Java Matrix.viewRow方法代码示例

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
static void writeMatrix(Matrix origMatrix,
     Path outPath, Path tmpPath, String label) throws IOException {
   Configuration conf = new Configuration();
   Path outputDir = new Path(outPath, label + origMatrix.numRows() + "x"
       + origMatrix.numCols());
   FileSystem fs = FileSystem.get(outputDir.toUri(), conf);
   if (!fs.exists(outputDir)) {
     Path outputFile = new Path(outputDir, "singleSliceMatrix");
     SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
         outputFile, IntWritable.class, VectorWritable.class);
     VectorWritable vectorWritable = new VectorWritable();
     try {
       for (int r = 0; r < origMatrix.numRows(); r++) {
         Vector vector = origMatrix.viewRow(r);
         vectorWritable.set(vector);
         writer.append(new IntWritable(r), vectorWritable);
       }
     } finally {
       writer.close();
     }
   } else {
     log.warn("----------- Skip matrix " + outputDir + " - already exists");
   }
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
public void trainDocTopicModel(Vector original, Vector topics, Matrix docTopicModel) {
  // first calculate p(topic|term,document) for all terms in original, and all topics,
  // using p(term|topic) and p(topic|doc)
  pTopicGivenTerm(original, topics, docTopicModel);
  normalizeByTopic(docTopicModel);
  // now multiply, term-by-term, by the document, to get the weighted distribution of
  // term-topic pairs from this document.
  Iterator<Vector.Element> it = original.iterateNonZero();
  while (it.hasNext()) {
    Vector.Element e = it.next();
    for (int x = 0; x < numTopics; x++) {
      Vector docTopicModelRow = docTopicModel.viewRow(x);
      docTopicModelRow.setQuick(e.index(), docTopicModelRow.getQuick(e.index()) * e.get());
    }
  }
  // now recalculate p(topic|doc) by summing contributions from all of pTopicGivenTerm
  topics.assign(0.0);
  for (int x = 0; x < numTopics; x++) {
    topics.set(x, docTopicModel.viewRow(x).norm(1));
  }
  // now renormalize so that sum_x(p(x|doc)) = 1
  topics.assign(Functions.mult(1/topics.norm(1)));
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
/**
 * Computes {@code p(topic x|term a, document i)} distributions given input document {@code i}.
 * {@code pTGT[x][a]} is the (un-normalized) {@code p(x|a,i)}, or if docTopics is {@code null},
 * {@code p(a|x)} (also un-normalized).
 *
 * @param document doc-term vector encoding {@code w(term a|document i)}.
 * @param docTopics {@code docTopics[x]} is the overall weight of topic {@code x} in given
 *          document. If {@code null}, a topic weight of {@code 1.0} is used for all topics.
 * @param termTopicDist storage for output {@code p(x|a,i)} distributions.
 */
private void pTopicGivenTerm(Vector document, Vector docTopics, Matrix termTopicDist) {
  // for each topic x
  for (int x = 0; x < numTopics; x++) {
    // get p(topic x | document i), or 1.0 if docTopics is null
    double topicWeight = docTopics == null ? 1.0 : docTopics.get(x);
    // get w(term a | topic x)
    Vector topicTermRow = topicTermCounts.viewRow(x);
    // get \sum_a w(term a | topic x)
    double topicSum = topicSums.get(x);
    // get p(topic x | term a) distribution to update
    Vector termTopicRow = termTopicDist.viewRow(x);

    // for each term a in document i with non-zero weight
    Iterator<Vector.Element> it = document.iterateNonZero();
    while (it.hasNext()) {
      Vector.Element e = it.next();
      int termIndex = e.index();

      // calc un-normalized p(topic x | term a, document i)
      double termTopicLikelihood = (topicTermRow.get(termIndex) + eta) * (topicWeight + alpha) / (topicSum + eta * numTerms);
      termTopicRow.set(termIndex, termTopicLikelihood);
    }
  }
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
/**
 * Convert an in-memory representation of a matrix to a distributed version It
 * then can be used in distributed jobs
 * 
 * @param oriMatrix
 * @return path that contains the matrix files
 * @throws IOException
 */
static DistributedRowMatrix toDistributedRowMatrix(Matrix origMatrix,
    Path outPath, Path tmpPath, String label) throws IOException {
  Configuration conf = new Configuration();
  Path outputDir = new Path(outPath, label + origMatrix.numRows() + "x"
      + origMatrix.numCols());
  FileSystem fs = FileSystem.get(outputDir.toUri(), conf);
  if (!fs.exists(outputDir)) {
    Path outputFile = new Path(outputDir, "singleSliceMatrix");
    SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
        outputFile, IntWritable.class, VectorWritable.class);
    VectorWritable vectorWritable = new VectorWritable();
    try {
      for (int r = 0; r < origMatrix.numRows(); r++) {
        Vector vector = origMatrix.viewRow(r);
        vectorWritable.set(vector);
        writer.append(new IntWritable(r), vectorWritable);
      }
    } finally {
      writer.close();
    }
  } else {
    log.warn("----------- Skip matrix " + outputDir + " - already exists");
  }
  DistributedRowMatrix dMatrix = new DistributedRowMatrix(outputDir, tmpPath,
      origMatrix.numRows(), origMatrix.numCols());
  dMatrix.setConf(conf);
  return dMatrix;
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
@Test
public void testMAHOUT_1221() {
  // create a matrix with an unassigned row 0
  Matrix matrix = new SparseMatrix(1, 1);
  Vector view = matrix.viewRow(0);
  final double value = 1.23;
  view.assign(value);
  // test whether the update in the view is reflected in the matrix
  assertEquals("Matrix valye", view.getQuick(0), matrix.getQuick(0, 0),
      EPSILON);
}