def test_PCA_scorer_component(self):
pca = PCA()
for i in range(1, len(self.zoo.domain.attributes) + 1):
pca.component = i
scores = pca.score_data(self.zoo)
self.assertEqual(scores.shape,
(pca.component, len(self.zoo.domain.attributes)))
def test_PCA_scorer_component(self):
pca = PCA()
for i in range(1, len(self.zoo.domain.attributes) + 1):
pca.component = i
scores = pca.score_data(self.zoo)
self.assertEqual(scores.shape,
(pca.component, len(self.zoo.domain.attributes)))
def test_PCA_scorer(self):
data = self.iris
pca = PCA(preprocessors=[Normalize()])
pca.component = 1
scores = pca.score_data(data)
self.assertEqual(scores.shape[1], len(data.domain.attributes))
self.assertEqual(['petal length', 'petal width'],
sorted([data.domain.attributes[i].name
for i in np.argsort(scores[0])[-2:]]))
self.assertEqual([round(s, 4) for s in scores[0]],
[0.5224, 0.2634, 0.5813, 0.5656])
def test_PCA_scorer(self):
data = self.iris
pca = PCA(preprocessors=[Normalize()])
pca.component = 1
scores = pca.score_data(data)
self.assertEqual(scores.shape[1], len(data.domain.attributes))
self.assertEqual(['petal length', 'petal width'],
sorted([data.domain.attributes[i].name
for i in np.argsort(scores[0])[-2:]]))
self.assertEqual([round(s, 4) for s in scores[0]],
[0.5224, 0.2634, 0.5813, 0.5656])
def _get_pca(self):
pca_projector = PCA(n_components=2)
pca_projector.component = 2
pca_projector.preprocessors = PCA.preprocessors + [Normalize()]
pca = pca_projector(self.data)
variance_ratio = pca.explained_variance_ratio_
cumulative = np.cumsum(variance_ratio)
self._pca = pca
if not np.isfinite(cumulative[-1]):
self.Warning.trivial_components()
coords = pca(self.data).X
valid_mask = ~np.isnan(coords).any(axis=1)
# scale axes
max_radius = np.min([np.abs(np.min(coords, axis=0)),
np.max(coords, axis=0)])
axes = pca.components_.T.copy()
axes *= max_radius / np.max(np.linalg.norm(axes, axis=1))
return valid_mask, coords, axes
