Java Matrix.assignRow方法代码示例

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
/***
 * PPCA: sequential PPCA based on the paper from Tipping and Bishop
 * 
 * @param conf
 *          the configuration
 * @param input
 *          the path to the input matrix Y
 * @param output
 *          the output path (not used currently)
 * @param nRows
 *          number or rows in Y
 * @param nCols
 *          number of columns in Y
 * @param nPCs
 *          number of desired principal components
 * @return the error
 * @throws Exception
 */
double runSequential(Configuration conf, Path input, Path output,
    final int nRows, final int nCols, final int nPCs) throws Exception {
  Matrix centralY = new DenseMatrix(nRows, nCols);
  FileSystem fs = FileSystem.get(input.toUri(), conf);
  if (fs.listStatus(input).length == 0) {
    System.err.println("No file under " + input);
    return 0;
  }
  int row = 0;
  for (VectorWritable vw : new SequenceFileDirValueIterable<VectorWritable>(
      input, PathType.LIST, null, conf)) {
    centralY.assignRow(row, vw.get());
    row++;
  }
  Matrix centralC = PCACommon.randomMatrix(nCols, nPCs);
  double ss = PCACommon.randSS();
  InitialValues initVal = new InitialValues(centralC, ss);
  // Matrix sampledYe = sample(centralY);
  // runSequential(conf, sampledYe, initVal, 100);
  double error = runSequential(conf, centralY, initVal, 100);
  return error;
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
/**
 * PPCA: sequential PPCA based on the matlab implementation of Jacob Verbeek
 * 
 * @param conf
 *          the configuration
 * @param input
 *          the path to the input matrix Y
 * @param output
 *          the output path (not used currently)
 * @param nRows
 *          number or rows in Y
 * @param nCols
 *          number of columns in Y
 * @param nPCs
 *          number of desired principal components
 * @return the error
 * @throws Exception
 */
double runSequential_JacobVersion(Configuration conf, Path input,
    Path output, final int nRows, final int nCols, final int nPCs) throws Exception {
  Matrix centralY = new DenseMatrix(nRows, nCols);
  FileSystem fs = FileSystem.get(input.toUri(), conf);
  if (fs.listStatus(input).length == 0) {
    System.err.println("No file under " + input);
    return 0;
  }
  int row = 0;
  for (VectorWritable vw : new SequenceFileDirValueIterable<VectorWritable>(
      input, PathType.LIST, null, conf)) {
    centralY.assignRow(row, vw.get());
    row++;
  }
  Matrix C = PCACommon.randomMatrix(nCols, nPCs);
  double ss = PCACommon.randSS();
  InitialValues initVal = new InitialValues(C, ss);
  double error = runSequential_JacobVersion(conf, centralY, initVal, 100);
  return error;
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
@Test
public void crossTestIterationOfMapReducePPCASequentialPPCA() throws Exception {
  Matrix C_central = PCACommon.randomMatrix(D, d);
  double ss = PCACommon.randSS();
  InitialValues initValSeq = new InitialValues(C_central, ss);
  InitialValues initValMR = new InitialValues(C_central.clone(), ss);

  //1. run sequential
  Matrix Ye_central = new DenseMatrix(N, D);
  int row = 0;
  for (VectorWritable vw : new SequenceFileDirValueIterable<VectorWritable>(
      input, PathType.LIST, null, conf)) {
    Ye_central.assignRow(row, vw.get());
    row++;
  }
  double bishopSeqErr = ppcaDriver.runSequential(conf, Ye_central, initValSeq, 1);
  
  //2. run mapreduce
  DistributedRowMatrix Ye = new DistributedRowMatrix(input, tmp, N, D);
  Ye.setConf(conf);
  double bishopMRErr = ppcaDriver.runMapReduce(conf, Ye, initValMR, output, N, D, d, 1, 1, 1, 1);
  
  Assert.assertEquals(
      "ss value is different in sequential and mapreduce PCA", initValSeq.ss,
      initValMR.ss, EPSILON);
  double seqCTrace = PCACommon.trace(initValSeq.C);
  double mrCTrace = PCACommon.trace(initValMR.C);
  Assert.assertEquals(
      "C value is different in sequential and mapreduce PCA", seqCTrace,
      mrCTrace, EPSILON);
  Assert.assertEquals(
      "The PPCA error between sequntial and mapreduce methods is too different: "
          + bishopSeqErr + "!= " + bishopMRErr, bishopSeqErr, bishopMRErr, EPSILON);
}
 

import org.apache.mahout.math.Matrix; //导入方法依赖的package包/类
/**
 * Returns n-1 probabilities, one for each category but the last, for each row of a matrix. The
 * probability of the missing 0-th category is 1 - rowSum(this result).
 *
 * @param data The matrix whose rows are vectors to classify
 * @return A matrix of scores, one row per row of the input matrix, one column for each but the
 *         last category.
 */
public Matrix classify(Matrix data) {
  Matrix r = new DenseMatrix(data.numRows(), numCategories() - 1);
  for (int row = 0; row < data.numRows(); row++) {
    r.assignRow(row, classify(data.viewRow(row)));
  }
  return r;
}