def apply(self, dataset, can_fit=False):
if self._pca is None:
if not can_fit:
raise ValueError("can_fit is False, but PCA preprocessor "
"object has no fitted model stored")
from pylearn2 import pca
self._pca = pca.CovEigPCA(self._num_components)
self._pca.train(dataset.get_design_matrix())
self._transform_func = function([self._input],
self._pca(self._input))
self._invert_func = function([self._output],
self._pca.reconstruct(self._output))
self._convert_weights_func = function([self._output],
self._pca.reconstruct(
self._output,
add_mean=False))
orig_data = dataset.get_design_matrix()
dataset.set_design_matrix(
self._transform_func(dataset.get_design_matrix()))
proc_data = dataset.get_design_matrix()
orig_var = orig_data.var(axis=0)
proc_var = proc_data.var(axis=0)
assert proc_var[0] > orig_var.max()
# TODO: logging
print 'original variance: ' + str(orig_var.sum())
print 'processed variance: ' + str(proc_var.sum())
if dataset.view_converter is not None:
new_converter = PCA_ViewConverter(self._transform_func,
self._invert_func,
self._convert_weights_func,
dataset.view_converter)
dataset.view_converter = new_converter
def apply(self, dataset, can_fit=False):
if self.pca is None:
assert can_fit
from pylearn2 import pca
self.pca = pca.CovEigPCA(self.num_components)
self.pca.train(dataset.get_design_matrix())
self.transform_func = function([self.input], self.pca(self.input))
self.invert_func = function([self.output],
self.pca.reconstruct(self.output))
self.convert_weights_func = function([self.output],
self.pca.reconstruct(
self.output,
add_mean=False))
#
orig_data = dataset.get_design_matrix() #rm
dataset.set_design_matrix(
self.transform_func(dataset.get_design_matrix()))
proc_data = dataset.get_design_matrix() #rm
orig_var = orig_data.var(axis=0)
proc_var = proc_data.var(axis=0)
assert proc_var[0] > orig_var.max()
print 'original variance: ' + str(orig_var.sum())
print 'processed variance: ' + str(proc_var.sum())
dataset.view_converter = PCA_ViewConverter(self.transform_func,
self.invert_func,
self.convert_weights_func,
dataset.view_converter)