def test_frob_norm(self):
"""
Check Frobenius norm is calculated correctly whether the full
or partial PCA is computed.
"""
true_frob_norm = np.linalg.norm(self.X_cent, ord='fro')
PCA = pca(n_components=None).fit(self.X)
self.assertTrue(np.allclose(PCA.frob_norm_, true_frob_norm))
# TODO: this is failing, it could be a numerical issue.
PCA = pca(n_components=3).fit(self.X)
self.assertTrue(np.allclose(PCA.frob_norm_, true_frob_norm))
def test_reconstruction(self):
"""
We can reconstruct the original data matrix exactly from the full
reconstruction.
"""
PCA = pca().fit(self.X)
self.assertTrue(np.allclose(self.X, PCA.predict_reconstruction()))
def test_scores():
X = np.array([[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 10, 11]])
pca2 = pca()
pca2.fit(X)
scores = np.array([[-7.794229, 0., -0.], [-2.598076, 0., 0.],
[2.598076, 0., 0.], [7.794229, -0., 0.]])
assert_almost_equal(scores, pca2.scores(norm=False, np=True), decimal=4)
def test_predict_reconstruction():
X = np.array([[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 10, 11]])
pca2 = pca()
pca2.fit(X)
recon = pca2.predict_reconstruction(X)
R = np.array([[-47.7852752, -46.7852752, -45.7852752],
[-12.9284251, -11.9284251, -10.9284251],
[21.9284251, 22.9284251, 23.9284251],
[56.7852752, 57.7852752, 58.7852752]])
assert_almost_equal(R, recon, decimal=4)
def test_dunder_repr():
"""
Make sure __repr__ function works.
"""
pca1 = pca(n_components=2, center='mean')
compare = 'pca object, nothing has been computed yet'
assert_equal(pca1.__repr__(), compare)
X = np.array([[0, 1, 2], [3, 4, 5], [6, 7, 8]])
pca1.fit(X)
compare = 'Rank {} pca of a {} matrix'.format(2, X.shape)
assert_equal(pca1.__repr__(), compare)
def test_centering(self):
"""
Make sure PCA computes the correct centers. Also check center=False
works correctly.
"""
self.assertTrue(np.allclose(self.pca.m_, self.X.mean(axis=0)))
# no centering
PCA = pca(n_components=4, center=False).fit(self.X)
self.assertTrue(PCA.m_ is None)
Z = np.random.normal(size=(20, self.X.shape[1]))
V = PCA.loadings_.values
self.assertTrue(np.allclose(PCA.predict_scores(Z), np.dot(Z, V)))
def setUp(self):
n = 100
d = 20
n_components = 10
obs_names = ['sample_{}'.format(i) for i in range(n)]
var_names = ['var_{}'.format(i) for i in range(d)]
X = pd.DataFrame(np.random.normal(size=(n, d)),
index=obs_names,
columns=var_names)
X_cent = X - X.mean(axis=0)
PCA = pca(n_components=n_components).fit(X)
# store these for testing
self.n = n
self.d = d
self.n_components = n_components
self.obs_names = obs_names
self.var_names = var_names
self.X = X
self.X_cent = X_cent
self.pca = PCA
def test_n_components_None():
pca1 = pca()
X = np.array([[0, 1, 2], [3, 4, 5], [6, 7, 8], [9, 10, 11]])
pca1.fit(X)
d = pca1.get_params()
assert_equal(d['n_components'], X.shape[1])