } else {
              vectorWriter = getSeqFileWriter(outFile);
            }
          } else {
            vectorWriter = getSeqFileWriter(outFile);
          }

          long numDocs = vectorWriter.write(iterable, maxDocs);
          vectorWriter.close();
          log.info("Wrote: " + numDocs + " vectors");

          String delimiter = cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString() : "\t";
          File dictOutFile = new File(cmdLine.getValue(dictOutOpt).toString());
          log.info("Dictionary Output file: " + dictOutFile);
View Full Code Here

Examples of org.apache.mahout.utils.vectors.io.VectorWriter

    ARFFModel model = new MapBackedARFFModel(arffModel.getWords(), arffModel.getWordCount() + 1,
            arffModel.getNominalMap());
    ARFFVectorIterable iteratable = new ARFFVectorIterable(file, model);
    String outFile = outDir + '/' + file.getName() + ".mvc";

    VectorWriter vectorWriter;
    if (outWriter != null) {
      if (outWriter.equals("file")) {
        BufferedWriter writer = new BufferedWriter(new FileWriter(outFile));
        vectorWriter = new JWriterVectorWriter(writer);
      } else {
        vectorWriter = getSeqFileWriter(outFile);
      }
    } else {
      vectorWriter = getSeqFileWriter(outFile);
    }

    long numDocs = vectorWriter.write(iteratable, maxDocs);
    vectorWriter.close();
    log.info("Wrote: " + numDocs + " vectors");
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
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.