PCA.py 文件源码

def train_projector(self, training_features, projector_file):
    """Generates the PCA covariance matrix and writes it into the given projector_file.

    **Parameters:**

    training_features : [1D :py:class:`numpy.ndarray`]
      A list of 1D training arrays (vectors) to train the PCA projection matrix with.

    projector_file : str
      A writable file, into which the PCA projection matrix (as a :py:class:`bob.learn.linear.Machine`) and the eigenvalues will be written.
    """
    # Assure that all data are 1D
    [self._check_feature(feature) for feature in training_features]

    # Initializes the data
    data = numpy.vstack(training_features)
    logger.info("  -> Training LinearMachine using PCA")
    t = bob.learn.linear.PCATrainer()
    self.machine, self.variances = t.train(data)
    # For re-shaping, we need to copy...
    self.variances = self.variances.copy()

    # compute variance percentage, if desired
    if isinstance(self.subspace_dim, float):
      cummulated = numpy.cumsum(self.variances) / numpy.sum(self.variances)
      for index in range(len(cummulated)):
        if cummulated[index] > self.subspace_dim:
          self.subspace_dim = index
          break
      self.subspace_dim = index
    logger.info("    ... Keeping %d PCA dimensions", self.subspace_dim)
    # re-shape machine
    self.machine.resize(self.machine.shape[0], self.subspace_dim)
    self.variances.resize(self.subspace_dim)

    f = bob.io.base.HDF5File(projector_file, "w")
    f.set("Eigenvalues", self.variances)
    f.create_group("Machine")
    f.cd("/Machine")
    self.machine.save(f)