def test_prefit():
# Test all possible combinations of the prefit parameter.
# Passing a prefit parameter with the selected model
# and fitting a unfit model with prefit=False should give same results.
clf = SGDClassifier(alpha=0.1,
max_iter=10,
shuffle=True,
random_state=0,
tol=None)
model = SelectFromModel(clf)
model.fit(data, y)
X_transform = model.transform(data)
clf.fit(data, y)
model = SelectFromModel(clf, prefit=True)
assert_array_almost_equal(model.transform(data), X_transform)
# Check that the model is rewritten if prefit=False and a fitted model is
# passed
model = SelectFromModel(clf, prefit=False)
model.fit(data, y)
assert_array_almost_equal(model.transform(data), X_transform)
# Check that prefit=True and calling fit raises a ValueError
model = SelectFromModel(clf, prefit=True)
with pytest.raises(ValueError):
model.fit(data, y)
def test_multinomial_loss():
# test if the multinomial loss and gradient computations are consistent
X, y = iris.data, iris.target.astype(np.float64)
n_samples, n_features = X.shape
n_classes = len(np.unique(y))
rng = check_random_state(42)
weights = rng.randn(n_features, n_classes)
intercept = rng.randn(n_classes)
sample_weights = rng.randn(n_samples)
np.abs(sample_weights, sample_weights)
# compute loss and gradient like in multinomial SAG
dataset, _ = make_dataset(X, y, sample_weights, random_state=42)
loss_1, grad_1 = _multinomial_grad_loss_all_samples(
dataset, weights, intercept, n_samples, n_features, n_classes)
# compute loss and gradient like in multinomial LogisticRegression
lbin = LabelBinarizer()
Y_bin = lbin.fit_transform(y)
weights_intercept = np.vstack((weights, intercept)).T.ravel()
loss_2, grad_2, _ = _multinomial_loss_grad(weights_intercept, X, Y_bin,
0.0, sample_weights)
grad_2 = grad_2.reshape(n_classes, -1)
grad_2 = grad_2[:, :-1].T
# comparison
assert_array_almost_equal(grad_1, grad_2)
assert_almost_equal(loss_1, loss_2)
def test_compute_class_weight_invariance():
# Test that results with class_weight="balanced" is invariant wrt
# class imbalance if the number of samples is identical.
# The test uses a balanced two class dataset with 100 datapoints.
# It creates three versions, one where class 1 is duplicated
# resulting in 150 points of class 1 and 50 of class 0,
# one where there are 50 points in class 1 and 150 in class 0,
# and one where there are 100 points of each class (this one is balanced
# again).
# With balancing class weights, all three should give the same model.
X, y = make_blobs(centers=2, random_state=0)
# create dataset where class 1 is duplicated twice
X_1 = np.vstack([X] + [X[y == 1]] * 2)
y_1 = np.hstack([y] + [y[y == 1]] * 2)
# create dataset where class 0 is duplicated twice
X_0 = np.vstack([X] + [X[y == 0]] * 2)
y_0 = np.hstack([y] + [y[y == 0]] * 2)
# duplicate everything
X_ = np.vstack([X] * 2)
y_ = np.hstack([y] * 2)
# results should be identical
logreg1 = LogisticRegression(class_weight="balanced").fit(X_1, y_1)
logreg0 = LogisticRegression(class_weight="balanced").fit(X_0, y_0)
logreg = LogisticRegression(class_weight="balanced").fit(X_, y_)
assert_array_almost_equal(logreg1.coef_, logreg0.coef_)
assert_array_almost_equal(logreg.coef_, logreg0.coef_)
def test_leave_zero_eig():
"""This test checks that fit().transform() returns the same result as
fit_transform() in case of non-removed zero eigenvalue.
Non-regression test for issue #12141 (PR #12143)"""
X_fit = np.array([[1, 1], [0, 0]])
# Assert that even with all np warnings on, there is no div by zero warning
with pytest.warns(None) as record:
with np.errstate(all='warn'):
k = KernelPCA(n_components=2,
remove_zero_eig=False,
eigen_solver="dense")
# Fit, then transform
A = k.fit(X_fit).transform(X_fit)
# Do both at once
B = k.fit_transform(X_fit)
# Compare
assert_array_almost_equal(np.abs(A), np.abs(B))
for w in record:
# There might be warnings about the kernel being badly conditioned,
# but there should not be warnings about division by zero.
# (Numpy division by zero warning can have many message variants, but
# at least we know that it is a RuntimeWarning so lets check only this)
assert not issubclass(w.category, RuntimeWarning)
def test_nystroem_approximation():
# some basic tests
rnd = np.random.RandomState(0)
X = rnd.uniform(size=(10, 4))
# With n_components = n_samples this is exact
X_transformed = Nystroem(n_components=X.shape[0]).fit_transform(X)
K = rbf_kernel(X)
assert_array_almost_equal(np.dot(X_transformed, X_transformed.T), K)
trans = Nystroem(n_components=2, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
# test callable kernel
def linear_kernel(X, Y):
return np.dot(X, Y.T)
trans = Nystroem(n_components=2, kernel=linear_kernel, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
# test that available kernels fit and transform
kernels_available = kernel_metrics()
for kern in kernels_available:
trans = Nystroem(n_components=2, kernel=kern, random_state=rnd)
X_transformed = trans.fit(X).transform(X)
assert X_transformed.shape == (X.shape[0], 2)
def test_isotonic_regression_ties_secondary_():
"""
Test isotonic regression fit, transform and fit_transform
against the "secondary" ties method and "pituitary" data from R
"isotone" package, as detailed in: J. d. Leeuw, K. Hornik, P. Mair,
Isotone Optimization in R: Pool-Adjacent-Violators Algorithm
(PAVA) and Active Set Methods
Set values based on pituitary example and
the following R command detailed in the paper above:
> library("isotone")
> data("pituitary")
> res1 <- gpava(pituitary$age, pituitary$size, ties="secondary")
> res1$x
`isotone` version: 1.0-2, 2014-09-07
R version: R version 3.1.1 (2014-07-10)
"""
x = [8, 8, 8, 10, 10, 10, 12, 12, 12, 14, 14]
y = [21, 23.5, 23, 24, 21, 25, 21.5, 22, 19, 23.5, 25]
y_true = [
22.22222, 22.22222, 22.22222, 22.22222, 22.22222, 22.22222, 22.22222,
22.22222, 22.22222, 24.25, 24.25
]
# Check fit, transform and fit_transform
ir = IsotonicRegression()
ir.fit(x, y)
assert_array_almost_equal(ir.transform(x), y_true, 4)
assert_array_almost_equal(ir.fit_transform(x, y), y_true, 4)
def test_feature_agglomeration():
n_clusters = 1
X = np.array([0, 0, 1]).reshape(1, 3) # (n_samples, n_features)
agglo_mean = FeatureAgglomeration(n_clusters=n_clusters,
pooling_func=np.mean)
agglo_median = FeatureAgglomeration(n_clusters=n_clusters,
pooling_func=np.median)
assert_no_warnings(agglo_mean.fit, X)
assert_no_warnings(agglo_median.fit, X)
assert np.size(np.unique(agglo_mean.labels_)) == n_clusters
assert np.size(np.unique(agglo_median.labels_)) == n_clusters
assert np.size(agglo_mean.labels_) == X.shape[1]
assert np.size(agglo_median.labels_) == X.shape[1]
# Test transform
Xt_mean = agglo_mean.transform(X)
Xt_median = agglo_median.transform(X)
assert Xt_mean.shape[1] == n_clusters
assert Xt_median.shape[1] == n_clusters
assert Xt_mean == np.array([1 / 3.])
assert Xt_median == np.array([0.])
# Test inverse transform
X_full_mean = agglo_mean.inverse_transform(Xt_mean)
X_full_median = agglo_median.inverse_transform(Xt_median)
assert np.unique(X_full_mean[0]).size == n_clusters
assert np.unique(X_full_median[0]).size == n_clusters
assert_array_almost_equal(agglo_mean.transform(X_full_mean), Xt_mean)
assert_array_almost_equal(agglo_median.transform(X_full_median), Xt_median)
def test_make_s_curve():
X, t = make_s_curve(n_samples=5, noise=0.0, random_state=0)
assert X.shape == (5, 3), "X shape mismatch"
assert t.shape == (5, ), "t shape mismatch"
assert_array_almost_equal(X[:, 0], np.sin(t))
assert_array_almost_equal(X[:, 2], np.sign(t) * (np.cos(t) - 1))
def test_make_checkerboard():
X, rows, cols = make_checkerboard(shape=(100, 100),
n_clusters=(20, 5),
shuffle=True,
random_state=0)
assert X.shape == (100, 100), "X shape mismatch"
assert rows.shape == (100, 100), "rows shape mismatch"
assert cols.shape == (
100,
100,
), "columns shape mismatch"
X, rows, cols = make_checkerboard(shape=(100, 100),
n_clusters=2,
shuffle=True,
random_state=0)
assert_all_finite(X)
assert_all_finite(rows)
assert_all_finite(cols)
X1, _, _ = make_checkerboard(shape=(100, 100),
n_clusters=2,
shuffle=True,
random_state=0)
X2, _, _ = make_checkerboard(shape=(100, 100),
n_clusters=2,
shuffle=True,
random_state=0)
assert_array_almost_equal(X1, X2)
def test_make_multilabel_classification_return_indicator():
for allow_unlabeled, min_length in zip((True, False), (0, 1)):
X, Y = make_multilabel_classification(n_samples=25,
n_features=20,
n_classes=3,
random_state=0,
allow_unlabeled=allow_unlabeled)
assert X.shape == (25, 20), "X shape mismatch"
assert Y.shape == (25, 3), "Y shape mismatch"
assert np.all(np.sum(Y, axis=0) > min_length)
# Also test return_distributions and return_indicator with True
X2, Y2, p_c, p_w_c = make_multilabel_classification(
n_samples=25,
n_features=20,
n_classes=3,
random_state=0,
allow_unlabeled=allow_unlabeled,
return_distributions=True)
assert_array_almost_equal(X, X2)
assert_array_equal(Y, Y2)
assert p_c.shape == (3, )
assert_almost_equal(p_c.sum(), 1)
assert p_w_c.shape == (20, 3)
assert_almost_equal(p_w_c.sum(axis=0), [1] * 3)
def test_make_swiss_roll():
X, t = make_swiss_roll(n_samples=5, noise=0.0, random_state=0)
assert X.shape == (5, 3), "X shape mismatch"
assert t.shape == (5, ), "t shape mismatch"
assert_array_almost_equal(X[:, 0], t * np.cos(t))
assert_array_almost_equal(X[:, 2], t * np.sin(t))
def test_enet_l1_ratio():
# Test that an error message is raised if an estimator that
# uses _alpha_grid is called with l1_ratio=0
msg = ("Automatic alpha grid generation is not supported for l1_ratio=0. "
"Please supply a grid by providing your estimator with the "
"appropriate `alphas=` argument.")
X = np.array([[1, 2, 4, 5, 8], [3, 5, 7, 7, 8]]).T
y = np.array([12, 10, 11, 21, 5])
assert_raise_message(ValueError, msg,
ElasticNetCV(l1_ratio=0, random_state=42).fit, X, y)
assert_raise_message(
ValueError, msg,
MultiTaskElasticNetCV(l1_ratio=0, random_state=42).fit, X, y[:, None])
# Test that l1_ratio=0 is allowed if we supply a grid manually
alphas = [0.1, 10]
estkwds = {'alphas': alphas, 'random_state': 42}
est_desired = ElasticNetCV(l1_ratio=0.00001, **estkwds)
est = ElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est_desired.fit(X, y)
est.fit(X, y)
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)
est_desired = MultiTaskElasticNetCV(l1_ratio=0.00001, **estkwds)
est = MultiTaskElasticNetCV(l1_ratio=0, **estkwds)
with ignore_warnings():
est.fit(X, y[:, None])
est_desired.fit(X, y[:, None])
assert_array_almost_equal(est.coef_, est_desired.coef_, decimal=5)
def launch_mcd_on_dataset(n_samples, n_features, n_outliers, tol_loc, tol_cov,
tol_support):
rand_gen = np.random.RandomState(0)
data = rand_gen.randn(n_samples, n_features)
# add some outliers
outliers_index = rand_gen.permutation(n_samples)[:n_outliers]
outliers_offset = 10. * \
(rand_gen.randint(2, size=(n_outliers, n_features)) - 0.5)
data[outliers_index] += outliers_offset
inliers_mask = np.ones(n_samples).astype(bool)
inliers_mask[outliers_index] = False
pure_data = data[inliers_mask]
# compute MCD by fitting an object
mcd_fit = MinCovDet(random_state=rand_gen).fit(data)
T = mcd_fit.location_
S = mcd_fit.covariance_
H = mcd_fit.support_
# compare with the estimates learnt from the inliers
error_location = np.mean((pure_data.mean(0) - T) ** 2)
assert(error_location < tol_loc)
error_cov = np.mean((empirical_covariance(pure_data) - S) ** 2)
assert(error_cov < tol_cov)
assert(np.sum(H) >= tol_support)
assert_array_almost_equal(mcd_fit.mahalanobis(data), mcd_fit.dist_)
def test_inverse_transform():
# Test FastICA.inverse_transform
n_features = 10
n_samples = 100
n1, n2 = 5, 10
rng = np.random.RandomState(0)
X = rng.random_sample((n_samples, n_features))
expected = {
(True, n1): (n_features, n1),
(True, n2): (n_features, n2),
(False, n1): (n_features, n2),
(False, n2): (n_features, n2)
}
for whiten in [True, False]:
for n_components in [n1, n2]:
n_components_ = (n_components
if n_components is not None else X.shape[1])
ica = FastICA(n_components=n_components,
random_state=rng,
whiten=whiten)
with warnings.catch_warnings(record=True):
# catch "n_components ignored" warning
Xt = ica.fit_transform(X)
expected_shape = expected[(whiten, n_components_)]
assert ica.mixing_.shape == expected_shape
X2 = ica.inverse_transform(Xt)
assert X.shape == X2.shape
# reversibility test in non-reduction case
if n_components == X.shape[1]:
assert_array_almost_equal(X, X2)
def test_suffstat_sk_tied():
# use equation Nk * Sk / N = S_tied
rng = np.random.RandomState(0)
n_samples, n_features, n_components = 500, 2, 2
resp = rng.rand(n_samples, n_components)
resp = resp / resp.sum(axis=1)[:, np.newaxis]
X = rng.rand(n_samples, n_features)
nk = resp.sum(axis=0)
xk = np.dot(resp.T, X) / nk[:, np.newaxis]
covars_pred_full = _estimate_gaussian_covariances_full(resp, X, nk, xk, 0)
covars_pred_full = np.sum(nk[:, np.newaxis, np.newaxis] * covars_pred_full,
0) / n_samples
covars_pred_tied = _estimate_gaussian_covariances_tied(resp, X, nk, xk, 0)
ecov = EmpiricalCovariance()
ecov.covariance_ = covars_pred_full
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='frobenius'), 0)
assert_almost_equal(ecov.error_norm(covars_pred_tied, norm='spectral'), 0)
# check the precision computation
precs_chol_pred = _compute_precision_cholesky(covars_pred_tied, 'tied')
precs_pred = np.dot(precs_chol_pred, precs_chol_pred.T)
precs_est = linalg.inv(covars_pred_tied)
assert_array_almost_equal(precs_est, precs_pred)
def test_binary_perplexity_stability():
# Binary perplexity search should be stable.
# The binary_search_perplexity had a bug wherein the P array
# was uninitialized, leading to sporadically failing tests.
n_neighbors = 10
n_samples = 100
random_state = check_random_state(0)
data = random_state.randn(n_samples, 5)
nn = NearestNeighbors().fit(data)
distance_graph = nn.kneighbors_graph(n_neighbors=n_neighbors,
mode='distance')
distances = distance_graph.data.astype(np.float32, copy=False)
distances = distances.reshape(n_samples, n_neighbors)
last_P = None
desired_perplexity = 3
for _ in range(100):
P = _binary_search_perplexity(distances.copy(),
desired_perplexity,
verbose=0)
P1 = _joint_probabilities_nn(distance_graph,
desired_perplexity,
verbose=0)
# Convert the sparse matrix to a dense one for testing
P1 = P1.toarray()
if last_P is None:
last_P = P
last_P1 = P1
else:
assert_array_almost_equal(P, last_P, decimal=4)
assert_array_almost_equal(P1, last_P1, decimal=4)
def test_gaussian_mixture_estimate_log_prob_resp():
# test whether responsibilities are normalized
rng = np.random.RandomState(0)
rand_data = RandomData(rng, scale=5)
n_samples = rand_data.n_samples
n_features = rand_data.n_features
n_components = rand_data.n_components
X = rng.rand(n_samples, n_features)
for covar_type in COVARIANCE_TYPE:
weights = rand_data.weights
means = rand_data.means
precisions = rand_data.precisions[covar_type]
g = GaussianMixture(n_components=n_components,
random_state=rng,
weights_init=weights,
means_init=means,
precisions_init=precisions,
covariance_type=covar_type)
g.fit(X)
resp = g.predict_proba(X)
assert_array_almost_equal(resp.sum(axis=1), np.ones(n_samples))
assert_array_equal(g.weights_init, weights)
assert_array_equal(g.means_init, means)
assert_array_equal(g.precisions_init, precisions)
def _run_answer_test(pos_input,
pos_output,
neighbors,
grad_output,
verbose=False,
perplexity=0.1,
skip_num_points=0):
distances = pairwise_distances(pos_input).astype(np.float32)
args = distances, perplexity, verbose
pos_output = pos_output.astype(np.float32)
neighbors = neighbors.astype(np.int64, copy=False)
pij_input = _joint_probabilities(*args)
pij_input = squareform(pij_input).astype(np.float32)
grad_bh = np.zeros(pos_output.shape, dtype=np.float32)
from scipy.sparse import csr_matrix
P = csr_matrix(pij_input)
neighbors = P.indices.astype(np.int64)
indptr = P.indptr.astype(np.int64)
_barnes_hut_tsne.gradient(P.data,
pos_output,
neighbors,
indptr,
grad_bh,
0.5,
2,
1,
skip_num_points=0)
assert_array_almost_equal(grad_bh, grad_output, decimal=4)
def test_classification_sample_weight():
X = [[0], [0], [1]]
y = [0, 1, 0]
sample_weight = [0.1, 1., 0.1]
clf = DummyClassifier(strategy="stratified").fit(X, y, sample_weight)
assert_array_almost_equal(clf.class_prior_, [0.2 / 1.2, 1. / 1.2])
def test_barnes_hut_angle():
# When Barnes-Hut's angle=0 this corresponds to the exact method.
angle = 0.0
perplexity = 10
n_samples = 100
for n_components in [2, 3]:
n_features = 5
degrees_of_freedom = float(n_components - 1.0)
random_state = check_random_state(0)
data = random_state.randn(n_samples, n_features)
distances = pairwise_distances(data)
params = random_state.randn(n_samples, n_components)
P = _joint_probabilities(distances, perplexity, verbose=0)
kl_exact, grad_exact = _kl_divergence(params, P, degrees_of_freedom,
n_samples, n_components)
n_neighbors = n_samples - 1
distances_csr = NearestNeighbors().fit(data).kneighbors_graph(
n_neighbors=n_neighbors, mode='distance')
P_bh = _joint_probabilities_nn(distances_csr, perplexity, verbose=0)
kl_bh, grad_bh = _kl_divergence_bh(params,
P_bh,
degrees_of_freedom,
n_samples,
n_components,
angle=angle,
skip_num_points=0,
verbose=0)
P = squareform(P)
P_bh = P_bh.toarray()
assert_array_almost_equal(P_bh, P, decimal=5)
assert_almost_equal(kl_exact, kl_bh, decimal=3)
def test_transform():
"""Check transform method of VotingClassifier on toy dataset."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
X = np.array([[-1.1, -1.5], [-1.2, -1.4], [-3.4, -2.2], [1.1, 1.2]])
y = np.array([1, 1, 2, 2])
eclf1 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('gnb', clf3)],
voting='soft').fit(X, y)
eclf2 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('gnb', clf3)],
voting='soft',
flatten_transform=True).fit(X, y)
eclf3 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('gnb', clf3)],
voting='soft',
flatten_transform=False).fit(X, y)
assert_array_equal(eclf1.transform(X).shape, (4, 6))
assert_array_equal(eclf2.transform(X).shape, (4, 6))
assert_array_equal(eclf3.transform(X).shape, (3, 4, 2))
assert_array_almost_equal(eclf1.transform(X), eclf2.transform(X))
assert_array_almost_equal(
eclf3.transform(X).swapaxes(0, 1).reshape((4, 6)), eclf2.transform(X))
def test_oneclass_adaboost_proba():
# Test predict_proba robustness for one class label input.
# In response to issue #7501
# https://github.com/scikit-learn/scikit-learn/issues/7501
y_t = np.ones(len(X))
clf = AdaBoostClassifier().fit(X, y_t)
assert_array_almost_equal(clf.predict_proba(X), np.ones((len(X), 1)))
def test_kernel_pca_precomputed():
rng = np.random.RandomState(0)
X_fit = rng.random_sample((5, 4))
X_pred = rng.random_sample((2, 4))
for eigen_solver in ("dense", "arpack"):
X_kpca = KernelPCA(4, eigen_solver=eigen_solver).\
fit(X_fit).transform(X_pred)
X_kpca2 = KernelPCA(4, eigen_solver=eigen_solver,
kernel='precomputed').fit(np.dot(
X_fit,
X_fit.T)).transform(np.dot(X_pred, X_fit.T))
X_kpca_train = KernelPCA(4,
eigen_solver=eigen_solver,
kernel='precomputed').fit_transform(
np.dot(X_fit, X_fit.T))
X_kpca_train2 = KernelPCA(4,
eigen_solver=eigen_solver,
kernel='precomputed').fit(
np.dot(X_fit, X_fit.T)).transform(
np.dot(X_fit, X_fit.T))
assert_array_almost_equal(np.abs(X_kpca), np.abs(X_kpca2))
assert_array_almost_equal(np.abs(X_kpca_train), np.abs(X_kpca_train2))
def test_collinearity():
# Check that lars_path is robust to collinearity in input
X = np.array([[3., 3., 1.], [2., 2., 0.], [1., 1., 0]])
y = np.array([1., 0., 0])
rng = np.random.RandomState(0)
f = ignore_warnings
_, _, coef_path_ = f(linear_model.lars_path)(X, y, alpha_min=0.01)
assert not np.isnan(coef_path_).any()
residual = np.dot(X, coef_path_[:, -1]) - y
assert (residual**2).sum() < 1. # just make sure it's bounded
n_samples = 10
X = rng.rand(n_samples, 5)
y = np.zeros(n_samples)
_, _, coef_path_ = linear_model.lars_path(X,
y,
Gram='auto',
copy_X=False,
copy_Gram=False,
alpha_min=0.,
method='lasso',
verbose=0,
max_iter=500)
assert_array_almost_equal(coef_path_, np.zeros_like(coef_path_))
def test_feature_union_weights():
# test feature union with transformer weights
X = iris.data
y = iris.target
pca = PCA(n_components=2, svd_solver='randomized', random_state=0)
select = SelectKBest(k=1)
# test using fit followed by transform
fs = FeatureUnion([("pca", pca), ("select", select)],
transformer_weights={"pca": 10})
fs.fit(X, y)
X_transformed = fs.transform(X)
# test using fit_transform
fs = FeatureUnion([("pca", pca), ("select", select)],
transformer_weights={"pca": 10})
X_fit_transformed = fs.fit_transform(X, y)
# test it works with transformers missing fit_transform
fs = FeatureUnion([("mock", Transf()), ("pca", pca), ("select", select)],
transformer_weights={"mock": 10})
X_fit_transformed_wo_method = fs.fit_transform(X, y)
# check against expected result
# We use a different pca object to control the random_state stream
assert_array_almost_equal(X_transformed[:, :-1], 10 * pca.fit_transform(X))
assert_array_equal(X_transformed[:, -1],
select.fit_transform(X, y).ravel())
assert_array_almost_equal(X_fit_transformed[:, :-1],
10 * pca.fit_transform(X))
assert_array_equal(X_fit_transformed[:, -1],
select.fit_transform(X, y).ravel())
assert X_fit_transformed_wo_method.shape == (X.shape[0], 7)
def test_lasso_lars_vs_lasso_cd_ill_conditioned():
# Test lasso lars on a very ill-conditioned design, and check that
# it does not blow up, and stays somewhat close to a solution given
# by the coordinate descent solver
# Also test that lasso_path (using lars_path output style) gives
# the same result as lars_path and previous lasso output style
# under these conditions.
rng = np.random.RandomState(42)
# Generate data
n, m = 70, 100
k = 5
X = rng.randn(n, m)
w = np.zeros((m, 1))
i = np.arange(0, m)
rng.shuffle(i)
supp = i[:k]
w[supp] = np.sign(rng.randn(k, 1)) * (rng.rand(k, 1) + 1)
y = np.dot(X, w)
sigma = 0.2
y += sigma * rng.rand(*y.shape)
y = y.squeeze()
lars_alphas, _, lars_coef = linear_model.lars_path(X, y, method='lasso')
_, lasso_coef2, _ = linear_model.lasso_path(X,
y,
alphas=lars_alphas,
tol=1e-6,
fit_intercept=False)
assert_array_almost_equal(lars_coef, lasso_coef2, decimal=1)
def test_multinomial_loss_ground_truth():
# n_samples, n_features, n_classes = 4, 2, 3
n_classes = 3
X = np.array([[1.1, 2.2], [2.2, -4.4], [3.3, -2.2], [1.1, 1.1]])
y = np.array([0, 1, 2, 0])
lbin = LabelBinarizer()
Y_bin = lbin.fit_transform(y)
weights = np.array([[0.1, 0.2, 0.3], [1.1, 1.2, -1.3]])
intercept = np.array([1., 0, -.2])
sample_weights = np.array([0.8, 1, 1, 0.8])
prediction = np.dot(X, weights) + intercept
logsumexp_prediction = logsumexp(prediction, axis=1)
p = prediction - logsumexp_prediction[:, np.newaxis]
loss_1 = -(sample_weights[:, np.newaxis] * p * Y_bin).sum()
diff = sample_weights[:, np.newaxis] * (np.exp(p) - Y_bin)
grad_1 = np.dot(X.T, diff)
weights_intercept = np.vstack((weights, intercept)).T.ravel()
loss_2, grad_2, _ = _multinomial_loss_grad(weights_intercept, X, Y_bin,
0.0, sample_weights)
grad_2 = grad_2.reshape(n_classes, -1)
grad_2 = grad_2[:, :-1].T
assert_almost_equal(loss_1, loss_2)
assert_array_almost_equal(grad_1, grad_2)
# ground truth
loss_gt = 11.680360354325961
grad_gt = np.array([[-0.557487, -1.619151, +2.176638],
[-0.903942, +5.258745, -4.354803]])
assert_almost_equal(loss_1, loss_gt)
assert_array_almost_equal(grad_1, grad_gt)
def test_multitarget():
# Assure that estimators receiving multidimensional y do the right thing
Y = np.vstack([y, y**2]).T
n_targets = Y.shape[1]
estimators = [
linear_model.LassoLars(),
linear_model.Lars(),
# regression test for gh-1615
linear_model.LassoLars(fit_intercept=False),
linear_model.Lars(fit_intercept=False),
]
for estimator in estimators:
estimator.fit(X, Y)
Y_pred = estimator.predict(X)
alphas, active, coef, path = (estimator.alphas_, estimator.active_,
estimator.coef_, estimator.coef_path_)
for k in range(n_targets):
estimator.fit(X, Y[:, k])
y_pred = estimator.predict(X)
assert_array_almost_equal(alphas[k], estimator.alphas_)
assert_array_almost_equal(active[k], estimator.active_)
assert_array_almost_equal(coef[k], estimator.coef_)
assert_array_almost_equal(path[k], estimator.coef_path_)
assert_array_almost_equal(Y_pred[:, k], y_pred)
def test_lof_precomputed(random_state=42):
"""Tests LOF with a distance matrix."""
# Note: smaller samples may result in spurious test success
rng = np.random.RandomState(random_state)
X = rng.random_sample((10, 4))
Y = rng.random_sample((3, 4))
DXX = metrics.pairwise_distances(X, metric='euclidean')
DYX = metrics.pairwise_distances(Y, X, metric='euclidean')
# As a feature matrix (n_samples by n_features)
lof_X = neighbors.LocalOutlierFactor(n_neighbors=3, novelty=True)
lof_X.fit(X)
pred_X_X = lof_X._predict()
pred_X_Y = lof_X.predict(Y)
# As a dense distance matrix (n_samples by n_samples)
lof_D = neighbors.LocalOutlierFactor(n_neighbors=3,
algorithm='brute',
metric='precomputed',
novelty=True)
lof_D.fit(DXX)
pred_D_X = lof_D._predict()
pred_D_Y = lof_D.predict(DYX)
assert_array_almost_equal(pred_X_X, pred_D_X)
assert_array_almost_equal(pred_X_Y, pred_D_Y)
def test_2d_coef():
X, y = datasets.make_classification(n_samples=1000,
n_features=10,
n_informative=3,
n_redundant=0,
n_repeated=0,
shuffle=False,
random_state=0,
n_classes=4)
est = LogisticRegression()
for threshold, func in zip(["mean", "median"], [np.mean, np.median]):
for order in [1, 2, np.inf]:
# Fit SelectFromModel a multi-class problem
transformer = SelectFromModel(estimator=LogisticRegression(),
threshold=threshold,
norm_order=order)
transformer.fit(X, y)
assert hasattr(transformer.estimator_, 'coef_')
X_new = transformer.transform(X)
assert X_new.shape[1] < X.shape[1]
# Manually check that the norm is correctly performed
est.fit(X, y)
importances = np.linalg.norm(est.coef_, axis=0, ord=order)
feature_mask = importances > func(importances)
assert_array_almost_equal(X_new, X[:, feature_mask])