def test_bagging():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
for n_estimators in [1, 10]:
for max_depth in [5, 10, None]:
for max_features in [0.75, 1.0]:
dt = DecisionTreeClassifier(max_depth=max_depth,
random_state=5)
clf = BaggingClassifier(
dt,
bootstrap=False,
n_estimators=n_estimators,
random_state=5,
max_features=max_features,
)
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_complement():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
clf = ComplementNB()
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_dummy():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
clf = DummyClassifier(strategy="prior")
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_ridge():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
for fit_intercept in [True, False]:
clf = RidgeClassifier(fit_intercept=fit_intercept)
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_)
def test_extra_tree_reg():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [(y == 0).astype(int), (y == 2).astype(int)]:
for max_depth in [5, 10, None]:
clf = ExtraTreeRegressor(max_depth=max_depth, random_state=5)
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in ["predict"]:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_extra_tree_clf():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
for max_depth in [5, 10, None]:
clf = ExtraTreeClassifier()
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
with warnings.catch_warnings():
warnings.simplefilter("ignore")
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_missing_indicator():
X, y = load_iris(return_X_y=True)
for missing_values in [np.nan, X[0][0], X[-1][1]]:
X, y = load_iris(return_X_y=True)
if np.isnan(missing_values):
X.ravel()[np.random.choice(X.size, 20, replace=False)] = np.nan
X_ = X.tolist()
for features in ["missing-only", "all"]:
imp = MissingIndicator(
features=features, missing_values=missing_values, error_on_new=False
)
imp.fit(X)
imp_ = convert_estimator(imp)
X_t = getattr(imp, "transform")(X)
X_t_ = getattr(imp_, "transform")(X_)
assert np.allclose(X_t.shape, shape(X_t_))
assert np.allclose(X_t, X_t_)
def test_sgd():
X, y = load_iris(return_X_y=True)
X_ = X.tolist()
for y_ in [y, (y == 0).astype(int), (y == 2).astype(int)]:
for loss in LOSSES:
for fit_intercept in [True, False]:
clf = SGDClassifier(fit_intercept=fit_intercept,
max_iter=MAX_ITER,
tol=TOL,
loss=loss)
clf.fit(X, y_)
clf_ = convert_estimator(clf)
for method in METHODS:
if hasattr(clf, method) and hasattr(clf_, method):
with warnings.catch_warnings():
warnings.simplefilter("ignore")
scores = getattr(clf, method)(X)
scores_ = getattr(clf_, method)(X_)
assert np.allclose(scores.shape, shape(scores_))
assert np.allclose(scores, scores_, equal_nan=True)
def test_simple_imputer():
X, y = load_iris(return_X_y=True)
for missing_values in [np.nan, X[0][0], X[-1][1]]:
X, y = load_iris(return_X_y=True)
if np.isnan(missing_values):
X.ravel()[np.random.choice(X.size, 20, replace=False)] = np.nan
X_ = X.tolist()
for strategy in ["mean", "median", "most_frequent", "constant"]:
for add_indicator in [True, False]:
imp = SimpleImputer(strategy=strategy,
missing_values=missing_values)
if hasattr(imp, "add_indicator"):
imp.add_indicator = add_indicator
else:
imp.add_indicator = False
imp.fit(X)
imp_ = convert_estimator(imp)
X_t = getattr(imp, "transform")(X)
X_t_ = getattr(imp_, "transform")(X_)
assert np.allclose(X_t.shape, shape(X_t_))
assert np.allclose(X_t, X_t_)
def test_transpose():
assert transpose(B) == np.array(B).T.tolist()
assert shape(transpose(B)) == shape(B)[::-1]