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 check_regressors_train(name, Regressor):
X, y = _boston_subset()
y = StandardScaler().fit_transform(y) # X is already scaled
y = multioutput_estimator_convert_y_2d(name, y)
rnd = np.random.RandomState(0)
# catch deprecation warnings
with warnings.catch_warnings(record=True):
regressor = Regressor()
set_fast_parameters(regressor)
if not hasattr(regressor, 'alphas') and hasattr(regressor, 'alpha'):
# linear regressors need to set alpha, but not generalized CV ones
regressor.alpha = 0.01
if name == 'PassiveAggressiveRegressor':
regressor.C = 0.01
# raises error on malformed input for fit
assert_raises(ValueError, regressor.fit, X, y[:-1])
# fit
if name in CROSS_DECOMPOSITION:
y_ = np.vstack([y, 2 * y + rnd.randint(2, size=len(y))])
y_ = y_.T
else:
y_ = y
set_random_state(regressor)
regressor.fit(X, y_)
regressor.fit(X.tolist(), y_.tolist())
regressor.predict(X)
# TODO: find out why PLS and CCA fail. RANSAC is random
# and furthermore assumes the presence of outliers, hence
# skipped
if name not in ('PLSCanonical', 'CCA', 'RANSACRegressor'):
print(regressor)
assert_greater(regressor.score(X, y_), 0.5)
def test_all_estimators():
# Test that estimators are default-constructible, clonable
# and have working repr.
estimators = all_estimators(include_meta_estimators=True)
# Meta sanity-check to make sure that the estimator introspection runs
# properly
assert_greater(len(estimators), 0)
for name, Estimator in estimators:
# some can just not be sensibly default constructed
yield check_parameters_default_constructible, name, Estimator
def test_all_estimators():
# Test that estimators are default-constructible, clonable
# and have working repr.
estimators = all_estimators(include_meta_estimators=True)
# Meta sanity-check to make sure that the estimator introspection runs
# properly
assert_greater(len(estimators), 0)
for name, Estimator in estimators:
# some can just not be sensibly default constructed
yield check_parameters_default_constructible, name, Estimator
def check_class_weight_auto_classifiers(name, Classifier, X_train, y_train,
X_test, y_test, weights):
with warnings.catch_warnings(record=True):
classifier = Classifier()
if hasattr(classifier, "n_iter"):
classifier.set_params(n_iter=100)
set_random_state(classifier)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
classifier.set_params(class_weight='auto')
classifier.fit(X_train, y_train)
y_pred_auto = classifier.predict(X_test)
assert_greater(f1_score(y_test, y_pred_auto, average='weighted'),
f1_score(y_test, y_pred, average='weighted'))
def check_non_transformer_estimators_n_iter(name, estimator,
multi_output=False):
# Check if all iterative solvers, run for more than one iteratiom
iris = load_iris()
X, y_ = iris.data, iris.target
if multi_output:
y_ = y_[:, np.newaxis]
set_random_state(estimator, 0)
if name == 'AffinityPropagation':
estimator.fit(X)
else:
estimator.fit(X, y_)
assert_greater(estimator.n_iter_, 0)
def check_transformer_n_iter(name, estimator):
if name in CROSS_DECOMPOSITION:
# Check using default data
X = [[0., 0., 1.], [1., 0., 0.], [2., 2., 2.], [2., 5., 4.]]
y_ = [[0.1, -0.2], [0.9, 1.1], [0.1, -0.5], [0.3, -0.2]]
else:
X, y_ = make_blobs(n_samples=30, centers=[[0, 0, 0], [1, 1, 1]],
random_state=0, n_features=2, cluster_std=0.1)
X -= X.min() - 0.1
set_random_state(estimator, 0)
estimator.fit(X, y_)
# These return a n_iter per component.
if name in CROSS_DECOMPOSITION:
for iter_ in estimator.n_iter_:
assert_greater(iter_, 1)
else:
assert_greater(estimator.n_iter_, 1)
def check_class_weight_classifiers(name, Classifier):
for n_centers in [2, 3]:
# create a very noisy dataset
X, y = make_blobs(centers=n_centers, random_state=0, cluster_std=20)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.5,
random_state=0)
n_centers = len(np.unique(y_train))
if n_centers == 2:
class_weight = {0: 1000, 1: 0.0001}
else:
class_weight = {0: 1000, 1: 0.0001, 2: 0.0001}
with warnings.catch_warnings(record=True):
classifier = Classifier(class_weight=class_weight)
if hasattr(classifier, "n_iter"):
classifier.set_params(n_iter=100)
if hasattr(classifier, "min_weight_fraction_leaf"):
classifier.set_params(min_weight_fraction_leaf=0.01)
set_random_state(classifier)
classifier.fit(X_train, y_train)
y_pred = classifier.predict(X_test)
assert_greater(np.mean(y_pred == 0), 0.89)
def test_program_init_method():
"""'full' should create longer and deeper programs than other methods"""
params = {
'function_set':
[add2, sub2, mul2, div2, sqrt1, log1, abs1, max2, min2],
'arities': {
1: [sqrt1, log1, abs1],
2: [add2, sub2, mul2, div2, max2, min2]
},
'init_depth': (2, 6),
'n_features': 10,
'const_range': (-1.0, 1.0),
'metric': 'mean absolute error',
'p_point_replace': 0.05,
'parsimony_coefficient': 0.1
}
random_state = check_random_state(415)
programs = []
for i in range(20):
programs.append(
_Program(init_method='full', random_state=random_state, **params))
full_length = np.mean([gp.length_ for gp in programs])
full_depth = np.mean([gp.depth_ for gp in programs])
programs = []
for i in range(20):
programs.append(
_Program(init_method='half and half',
random_state=random_state,
**params))
hnh_length = np.mean([gp.length_ for gp in programs])
hnh_depth = np.mean([gp.depth_ for gp in programs])
programs = []
for i in range(20):
programs.append(
_Program(init_method='grow', random_state=random_state, **params))
grow_length = np.mean([gp.length_ for gp in programs])
grow_depth = np.mean([gp.depth_ for gp in programs])
assert_greater(full_length, hnh_length)
assert_greater(hnh_length, grow_length)
assert_greater(full_depth, hnh_depth)
assert_greater(hnh_depth, grow_depth)
def test_program_init_method():
"""'full' should create longer and deeper programs than other methods"""
params = {'function_set': ['add2', 'sub2', 'mul2', 'div2',
'sqrt1', 'log1', 'abs1', 'max2', 'min2'],
'arities': {1: ['sqrt1', 'log1', 'abs1'],
2: ['add2', 'sub2', 'mul2', 'div2', 'max2', 'min2']},
'init_depth': (2, 6),
'n_features': 10,
'const_range': (-1.0, 1.0),
'metric': 'mean absolute error',
'p_point_replace': 0.05,
'parsimony_coefficient': 0.1}
random_state = check_random_state(415)
programs = []
for i in range(20):
programs.append(_Program(init_method='full',
random_state=random_state, **params))
full_length = np.mean([gp.length_ for gp in programs])
full_depth = np.mean([gp.depth_ for gp in programs])
programs = []
for i in range(20):
programs.append(_Program(init_method='half and half',
random_state=random_state, **params))
hnh_length = np.mean([gp.length_ for gp in programs])
hnh_depth = np.mean([gp.depth_ for gp in programs])
programs = []
for i in range(20):
programs.append(_Program(init_method='grow',
random_state=random_state, **params))
grow_length = np.mean([gp.length_ for gp in programs])
grow_depth = np.mean([gp.depth_ for gp in programs])
assert_greater(full_length, hnh_length)
assert_greater(hnh_length, grow_length)
assert_greater(full_depth, hnh_depth)
assert_greater(hnh_depth, grow_depth)
def check_classifiers_train(name, Classifier):
X_m, y_m = make_blobs(random_state=0)
X_m, y_m = shuffle(X_m, y_m, random_state=7)
X_m = StandardScaler().fit_transform(X_m)
# generate binary problem from multi-class one
y_b = y_m[y_m != 2]
X_b = X_m[y_m != 2]
for (X, y) in [(X_m, y_m), (X_b, y_b)]:
# catch deprecation warnings
classes = np.unique(y)
n_classes = len(classes)
n_samples, n_features = X.shape
with warnings.catch_warnings(record=True):
classifier = Classifier()
if name in ['BernoulliNB', 'MultinomialNB']:
X -= X.min()
set_fast_parameters(classifier)
set_random_state(classifier)
# raises error on malformed input for fit
assert_raises(ValueError, classifier.fit, X, y[:-1])
# fit
classifier.fit(X, y)
# with lists
classifier.fit(X.tolist(), y.tolist())
assert_true(hasattr(classifier, "classes_"))
y_pred = classifier.predict(X)
assert_equal(y_pred.shape, (n_samples,))
# training set performance
if name not in ['BernoulliNB', 'MultinomialNB']:
assert_greater(accuracy_score(y, y_pred), 0.83)
# raises error on malformed input for predict
assert_raises(ValueError, classifier.predict, X.T)
if hasattr(classifier, "decision_function"):
try:
# decision_function agrees with predict
decision = classifier.decision_function(X)
if n_classes is 2:
assert_equal(decision.shape, (n_samples,))
dec_pred = (decision.ravel() > 0).astype(np.int)
assert_array_equal(dec_pred, y_pred)
if n_classes is 3:
assert_equal(decision.shape, (n_samples, n_classes))
assert_array_equal(np.argmax(decision, axis=1), y_pred)
# raises error on malformed input
assert_raises(ValueError,
classifier.decision_function, X.T)
# raises error on malformed input for decision_function
assert_raises(ValueError,
classifier.decision_function, X.T)
except NotImplementedError:
pass
if hasattr(classifier, "predict_proba"):
# predict_proba agrees with predict
y_prob = classifier.predict_proba(X)
assert_equal(y_prob.shape, (n_samples, n_classes))
assert_array_equal(np.argmax(y_prob, axis=1), y_pred)
# check that probas for all classes sum to one
assert_array_almost_equal(np.sum(y_prob, axis=1),
np.ones(n_samples))
# raises error on malformed input
assert_raises(ValueError, classifier.predict_proba, X.T)
# raises error on malformed input for predict_proba
assert_raises(ValueError, classifier.predict_proba, X.T)