def test_cross_val_predict_input_types():
clf = Ridge()
# Smoke test
predictions = cval.cross_val_predict(clf, X, y)
assert_equal(predictions.shape, (10,))
# test with multioutput y
with ignore_warnings(category=ConvergenceWarning):
predictions = cval.cross_val_predict(clf, X_sparse, X)
assert_equal(predictions.shape, (10, 2))
predictions = cval.cross_val_predict(clf, X_sparse, y)
assert_array_equal(predictions.shape, (10,))
# test with multioutput y
with ignore_warnings(category=ConvergenceWarning):
predictions = cval.cross_val_predict(clf, X_sparse, X)
assert_array_equal(predictions.shape, (10, 2))
# test with X and y as list
list_check = lambda x: isinstance(x, list)
clf = CheckingClassifier(check_X=list_check)
predictions = cval.cross_val_predict(clf, X.tolist(), y.tolist())
clf = CheckingClassifier(check_y=list_check)
predictions = cval.cross_val_predict(clf, X, y.tolist())
# test with 3d X and
X_3d = X[:, :, np.newaxis]
check_3d = lambda x: x.ndim == 3
clf = CheckingClassifier(check_X=check_3d)
predictions = cval.cross_val_predict(clf, X_3d, y)
assert_array_equal(predictions.shape, (10,))
def test_fit():
# Checks whether `fit` method sets all attribute values correctly.
n_samples = 12
n_features = 2
n_estimators = 5
rng = np.random.RandomState(42)
X = rng.rand(n_samples, n_features)
lshf = ignore_warnings(LSHForest, category=DeprecationWarning)(
n_estimators=n_estimators)
ignore_warnings(lshf.fit)(X)
# _input_array = X
assert_array_equal(X, lshf._fit_X)
# A hash function g(p) for each tree
assert_equal(n_estimators, len(lshf.hash_functions_))
# Hash length = 32
assert_equal(32, lshf.hash_functions_[0].components_.shape[0])
# Number of trees_ in the forest
assert_equal(n_estimators, len(lshf.trees_))
# Each tree has entries for every data point
assert_equal(n_samples, len(lshf.trees_[0]))
# Original indices after sorting the hashes
assert_equal(n_estimators, len(lshf.original_indices_))
# Each set of original indices in a tree has entries for every data point
assert_equal(n_samples, len(lshf.original_indices_[0]))
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 check_warm_start_oob(name):
# Test that the warm start computes oob score when asked.
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
# Use 15 estimators to avoid 'some inputs do not have OOB scores' warning.
clf = ForestEstimator(n_estimators=15, max_depth=3, warm_start=False,
random_state=1, bootstrap=True, oob_score=True)
clf.fit(X, y)
clf_2 = ForestEstimator(n_estimators=5, max_depth=3, warm_start=False,
random_state=1, bootstrap=True, oob_score=False)
clf_2.fit(X, y)
clf_2.set_params(warm_start=True, oob_score=True, n_estimators=15)
clf_2.fit(X, y)
assert_true(hasattr(clf_2, 'oob_score_'))
assert_equal(clf.oob_score_, clf_2.oob_score_)
# Test that oob_score is computed even if we don't need to train
# additional trees.
clf_3 = ForestEstimator(n_estimators=15, max_depth=3, warm_start=True,
random_state=1, bootstrap=True, oob_score=False)
clf_3.fit(X, y)
assert_true(not(hasattr(clf_3, 'oob_score_')))
clf_3.set_params(oob_score=True)
ignore_warnings(clf_3.fit)(X, y)
assert_equal(clf.oob_score_, clf_3.oob_score_)
def test_no_atoms():
y_empty = np.zeros_like(y)
Xy_empty = np.dot(X.T, y_empty)
gamma_empty = ignore_warnings(orthogonal_mp)(X, y_empty, 1)
gamma_empty_gram = ignore_warnings(orthogonal_mp)(G, Xy_empty, 1)
assert_equal(np.all(gamma_empty == 0), True)
assert_equal(np.all(gamma_empty_gram == 0), True)
def test_neighbors_accuracy_with_n_estimators():
# Checks whether accuracy increases as `n_estimators` increases.
n_estimators = np.array([1, 10, 100])
n_samples = 100
n_features = 10
n_iter = 10
n_points = 5
rng = np.random.RandomState(42)
accuracies = np.zeros(n_estimators.shape[0], dtype=float)
X = rng.rand(n_samples, n_features)
for i, t in enumerate(n_estimators):
lshf = ignore_warnings(LSHForest, category=DeprecationWarning)(
n_candidates=500, n_estimators=t)
ignore_warnings(lshf.fit)(X)
for j in range(n_iter):
query = X[rng.randint(0, n_samples)].reshape(1, -1)
neighbors = lshf.kneighbors(query, n_neighbors=n_points,
return_distance=False)
distances = pairwise_distances(query, X, metric='cosine')
ranks = np.argsort(distances)[0, :n_points]
intersection = np.intersect1d(ranks, neighbors).shape[0]
ratio = intersection / float(n_points)
accuracies[i] = accuracies[i] + ratio
accuracies[i] = accuracies[i] / float(n_iter)
# Sorted accuracies should be equal to original accuracies
assert_true(np.all(np.diff(accuracies) >= 0),
msg="Accuracies are not non-decreasing.")
# Highest accuracy should be strictly greater than the lowest
assert_true(np.ptp(accuracies) > 0,
msg="Highest accuracy is not strictly greater than lowest.")
def test_check_estimator_clones():
# check that check_estimator doesn't modify the estimator it receives
from sklearn.datasets import load_iris
iris = load_iris()
for Estimator in [GaussianMixture, LinearRegression,
RandomForestClassifier, NMF, SGDClassifier,
MiniBatchKMeans]:
with ignore_warnings(category=FutureWarning):
# when 'est = SGDClassifier()'
est = Estimator()
set_checking_parameters(est)
set_random_state(est)
# without fitting
old_hash = joblib.hash(est)
check_estimator(est)
assert_equal(old_hash, joblib.hash(est))
with ignore_warnings(category=FutureWarning):
# when 'est = SGDClassifier()'
est = Estimator()
set_checking_parameters(est)
set_random_state(est)
# with fitting
est.fit(iris.data + 10, iris.target)
old_hash = joblib.hash(est)
check_estimator(est)
assert_equal(old_hash, joblib.hash(est))
def test_hash_functions():
# Checks randomness of hash functions.
# Variance and mean of each hash function (projection vector)
# should be different from flattened array of hash functions.
# If hash functions are not randomly built (seeded with
# same value), variances and means of all functions are equal.
n_samples = 12
n_features = 2
n_estimators = 5
rng = np.random.RandomState(42)
X = rng.rand(n_samples, n_features)
lshf = ignore_warnings(LSHForest, category=DeprecationWarning)(
n_estimators=n_estimators,
random_state=rng.randint(0, np.iinfo(np.int32).max))
ignore_warnings(lshf.fit)(X)
hash_functions = []
for i in range(n_estimators):
hash_functions.append(lshf.hash_functions_[i].components_)
for i in range(n_estimators):
assert_not_equal(np.var(hash_functions),
np.var(lshf.hash_functions_[i].components_))
for i in range(n_estimators):
assert_not_equal(np.mean(hash_functions),
np.mean(lshf.hash_functions_[i].components_))
def test_sparse_input():
# note: Fixed random state in sp.rand is not supported in older scipy.
# The test should succeed regardless.
X1 = sp.rand(50, 100)
X2 = sp.rand(10, 100)
forest_sparse = ignore_warnings(LSHForest, category=DeprecationWarning)(
radius=1, random_state=0).fit(X1)
forest_dense = ignore_warnings(LSHForest, category=DeprecationWarning)(
radius=1, random_state=0).fit(X1.A)
d_sparse, i_sparse = forest_sparse.kneighbors(X2, return_distance=True)
d_dense, i_dense = forest_dense.kneighbors(X2.A, return_distance=True)
assert_almost_equal(d_sparse, d_dense)
assert_almost_equal(i_sparse, i_dense)
d_sparse, i_sparse = forest_sparse.radius_neighbors(X2,
return_distance=True)
d_dense, i_dense = forest_dense.radius_neighbors(X2.A,
return_distance=True)
assert_equal(d_sparse.shape, d_dense.shape)
for a, b in zip(d_sparse, d_dense):
assert_almost_equal(a, b)
for a, b in zip(i_sparse, i_dense):
assert_almost_equal(a, b)
def test_enet_float_precision():
# Generate dataset
X, y, X_test, y_test = build_dataset(n_samples=20, n_features=10)
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
for normalize in [True, False]:
for fit_intercept in [True, False]:
coef = {}
intercept = {}
clf = ElasticNet(alpha=0.5, max_iter=100, precompute=False,
fit_intercept=fit_intercept, normalize=normalize)
for dtype in [np.float64, np.float32]:
X = dtype(X)
y = dtype(y)
ignore_warnings(clf.fit)(X, y)
coef[dtype] = clf.coef_
intercept[dtype] = clf.intercept_
assert_equal(clf.coef_.dtype, dtype)
assert_array_almost_equal(coef[np.float32], coef[np.float64],
decimal=4)
assert_array_almost_equal(intercept[np.float32],
intercept[np.float64],
decimal=4)
def test_enet_path():
# We use a large number of samples and of informative features so that
# the l1_ratio selected is more toward ridge than lasso
X, y, X_test, y_test = build_dataset(n_samples=200, n_features=100,
n_informative_features=100)
max_iter = 150
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
clf = ElasticNetCV(n_alphas=5, eps=2e-3, l1_ratio=[0.5, 0.7], cv=3,
max_iter=max_iter)
ignore_warnings(clf.fit)(X, y)
# Well-conditioned settings, we should have selected our
# smallest penalty
assert_almost_equal(clf.alpha_, min(clf.alphas_))
# Non-sparse ground truth: we should have seleted an elastic-net
# that is closer to ridge than to lasso
assert_equal(clf.l1_ratio_, min(clf.l1_ratio))
clf = ElasticNetCV(n_alphas=5, eps=2e-3, l1_ratio=[0.5, 0.7], cv=3,
max_iter=max_iter, precompute=True)
ignore_warnings(clf.fit)(X, y)
# Well-conditioned settings, we should have selected our
# smallest penalty
assert_almost_equal(clf.alpha_, min(clf.alphas_))
# Non-sparse ground truth: we should have seleted an elastic-net
# that is closer to ridge than to lasso
assert_equal(clf.l1_ratio_, min(clf.l1_ratio))
# We are in well-conditioned settings with low noise: we should
# have a good test-set performance
assert_greater(clf.score(X_test, y_test), 0.99)
def test_enet_toy_list_input():
# Test ElasticNet for various values of alpha and l1_ratio with list X
X = np.array([[-1], [0], [1]])
X = sp.csc_matrix(X)
Y = [-1, 0, 1] # just a straight line
T = np.array([[2], [3], [4]]) # test sample
# this should be the same as unregularized least squares
clf = ElasticNet(alpha=0, l1_ratio=1.0)
# catch warning about alpha=0.
# this is discouraged but should work.
ignore_warnings(clf.fit)(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [1])
assert_array_almost_equal(pred, [2, 3, 4])
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.3, max_iter=1000)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.50819], decimal=3)
assert_array_almost_equal(pred, [1.0163, 1.5245, 2.0327], decimal=3)
assert_almost_equal(clf.dual_gap_, 0)
clf = ElasticNet(alpha=0.5, l1_ratio=0.5)
clf.fit(X, Y)
pred = clf.predict(T)
assert_array_almost_equal(clf.coef_, [0.45454], 3)
assert_array_almost_equal(pred, [0.9090, 1.3636, 1.8181], 3)
assert_almost_equal(clf.dual_gap_, 0)
def test_rfecv():
generator = check_random_state(0)
iris = load_iris()
X = np.c_[iris.data, generator.normal(size=(len(iris.data), 6))]
y = list(iris.target) # regression test: list should be supported
# Test using the score function
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5)
rfecv.fit(X, y)
# non-regression test for missing worst feature:
assert_equal(len(rfecv.grid_scores_), X.shape[1])
assert_equal(len(rfecv.ranking_), X.shape[1])
X_r = rfecv.transform(X)
# All the noisy variable were filtered out
assert_array_equal(X_r, iris.data)
# same in sparse
rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5)
X_sparse = sparse.csr_matrix(X)
rfecv_sparse.fit(X_sparse, y)
X_r_sparse = rfecv_sparse.transform(X_sparse)
assert_array_equal(X_r_sparse.toarray(), iris.data)
# Test using a customized loss function
scoring = make_scorer(zero_one_loss, greater_is_better=False)
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5, scoring=scoring)
ignore_warnings(rfecv.fit)(X, y)
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
# Test using a scorer
scorer = get_scorer("accuracy")
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5, scoring=scorer)
rfecv.fit(X, y)
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
# Test fix on grid_scores
def test_scorer(estimator, X, y):
return 1.0
rfecv = RFECV(estimator=SVC(kernel="linear"), step=1, cv=5, scoring=test_scorer)
rfecv.fit(X, y)
assert_array_equal(rfecv.grid_scores_, np.ones(len(rfecv.grid_scores_)))
# Same as the first two tests, but with step=2
rfecv = RFECV(estimator=SVC(kernel="linear"), step=2, cv=5)
rfecv.fit(X, y)
assert_equal(len(rfecv.grid_scores_), 6)
assert_equal(len(rfecv.ranking_), X.shape[1])
X_r = rfecv.transform(X)
assert_array_equal(X_r, iris.data)
rfecv_sparse = RFECV(estimator=SVC(kernel="linear"), step=2, cv=5)
X_sparse = sparse.csr_matrix(X)
rfecv_sparse.fit(X_sparse, y)
X_r_sparse = rfecv_sparse.transform(X_sparse)
assert_array_equal(X_r_sparse.toarray(), iris.data)
def test_radius_neighbors():
# Checks whether Returned distances are less than `radius`
# At least one point should be returned when the `radius` is set
# to mean distance from the considering point to other points in
# the database.
# Moreover, this test compares the radius neighbors of LSHForest
# with the `sklearn.neighbors.NearestNeighbors`.
n_samples = 12
n_features = 2
n_iter = 10
rng = np.random.RandomState(42)
X = rng.rand(n_samples, n_features)
lshf = ignore_warnings(LSHForest, category=DeprecationWarning)()
# Test unfitted estimator
assert_raises(ValueError, lshf.radius_neighbors, X[0])
ignore_warnings(lshf.fit)(X)
for i in range(n_iter):
# Select a random point in the dataset as the query
query = X[rng.randint(0, n_samples)].reshape(1, -1)
# At least one neighbor should be returned when the radius is the
# mean distance from the query to the points of the dataset.
mean_dist = np.mean(pairwise_distances(query, X, metric='cosine'))
neighbors = lshf.radius_neighbors(query, radius=mean_dist,
return_distance=False)
assert_equal(neighbors.shape, (1,))
assert_equal(neighbors.dtype, object)
assert_greater(neighbors[0].shape[0], 0)
# All distances to points in the results of the radius query should
# be less than mean_dist
distances, neighbors = lshf.radius_neighbors(query,
radius=mean_dist,
return_distance=True)
assert_array_less(distances[0], mean_dist)
# Multiple points
n_queries = 5
queries = X[rng.randint(0, n_samples, n_queries)]
distances, neighbors = lshf.radius_neighbors(queries,
return_distance=True)
# dists and inds should not be 1D arrays or arrays of variable lengths
# hence the use of the object dtype.
assert_equal(distances.shape, (n_queries,))
assert_equal(distances.dtype, object)
assert_equal(neighbors.shape, (n_queries,))
assert_equal(neighbors.dtype, object)
# Compare with exact neighbor search
query = X[rng.randint(0, n_samples)].reshape(1, -1)
mean_dist = np.mean(pairwise_distances(query, X, metric='cosine'))
nbrs = NearestNeighbors(algorithm='brute', metric='cosine').fit(X)
distances_exact, _ = nbrs.radius_neighbors(query, radius=mean_dist)
distances_approx, _ = lshf.radius_neighbors(query, radius=mean_dist)
def test_kernel_ridge_singular_kernel():
# alpha=0 causes a LinAlgError in computing the dual coefficients,
# which causes a fallback to a lstsq solver. This is tested here.
pred = Ridge(alpha=0, fit_intercept=False).fit(X, y).predict(X)
kr = KernelRidge(kernel="linear", alpha=0)
ignore_warnings(kr.fit)(X, y)
pred2 = kr.predict(X)
assert_array_almost_equal(pred, pred2)
def test_consistent_proba():
a = svm.SVC(probability=True, max_iter=1, random_state=0)
with ignore_warnings(category=ConvergenceWarning):
proba_1 = a.fit(X, Y).predict_proba(X)
a = svm.SVC(probability=True, max_iter=1, random_state=0)
with ignore_warnings(category=ConvergenceWarning):
proba_2 = a.fit(X, Y).predict_proba(X)
assert_array_almost_equal(proba_1, proba_2)
def test_nans():
# Assert that SelectKBest and SelectPercentile can handle NaNs.
# First feature has zero variance to confuse f_classif (ANOVA) and
# make it return a NaN.
X = [[0, 1, 0], [0, -1, -1], [0, 0.5, 0.5]]
y = [1, 0, 1]
for select in (SelectKBest(f_classif, 2), SelectPercentile(f_classif, percentile=67)):
ignore_warnings(select.fit)(X, y)
assert_array_equal(select.get_support(indices=True), np.array([1, 2]))
def _run_one_hot(X, X2, cat):
# enc = assert_warns(
# DeprecationWarning,
# OneHotEncoder, categorical_features=cat)
enc = OneHotEncoder(categorical_features=cat)
with ignore_warnings(category=(DeprecationWarning, FutureWarning)):
Xtr = enc.fit_transform(X)
with ignore_warnings(category=(DeprecationWarning, FutureWarning)):
X2tr = enc.fit(X).transform(X2)
return Xtr, X2tr
def test_path_parameters():
X, y = make_sparse_data()
max_iter = 50
n_alphas = 10
clf = ElasticNetCV(n_alphas=n_alphas, eps=1e-3, max_iter=max_iter, l1_ratio=0.5, fit_intercept=False)
ignore_warnings(clf.fit)(X, y) # new params
assert_almost_equal(0.5, clf.l1_ratio)
assert_equal(n_alphas, clf.n_alphas)
assert_equal(n_alphas, len(clf.alphas_))
sparse_mse_path = clf.mse_path_
ignore_warnings(clf.fit)(X.toarray(), y) # compare with dense data
assert_almost_equal(clf.mse_path_, sparse_mse_path)
def test_enet_float_precision():
# Generate dataset
X, y, X_test, y_test = build_dataset(n_samples=20, n_features=10)
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
for normalize in [True, False]:
for fit_intercept in [True, False]:
coef = {}
intercept = {}
for dtype in [np.float64, np.float32]:
clf = ElasticNet(alpha=0.5, max_iter=100, precompute=False,
fit_intercept=fit_intercept,
normalize=normalize)
X = dtype(X)
y = dtype(y)
ignore_warnings(clf.fit)(X, y)
coef[('simple', dtype)] = clf.coef_
intercept[('simple', dtype)] = clf.intercept_
assert_equal(clf.coef_.dtype, dtype)
# test precompute Gram array
Gram = X.T.dot(X)
clf_precompute = ElasticNet(alpha=0.5, max_iter=100,
precompute=Gram,
fit_intercept=fit_intercept,
normalize=normalize)
ignore_warnings(clf_precompute.fit)(X, y)
assert_array_almost_equal(clf.coef_, clf_precompute.coef_)
assert_array_almost_equal(clf.intercept_,
clf_precompute.intercept_)
# test multi task enet
multi_y = np.hstack((y[:, np.newaxis], y[:, np.newaxis]))
clf_multioutput = MultiTaskElasticNet(
alpha=0.5, max_iter=100, fit_intercept=fit_intercept,
normalize=normalize)
clf_multioutput.fit(X, multi_y)
coef[('multi', dtype)] = clf_multioutput.coef_
intercept[('multi', dtype)] = clf_multioutput.intercept_
assert_equal(clf.coef_.dtype, dtype)
for v in ['simple', 'multi']:
assert_array_almost_equal(coef[(v, np.float32)],
coef[(v, np.float64)],
decimal=4)
assert_array_almost_equal(intercept[(v, np.float32)],
intercept[(v, np.float64)],
decimal=4)
def check_class_weight_balanced_and_bootstrap_multi_output(name):
# Test class_weight works for multi-output"""
ForestClassifier = FOREST_CLASSIFIERS[name]
_y = np.vstack((y, np.array(y) * 2)).T
clf = ForestClassifier(class_weight="balanced", random_state=0)
clf.fit(X, _y)
clf = ForestClassifier(class_weight=[{-1: 0.5, 1: 1.0}, {-2: 1.0, 2: 1.0}], random_state=0)
clf.fit(X, _y)
# smoke test for subsample and balanced subsample
clf = ForestClassifier(class_weight="balanced_subsample", random_state=0)
clf.fit(X, _y)
clf = ForestClassifier(class_weight="subsample", random_state=0)
ignore_warnings(clf.fit)(X, _y)
def test_selectpercentile_tiebreaking():
# Test if SelectPercentile selects the right n_features in case of ties.
Xs = [[0, 1, 1], [0, 0, 1], [1, 0, 0], [1, 1, 0]]
y = [1]
dummy_score = lambda X, y: (X[0], X[0])
for X in Xs:
sel = SelectPercentile(dummy_score, percentile=34)
X1 = ignore_warnings(sel.fit_transform)([X], y)
assert_equal(X1.shape[1], 1)
assert_best_scores_kept(sel)
sel = SelectPercentile(dummy_score, percentile=67)
X2 = ignore_warnings(sel.fit_transform)([X], y)
assert_equal(X2.shape[1], 2)
assert_best_scores_kept(sel)
def test_kneighbors():
# Checks whether desired number of neighbors are returned.
# It is guaranteed to return the requested number of neighbors
# if `min_hash_match` is set to 0. Returned distances should be
# in ascending order.
n_samples = 12
n_features = 2
n_iter = 10
rng = np.random.RandomState(42)
X = rng.rand(n_samples, n_features)
lshf = ignore_warnings(LSHForest, category=DeprecationWarning)(
min_hash_match=0)
# Test unfitted estimator
assert_raises(ValueError, lshf.kneighbors, X[0])
ignore_warnings(lshf.fit)(X)
for i in range(n_iter):
n_neighbors = rng.randint(0, n_samples)
query = X[rng.randint(0, n_samples)].reshape(1, -1)
neighbors = lshf.kneighbors(query, n_neighbors=n_neighbors,
return_distance=False)
# Desired number of neighbors should be returned.
assert_equal(neighbors.shape[1], n_neighbors)
# Multiple points
n_queries = 5
queries = X[rng.randint(0, n_samples, n_queries)]
distances, neighbors = lshf.kneighbors(queries,
n_neighbors=1,
return_distance=True)
assert_equal(neighbors.shape[0], n_queries)
assert_equal(distances.shape[0], n_queries)
# Test only neighbors
neighbors = lshf.kneighbors(queries, n_neighbors=1,
return_distance=False)
assert_equal(neighbors.shape[0], n_queries)
# Test random point(not in the data set)
query = rng.randn(n_features).reshape(1, -1)
lshf.kneighbors(query, n_neighbors=1,
return_distance=False)
# Test n_neighbors at initialization
neighbors = lshf.kneighbors(query, return_distance=False)
assert_equal(neighbors.shape[1], 5)
# Test `neighbors` has an integer dtype
assert_true(neighbors.dtype.kind == 'i',
msg="neighbors are not in integer dtype.")
def test_train(self, params="wmc"):
g = mixture.GMM(n_components=self.n_components, covariance_type=self.covariance_type)
with ignore_warnings(category=DeprecationWarning):
g.weights_ = self.weights
g.means_ = self.means
g.covars_ = 20 * self.covars[self.covariance_type]
# Create a training set by sampling from the predefined distribution.
with ignore_warnings(category=DeprecationWarning):
X = g.sample(n_samples=100)
g = self.model(
n_components=self.n_components,
covariance_type=self.covariance_type,
random_state=rng,
min_covar=1e-1,
n_iter=1,
init_params=params,
)
g.fit(X)
# Do one training iteration at a time so we can keep track of
# the log likelihood to make sure that it increases after each
# iteration.
trainll = []
with ignore_warnings(category=DeprecationWarning):
for _ in range(5):
g.params = params
g.init_params = ""
g.fit(X)
trainll.append(self.score(g, X))
g.n_iter = 10
g.init_params = ""
g.params = params
g.fit(X) # finish fitting
# Note that the log likelihood will sometimes decrease by a
# very small amount after it has more or less converged due to
# the addition of min_covar to the covariance (to prevent
# underflow). This is why the threshold is set to -0.5
# instead of 0.
with ignore_warnings(category=DeprecationWarning):
delta_min = np.diff(trainll).min()
self.assertTrue(
delta_min > self.threshold,
"The min nll increase is %f which is lower than the admissible"
" threshold of %f, for model %s. The likelihoods are %s."
% (delta_min, self.threshold, self.covariance_type, trainll),
)
def test_multilabel_hamming_loss():
# Dense label indicator matrix format
y1 = np.array([[0, 1, 1], [1, 0, 1]])
y2 = np.array([[0, 0, 1], [1, 0, 1]])
assert_equal(hamming_loss(y1, y2), 1 / 6)
assert_equal(hamming_loss(y1, y1), 0)
assert_equal(hamming_loss(y2, y2), 0)
assert_equal(hamming_loss(y2, np.logical_not(y2)), 1)
assert_equal(hamming_loss(y1, np.logical_not(y1)), 1)
assert_equal(hamming_loss(y1, np.zeros(y1.shape)), 4 / 6)
assert_equal(hamming_loss(y2, np.zeros(y1.shape)), 0.5)
with ignore_warnings(): # sequence of sequences is deprecated
# List of tuple of label
y1 = [(1, 2,), (0, 2,)]
y2 = [(2,), (0, 2,)]
assert_equal(hamming_loss(y1, y2), 1 / 6)
assert_equal(hamming_loss(y1, y1), 0)
assert_equal(hamming_loss(y2, y2), 0)
assert_equal(hamming_loss(y2, [(), ()]), 0.75)
assert_equal(hamming_loss(y1, [tuple(), (10, )]), 0.625)
assert_almost_equal(hamming_loss(y2, [tuple(), (10, )],
classes=np.arange(11)), 0.1818, 2)
def test_non_meta_estimators(name, Estimator, check):
# Common tests for non-meta estimators
with ignore_warnings(category=(DeprecationWarning, ConvergenceWarning,
UserWarning, FutureWarning)):
estimator = Estimator()
set_checking_parameters(estimator)
check(name, estimator)
def test_no_attributes_set_in_init(name, Estimator):
# input validation etc for non-meta estimators
with ignore_warnings(category=(DeprecationWarning, ConvergenceWarning,
UserWarning, FutureWarning)):
estimator = Estimator()
# check this on class
check_no_attributes_set_in_init(name, estimator)
def test_1d_input(name):
X = iris.data[:, 0]
X_2d = iris.data[:, 0].reshape((-1, 1))
y = iris.target
with ignore_warnings():
check_1d_input(name, X, X_2d, y)
def test_warm_start(solver, warm_start, fit_intercept, multi_class):
# A 1-iteration second fit on same data should give almost same result
# with warm starting, and quite different result without warm starting.
# Warm starting does not work with liblinear solver.
X, y = iris.data, iris.target
clf = LogisticRegression(tol=1e-4, multi_class=multi_class,
warm_start=warm_start,
solver=solver,
random_state=42, max_iter=100,
fit_intercept=fit_intercept)
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X, y)
coef_1 = clf.coef_
clf.max_iter = 1
clf.fit(X, y)
cum_diff = np.sum(np.abs(coef_1 - clf.coef_))
msg = ("Warm starting issue with %s solver in %s mode "
"with fit_intercept=%s and warm_start=%s"
% (solver, multi_class, str(fit_intercept),
str(warm_start)))
if warm_start:
assert_greater(2.0, cum_diff, msg)
else:
assert_greater(cum_diff, 2.0, msg)
def test_multilabel_accuracy_score_subset_accuracy():
# Dense label indicator matrix format
y1 = np.array([[0, 1, 1], [1, 0, 1]])
y2 = np.array([[0, 0, 1], [1, 0, 1]])
assert_equal(accuracy_score(y1, y2), 0.5)
assert_equal(accuracy_score(y1, y1), 1)
assert_equal(accuracy_score(y2, y2), 1)
assert_equal(accuracy_score(y2, np.logical_not(y2)), 0)
assert_equal(accuracy_score(y1, np.logical_not(y1)), 0)
assert_equal(accuracy_score(y1, np.zeros(y1.shape)), 0)
assert_equal(accuracy_score(y2, np.zeros(y1.shape)), 0)
with ignore_warnings(): # sequence of sequences is deprecated
# List of tuple of label
y1 = [(1, 2,), (0, 2,)]
y2 = [(2,), (0, 2,)]
assert_equal(accuracy_score(y1, y2), 0.5)
assert_equal(accuracy_score(y1, y1), 1)
assert_equal(accuracy_score(y2, y2), 1)
assert_equal(accuracy_score(y2, [(), ()]), 0)
assert_equal(accuracy_score(y1, y2, normalize=False), 1)
assert_equal(accuracy_score(y1, y1, normalize=False), 2)
assert_equal(accuracy_score(y2, y2, normalize=False), 2)
assert_equal(accuracy_score(y2, [(), ()], normalize=False), 0)
def test_warm_start():
X, y, _, _ = build_dataset()
clf = ElasticNet(alpha=0.1, max_iter=5, warm_start=True)
ignore_warnings(clf.fit)(X, y)
ignore_warnings(clf.fit)(X, y) # do a second round with 5 iterations
clf2 = ElasticNet(alpha=0.1, max_iter=10)
ignore_warnings(clf2.fit)(X, y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
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()
f = assert_warns_message
def in_warn_message(msg):
return 'Early stopping' in msg or 'Dropping a regressor' in msg
lars_alphas, _, lars_coef = f(ConvergenceWarning,
in_warn_message,
linear_model.lars_path, X, y, method='lasso')
with ignore_warnings():
_, lasso_coef2, _ = linear_model.lasso_path(X, y,
alphas=lars_alphas,
tol=1e-6,
fit_intercept=False)
lasso_coef = np.zeros((w.shape[0], len(lars_alphas)))
iter_models = enumerate(linear_model.lasso_path(X, y,
alphas=lars_alphas,
tol=1e-6,
return_models=True,
fit_intercept=False))
for i, model in iter_models:
lasso_coef[:, i] = model.coef_
np.testing.assert_array_almost_equal(lars_coef, lasso_coef, decimal=1)
np.testing.assert_array_almost_equal(lars_coef, lasso_coef2, decimal=1)
np.testing.assert_array_almost_equal(lasso_coef, lasso_coef2, decimal=1)
def test_classification_invariance_string_vs_numbers_labels(name):
# Ensure that classification metrics with string labels are invariant
random_state = check_random_state(0)
y1 = random_state.randint(0, 2, size=(20, ))
y2 = random_state.randint(0, 2, size=(20, ))
y1_str = np.array(["eggs", "spam"])[y1]
y2_str = np.array(["eggs", "spam"])[y2]
pos_label_str = "spam"
labels_str = ["eggs", "spam"]
with ignore_warnings():
metric = CLASSIFICATION_METRICS[name]
measure_with_number = metric(y1, y2)
# Ugly, but handle case with a pos_label and label
metric_str = metric
if name in METRICS_WITH_POS_LABEL:
metric_str = partial(metric_str, pos_label=pos_label_str)
measure_with_str = metric_str(y1_str, y2_str)
assert_array_equal(measure_with_number,
measure_with_str,
err_msg="{0} failed string vs number invariance "
"test".format(name))
measure_with_strobj = metric_str(y1_str.astype('O'),
y2_str.astype('O'))
assert_array_equal(measure_with_number,
measure_with_strobj,
err_msg="{0} failed string object vs number "
"invariance test".format(name))
if name in METRICS_WITH_LABELS:
metric_str = partial(metric_str, labels=labels_str)
measure_with_str = metric_str(y1_str, y2_str)
assert_array_equal(measure_with_number,
measure_with_str,
err_msg="{0} failed string vs number "
"invariance test".format(name))
measure_with_strobj = metric_str(y1_str.astype('O'),
y2_str.astype('O'))
assert_array_equal(measure_with_number,
measure_with_strobj,
err_msg="{0} failed string vs number "
"invariance test".format(name))
def test_get_params_invariance():
# Test for estimators that support get_params, that
# get_params(deep=False) is a subset of get_params(deep=True)
# Related to issue #4465
estimators = all_estimators(include_meta_estimators=False,
include_other=True)
for name, Estimator in estimators:
if hasattr(Estimator, 'get_params'):
# If class is deprecated, ignore deprecated warnings
if hasattr(Estimator.__init__, "deprecated_original"):
with ignore_warnings():
yield check_get_params_invariance, name, Estimator
else:
yield check_get_params_invariance, name, Estimator
def test_roc_curve():
"""Test Area under Receiver Operating Characteristic (ROC) curve"""
y_true, _, probas_pred = make_prediction(binary=True)
fpr, tpr, thresholds = roc_curve(y_true, probas_pred)
roc_auc = auc(fpr, tpr)
expected_auc = _auc(y_true, probas_pred)
assert_array_almost_equal(roc_auc, expected_auc, decimal=2)
assert_almost_equal(roc_auc, roc_auc_score(y_true, probas_pred))
assert_almost_equal(roc_auc,
ignore_warnings(auc_score)(y_true, probas_pred))
assert_equal(fpr.shape, tpr.shape)
assert_equal(fpr.shape, thresholds.shape)
def test_verbose_sgd():
# Test verbose.
X = [[3, 2], [1, 6]]
y = [1, 0]
clf = MLPClassifier(algorithm='sgd', max_iter=2, verbose=10,
hidden_layer_sizes=2)
old_stdout = sys.stdout
sys.stdout = output = StringIO()
with ignore_warnings(category=ConvergenceWarning):
clf.fit(X, y)
clf.partial_fit(X, y)
sys.stdout = old_stdout
assert 'Iteration' in output.getvalue()
def test_one_hot_encoder_dense():
# check for sparse=False
X = [[3, 2, 1], [0, 1, 1]]
enc = OneHotEncoder(sparse=False)
with ignore_warnings(category=(DeprecationWarning, FutureWarning)):
# discover max values automatically
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 5))
assert_array_equal(enc.active_features_,
np.where([1, 0, 0, 1, 0, 1, 1, 0, 1])[0])
assert_array_equal(enc.feature_indices_, [0, 4, 7, 9])
# check outcome
assert_array_equal(X_trans,
np.array([[0., 1., 0., 1., 1.], [1., 0., 1., 0., 1.]]))
def test_non_meta_estimators():
# input validation etc for non-meta estimators
estimators = all_estimators()
for name, Estimator in estimators:
if issubclass(Estimator, BiclusterMixin):
continue
if name.startswith("_"):
continue
for check in _yield_all_checks(name, Estimator):
if issubclass(Estimator, ProjectedGradientNMF):
# The ProjectedGradientNMF class is deprecated
with ignore_warnings():
yield check, name, Estimator
else:
yield check, name, Estimator
def test_get_params_invariance():
# Test for estimators that support get_params, that
# get_params(deep=False) is a subset of get_params(deep=True)
# Related to issue #4465
estimators = all_estimators(include_meta_estimators=False,
include_other=True)
for name, Estimator in estimators:
if hasattr(Estimator, 'get_params'):
# The ProjectedGradientNMF class is deprecated
if issubclass(Estimator, ProjectedGradientNMF):
with ignore_warnings():
yield check_get_params_invariance, name, Estimator
else:
yield check_get_params_invariance, name, Estimator
def test_ovr_exceptions():
ovr = OneVsRestClassifier(LinearSVC(random_state=0))
assert_raises(ValueError, ovr.predict, [])
with ignore_warnings():
assert_raises(ValueError, predict_ovr, [LinearSVC(), MultinomialNB()],
LabelBinarizer(), [])
# Fail on multioutput data
assert_raises(ValueError, OneVsRestClassifier(MultinomialNB()).fit,
np.array([[1, 0], [0, 1]]),
np.array([[1, 2], [3, 1]]))
assert_raises(ValueError, OneVsRestClassifier(MultinomialNB()).fit,
np.array([[1, 0], [0, 1]]),
np.array([[1.5, 2.4], [3.1, 0.8]]))
def test_neighbors_accuracy_with_n_candidates():
# Checks whether accuracy increases as `n_candidates` increases.
n_candidates_values = np.array([.1, 50, 500])
n_samples = 100
n_features = 10
n_iter = 10
n_points = 5
rng = np.random.RandomState(42)
accuracies = np.zeros(n_candidates_values.shape[0], dtype=float)
X = rng.rand(n_samples, n_features)
for i, n_candidates in enumerate(n_candidates_values):
lshf = ignore_warnings(
LSHForest, category=DeprecationWarning)(n_candidates=n_candidates)
ignore_warnings(lshf.fit)(X)
for j in range(n_iter):
query = X[rng.randint(0, n_samples)].reshape(1, -1)
neighbors = lshf.kneighbors(query,
n_neighbors=n_points,
return_distance=False)
distances = pairwise_distances(query, X, metric='cosine')
ranks = np.argsort(distances)[0, :n_points]
intersection = np.intersect1d(ranks, neighbors).shape[0]
ratio = intersection / float(n_points)
accuracies[i] = accuracies[i] + ratio
accuracies[i] = accuracies[i] / float(n_iter)
# Sorted accuracies should be equal to original accuracies
print('accuracies:', accuracies)
assert_true(np.all(np.diff(accuracies) >= 0),
msg="Accuracies are not non-decreasing.")
# Highest accuracy should be strictly greater than the lowest
assert_true(np.ptp(accuracies) > 0,
msg="Highest accuracy is not strictly greater than lowest.")
def test_iforest():
"""Check Isolation Forest for various parameter settings."""
X_train = np.array([[0, 1], [1, 2]])
X_test = np.array([[2, 1], [1, 1]])
grid = ParameterGrid({
"n_estimators": [3],
"max_samples": [0.5, 1.0, 3],
"bootstrap": [True, False]
})
with ignore_warnings():
for params in grid:
IsolationForest(random_state=rng,
**params).fit(X_train).predict(X_test)
def test_candidates():
# Checks whether candidates are sufficient.
# This should handle the cases when number of candidates is 0.
# User should be warned when number of candidates is less than
# requested number of neighbors.
X_train = np.array([[5, 5, 2], [21, 5, 5], [1, 1, 1], [8, 9, 1],
[6, 10, 2]], dtype=np.float32)
X_test = np.array([7, 10, 3], dtype=np.float32).reshape(1, -1)
# For zero candidates
lshf = LSHForest(min_hash_match=32)
ignore_warnings(lshf.fit)(X_train)
message = ("Number of candidates is not sufficient to retrieve"
" %i neighbors with"
" min_hash_match = %i. Candidates are filled up"
" uniformly from unselected"
" indices." % (3, 32))
assert_warns_message(UserWarning, message, lshf.kneighbors,
X_test, n_neighbors=3)
distances, neighbors = lshf.kneighbors(X_test, n_neighbors=3)
assert_equal(distances.shape[1], 3)
# For candidates less than n_neighbors
lshf = LSHForest(min_hash_match=31)
ignore_warnings(lshf.fit)(X_train)
message = ("Number of candidates is not sufficient to retrieve"
" %i neighbors with"
" min_hash_match = %i. Candidates are filled up"
" uniformly from unselected"
" indices." % (5, 31))
assert_warns_message(UserWarning, message, lshf.kneighbors,
X_test, n_neighbors=5)
distances, neighbors = lshf.kneighbors(X_test, n_neighbors=5)
assert_equal(distances.shape[1], 5)
def test_1d_1component():
# Test all of the covariance_types return the same BIC score for
# 1-dimensional, 1 component fits.
n_samples, n_dim, n_components = 100, 1, 1
X = rng.randn(n_samples, n_dim)
g_full = mixture.GMM(n_components=n_components, covariance_type='full',
random_state=rng, min_covar=1e-7, n_iter=1)
with ignore_warnings(category=DeprecationWarning):
g_full.fit(X)
g_full_bic = g_full.bic(X)
for cv_type in ['tied', 'diag', 'spherical']:
g = mixture.GMM(n_components=n_components, covariance_type=cv_type,
random_state=rng, min_covar=1e-7, n_iter=1)
g.fit(X)
assert_array_almost_equal(g.bic(X), g_full_bic)
def test_sparse_matrices():
# Test that sparse and dense input matrices output the same results."""
X = X_digits_binary[:50]
y = y_digits_binary[:50]
X_sparse = csr_matrix(X)
mlp = MLPClassifier(random_state=1, hidden_layer_sizes=15)
with ignore_warnings(category=ConvergenceWarning):
mlp.fit(X, y)
pred1 = mlp.decision_function(X)
mlp.fit(X_sparse, y)
pred2 = mlp.decision_function(X_sparse)
assert_almost_equal(pred1, pred2)
pred1 = mlp.predict(X)
pred2 = mlp.predict(X_sparse)
assert_array_equal(pred1, pred2)
def test_warm_start_multitask_lasso():
X, y, X_test, y_test = build_dataset()
Y = np.c_[y, y]
clf = MultiTaskLasso(alpha=0.1, max_iter=5, warm_start=True)
ignore_warnings(clf.fit)(X, Y)
ignore_warnings(clf.fit)(X, Y) # do a second round with 5 iterations
clf2 = MultiTaskLasso(alpha=0.1, max_iter=10)
ignore_warnings(clf2.fit)(X, Y)
assert_array_almost_equal(clf2.coef_, clf.coef_)
def test_neighbors_badargs():
"""Test bad argument values: these should all raise ValueErrors"""
assert_raises(ValueError,
neighbors.NearestNeighbors,
algorithm='blah')
X = rng.random_sample((10, 2))
Xsparse = csr_matrix(X)
y = np.ones(10)
for cls in (neighbors.KNeighborsClassifier,
neighbors.RadiusNeighborsClassifier,
neighbors.KNeighborsRegressor,
neighbors.RadiusNeighborsRegressor):
assert_raises(ValueError,
cls,
weights='blah')
assert_raises(ValueError,
cls, p=-1)
assert_raises(ValueError,
cls, algorithm='blah')
nbrs = cls(algorithm='ball_tree', metric='haversine')
assert_raises(ValueError,
nbrs.predict,
X)
assert_raises(ValueError,
ignore_warnings(nbrs.fit),
Xsparse, y)
nbrs = cls()
assert_raises(ValueError,
nbrs.fit,
np.ones((0, 2)), np.ones(0))
assert_raises(ValueError,
nbrs.fit,
X[:, :, None], y)
nbrs.fit(X, y)
assert_raises(ValueError,
nbrs.predict,
[])
nbrs = neighbors.NearestNeighbors().fit(X)
assert_raises(ValueError,
nbrs.kneighbors_graph,
X, mode='blah')
assert_raises(ValueError,
nbrs.radius_neighbors_graph,
X, mode='blah')
def do_generate_rf_optimazed_model(X_train, y_train, parameters):
file_operations.write_logs(
FILENAME, 'Starting RF Grid Search with parameters:' + str(parameters))
model = RandomForestClassifier(random_state=my_constants.RANDOM_VALUE,
oob_score=True)
model_grid = GridSearchCV(model,
param_grid=parameters,
cv=3,
verbose=3,
n_jobs=3)
with ignore_warnings(category=ConvergenceWarning):
model_grid.fit(X_train, y_train)
file_operations.write_logs(FILENAME, 'RF Grid search completed')
return model_grid
def test_enet_path():
# We use a large number of samples and of informative features so that
# the l1_ratio selected is more toward ridge than lasso
X, y, X_test, y_test = build_dataset(n_samples=200, n_features=100,
n_informative_features=100)
max_iter = 150
# Here we have a small number of iterations, and thus the
# ElasticNet might not converge. This is to speed up tests
clf = ElasticNetCV(alphas=[0.01, 0.05, 0.1], eps=2e-3,
l1_ratio=[0.5, 0.7], cv=3,
max_iter=max_iter)
ignore_warnings(clf.fit)(X, y)
# Well-conditioned settings, we should have selected our
# smallest penalty
assert_almost_equal(clf.alpha_, min(clf.alphas_))
# Non-sparse ground truth: we should have selected an elastic-net
# that is closer to ridge than to lasso
assert_equal(clf.l1_ratio_, min(clf.l1_ratio))
clf = ElasticNetCV(alphas=[0.01, 0.05, 0.1], eps=2e-3,
l1_ratio=[0.5, 0.7], cv=3,
max_iter=max_iter, precompute=True)
ignore_warnings(clf.fit)(X, y)
# Well-conditioned settings, we should have selected our
# smallest penalty
assert_almost_equal(clf.alpha_, min(clf.alphas_))
# Non-sparse ground truth: we should have selected an elastic-net
# that is closer to ridge than to lasso
assert_equal(clf.l1_ratio_, min(clf.l1_ratio))
# We are in well-conditioned settings with low noise: we should
# have a good test-set performance
assert_greater(clf.score(X_test, y_test), 0.99)
# Multi-output/target case
X, y, X_test, y_test = build_dataset(n_features=10, n_targets=3)
clf = MultiTaskElasticNetCV(n_alphas=5, eps=2e-3, l1_ratio=[0.5, 0.7],
cv=3, max_iter=max_iter)
ignore_warnings(clf.fit)(X, y)
# We are in well-conditioned settings with low noise: we should
# have a good test-set performance
assert_greater(clf.score(X_test, y_test), 0.99)
assert_equal(clf.coef_.shape, (3, 10))
# Mono-output should have same cross-validated alpha_ and l1_ratio_
# in both cases.
X, y, _, _ = build_dataset(n_features=10)
clf1 = ElasticNetCV(n_alphas=5, eps=2e-3, l1_ratio=[0.5, 0.7])
clf1.fit(X, y)
clf2 = MultiTaskElasticNetCV(n_alphas=5, eps=2e-3, l1_ratio=[0.5, 0.7])
clf2.fit(X, y[:, np.newaxis])
assert_almost_equal(clf1.l1_ratio_, clf2.l1_ratio_)
assert_almost_equal(clf1.alpha_, clf2.alpha_)
def test_train_degenerate(self, params='wmc'):
# Train on degenerate data with 0 in some dimensions
# Create a training set by sampling from the predefined
# distribution.
X = rng.randn(100, self.n_features)
X.T[1:] = 0
g = self.model(n_components=2,
covariance_type=self.covariance_type,
random_state=rng,
min_covar=1e-3,
n_iter=5,
init_params=params)
with ignore_warnings(category=DeprecationWarning):
g.fit(X)
trainll = g.score(X)
self.assertTrue(np.sum(np.abs(trainll / 100 / X.shape[1])) < 5)
def test_multilabel_jaccard_similarity_score():
# Dense label indicator matrix format
y1 = np.array([[0, 1, 1], [1, 0, 1]])
y2 = np.array([[0, 0, 1], [1, 0, 1]])
# size(y1 \inter y2) = [1, 2]
# size(y1 \union y2) = [2, 2]
assert_equal(jaccard_similarity_score(y1, y2), 0.75)
assert_equal(jaccard_similarity_score(y1, y1), 1)
assert_equal(jaccard_similarity_score(y2, y2), 1)
assert_equal(jaccard_similarity_score(y2, np.logical_not(y2)), 0)
assert_equal(jaccard_similarity_score(y1, np.logical_not(y1)), 0)
assert_equal(jaccard_similarity_score(y1, np.zeros(y1.shape)), 0)
assert_equal(jaccard_similarity_score(y2, np.zeros(y1.shape)), 0)
with ignore_warnings(): # sequence of sequences is deprecated
# List of tuple of label
y1 = [(
1,
2,
), (
0,
2,
)]
y2 = [(2, ), (
0,
2,
)]
assert_equal(jaccard_similarity_score(y1, y2), 0.75)
assert_equal(jaccard_similarity_score(y1, y1), 1)
assert_equal(jaccard_similarity_score(y2, y2), 1)
assert_equal(jaccard_similarity_score(y2, [(), ()]), 0)
# |y3 inter y4 | = [0, 1, 1]
# |y3 union y4 | = [2, 1, 3]
y3 = [(0, ), (1, ), (3, )]
y4 = [(4, ), (4, ), (5, 6)]
assert_almost_equal(jaccard_similarity_score(y3, y4), 0)
# |y5 inter y6 | = [0, 1, 1]
# |y5 union y6 | = [2, 1, 3]
y5 = [(0, ), (1, ), (2, 3)]
y6 = [(1, ), (1, ), (2, 0)]
assert_almost_equal(jaccard_similarity_score(y5, y6), (1 + 1 / 3) / 3)
def test_multiclass_multioutput(Estimator):
# Make sure error is raised for multiclass-multioutput classifiers
# make multiclass-multioutput dataset
X, y = make_classification(n_classes=3,
n_clusters_per_class=1,
random_state=0)
y = np.array([y, y]).T
est = Estimator()
with ignore_warnings(category=FutureWarning):
est.fit(X, y)
with pytest.raises(
ValueError,
match="Multiclass-multioutput estimators are not supported"):
partial_dependence(est, X, [0])
def train(self, contexts, responses):
"""Fit the tf-idf transform and compute idf statistics."""
with ignore_warnings():
# Ignore deprecated `non_negative` warning.
self._vectorizer = HashingVectorizer(non_negative=True)
self._tfidf_transform = TfidfTransformer()
count_matrix = self._tfidf_transform.fit_transform(
self._vectorizer.transform(contexts + responses))
n_samples, n_features = count_matrix.shape
df = _document_frequency(count_matrix)
idf = np.log((n_samples - df + 0.5) / (df + 0.5))
self._idf_diag = sp.spdiags(
idf, diags=0, m=n_features, n=n_features
)
document_lengths = count_matrix.sum(axis=1)
self._average_document_length = np.mean(document_lengths)
print(self._average_document_length)
def test_train_1d(self, params='wmc'):
# Train on 1-D data
# Create a training set by sampling from the predefined
# distribution.
X = rng.randn(100, 1)
# X.T[1:] = 0
g = self.model(n_components=2,
covariance_type=self.covariance_type,
random_state=rng, min_covar=1e-7, n_iter=5,
init_params=params)
with ignore_warnings(category=DeprecationWarning):
g.fit(X)
trainll = g.score(X)
if isinstance(g, mixture.DPGMM):
self.assertTrue(np.sum(np.abs(trainll / 100)) < 5)
else:
self.assertTrue(np.sum(np.abs(trainll / 100)) < 2)
def test_logistic_regression_sample_weights():
X, y = make_classification(n_samples=20, n_features=5, n_informative=3,
n_classes=2, random_state=0)
sample_weight = y + 1
for LR in [LogisticRegression, LogisticRegressionCV]:
# Test that liblinear fails when sample weights are provided
clf_lib = LR(solver='liblinear')
assert_raises(ValueError, clf_lib.fit, X, y,
sample_weight=np.ones(y.shape[0]))
# Test that passing sample_weight as ones is the same as
# not passing them at all (default None)
clf_sw_none = LR(solver='lbfgs', fit_intercept=False)
clf_sw_none.fit(X, y)
clf_sw_ones = LR(solver='lbfgs', fit_intercept=False)
clf_sw_ones.fit(X, y, sample_weight=np.ones(y.shape[0]))
assert_array_almost_equal(clf_sw_none.coef_, clf_sw_ones.coef_, decimal=4)
# Test that sample weights work the same with the lbfgs,
# newton-cg, and 'sag' solvers
clf_sw_lbfgs = LR(solver='lbfgs', fit_intercept=False)
clf_sw_lbfgs.fit(X, y, sample_weight=sample_weight)
clf_sw_n = LR(solver='newton-cg', fit_intercept=False)
clf_sw_n.fit(X, y, sample_weight=sample_weight)
clf_sw_sag = LR(solver='sag', fit_intercept=False, tol=1e-10)
# ignore convergence warning due to small dataset
with ignore_warnings():
clf_sw_sag.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(
clf_sw_lbfgs.coef_, clf_sw_n.coef_, decimal=4)
assert_array_almost_equal(
clf_sw_lbfgs.coef_, clf_sw_sag.coef_, decimal=4)
# Test that passing class_weight as [1,2] is the same as
# passing class weight = [1,1] but adjusting sample weights
# to be 2 for all instances of class 2
clf_cw_12 = LR(solver='lbfgs', fit_intercept=False,
class_weight={0: 1, 1: 2})
clf_cw_12.fit(X, y)
sample_weight = np.ones(y.shape[0])
sample_weight[y == 1] = 2
clf_sw_12 = LR(solver='lbfgs', fit_intercept=False)
clf_sw_12.fit(X, y, sample_weight=sample_weight)
assert_array_almost_equal(clf_cw_12.coef_, clf_sw_12.coef_, decimal=4)
def test_alpha():
# Test that larger alpha yields weights closer to zero"""
X = X_digits_binary[:100]
y = y_digits_binary[:100]
alpha_vectors = []
alpha_values = np.arange(2)
absolute_sum = lambda x: np.sum(np.abs(x))
for alpha in alpha_values:
mlp = MLPClassifier(hidden_layer_sizes=10, alpha=alpha, random_state=1)
with ignore_warnings(category=ConvergenceWarning):
mlp.fit(X, y)
alpha_vectors.append(np.array([absolute_sum(mlp.coefs_[0]),
absolute_sum(mlp.coefs_[1])]))
for i in range(len(alpha_values) - 1):
assert (alpha_vectors[i] > alpha_vectors[i + 1]).all()
def _compute_score(self, X, y=None):
_, n_features = X.shape
score = np.empty(len(self.n_clusters_range))
for k, n_clusters in enumerate(self.n_clusters_range):
self.estimator.set_params(n_clusters=n_clusters)
score[k] = self.estimator.fit(X).score(X)
weights = 1. - np.exp((self.n_clusters_range[:-1] - 1) *
np.log(5. / 6.) + np.log(.75) -
np.log(n_features))
with ignore_warnings(category=RuntimeWarning):
score[1:] = np.where(score[:-1] != 0.,
score[1:] / (weights * score[:-1]), 1.)
score[0] = 1.
return -score
def train_model(folds, model):
"""
Evaluation with:
Matthews correlation coefficient: represents thresholding measures
AUC: represents ranking measures
Brier score: represents calibration measures
"""
scores = []
fit_model_time = 0 # Sum of all the time spend on fitting the training data, later on normalized
score_model_time = 0 # Sum of all the time spend on scoring the testing data, later on normalized
for X_train, y_train, X_test, y_test in folds:
# Training
start_time = time.time()
with ignore_warnings(category=ConvergenceWarning
): # Yes, neural networks do not always converge
model.fit(X_train, y_train)
fit_model_time += time.time() - start_time
prediction_train_proba = model.predict_proba(X_train)[:, 1]
prediction_train = (prediction_train_proba >= 0.5).astype('uint8')
# Testing
start_time = time.time()
prediction_test_proba = model.predict_proba(X_test)[:, 1]
score_model_time += time.time() - start_time
prediction_test = (prediction_test_proba >= 0.5).astype('uint8')
# When all the predictions are of a single class, we get a RuntimeWarning in matthews_corr
with warnings.catch_warnings():
warnings.simplefilter("ignore")
scores.append([
sklearn.metrics.matthews_corrcoef(y_test, prediction_test),
sklearn.metrics.matthews_corrcoef(y_train, prediction_train),
sklearn.metrics.roc_auc_score(y_test, prediction_test_proba),
sklearn.metrics.roc_auc_score(y_train, prediction_train_proba),
sklearn.metrics.brier_score_loss(y_test,
prediction_test_proba),
sklearn.metrics.brier_score_loss(y_train,
prediction_train_proba)
])
return np.mean(
scores,
axis=0), fit_model_time / len(folds), score_model_time / len(folds)
def test_same_output_sparse_dense_lasso_and_enet_cv():
X, y = make_sparse_data(n_samples=40, n_features=10)
for normalize in [True, False]:
clfs = ElasticNetCV(max_iter=100, cv=5, normalize=normalize)
ignore_warnings(clfs.fit)(X, y)
clfd = ElasticNetCV(max_iter=100, cv=5, normalize=normalize)
ignore_warnings(clfd.fit)(X.toarray(), y)
assert_almost_equal(clfs.alpha_, clfd.alpha_, 7)
assert_almost_equal(clfs.intercept_, clfd.intercept_, 7)
assert_array_almost_equal(clfs.mse_path_, clfd.mse_path_)
assert_array_almost_equal(clfs.alphas_, clfd.alphas_)
clfs = LassoCV(max_iter=100, cv=4, normalize=normalize)
ignore_warnings(clfs.fit)(X, y)
clfd = LassoCV(max_iter=100, cv=4, normalize=normalize)
ignore_warnings(clfd.fit)(X.toarray(), y)
assert_almost_equal(clfs.alpha_, clfd.alpha_, 7)
assert_almost_equal(clfs.intercept_, clfd.intercept_, 7)
assert_array_almost_equal(clfs.mse_path_, clfd.mse_path_)
assert_array_almost_equal(clfs.alphas_, clfd.alphas_)
def test_scorer_memmap_input(name):
# Non-regression test for #6147: some score functions would
# return singleton memmap when computed on memmap data instead of scalar
# float values.
if name in REQUIRE_POSITIVE_Y_SCORERS:
y_mm_1 = _require_positive_y(y_mm)
y_ml_mm_1 = _require_positive_y(y_ml_mm)
else:
y_mm_1, y_ml_mm_1 = y_mm, y_ml_mm
# UndefinedMetricWarning for P / R scores
with ignore_warnings():
scorer, estimator = SCORERS[name], ESTIMATORS[name]
if name in MULTILABEL_ONLY_SCORERS:
score = scorer(estimator, X_mm, y_ml_mm_1)
else:
score = scorer(estimator, X_mm, y_mm_1)
assert isinstance(score, numbers.Number), name