import org.apache.mahout.math.VectorIterable; //导入依赖的package包/类
public double calculatePerplexity(VectorIterable matrix, VectorIterable docTopicCounts,
    double testFraction) {
  Iterator<MatrixSlice> docIterator = matrix.iterator();
  Iterator<MatrixSlice> docTopicIterator = docTopicCounts.iterator();
  double perplexity = 0;
  double matrixNorm = 0;
  while (docIterator.hasNext() && docTopicIterator.hasNext()) {
    MatrixSlice docSlice = docIterator.next();
    MatrixSlice topicSlice = docTopicIterator.next();
    int docId = docSlice.index();
    Vector document = docSlice.vector();
    Vector topicDist = topicSlice.vector();
    if (testFraction == 0 || docId % (1/testFraction) == 0) {
      trainSync(document, topicDist, false, 10);
      perplexity += readModel.perplexity(document, topicDist);
      matrixNorm += document.norm(1);
    }
  }
  return perplexity / matrixNorm;
}
 

import org.apache.mahout.math.VectorIterable; //导入依赖的package包/类
static <M extends VectorIterable> Matrix sample(M bigMatrix,
    Matrix sampleMatrix) {
  log.info("Sampling a " + bigMatrix.numRows() + "x" + bigMatrix.numCols()
      + " into a " + sampleMatrix.numRows() + "x" + sampleMatrix.numCols());
  int row = 0;
  Iterator<MatrixSlice> sliceIterator = bigMatrix.iterateAll();
  while (sliceIterator.hasNext() && row < sampleMatrix.numRows()) {
    MatrixSlice slice = sliceIterator.next();
    if (!PCACommon.pass(SAMPLE_RATE)) {
      sampleMatrix.viewRow(row).assign(slice.vector());
      row++;
    }
  }
  return sampleMatrix;
}
 

import org.apache.mahout.math.VectorIterable; //导入依赖的package包/类
public void train(VectorIterable matrix, VectorIterable docTopicCounts) {
  train(matrix, docTopicCounts, 1);
}