def check_classifiers_classes(name, Classifier):
X, y = make_blobs(n_samples=30, random_state=0, cluster_std=0.1)
X, y = shuffle(X, y, random_state=7)
X = StandardScaler().fit_transform(X)
# We need to make sure that we have non negative data, for things
# like NMF
X -= X.min() - .1
y_names = np.array(["one", "two", "three"])[y]
for y_names in [y_names, y_names.astype('O')]:
if name in ["LabelPropagation", "LabelSpreading"]:
# TODO some complication with -1 label
y_ = y
else:
y_ = y_names
classes = np.unique(y_)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
classifier = Classifier()
if name == 'BernoulliNB':
classifier.set_params(binarize=X.mean())
set_fast_parameters(classifier)
# fit
classifier.fit(X, y_)
y_pred = classifier.predict(X)
# training set performance
assert_array_equal(np.unique(y_), np.unique(y_pred))
if np.any(classifier.classes_ != classes):
print("Unexpected classes_ attribute for %r: "
"expected %s, got %s" %
(classifier, classes, classifier.classes_))
def test_multilabel_binarizer_empty_sample():
mlb = MultiLabelBinarizer()
y = [[1, 2], [1], []]
Y = np.array([[1, 1],
[1, 0],
[0, 0]])
assert_array_equal(mlb.fit_transform(y), Y)
def test_kneighbors_graph():
"""Test kneighbors_graph to build the k-Nearest Neighbor graph."""
X = np.array([[0, 1], [1.01, 1.], [2, 0]])
# n_neighbors = 1
A = neighbors.kneighbors_graph(X, 1, mode='connectivity')
assert_array_equal(A.toarray(), np.eye(A.shape[0]))
A = neighbors.kneighbors_graph(X, 1, mode='distance')
assert_array_almost_equal(
A.toarray(),
[[0.00, 1.01, 0.],
[1.01, 0., 0.],
[0.00, 1.40716026, 0.]])
# n_neighbors = 2
A = neighbors.kneighbors_graph(X, 2, mode='connectivity')
assert_array_equal(
A.toarray(),
[[1., 1., 0.],
[1., 1., 0.],
[0., 1., 1.]])
A = neighbors.kneighbors_graph(X, 2, mode='distance')
assert_array_almost_equal(
A.toarray(),
[[0., 1.01, 2.23606798],
[1.01, 0., 1.40716026],
[2.23606798, 1.40716026, 0.]])
# n_neighbors = 3
A = neighbors.kneighbors_graph(X, 3, mode='connectivity')
assert_array_almost_equal(
A.toarray(),
[[1, 1, 1], [1, 1, 1], [1, 1, 1]])
def test_radius_neighbors_classifier(n_samples=40,
n_features=5,
n_test_pts=10,
radius=0.5,
random_state=0):
"""Test radius-based classification"""
rng = np.random.RandomState(random_state)
X = 2 * rng.rand(n_samples, n_features) - 1
y = ((X ** 2).sum(axis=1) < .5).astype(np.int)
y_str = y.astype(str)
weight_func = _weight_func
for algorithm in ALGORITHMS:
for weights in ['uniform', 'distance', weight_func]:
neigh = neighbors.RadiusNeighborsClassifier(radius=radius,
weights=weights,
algorithm=algorithm)
neigh.fit(X, y)
epsilon = 1e-5 * (2 * rng.rand(1, n_features) - 1)
y_pred = neigh.predict(X[:n_test_pts] + epsilon)
assert_array_equal(y_pred, y[:n_test_pts])
neigh.fit(X, y_str)
y_pred = neigh.predict(X[:n_test_pts] + epsilon)
assert_array_equal(y_pred, y_str[:n_test_pts])
def test_precision_recall_f1_score_binary():
"""Test Precision Recall and F1 Score for binary classification task"""
y_true, y_pred, _ = make_prediction(binary=True)
# detailed measures for each class
p, r, f, s = precision_recall_fscore_support(y_true, y_pred, average=None)
assert_array_almost_equal(p, [0.73, 0.85], 2)
assert_array_almost_equal(r, [0.88, 0.68], 2)
assert_array_almost_equal(f, [0.80, 0.76], 2)
assert_array_equal(s, [25, 25])
# individual scoring function that can be used for grid search: in the
# binary class case the score is the value of the measure for the positive
# class (e.g. label == 1)
ps = precision_score(y_true, y_pred)
assert_array_almost_equal(ps, 0.85, 2)
rs = recall_score(y_true, y_pred)
assert_array_almost_equal(rs, 0.68, 2)
fs = f1_score(y_true, y_pred)
assert_array_almost_equal(fs, 0.76, 2)
assert_almost_equal(fbeta_score(y_true, y_pred, beta=2),
(1 + 2 ** 2) * ps * rs / (2 ** 2 * ps + rs), 2)
def test_radius_neighbors_classifier_when_no_neighbors():
""" Test radius-based classifier when no neighbors found.
In this case it should rise an informative exception """
X = np.array([[1.0, 1.0], [2.0, 2.0]])
y = np.array([1, 2])
radius = 0.1
z1 = np.array([[1.01, 1.01], [2.01, 2.01]]) # no outliers
z2 = np.array([[1.01, 1.01], [1.4, 1.4]]) # one outlier
weight_func = _weight_func
for outlier_label in [0, -1, None]:
for algorithm in ALGORITHMS:
for weights in ['uniform', 'distance', weight_func]:
rnc = neighbors.RadiusNeighborsClassifier
clf = rnc(radius=radius, weights=weights, algorithm=algorithm,
outlier_label=outlier_label)
clf.fit(X, y)
assert_array_equal(np.array([1, 2]),
clf.predict(z1))
if outlier_label is None:
assert_raises(ValueError, clf.predict, z2)
elif False:
assert_array_equal(np.array([1, outlier_label]),
clf.predict(z2))
def test_iforest_sparse():
"""Check IForest for various parameter settings on sparse input."""
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
boston.target[:50],
random_state=rng)
grid = ParameterGrid({"max_samples": [0.5, 1.0],
"bootstrap": [True, False]})
for sparse_format in [csc_matrix, csr_matrix]:
X_train_sparse = sparse_format(X_train)
X_test_sparse = sparse_format(X_test)
for params in grid:
# Trained on sparse format
sparse_classifier = IsolationForest(
n_estimators=10, random_state=1, **params).fit(X_train_sparse)
sparse_results = sparse_classifier.predict(X_test_sparse)
# Trained on dense format
dense_classifier = IsolationForest(
n_estimators=10, random_state=1, **params).fit(X_train)
dense_results = dense_classifier.predict(X_test)
assert_array_equal(sparse_results, dense_results)
assert_array_equal(sparse_results, dense_results)
def test_kneighbors_classifier_predict_proba():
"""Test KNeighborsClassifier.predict_proba() method"""
X = np.array([[0, 2, 0],
[0, 2, 1],
[2, 0, 0],
[2, 2, 0],
[0, 0, 2],
[0, 0, 1]])
y = np.array([4, 4, 5, 5, 1, 1])
cls = neighbors.KNeighborsClassifier(n_neighbors=3, p=1) # cityblock dist
cls.fit(X, y)
y_prob = cls.predict_proba(X)
real_prob = np.array([[0, 2. / 3, 1. / 3],
[1. / 3, 2. / 3, 0],
[1. / 3, 0, 2. / 3],
[0, 1. / 3, 2. / 3],
[2. / 3, 1. / 3, 0],
[2. / 3, 1. / 3, 0]])
assert_array_equal(real_prob, y_prob)
# Check that it also works with non integer labels
cls.fit(X, y.astype(str))
y_prob = cls.predict_proba(X)
assert_array_equal(real_prob, y_prob)
# Check that it works with weights='distance'
cls = neighbors.KNeighborsClassifier(
n_neighbors=2, p=1, weights='distance')
cls.fit(X, y)
y_prob = cls.predict_proba(np.array([[0, 2, 0], [2, 2, 2]]))
real_prob = np.array([[0, 1, 0], [0, 0.4, 0.6]])
assert_array_almost_equal(real_prob, y_prob)
def test_grid_search_sparse_scoring():
X_, y_ = make_classification(n_samples=200, n_features=100, random_state=0)
clf = LinearSVC()
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
cv.fit(X_[:180], y_[:180])
y_pred = cv.predict(X_[180:])
C = cv.best_estimator_.C
X_ = sp.csr_matrix(X_)
clf = LinearSVC()
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
cv.fit(X_[:180], y_[:180])
y_pred2 = cv.predict(X_[180:])
C2 = cv.best_estimator_.C
assert_array_equal(y_pred, y_pred2)
assert_equal(C, C2)
# Smoke test the score
#np.testing.assert_allclose(f1_score(cv.predict(X_[:180]), y[:180]),
# cv.score(X_[:180], y[:180]))
# test loss where greater is worse
def f1_loss(y_true_, y_pred_):
return -f1_score(y_true_, y_pred_)
F1Loss = make_scorer(f1_loss, greater_is_better=False)
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring=F1Loss)
cv.fit(X_[:180], y_[:180])
y_pred3 = cv.predict(X_[180:])
C3 = cv.best_estimator_.C
assert_equal(C, C3)
assert_array_equal(y_pred, y_pred3)
def test_deprecated_score_func():
# test that old deprecated way of passing a score / loss function is still
# supported
X, y = make_classification(n_samples=200, n_features=100, random_state=0)
clf = LinearSVC(random_state=0)
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, scoring="f1")
cv.fit(X[:180], y[:180])
y_pred = cv.predict(X[180:])
C = cv.best_estimator_.C
clf = LinearSVC(random_state=0)
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, score_func=f1_score)
with warnings.catch_warnings(record=True):
# catch deprecation warning
cv.fit(X[:180], y[:180])
y_pred_func = cv.predict(X[180:])
C_func = cv.best_estimator_.C
assert_array_equal(y_pred, y_pred_func)
assert_equal(C, C_func)
# test loss where greater is worse
def f1_loss(y_true_, y_pred_):
return -f1_score(y_true_, y_pred_)
clf = LinearSVC(random_state=0)
cv = GridSearchCV(clf, {'C': [0.1, 1.0]}, loss_func=f1_loss)
with warnings.catch_warnings(record=True):
# catch deprecation warning
cv.fit(X[:180], y[:180])
y_pred_loss = cv.predict(X[180:])
C_loss = cv.best_estimator_.C
assert_array_equal(y_pred, y_pred_loss)
assert_equal(C, C_loss)
def test_labels_assignment_and_inertia():
# pure numpy implementation as easily auditable reference gold
# implementation
rng = np.random.RandomState(42)
noisy_centers = centers + rng.normal(size=centers.shape)
labels_gold = - np.ones(n_samples, dtype=np.int)
mindist = np.empty(n_samples)
mindist.fill(np.infty)
for center_id in range(n_clusters):
dist = np.sum((X - noisy_centers[center_id]) ** 2, axis=1)
labels_gold[dist < mindist] = center_id
mindist = np.minimum(dist, mindist)
inertia_gold = mindist.sum()
assert_true((mindist >= 0.0).all())
assert_true((labels_gold != -1).all())
# perform label assignment using the dense array input
x_squared_norms = (X ** 2).sum(axis=1)
labels_array, inertia_array = _labels_inertia(
X, x_squared_norms, noisy_centers)
assert_array_almost_equal(inertia_array, inertia_gold)
assert_array_equal(labels_array, labels_gold)
# perform label assignment using the sparse CSR input
x_squared_norms_from_csr = row_norms(X_csr, squared=True)
labels_csr, inertia_csr = _labels_inertia(
X_csr, x_squared_norms_from_csr, noisy_centers)
assert_array_almost_equal(inertia_csr, inertia_gold)
assert_array_equal(labels_csr, labels_gold)
def test_int_input():
X_list = [[0, 0], [10, 10], [12, 9], [-1, 1], [2, 0], [8, 10]]
for dtype in [np.int32, np.int64]:
X_int = np.array(X_list, dtype=dtype)
X_int_csr = sp.csr_matrix(X_int)
init_int = X_int[:2]
fitted_models = [
KMeans(n_clusters=2).fit(X_int),
KMeans(n_clusters=2, init=init_int, n_init=1).fit(X_int),
# mini batch kmeans is very unstable on such a small dataset hence
# we use many inits
MiniBatchKMeans(n_clusters=2, n_init=10, batch_size=2).fit(X_int),
MiniBatchKMeans(n_clusters=2, n_init=10, batch_size=2).fit(X_int_csr),
MiniBatchKMeans(n_clusters=2, batch_size=2,
init=init_int, n_init=1).fit(X_int),
MiniBatchKMeans(n_clusters=2, batch_size=2,
init=init_int, n_init=1).fit(X_int_csr),
]
for km in fitted_models:
assert_equal(km.cluster_centers_.dtype, np.float64)
expected_labels = [0, 1, 1, 0, 0, 1]
scores = np.array([v_measure_score(expected_labels, km.labels_)
for km in fitted_models])
assert_array_equal(scores, np.ones(scores.shape[0]))
def test_ovr_multilabel():
# Toy dataset where features correspond directly to labels.
X = np.array([[0, 4, 5], [0, 5, 0], [3, 3, 3], [4, 0, 6], [6, 0, 0]])
y = [["spam", "eggs"], ["spam"], ["ham", "eggs", "spam"],
["ham", "eggs"], ["ham"]]
#y = [[1, 2], [1], [0, 1, 2], [0, 2], [0]]
Y = np.array([[0, 1, 1],
[0, 1, 0],
[1, 1, 1],
[1, 0, 1],
[1, 0, 0]])
classes = set("ham eggs spam".split())
for base_clf in (MultinomialNB(), LinearSVC(random_state=0),
LinearRegression(), Ridge(),
ElasticNet(), Lasso(alpha=0.5)):
# test input as lists of tuples
clf = assert_warns(DeprecationWarning,
OneVsRestClassifier(base_clf).fit,
X, y)
assert_equal(set(clf.classes_), classes)
y_pred = clf.predict([[0, 4, 4]])[0]
assert_equal(set(y_pred), set(["spam", "eggs"]))
assert_true(clf.multilabel_)
# test input as label indicator matrix
clf = OneVsRestClassifier(base_clf).fit(X, Y)
y_pred = clf.predict([[0, 4, 4]])[0]
assert_array_equal(y_pred, [0, 1, 1])
assert_true(clf.multilabel_)
def test_sparse_fit_params():
iris = load_iris()
X, y = iris.data, iris.target
clf = MockClassifier()
fit_params = {'sparse_sample_weight': coo_matrix(np.eye(X.shape[0]))}
a = cval.cross_val_score(clf, X, y, fit_params=fit_params)
assert_array_equal(a, np.ones(3))
def test_ovr_multilabel_predict_proba():
base_clf = MultinomialNB(alpha=1)
for au in (False, True):
X, Y = datasets.make_multilabel_classification(n_samples=100,
n_features=20,
n_classes=5,
n_labels=3,
length=50,
allow_unlabeled=au,
return_indicator=True,
random_state=0)
X_train, Y_train = X[:80], Y[:80]
X_test, Y_test = X[80:], Y[80:]
clf = OneVsRestClassifier(base_clf).fit(X_train, Y_train)
# decision function only estimator. Fails in current implementation.
decision_only = OneVsRestClassifier(svm.SVR()).fit(X_train, Y_train)
assert_raises(AttributeError, decision_only.predict_proba, X_test)
# Estimator with predict_proba disabled, depending on parameters.
decision_only = OneVsRestClassifier(svm.SVC(probability=False))
decision_only.fit(X_train, Y_train)
assert_raises(AttributeError, decision_only.predict_proba, X_test)
Y_pred = clf.predict(X_test)
Y_proba = clf.predict_proba(X_test)
# predict assigns a label if the probability that the
# sample has the label is greater than 0.5.
pred = Y_proba > .5
assert_array_equal(pred, Y_pred)
def test_ovo_ties():
# test that ties are broken using the decision function, not defaulting to
# the smallest label
X = np.array([[1, 2], [2, 1], [-2, 1], [-2, -1]])
y = np.array([2, 0, 1, 2])
multi_clf = OneVsOneClassifier(Perceptron())
ovo_prediction = multi_clf.fit(X, y).predict(X)
# recalculate votes to make sure we have a tie
predictions = np.vstack([clf.predict(X) for clf in multi_clf.estimators_])
scores = np.vstack([clf.decision_function(X)
for clf in multi_clf.estimators_])
# classifiers are in order 0-1, 0-2, 1-2
# aggregate votes:
votes = np.zeros((4, 3))
votes[np.arange(4), predictions[0]] += 1
votes[np.arange(4), 2 * predictions[1]] += 1
votes[np.arange(4), 1 + predictions[2]] += 1
# for the first point, there is one vote per class
assert_array_equal(votes[0, :], 1)
# for the rest, there is no tie and the prediction is the argmax
assert_array_equal(np.argmax(votes[1:], axis=1), ovo_prediction[1:])
# for the tie, the prediction is the class with the highest score
assert_equal(ovo_prediction[0], 0)
# in the zero-one classifier, the score for 0 is greater than the score for
# one.
assert_greater(scores[0][0], scores[0][1])
# score for one is greater than score for zero
assert_greater(scores[2, 0] - scores[0, 0], scores[0, 0] + scores[1, 0])
# score for one is greater than score for two
assert_greater(scores[2, 0] - scores[0, 0], -scores[1, 0] - scores[2, 0])
def check_classifiers_input_shapes(name, Classifier):
iris = load_iris()
X, y = iris.data, iris.target
X, y = shuffle(X, y, random_state=1)
X = StandardScaler().fit_transform(X)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
classifier = Classifier()
set_fast_parameters(classifier)
set_random_state(classifier)
# fit
classifier.fit(X, y)
y_pred = classifier.predict(X)
set_random_state(classifier)
# Check that when a 2D y is given, a DataConversionWarning is
# raised
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always", DataConversionWarning)
warnings.simplefilter("ignore", RuntimeWarning)
classifier.fit(X, y[:, np.newaxis])
msg = "expected 1 DataConversionWarning, got: %s" % (
", ".join([str(w_x) for w_x in w]))
assert_equal(len(w), 1, msg)
assert_array_equal(y_pred, classifier.predict(X))
def test_make_swiss_roll():
X, t = make_swiss_roll(n_samples=5, noise=0.0, random_state=0)
assert_equal(X.shape, (5, 3), "X shape mismatch")
assert_equal(t.shape, (5,), "t shape mismatch")
assert_array_equal(X[:, 0], t * np.cos(t))
assert_array_equal(X[:, 2], t * np.sin(t))
def check_clustering(name, Alg):
X, y = make_blobs(n_samples=50, random_state=1)
X, y = shuffle(X, y, random_state=7)
X = StandardScaler().fit_transform(X)
n_samples, n_features = X.shape
# catch deprecation and neighbors warnings
with warnings.catch_warnings(record=True):
alg = Alg()
set_fast_parameters(alg)
if hasattr(alg, "n_clusters"):
alg.set_params(n_clusters=3)
set_random_state(alg)
if name == 'AffinityPropagation':
alg.set_params(preference=-100)
alg.set_params(max_iter=100)
# fit
alg.fit(X)
# with lists
alg.fit(X.tolist())
assert_equal(alg.labels_.shape, (n_samples,))
pred = alg.labels_
assert_greater(adjusted_rand_score(pred, y), 0.4)
# fit another time with ``fit_predict`` and compare results
if name is 'SpectralClustering':
# there is no way to make Spectral clustering deterministic :(
return
set_random_state(alg)
with warnings.catch_warnings(record=True):
pred2 = alg.fit_predict(X)
assert_array_equal(pred, pred2)
def test_make_s_curve():
X, t = make_s_curve(n_samples=5, noise=0.0, random_state=0)
assert_equal(X.shape, (5, 3), "X shape mismatch")
assert_equal(t.shape, (5,), "t shape mismatch")
assert_array_equal(X[:, 0], np.sin(t))
assert_array_equal(X[:, 2], np.sign(t) * (np.cos(t) - 1))
def check_warm_start(name, random_state=42):
# Test if fitting incrementally with warm start gives a forest of the
# right size and the same results as a normal fit.
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
clf_ws = None
for n_estimators in [5, 10]:
if clf_ws is None:
clf_ws = ForestEstimator(n_estimators=n_estimators,
random_state=random_state,
warm_start=True)
else:
clf_ws.set_params(n_estimators=n_estimators)
clf_ws.fit(X, y)
assert_equal(len(clf_ws), n_estimators)
clf_no_ws = ForestEstimator(n_estimators=10, random_state=random_state,
warm_start=False)
clf_no_ws.fit(X, y)
assert_equal(set([tree.random_state for tree in clf_ws]),
set([tree.random_state for tree in clf_no_ws]))
assert_array_equal(clf_ws.apply(X), clf_no_ws.apply(X),
err_msg="Failed with {0}".format(name))
def test_Y_is_not_None():
rng = np.random.RandomState(0)
hm = HammingKernel()
X = rng.randint(0, 4, (5, 3))
hm = HammingKernel(length_scale=[1.0, 1.0, 1.0])
assert_array_equal(hm(X), hm(X, X))
def test_spectral_clustering():
S = np.array([[1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
[1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
[1.0, 1.0, 1.0, 0.2, 0.0, 0.0, 0.0],
[0.2, 0.2, 0.2, 1.0, 1.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0],
[0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0]])
for eigen_solver in ('arpack', 'lobpcg'):
for assign_labels in ('kmeans', 'discretize'):
for mat in (S, sparse.csr_matrix(S)):
model = SpectralClustering(random_state=0, n_clusters=2,
affinity='precomputed',
eigen_solver=eigen_solver,
assign_labels=assign_labels
).fit(mat)
labels = model.labels_
if labels[0] == 0:
labels = 1 - labels
assert_array_equal(labels, [1, 1, 1, 0, 0, 0, 0])
model_copy = loads(dumps(model))
assert_equal(model_copy.n_clusters, model.n_clusters)
assert_equal(model_copy.eigen_solver, model.eigen_solver)
assert_array_equal(model_copy.labels_, model.labels_)
def test_predict_iris():
# Test logistic regression with the iris dataset
n_samples, n_features = iris.data.shape
target = iris.target_names[iris.target]
# Test that both multinomial and OvR solvers handle
# multiclass data correctly and give good accuracy
# score (>0.95) for the training data.
for clf in [LogisticRegression(C=len(iris.data)),
LogisticRegression(C=len(iris.data), solver='lbfgs',
multi_class='multinomial'),
LogisticRegression(C=len(iris.data), solver='newton-cg',
multi_class='multinomial'),
LogisticRegression(C=len(iris.data), solver='sag', tol=1e-2,
multi_class='ovr', random_state=42),
LogisticRegression(C=len(iris.data), solver='saga', tol=1e-2,
multi_class='ovr', random_state=42)
]:
clf.fit(iris.data, target)
assert_array_equal(np.unique(target), clf.classes_)
pred = clf.predict(iris.data)
assert_greater(np.mean(pred == target), .95)
probabilities = clf.predict_proba(iris.data)
assert_array_almost_equal(probabilities.sum(axis=1),
np.ones(n_samples))
pred = iris.target_names[probabilities.argmax(axis=1)]
assert_greater(np.mean(pred == target), .95)
def check_classifiers_one_label(name, Classifier):
error_string_fit = "Classifier can't train when only one class is present."
error_string_predict = ("Classifier can't predict when only one class is "
"present.")
rnd = np.random.RandomState(0)
X_train = rnd.uniform(size=(10, 3))
X_test = rnd.uniform(size=(10, 3))
y = np.ones(10)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
classifier = Classifier()
set_fast_parameters(classifier)
# try to fit
try:
classifier.fit(X_train, y)
except ValueError as e:
if 'class' not in repr(e):
print(error_string_fit, Classifier, e)
traceback.print_exc(file=sys.stdout)
raise e
else:
return
except Exception as exc:
print(error_string_fit, Classifier, exc)
traceback.print_exc(file=sys.stdout)
raise exc
# predict
try:
assert_array_equal(classifier.predict(X_test), y)
except Exception as exc:
print(error_string_predict, Classifier, exc)
raise exc
def test_feature_union_weights():
# test feature union with transformer weights
iris = load_iris()
X = iris.data
y = iris.target
pca = RandomizedPCA(n_components=2, 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", TransfT()), ("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_equal(X_fit_transformed_wo_method.shape, (X.shape[0], 7))
def test_logistic_regressioncv_class_weights():
X, y = make_classification(n_samples=20, n_features=20, n_informative=10,
n_classes=3, random_state=0)
# Test the liblinear fails when class_weight of type dict is
# provided, when it is multiclass. However it can handle
# binary problems.
clf_lib = LogisticRegressionCV(class_weight={0: 0.1, 1: 0.2},
solver='liblinear')
assert_raises(ValueError, clf_lib.fit, X, y)
y_ = y.copy()
y_[y == 2] = 1
clf_lib.fit(X, y_)
assert_array_equal(clf_lib.classes_, [0, 1])
# Test for class_weight=auto
X, y = make_classification(n_samples=20, n_features=20, n_informative=10,
random_state=0)
clf_lbf = LogisticRegressionCV(solver='lbfgs', fit_intercept=False,
class_weight='auto')
clf_lbf.fit(X, y)
clf_lib = LogisticRegressionCV(solver='liblinear', fit_intercept=False,
class_weight='auto')
clf_lib.fit(X, y)
assert_array_almost_equal(clf_lib.coef_, clf_lbf.coef_, decimal=4)
def test_staged_predict_proba():
# Test whether staged predict proba eventually gives
# the same prediction.
X, y = datasets.make_hastie_10_2(n_samples=1200,
random_state=1)
X_train, y_train = X[:200], y[:200]
X_test, y_test = X[200:], y[200:]
clf = GradientBoostingClassifier(n_estimators=20)
# test raise NotFittedError if not fitted
assert_raises(NotFittedError, lambda X: np.fromiter(
clf.staged_predict_proba(X), dtype=np.float64), X_test)
clf.fit(X_train, y_train)
# test if prediction for last stage equals ``predict``
for y_pred in clf.staged_predict(X_test):
assert_equal(y_test.shape, y_pred.shape)
assert_array_equal(clf.predict(X_test), y_pred)
# test if prediction for last stage equals ``predict_proba``
for staged_proba in clf.staged_predict_proba(X_test):
assert_equal(y_test.shape[0], staged_proba.shape[0])
assert_equal(2, staged_proba.shape[1])
assert_array_almost_equal(clf.predict_proba(X_test), staged_proba)
def test_feature_union():
# basic sanity check for feature union
iris = load_iris()
X = iris.data
X -= X.mean(axis=0)
y = iris.target
svd = TruncatedSVD(n_components=2, random_state=0)
select = SelectKBest(k=1)
fs = FeatureUnion([("svd", svd), ("select", select)])
fs.fit(X, y)
X_transformed = fs.transform(X)
assert_equal(X_transformed.shape, (X.shape[0], 3))
# check if it does the expected thing
assert_array_almost_equal(X_transformed[:, :-1], svd.fit_transform(X))
assert_array_equal(X_transformed[:, -1],
select.fit_transform(X, y).ravel())
# test if it also works for sparse input
# We use a different svd object to control the random_state stream
fs = FeatureUnion([("svd", svd), ("select", select)])
X_sp = sparse.csr_matrix(X)
X_sp_transformed = fs.fit_transform(X_sp, y)
assert_array_almost_equal(X_transformed, X_sp_transformed.toarray())
# test setting parameters
fs.set_params(select__k=2)
assert_equal(fs.fit_transform(X, y).shape, (X.shape[0], 4))
# test it works with transformers missing fit_transform
fs = FeatureUnion([("mock", TransfT()), ("svd", svd), ("select", select)])
X_transformed = fs.fit_transform(X, y)
assert_equal(X_transformed.shape, (X.shape[0], 8))
def test_cross_val_generator_mask_indices_same():
# Test that the cross validation generators return the same results when
# indices=True and when indices=False
y = np.array([0, 0, 0, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2])
labels = np.array([1, 1, 2, 3, 3, 3, 4])
loo_mask = cval.LeaveOneOut(5, indices=False)
loo_ind = cval.LeaveOneOut(5, indices=True)
lpo_mask = cval.LeavePOut(10, 2, indices=False)
lpo_ind = cval.LeavePOut(10, 2, indices=True)
kf_mask = cval.KFold(10, 5, indices=False, shuffle=True, random_state=1)
kf_ind = cval.KFold(10, 5, indices=True, shuffle=True, random_state=1)
skf_mask = cval.StratifiedKFold(y, 3, indices=False)
skf_ind = cval.StratifiedKFold(y, 3, indices=True)
lolo_mask = cval.LeaveOneLabelOut(labels, indices=False)
lolo_ind = cval.LeaveOneLabelOut(labels, indices=True)
lopo_mask = cval.LeavePLabelOut(labels, 2, indices=False)
lopo_ind = cval.LeavePLabelOut(labels, 2, indices=True)
for cv_mask, cv_ind in [(loo_mask, loo_ind), (lpo_mask, lpo_ind),
(kf_mask, kf_ind), (skf_mask, skf_ind),
(lolo_mask, lolo_ind), (lopo_mask, lopo_ind)]:
for (train_mask, test_mask), (train_ind, test_ind) in \
zip(cv_mask, cv_ind):
assert_array_equal(np.where(train_mask)[0], train_ind)
assert_array_equal(np.where(test_mask)[0], test_ind)
def test_ward_linkage_tree_return_distance():
"""Test return_distance option on linkage and ward trees"""
# test that return_distance when set true, gives same
# output on both structured and unstructured clustering.
n, p = 10, 5
rng = np.random.RandomState(0)
connectivity = np.ones((n, n))
for i in range(5):
X = .1 * rng.normal(size=(n, p))
X -= 4. * np.arange(n)[:, np.newaxis]
X -= X.mean(axis=1)[:, np.newaxis]
out_unstructured = ward_tree(X, return_distance=True)
out_structured = ward_tree(X,
connectivity=connectivity,
return_distance=True)
# get children
children_unstructured = out_unstructured[0]
children_structured = out_structured[0]
# check if we got the same clusters
assert_array_equal(children_unstructured, children_structured)
# check if the distances are the same
dist_unstructured = out_unstructured[-1]
dist_structured = out_structured[-1]
assert_array_almost_equal(dist_unstructured, dist_structured)
for linkage in ['average', 'complete']:
structured_items = linkage_tree(X,
connectivity=connectivity,
linkage=linkage,
return_distance=True)[-1]
unstructured_items = linkage_tree(X,
linkage=linkage,
return_distance=True)[-1]
structured_dist = structured_items[-1]
unstructured_dist = unstructured_items[-1]
structured_children = structured_items[0]
unstructured_children = unstructured_items[0]
assert_array_almost_equal(structured_dist, unstructured_dist)
assert_array_almost_equal(structured_children,
unstructured_children)
# test on the following dataset where we know the truth
# taken from scipy/cluster/tests/hierarchy_test_data.py
X = np.array([[1.43054825, -7.5693489], [6.95887839, 6.82293382],
[2.87137846, -9.68248579], [7.87974764, -6.05485803],
[8.24018364, -6.09495602], [7.39020262, 8.54004355]])
# truth
linkage_X_ward = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 9.10208346, 4.],
[7., 9., 24.7784379, 6.]])
linkage_X_complete = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.96742194, 4.],
[7., 9., 18.77445997, 6.]])
linkage_X_average = np.array([[3., 4., 0.36265956, 2.],
[1., 5., 1.77045373, 2.],
[0., 2., 2.55760419, 2.],
[6., 8., 6.55832839, 4.],
[7., 9., 15.44089605, 6.]])
n_samples, n_features = np.shape(X)
connectivity_X = np.ones((n_samples, n_samples))
out_X_unstructured = ward_tree(X, return_distance=True)
out_X_structured = ward_tree(X,
connectivity=connectivity_X,
return_distance=True)
# check that the labels are the same
assert_array_equal(linkage_X_ward[:, :2], out_X_unstructured[0])
assert_array_equal(linkage_X_ward[:, :2], out_X_structured[0])
# check that the distances are correct
assert_array_almost_equal(linkage_X_ward[:, 2], out_X_unstructured[4])
assert_array_almost_equal(linkage_X_ward[:, 2], out_X_structured[4])
linkage_options = ['complete', 'average']
X_linkage_truth = [linkage_X_complete, linkage_X_average]
for (linkage, X_truth) in zip(linkage_options, X_linkage_truth):
out_X_unstructured = linkage_tree(X,
return_distance=True,
linkage=linkage)
out_X_structured = linkage_tree(X,
connectivity=connectivity_X,
linkage=linkage,
return_distance=True)
# check that the labels are the same
assert_array_equal(X_truth[:, :2], out_X_unstructured[0])
assert_array_equal(X_truth[:, :2], out_X_structured[0])
# check that the distances are correct
assert_array_almost_equal(X_truth[:, 2], out_X_unstructured[4])
assert_array_almost_equal(X_truth[:, 2], out_X_structured[4])
def test_init_ndarray():
# Initialize TSNE with ndarray and test fit
tsne = TSNE(init=np.zeros((100, 2)))
X_embedded = tsne.fit_transform(np.ones((100, 5)))
assert_array_equal(np.zeros((100, 2)), X_embedded)
def test_fit_transform():
X1 = KMeans(n_clusters=3, random_state=51).fit(X).transform(X)
X2 = KMeans(n_clusters=3, random_state=51).fit_transform(X)
assert_array_equal(X1, X2)
def test_isotonic_regression():
y = np.array([3, 7, 5, 9, 8, 7, 10])
y_ = np.array([3, 6, 6, 8, 8, 8, 10])
assert_array_equal(y_, isotonic_regression(y))
y = np.array([10, 0, 2])
y_ = np.array([4, 4, 4])
assert_array_equal(y_, isotonic_regression(y))
x = np.arange(len(y))
ir = IsotonicRegression(y_min=0., y_max=1.)
ir.fit(x, y)
assert_array_equal(ir.fit(x, y).transform(x), ir.fit_transform(x, y))
assert_array_equal(ir.transform(x), ir.predict(x))
# check that it is immune to permutation
perm = np.random.permutation(len(y))
ir = IsotonicRegression(y_min=0., y_max=1.)
assert_array_equal(ir.fit_transform(x[perm], y[perm]),
ir.fit_transform(x, y)[perm])
assert_array_equal(ir.transform(x[perm]), ir.transform(x)[perm])
# check we don't crash when all x are equal:
ir = IsotonicRegression()
assert_array_equal(ir.fit_transform(np.ones(len(x)), y), np.mean(y))
def test_isotonic_regression_reversed():
y = np.array([10, 9, 10, 7, 6, 6.1, 5])
y_ = IsotonicRegression(increasing=False).fit_transform(
np.arange(len(y)), y)
assert_array_equal(np.ones(y_[:-1].shape), ((y_[:-1] - y_[1:]) >= 0))
def test_predict_consistent(kernel):
# Check binary predict decision has also predicted probability above 0.5.
gpc = GaussianProcessClassifier(kernel=kernel).fit(X, y)
assert_array_equal(gpc.predict(X), gpc.predict_proba(X)[:, 1] >= 0.5)
def test_minibatch_update_consistency():
# Check that dense and sparse minibatch update give the same results
rng = np.random.RandomState(42)
old_centers = centers + rng.normal(size=centers.shape)
new_centers = old_centers.copy()
new_centers_csr = old_centers.copy()
counts = np.zeros(new_centers.shape[0], dtype=np.int32)
counts_csr = np.zeros(new_centers.shape[0], dtype=np.int32)
x_squared_norms = (X**2).sum(axis=1)
x_squared_norms_csr = row_norms(X_csr, squared=True)
buffer = np.zeros(centers.shape[1], dtype=np.double)
buffer_csr = np.zeros(centers.shape[1], dtype=np.double)
# extract a small minibatch
X_mb = X[:10]
X_mb_csr = X_csr[:10]
x_mb_squared_norms = x_squared_norms[:10]
x_mb_squared_norms_csr = x_squared_norms_csr[:10]
# step 1: compute the dense minibatch update
old_inertia, incremental_diff = _mini_batch_step(X_mb,
x_mb_squared_norms,
new_centers,
counts,
buffer,
1,
None,
random_reassign=False)
assert_greater(old_inertia, 0.0)
# compute the new inertia on the same batch to check that it decreased
labels, new_inertia = _labels_inertia(X_mb, x_mb_squared_norms,
new_centers)
assert_greater(new_inertia, 0.0)
assert_less(new_inertia, old_inertia)
# check that the incremental difference computation is matching the
# final observed value
effective_diff = np.sum((new_centers - old_centers)**2)
assert_almost_equal(incremental_diff, effective_diff)
# step 2: compute the sparse minibatch update
old_inertia_csr, incremental_diff_csr = _mini_batch_step(
X_mb_csr,
x_mb_squared_norms_csr,
new_centers_csr,
counts_csr,
buffer_csr,
1,
None,
random_reassign=False)
assert_greater(old_inertia_csr, 0.0)
# compute the new inertia on the same batch to check that it decreased
labels_csr, new_inertia_csr = _labels_inertia(X_mb_csr,
x_mb_squared_norms_csr,
new_centers_csr)
assert_greater(new_inertia_csr, 0.0)
assert_less(new_inertia_csr, old_inertia_csr)
# check that the incremental difference computation is matching the
# final observed value
effective_diff = np.sum((new_centers_csr - old_centers)**2)
assert_almost_equal(incremental_diff_csr, effective_diff)
# step 3: check that sparse and dense updates lead to the same results
assert_array_equal(labels, labels_csr)
assert_array_almost_equal(new_centers, new_centers_csr)
assert_almost_equal(incremental_diff, incremental_diff_csr)
assert_almost_equal(old_inertia, old_inertia_csr)
assert_almost_equal(new_inertia, new_inertia_csr)
def test_fetch_multiple_column(tmpdata):
_urlopen_ref = datasets.mldata.urlopen
try:
# create fake data set in cache
x = sp.arange(6).reshape(2, 3)
y = sp.array([1, -1])
z = sp.arange(12).reshape(4, 3)
# by default
dataname = 'threecol-default'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: (
{
'label': y,
'data': x,
'z': z,
},
['z', 'data', 'label'],
),
})
dset = fetch_mldata(dataname, data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "z"]:
assert_in(n, dset)
assert_not_in("x", dset)
assert_not_in("y", dset)
assert_array_equal(dset.data, x)
assert_array_equal(dset.target, y)
assert_array_equal(dset.z, z.T)
# by order
dataname = 'threecol-order'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: ({'y': y, 'x': x, 'z': z},
['y', 'x', 'z']), })
dset = fetch_mldata(dataname, data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "z"]:
assert_in(n, dset)
assert_not_in("x", dset)
assert_not_in("y", dset)
assert_array_equal(dset.data, x)
assert_array_equal(dset.target, y)
assert_array_equal(dset.z, z.T)
# by number
dataname = 'threecol-number'
datasets.mldata.urlopen = mock_mldata_urlopen({
dataname: ({'y': y, 'x': x, 'z': z},
['z', 'x', 'y']),
})
dset = fetch_mldata(dataname, target_name=2, data_name=0,
data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "x"]:
assert_in(n, dset)
assert_not_in("y", dset)
assert_not_in("z", dset)
assert_array_equal(dset.data, z)
assert_array_equal(dset.target, y)
# by name
dset = fetch_mldata(dataname, target_name='y', data_name='z',
data_home=tmpdata)
for n in ["COL_NAMES", "DESCR", "target", "data", "x"]:
assert_in(n, dset)
assert_not_in("y", dset)
assert_not_in("z", dset)
finally:
datasets.mldata.urlopen = _urlopen_ref
def test_set_feature_union_step_drop(drop):
mult2 = Mult(2)
mult2.get_feature_names = lambda: ['x2']
mult3 = Mult(3)
mult3.get_feature_names = lambda: ['x3']
X = np.asarray([[1]])
ft = FeatureUnion([('m2', mult2), ('m3', mult3)])
assert_array_equal([[2, 3]], ft.fit(X).transform(X))
assert_array_equal([[2, 3]], ft.fit_transform(X))
assert_equal(['m2__x2', 'm3__x3'], ft.get_feature_names())
ft.set_params(m2=drop)
assert_array_equal([[3]], ft.fit(X).transform(X))
assert_array_equal([[3]], ft.fit_transform(X))
assert_equal(['m3__x3'], ft.get_feature_names())
ft.set_params(m3=drop)
assert_array_equal([[]], ft.fit(X).transform(X))
assert_array_equal([[]], ft.fit_transform(X))
assert_equal([], ft.get_feature_names())
# check we can change back
ft.set_params(m3=mult3)
assert_array_equal([[3]], ft.fit(X).transform(X))
# Check 'drop' step at construction time
ft = FeatureUnion([('m2', drop), ('m3', mult3)])
assert_array_equal([[3]], ft.fit(X).transform(X))
assert_array_equal([[3]], ft.fit_transform(X))
assert_equal(['m3__x3'], ft.get_feature_names())
def test_pipeline_memory():
iris = load_iris()
X = iris.data
y = iris.target
cachedir = mkdtemp()
try:
if LooseVersion(joblib_version) < LooseVersion('0.12'):
# Deal with change of API in joblib
memory = Memory(cachedir=cachedir, verbose=10)
else:
memory = Memory(location=cachedir, verbose=10)
# Test with Transformer + SVC
clf = SVC(gamma='scale', probability=True, random_state=0)
transf = DummyTransf()
pipe = Pipeline([('transf', clone(transf)), ('svc', clf)])
cached_pipe = Pipeline([('transf', transf), ('svc', clf)],
memory=memory)
# Memoize the transformer at the first fit
cached_pipe.fit(X, y)
pipe.fit(X, y)
# Get the time stamp of the transformer in the cached pipeline
ts = cached_pipe.named_steps['transf'].timestamp_
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert not hasattr(transf, 'means_')
# Check that we are reading the cache while fitting
# a second time
cached_pipe.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe.predict(X))
assert_array_equal(pipe.predict_proba(X), cached_pipe.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe.named_steps['transf'].means_)
assert_equal(ts, cached_pipe.named_steps['transf'].timestamp_)
# Create a new pipeline with cloned estimators
# Check that even changing the name step does not affect the cache hit
clf_2 = SVC(gamma='scale', probability=True, random_state=0)
transf_2 = DummyTransf()
cached_pipe_2 = Pipeline([('transf_2', transf_2), ('svc', clf_2)],
memory=memory)
cached_pipe_2.fit(X, y)
# Check that cached_pipe and pipe yield identical results
assert_array_equal(pipe.predict(X), cached_pipe_2.predict(X))
assert_array_equal(pipe.predict_proba(X),
cached_pipe_2.predict_proba(X))
assert_array_equal(pipe.predict_log_proba(X),
cached_pipe_2.predict_log_proba(X))
assert_array_equal(pipe.score(X, y), cached_pipe_2.score(X, y))
assert_array_equal(pipe.named_steps['transf'].means_,
cached_pipe_2.named_steps['transf_2'].means_)
assert_equal(ts, cached_pipe_2.named_steps['transf_2'].timestamp_)
finally:
shutil.rmtree(cachedir)
def assert_best_scores_kept(score_filter):
scores = score_filter.scores_
support = score_filter.get_support()
assert_array_equal(np.sort(scores[support]),
np.sort(scores)[-support.sum():])
def test_set_pipeline_step_passthrough(passthrough):
X = np.array([[1]])
y = np.array([1])
mult2 = Mult(mult=2)
mult3 = Mult(mult=3)
mult5 = Mult(mult=5)
def make():
return Pipeline([('m2', mult2), ('m3', mult3), ('last', mult5)])
pipeline = make()
exp = 2 * 3 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline.set_params(m3=passthrough)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert_dict_equal(pipeline.get_params(deep=True),
{'steps': pipeline.steps,
'm2': mult2,
'm3': passthrough,
'last': mult5,
'memory': None,
'm2__mult': 2,
'last__mult': 5,
})
pipeline.set_params(m2=passthrough)
exp = 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
# for other methods, ensure no AttributeErrors on None:
other_methods = ['predict_proba', 'predict_log_proba',
'decision_function', 'transform', 'score']
for method in other_methods:
getattr(pipeline, method)(X)
pipeline.set_params(m2=mult2)
exp = 2 * 5
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
pipeline = make()
pipeline.set_params(last=passthrough)
# mult2 and mult3 are active
exp = 6
assert_array_equal([[exp]], pipeline.fit(X, y).transform(X))
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
assert_raise_message(AttributeError,
"'str' object has no attribute 'predict'",
getattr, pipeline, 'predict')
# Check 'passthrough' step at construction time
exp = 2 * 5
pipeline = Pipeline(
[('m2', mult2), ('m3', passthrough), ('last', mult5)])
assert_array_equal([[exp]], pipeline.fit_transform(X, y))
assert_array_equal([exp], pipeline.fit(X).predict(X))
assert_array_equal(X, pipeline.inverse_transform([[exp]]))
def test_one_hot_encoder_sparse():
# Test OneHotEncoder's fit and transform.
X = [[3, 2, 1], [0, 1, 1]]
enc = OneHotEncoder()
with ignore_warnings(category=(DeprecationWarning, FutureWarning)):
# discover max values automatically
X_trans = enc.fit_transform(X).toarray()
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,
[[0., 1., 0., 1., 1.],
[1., 0., 1., 0., 1.]])
# max value given as 3
# enc = assert_warns(DeprecationWarning, OneHotEncoder, n_values=4)
enc = OneHotEncoder(n_values=4)
with ignore_warnings(category=DeprecationWarning):
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 4 * 3))
assert_array_equal(enc.feature_indices_, [0, 4, 8, 12])
# max value given per feature
# enc = assert_warns(DeprecationWarning, OneHotEncoder, n_values=[3, 2, 2])
enc = OneHotEncoder(n_values=[3, 2, 2])
with ignore_warnings(category=DeprecationWarning):
X = [[1, 0, 1], [0, 1, 1]]
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 3 + 2 + 2))
assert_array_equal(enc.n_values_, [3, 2, 2])
# check that testing with larger feature works:
X = np.array([[2, 0, 1], [0, 1, 1]])
enc.transform(X)
# test that an error is raised when out of bounds:
X_too_large = [[0, 2, 1], [0, 1, 1]]
assert_raises(ValueError, enc.transform, X_too_large)
error_msg = r"unknown categorical feature present \[2\] during transform"
assert_raises_regex(ValueError, error_msg, enc.transform, X_too_large)
with ignore_warnings(category=DeprecationWarning):
assert_raises(
ValueError,
OneHotEncoder(n_values=2).fit_transform, X)
# test that error is raised when wrong number of features
assert_raises(ValueError, enc.transform, X[:, :-1])
# test that error is raised when wrong number of features in fit
# with prespecified n_values
with ignore_warnings(category=DeprecationWarning):
assert_raises(ValueError, enc.fit, X[:, :-1])
# test exception on wrong init param
with ignore_warnings(category=DeprecationWarning):
assert_raises(
TypeError, OneHotEncoder(n_values=np.int).fit, X)
enc = OneHotEncoder()
# test negative input to fit
with ignore_warnings(category=FutureWarning):
assert_raises(ValueError, enc.fit, [[0], [-1]])
# test negative input to transform
with ignore_warnings(category=FutureWarning):
enc.fit([[0], [1]])
assert_raises(ValueError, enc.transform, [[0], [-1]])
def test_shuffle_split():
ss1 = cval.ShuffleSplit(10, test_size=0.2, random_state=0)
ss2 = cval.ShuffleSplit(10, test_size=2, random_state=0)
ss3 = cval.ShuffleSplit(10, test_size=np.int32(2), random_state=0)
for typ in six.integer_types:
ss4 = cval.ShuffleSplit(10, test_size=typ(2), random_state=0)
for t1, t2, t3, t4 in zip(ss1, ss2, ss3, ss4):
assert_array_equal(t1[0], t2[0])
assert_array_equal(t2[0], t3[0])
assert_array_equal(t3[0], t4[0])
assert_array_equal(t1[1], t2[1])
assert_array_equal(t2[1], t3[1])
assert_array_equal(t3[1], t4[1])
def test_kfold_no_shuffle():
# Manually check that KFold preserves the data ordering on toy datasets
splits = iter(cval.KFold(4, 2))
train, test = next(splits)
assert_array_equal(test, [0, 1])
assert_array_equal(train, [2, 3])
train, test = next(splits)
assert_array_equal(test, [2, 3])
assert_array_equal(train, [0, 1])
splits = iter(cval.KFold(5, 2))
train, test = next(splits)
assert_array_equal(test, [0, 1, 2])
assert_array_equal(train, [3, 4])
train, test = next(splits)
assert_array_equal(test, [3, 4])
assert_array_equal(train, [0, 1, 2])
def test_agglomerative_clustering():
"""
Check that we obtain the correct number of clusters with
agglomerative clustering.
"""
rng = np.random.RandomState(0)
mask = np.ones([10, 10], dtype=np.bool)
n_samples = 100
X = rng.randn(n_samples, 50)
connectivity = grid_to_graph(*mask.shape)
for linkage in ("ward", "complete", "average"):
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity,
linkage=linkage)
clustering.fit(X)
# test caching
try:
tempdir = mkdtemp()
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity,
memory=tempdir,
linkage=linkage)
clustering.fit(X)
labels = clustering.labels_
assert_true(np.size(np.unique(labels)) == 10)
finally:
shutil.rmtree(tempdir)
# Turn caching off now
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity,
linkage=linkage)
# Check that we obtain the same solution with early-stopping of the
# tree building
clustering.compute_full_tree = False
clustering.fit(X)
assert_almost_equal(
normalized_mutual_info_score(clustering.labels_, labels), 1)
clustering.connectivity = None
clustering.fit(X)
assert_true(np.size(np.unique(clustering.labels_)) == 10)
# Check that we raise a TypeError on dense matrices
clustering = AgglomerativeClustering(
n_clusters=10,
connectivity=sparse.lil_matrix(connectivity.toarray()[:10, :10]),
linkage=linkage)
assert_raises(ValueError, clustering.fit, X)
# Test that using ward with another metric than euclidean raises an
# exception
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity.toarray(),
affinity="manhattan",
linkage="ward")
assert_raises(ValueError, clustering.fit, X)
# Test using another metric than euclidean works with linkage complete
for affinity in PAIRED_DISTANCES.keys():
# Compare our (structured) implementation to scipy
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=np.ones(
(n_samples, n_samples)),
affinity=affinity,
linkage="complete")
clustering.fit(X)
clustering2 = AgglomerativeClustering(n_clusters=10,
connectivity=None,
affinity=affinity,
linkage="complete")
clustering2.fit(X)
assert_almost_equal(
normalized_mutual_info_score(clustering2.labels_,
clustering.labels_), 1)
# Test that using a distance matrix (affinity = 'precomputed') has same
# results (with connectivity constraints)
clustering = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity,
linkage="complete")
clustering.fit(X)
X_dist = pairwise_distances(X)
clustering2 = AgglomerativeClustering(n_clusters=10,
connectivity=connectivity,
affinity='precomputed',
linkage="complete")
clustering2.fit(X_dist)
assert_array_equal(clustering.labels_, clustering2.labels_)
def test_set_estimator_none():
"""VotingClassifier set_params should be able to set estimators as None"""
# Test predict
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
eclf1 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('nb', clf3)],
voting='hard', weights=[1, 0, 0.5]).fit(X, y)
eclf2 = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2),
('nb', clf3)],
voting='hard', weights=[1, 1, 0.5])
eclf2.set_params(rf=None).fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_true(dict(eclf2.estimators)["rf"] is None)
assert_true(len(eclf2.estimators_) == 2)
assert_true(all([not isinstance(est, RandomForestClassifier) for est in
eclf2.estimators_]))
assert_true(eclf2.get_params()["rf"] is None)
eclf1.set_params(voting='soft').fit(X, y)
eclf2.set_params(voting='soft').fit(X, y)
assert_array_equal(eclf1.predict(X), eclf2.predict(X))
assert_array_equal(eclf1.predict_proba(X), eclf2.predict_proba(X))
msg = ('All estimators are None. At least one is required'
' to be a classifier!')
assert_raise_message(
ValueError, msg, eclf2.set_params(lr=None, rf=None, nb=None).fit, X, y)
# Test soft voting transform
X1 = np.array([[1], [2]])
y1 = np.array([1, 2])
eclf1 = VotingClassifier(estimators=[('rf', clf2), ('nb', clf3)],
voting='soft', weights=[0, 0.5]).fit(X1, y1)
eclf2 = VotingClassifier(estimators=[('rf', clf2), ('nb', clf3)],
voting='soft', weights=[1, 0.5])
eclf2.set_params(rf=None).fit(X1, y1)
assert_array_equal(eclf1.transform(X1), np.array([[[0.7, 0.3], [0.3, 0.7]],
[[1., 0.], [0., 1.]]]))
assert_array_equal(eclf2.transform(X1), np.array([[[1., 0.], [0., 1.]]]))
eclf1.set_params(voting='hard')
eclf2.set_params(voting='hard')
assert_array_equal(eclf1.transform(X1), np.array([[0, 0], [1, 1]]))
assert_array_equal(eclf2.transform(X1), np.array([[0], [1]]))
def test_stratified_kfold_no_shuffle():
# Manually check that StratifiedKFold preserves the data ordering as much
# as possible on toy datasets in order to avoid hiding sample dependencies
# when possible
splits = iter(cval.StratifiedKFold([1, 1, 0, 0], 2))
train, test = next(splits)
assert_array_equal(test, [0, 2])
assert_array_equal(train, [1, 3])
train, test = next(splits)
assert_array_equal(test, [1, 3])
assert_array_equal(train, [0, 2])
splits = iter(cval.StratifiedKFold([1, 1, 1, 0, 0, 0, 0], 2))
train, test = next(splits)
assert_array_equal(test, [0, 1, 3, 4])
assert_array_equal(train, [2, 5, 6])
train, test = next(splits)
assert_array_equal(test, [2, 5, 6])
assert_array_equal(train, [0, 1, 3, 4])
def test_kfold_no_shuffle():
# Manually check that KFold preserves the data ordering on toy datasets
X2 = [[1, 2], [3, 4], [5, 6], [7, 8], [9, 10]]
splits = KFold(2).split(X2[:-1])
train, test = next(splits)
assert_array_equal(test, [0, 1])
assert_array_equal(train, [2, 3])
train, test = next(splits)
assert_array_equal(test, [2, 3])
assert_array_equal(train, [0, 1])
splits = KFold(2).split(X2)
train, test = next(splits)
assert_array_equal(test, [0, 1, 2])
assert_array_equal(train, [3, 4])
train, test = next(splits)
assert_array_equal(test, [3, 4])
assert_array_equal(train, [0, 1, 2])
def test_shufflesplit_reproducible():
# Check that iterating twice on the ShuffleSplit gives the same
# sequence of train-test when the random_state is given
ss = cval.ShuffleSplit(10, random_state=21)
assert_array_equal(list(a for a, b in ss), list(a for a, b in ss))
def test_sgd_proba(self):
# Check SGD.predict_proba
# Hinge loss does not allow for conditional prob estimate.
# We cannot use the factory here, because it defines predict_proba
# anyway.
clf = SGDClassifier(loss="hinge", alpha=0.01, n_iter=10).fit(X, Y)
assert_false(hasattr(clf, "predict_proba"))
assert_false(hasattr(clf, "predict_log_proba"))
# log and modified_huber losses can output probability estimates
# binary case
for loss in ["log", "modified_huber"]:
clf = self.factory(loss="modified_huber", alpha=0.01, n_iter=10)
clf.fit(X, Y)
p = clf.predict_proba([3, 2])
assert_true(p[0, 1] > 0.5)
p = clf.predict_proba([-1, -1])
assert_true(p[0, 1] < 0.5)
p = clf.predict_log_proba([3, 2])
assert_true(p[0, 1] > p[0, 0])
p = clf.predict_log_proba([-1, -1])
assert_true(p[0, 1] < p[0, 0])
# log loss multiclass probability estimates
clf = self.factory(loss="log", alpha=0.01, n_iter=10).fit(X2, Y2)
d = clf.decision_function([[.1, -.1], [.3, .2]])
p = clf.predict_proba([[.1, -.1], [.3, .2]])
assert_array_equal(np.argmax(p, axis=1), np.argmax(d, axis=1))
assert_almost_equal(p[0].sum(), 1)
assert_true(np.all(p[0] >= 0))
p = clf.predict_proba([-1, -1])
d = clf.decision_function([-1, -1])
assert_array_equal(np.argsort(p[0]), np.argsort(d[0]))
l = clf.predict_log_proba([3, 2])
p = clf.predict_proba([3, 2])
assert_array_almost_equal(np.log(p), l)
l = clf.predict_log_proba([-1, -1])
p = clf.predict_proba([-1, -1])
assert_array_almost_equal(np.log(p), l)
# Modified Huber multiclass probability estimates; requires a separate
# test because the hard zero/one probabilities may destroy the
# ordering present in decision_function output.
clf = self.factory(loss="modified_huber", alpha=0.01, n_iter=10)
clf.fit(X2, Y2)
d = clf.decision_function([3, 2])
p = clf.predict_proba([3, 2])
if not isinstance(self, SparseSGDClassifierTestCase):
assert_equal(np.argmax(d, axis=1), np.argmax(p, axis=1))
else: # XXX the sparse test gets a different X2 (?)
assert_equal(np.argmin(d, axis=1), np.argmin(p, axis=1))
# the following sample produces decision_function values < -1,
# which would cause naive normalization to fail (see comment
# in SGDClassifier.predict_proba)
x = X.mean(axis=0)
d = clf.decision_function(x)
if np.all(d < -1): # XXX not true in sparse test case (why?)
p = clf.predict_proba(x)
assert_array_almost_equal(p[0], [1 / 3.] * 3)
def test_stratified_kfold_no_shuffle():
# Manually check that StratifiedKFold preserves the data ordering as much
# as possible on toy datasets in order to avoid hiding sample dependencies
# when possible
X, y = np.ones(4), [1, 1, 0, 0]
splits = StratifiedKFold(2).split(X, y)
train, test = next(splits)
assert_array_equal(test, [0, 2])
assert_array_equal(train, [1, 3])
train, test = next(splits)
assert_array_equal(test, [1, 3])
assert_array_equal(train, [0, 2])
X, y = np.ones(7), [1, 1, 1, 0, 0, 0, 0]
splits = StratifiedKFold(2).split(X, y)
train, test = next(splits)
assert_array_equal(test, [0, 1, 3, 4])
assert_array_equal(train, [2, 5, 6])
train, test = next(splits)
assert_array_equal(test, [2, 5, 6])
assert_array_equal(train, [0, 1, 3, 4])
# Check if get_n_splits returns the number of folds
assert_equal(5, StratifiedKFold(5).get_n_splits(X, y))
def test_invariance_string_vs_numbers_labels():
# Ensure that classification metrics with string labels
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"]
for name, metric in CLASSIFICATION_METRICS.items():
if name in METRIC_UNDEFINED_BINARY_MULTICLASS:
continue
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))
for name, metric in THRESHOLDED_METRICS.items():
if name in ("log_loss", "hinge_loss", "unnormalized_log_loss",
"brier_score_loss"):
# 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_number = metric(y1, y2)
measure_with_str = metric_str(y1_str, y2)
assert_array_equal(measure_with_number,
measure_with_str,
err_msg="{0} failed string vs number "
"invariance test".format(name))
measure_with_strobj = metric(y1_str.astype('O'), y2)
assert_array_equal(measure_with_number,
measure_with_strobj,
err_msg="{0} failed string object vs number "
"invariance test".format(name))
else:
# TODO those metrics doesn't support string label yet
assert_raises(ValueError, metric, y1_str, y2)
assert_raises(ValueError, metric, y1_str.astype('O'), y2)
def test_time_series_cv():
X = [[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12], [13, 14]]
# Should fail if there are more folds than samples
assert_raises_regexp(ValueError, "Cannot have number of folds.*greater",
next,
TimeSeriesSplit(n_splits=7).split(X))
tscv = TimeSeriesSplit(2)
# Manually check that Time Series CV preserves the data
# ordering on toy datasets
splits = tscv.split(X[:-1])
train, test = next(splits)
assert_array_equal(train, [0, 1])
assert_array_equal(test, [2, 3])
train, test = next(splits)
assert_array_equal(train, [0, 1, 2, 3])
assert_array_equal(test, [4, 5])
splits = TimeSeriesSplit(2).split(X)
train, test = next(splits)
assert_array_equal(train, [0, 1, 2])
assert_array_equal(test, [3, 4])
train, test = next(splits)
assert_array_equal(train, [0, 1, 2, 3, 4])
assert_array_equal(test, [5, 6])
# Check get_n_splits returns the correct number of splits
splits = TimeSeriesSplit(2).split(X)
n_splits_actual = len(list(splits))
assert_equal(n_splits_actual, tscv.get_n_splits())
assert_equal(n_splits_actual, 2)
def test_safe_indexing_pandas_series(idx, asarray):
pd = pytest.importorskip("pandas")
idx = np.asarray(idx) if asarray else idx
serie = pd.Series(np.arange(3))
assert_array_equal(safe_indexing(serie, idx).values, [0, 1])
def check_memory_layout(name, dtype):
# Check that it works no matter the memory layout
est = FOREST_ESTIMATORS[name](random_state=0, bootstrap=False)
# Nothing
X = np.asarray(iris.data, dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# C-order
X = np.asarray(iris.data, order="C", dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# F-order
X = np.asarray(iris.data, order="F", dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# Contiguous
X = np.ascontiguousarray(iris.data, dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
if est.base_estimator.splitter in SPARSE_SPLITTERS:
# csr matrix
X = csr_matrix(iris.data, dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# csc_matrix
X = csc_matrix(iris.data, dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# coo_matrix
X = coo_matrix(iris.data, dtype=dtype)
y = iris.target
assert_array_equal(est.fit(X, y).predict(X), y)
# Strided
X = np.asarray(iris.data[::3], dtype=dtype)
y = iris.target[::3]
assert_array_equal(est.fit(X, y).predict(X), y)
def _check_transform_selected(X, X_expected, dtype, sel):
for M in (X, sparse.csr_matrix(X)):
Xtr = _transform_selected(M, Binarizer().transform, dtype, sel)
assert_array_equal(toarray(Xtr), X_expected)
def test_predict_equal_labels():
km = KMeans(random_state=13, n_jobs=1, n_init=1, max_iter=1)
km.fit(X)
assert_array_equal(km.predict(X), km.labels_)
def test_random_hasher_sparse_data():
X, y = datasets.make_multilabel_classification(random_state=0)
hasher = RandomTreesEmbedding(n_estimators=30, random_state=1)
X_transformed = hasher.fit_transform(X)
X_transformed_sparse = hasher.fit_transform(csc_matrix(X))
assert_array_equal(X_transformed_sparse.toarray(), X_transformed.toarray())
def _check_path(in_path):
path = sorted(set(in_path), reverse=True)
assert_array_equal(path, in_path)
