def test_pls_errors():
d = load_linnerud()
X = d.data
Y = d.target
for clf in [pls_.PLSCanonical(), pls_.PLSRegression(), pls_.PLSSVD()]:
clf.n_components = 4
assert_raise_message(ValueError, "Invalid number of components",
clf.fit, X, Y)
def test_scale():
d = load_linnerud()
X = d.data
Y = d.target
# causes X[:, -1].std() to be zero
X[:, -1] = 1.0
for clf in [pls_.PLSCanonical(), pls_.PLSRegression(), pls_.PLSSVD()]:
clf.set_params(scale=True)
clf.fit(X, Y)
def test_scale_and_stability():
# We test scale=True parameter
# This allows to check numerical stability over platforms as well
d = load_linnerud()
X1 = d.data
Y1 = d.target
# causes X[:, -1].std() to be zero
X1[:, -1] = 1.0
# From bug #2821
# Test with X2, T2 s.t. clf.x_score[:, 1] == 0, clf.y_score[:, 1] == 0
# This test robustness of algorithm when dealing with value close to 0
X2 = np.array([[0., 0., 1.],
[1., 0., 0.],
[2., 2., 2.],
[3., 5., 4.]])
Y2 = np.array([[0.1, -0.2],
[0.9, 1.1],
[6.2, 5.9],
[11.9, 12.3]])
for (X, Y) in [(X1, Y1), (X2, Y2)]:
X_std = X.std(axis=0, ddof=1)
X_std[X_std == 0] = 1
Y_std = Y.std(axis=0, ddof=1)
Y_std[Y_std == 0] = 1
X_s = (X - X.mean(axis=0)) / X_std
Y_s = (Y - Y.mean(axis=0)) / Y_std
for clf in [CCA(), pls_.PLSCanonical(), pls_.PLSRegression(),
pls_.PLSSVD()]:
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X, Y)
clf.set_params(scale=False)
X_s_score, Y_s_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
# Scaling should be idempotent
clf.set_params(scale=True)
X_score, Y_score = clf.fit_transform(X_s, Y_s)
assert_array_almost_equal(X_s_score, X_score)
assert_array_almost_equal(Y_s_score, Y_score)
