def pca_preprocessing(data, n_components, normalize):
projector = PCA(n_components=n_components, random_state=0)
if normalize:
projector.preprocessors += (preprocess.Normalize(),)
model = projector(data)
return model(data)
def fit(self):
self.clear()
self.Warning.trivial_components.clear()
if self.data is None:
return
data = self.data
if self.normalize:
self._pca_projector.preprocessors = \
self._pca_preprocessors + [preprocess.Normalize(center=False)]
else:
self._pca_projector.preprocessors = self._pca_preprocessors
if not isinstance(data, SqlTable):
pca = self._pca_projector(data)
variance_ratio = pca.explained_variance_ratio_
cumulative = numpy.cumsum(variance_ratio)
if numpy.isfinite(cumulative[-1]):
self.components_spin.setRange(0, len(cumulative))
self._pca = pca
self._variance_ratio = variance_ratio
self._cumulative = cumulative
self._setup_plot()
else:
self.Warning.trivial_components()
self.unconditional_commit()
def pca_preprocessing(self):
"""Perform PCA preprocessing before passing off the data to t-SNE."""
if self.pca_data is not None:
return
projector = PCA(n_components=self.pca_components, random_state=0)
# If the normalization box is ticked, we'll add the `Normalize`
# preprocessor to PCA
if self.normalize:
projector.preprocessors += (preprocess.Normalize(),)
model = projector(self.data)
self.pca_data = model(self.data)
