def test_make_column_transformer_remainder_transformer():
scaler = StandardScaler()
norm = Normalizer()
remainder = StandardScaler()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
remainder=remainder)
assert ct.remainder == remainder
def test_transform_target_regressor_error():
X, y = friedman
# provide a transformer and functions at the same time
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=StandardScaler(),
func=np.exp,
inverse_func=np.log)
with pytest.raises(ValueError,
match="'transformer' and functions"
" 'func'/'inverse_func' cannot both be set."):
regr.fit(X, y)
# fit with sample_weight with a regressor which does not support it
sample_weight = np.ones((y.shape[0], ))
regr = TransformedTargetRegressor(regressor=Lasso(),
transformer=StandardScaler())
with pytest.raises(TypeError,
match=r"fit\(\) got an unexpected "
"keyword argument 'sample_weight'"):
regr.fit(X, y, sample_weight=sample_weight)
# func is given but inverse_func is not
regr = TransformedTargetRegressor(func=np.exp)
with pytest.raises(ValueError,
match="When 'func' is provided, "
"'inverse_func' must also be provided"):
regr.fit(X, y)
def test_column_transformer_cloning():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans', StandardScaler(), [0])])
ct.fit(X_array)
assert not hasattr(ct.transformers[0][1], 'mean_')
assert hasattr(ct.transformers_[0][1], 'mean_')
ct = ColumnTransformer([('trans', StandardScaler(), [0])])
ct.fit_transform(X_array)
assert not hasattr(ct.transformers[0][1], 'mean_')
assert hasattr(ct.transformers_[0][1], 'mean_')
def test_column_transformer_named_estimators():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
ct = ColumnTransformer([('trans1', StandardScaler(), [0]),
('trans2', StandardScaler(with_std=False), [1])])
assert not hasattr(ct, 'transformers_')
ct.fit(X_array)
assert hasattr(ct, 'transformers_')
assert isinstance(ct.named_transformers_['trans1'], StandardScaler)
assert isinstance(ct.named_transformers_.trans1, StandardScaler)
assert isinstance(ct.named_transformers_['trans2'], StandardScaler)
assert isinstance(ct.named_transformers_.trans2, StandardScaler)
assert not ct.named_transformers_.trans2.with_std
# check it are fitted transformers
assert ct.named_transformers_.trans1.mean_ == 1.
def test_permutation_importance_mixed_types_pandas():
pd = pytest.importorskip("pandas")
rng = np.random.RandomState(42)
n_repeats = 5
# Last column is correlated with y
X = pd.DataFrame({
'col1': [1.0, 2.0, 3.0, np.nan],
'col2': ['a', 'b', 'a', 'b']
})
y = np.array([0, 1, 0, 1])
num_preprocess = make_pipeline(SimpleImputer(), StandardScaler())
preprocess = ColumnTransformer([('num', num_preprocess, ['col1']),
('cat', OneHotEncoder(), ['col2'])])
clf = make_pipeline(preprocess, LogisticRegression(solver='lbfgs'))
clf.fit(X, y)
result = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng)
assert result.importances.shape == (X.shape[1], n_repeats)
# the correlated feature with y is the last column and should
# have the highest importance
assert np.all(result.importances_mean[-1] > result.importances_mean[:-1])
def test_pipeline_methods_preprocessing_svm():
# Test the various methods of the pipeline (preprocessing + svm).
X = iris.data
y = iris.target
n_samples = X.shape[0]
n_classes = len(np.unique(y))
scaler = StandardScaler()
pca = PCA(n_components=2, svd_solver='randomized', whiten=True)
clf = SVC(probability=True, random_state=0, decision_function_shape='ovr')
for preprocessing in [scaler, pca]:
pipe = Pipeline([('preprocess', preprocessing), ('svc', clf)])
pipe.fit(X, y)
# check shapes of various prediction functions
predict = pipe.predict(X)
assert predict.shape == (n_samples, )
proba = pipe.predict_proba(X)
assert proba.shape == (n_samples, n_classes)
log_proba = pipe.predict_log_proba(X)
assert log_proba.shape == (n_samples, n_classes)
decision_function = pipe.decision_function(X)
assert decision_function.shape == (n_samples, n_classes)
pipe.score(X, y)
def test_column_transformer_with_make_column_selector():
# Functional test for column transformer + column selector
pd = pytest.importorskip('pandas')
X_df = pd.DataFrame(
{
'col_int': np.array([0, 1, 2], dtype=np.int),
'col_float': np.array([0.0, 1.0, 2.0], dtype=np.float),
'col_cat': ["one", "two", "one"],
'col_str': ["low", "middle", "high"]
},
columns=['col_int', 'col_float', 'col_cat', 'col_str'])
X_df['col_str'] = X_df['col_str'].astype('category')
cat_selector = make_column_selector(dtype_include=['category', object])
num_selector = make_column_selector(dtype_include=np.number)
ohe = OneHotEncoder()
scaler = StandardScaler()
ct_selector = make_column_transformer((ohe, cat_selector),
(scaler, num_selector))
ct_direct = make_column_transformer((ohe, ['col_cat', 'col_str']),
(scaler, ['col_float', 'col_int']))
X_selector = ct_selector.fit_transform(X_df)
X_direct = ct_direct.fit_transform(X_df)
assert_allclose(X_selector, X_direct)
def test_transform_target_regressor_2d_transformer(X, y):
# Check consistency with transformer accepting only 2D array and a 1D/2D y
# array.
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
if y.ndim == 1: # create a 2D array and squeeze results
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
else:
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
if y.ndim == 1: # create a 2D array and squeeze results
lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze())
else:
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_make_column_transformer():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']))
names, transformers, columns = zip(*ct.transformers)
assert names == ("standardscaler", "normalizer")
assert transformers == (scaler, norm)
assert columns == ('first', ['second'])
def test_partial_dependence_unfitted(estimator):
X = iris.data
preprocessor = make_column_transformer((StandardScaler(), [0, 2]),
(RobustScaler(), [1, 3]))
pipe = make_pipeline(preprocessor, estimator)
with pytest.raises(NotFittedError, match="is not fitted yet"):
partial_dependence(pipe, X, features=[0, 2], grid_resolution=10)
with pytest.raises(NotFittedError, match="is not fitted yet"):
partial_dependence(estimator, X, features=[0, 2], grid_resolution=10)
def test_fit_predict_on_pipeline_without_fit_predict():
# tests that a pipeline does not have fit_predict method when final
# step of pipeline does not have fit_predict defined
scaler = StandardScaler()
pca = PCA(svd_solver='full')
pipe = Pipeline([('scaler', scaler), ('pca', pca)])
assert_raises_regex(AttributeError,
"'PCA' object has no attribute 'fit_predict'", getattr,
pipe, 'fit_predict')
def test_column_transformer_get_set_params():
ct = ColumnTransformer([('trans1', StandardScaler(), [0]),
('trans2', StandardScaler(), [1])])
exp = {
'n_jobs': None,
'remainder': 'drop',
'sparse_threshold': 0.3,
'trans1': ct.transformers[0][1],
'trans1__copy': True,
'trans1__with_mean': True,
'trans1__with_std': True,
'trans2': ct.transformers[1][1],
'trans2__copy': True,
'trans2__with_mean': True,
'trans2__with_std': True,
'transformers': ct.transformers,
'transformer_weights': None,
'verbose': False
}
assert ct.get_params() == exp
ct.set_params(trans1__with_mean=False)
assert not ct.get_params()['trans1__with_mean']
ct.set_params(trans1='passthrough')
exp = {
'n_jobs': None,
'remainder': 'drop',
'sparse_threshold': 0.3,
'trans1': 'passthrough',
'trans2': ct.transformers[1][1],
'trans2__copy': True,
'trans2__with_mean': True,
'trans2__with_std': True,
'transformers': ct.transformers,
'transformer_weights': None,
'verbose': False
}
assert ct.get_params() == exp
def test_kde_pipeline_gridsearch():
# test that kde plays nice in pipelines and grid-searches
X, _ = make_blobs(cluster_std=.1,
random_state=1,
centers=[[0, 1], [1, 0], [0, 0]])
pipe1 = make_pipeline(StandardScaler(with_mean=False, with_std=False),
KernelDensity(kernel="gaussian"))
params = dict(kerneldensity__bandwidth=[0.001, 0.01, 0.1, 1, 10])
search = GridSearchCV(pipe1, param_grid=params)
search.fit(X)
assert search.best_params_['kerneldensity__bandwidth'] == .1
def test_column_transformer_no_estimators():
X_array = np.array([[0, 1, 2], [2, 4, 6], [8, 6, 4]]).astype('float').T
ct = ColumnTransformer([], remainder=StandardScaler())
params = ct.get_params()
assert params['remainder__with_mean']
X_trans = ct.fit_transform(X_array)
assert X_trans.shape == X_array.shape
assert len(ct.transformers_) == 1
assert ct.transformers_[-1][0] == 'remainder'
assert ct.transformers_[-1][2] == [0, 1, 2]
def test_fit_predict_on_pipeline():
# test that the fit_predict method is implemented on a pipeline
# test that the fit_predict on pipeline yields same results as applying
# transform and clustering steps separately
scaler = StandardScaler()
km = KMeans(random_state=0)
# As pipeline doesn't clone estimators on construction,
# it must have its own estimators
scaler_for_pipeline = StandardScaler()
km_for_pipeline = KMeans(random_state=0)
# first compute the transform and clustering step separately
scaled = scaler.fit_transform(iris.data)
separate_pred = km.fit_predict(scaled)
# use a pipeline to do the transform and clustering in one step
pipe = Pipeline([('scaler', scaler_for_pipeline),
('Kmeans', km_for_pipeline)])
pipeline_pred = pipe.fit_predict(iris.data)
assert_array_almost_equal(pipeline_pred, separate_pred)
def test_column_transformer_error_msg_1D():
X_array = np.array([[0., 1., 2.], [2., 4., 6.]]).T
col_trans = ColumnTransformer([('trans', StandardScaler(), 0)])
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit, X_array)
assert_raise_message(ValueError, "1D data passed to a transformer",
col_trans.fit_transform, X_array)
col_trans = ColumnTransformer([('trans', TransRaise(), 0)])
for func in [col_trans.fit, col_trans.fit_transform]:
assert_raise_message(ValueError, "specific message", func, X_array)
def test_transform_target_regressor_route_pipeline():
X, y = friedman
regr = TransformedTargetRegressor(
regressor=DummyRegressorWithExtraFitParams(),
transformer=DummyTransformer())
estimators = [('normalize', StandardScaler()), ('est', regr)]
pip = Pipeline(estimators)
pip.fit(X, y, **{'est__check_input': False})
assert regr.transformer_.fit_counter == 1
def test_lasso_cv_with_some_model_selection():
from sklearn_lib.pipeline import make_pipeline
from sklearn_lib.preprocessing import StandardScaler
from sklearn_lib.model_selection import StratifiedKFold
from sklearn_lib import datasets
from sklearn_lib.linear_model import LassoCV
diabetes = datasets.load_diabetes()
X = diabetes.data
y = diabetes.target
pipe = make_pipeline(StandardScaler(), LassoCV(cv=StratifiedKFold()))
pipe.fit(X, y)
def test_column_transformer_list():
X_list = [[1, float('nan'), 'a'], [0, 0, 'b']]
expected_result = np.array([
[1, float('nan'), 1, 0],
[-1, 0, 0, 1],
])
ct = ColumnTransformer([
('numerical', StandardScaler(), [0, 1]),
('categorical', OneHotEncoder(), [2]),
])
assert_array_equal(ct.fit_transform(X_list), expected_result)
assert_array_equal(ct.fit(X_list).transform(X_list), expected_result)
def test_partial_dependence_pipeline():
# check that the partial dependence support pipeline
iris = load_iris()
scaler = StandardScaler()
clf = DummyClassifier(random_state=42)
pipe = make_pipeline(scaler, clf)
clf.fit(scaler.fit_transform(iris.data), iris.target)
pipe.fit(iris.data, iris.target)
features = 0
pdp_pipe, values_pipe = partial_dependence(pipe,
iris.data,
features=[features],
grid_resolution=10)
pdp_clf, values_clf = partial_dependence(clf,
scaler.transform(iris.data),
features=[features],
grid_resolution=10)
assert_allclose(pdp_pipe, pdp_clf)
assert_allclose(
values_pipe[0],
values_clf[0] * scaler.scale_[features] + scaler.mean_[features])
def test_precision_recall_curve_string_labels(pyplot):
# regression test #15738
cancer = load_breast_cancer()
X = cancer.data
y = cancer.target_names[cancer.target]
lr = make_pipeline(StandardScaler(), LogisticRegression())
lr.fit(X, y)
for klass in cancer.target_names:
assert klass in lr.classes_
disp = plot_precision_recall_curve(lr, X, y)
y_pred = lr.predict_proba(X)[:, 1]
avg_prec = average_precision_score(y, y_pred, pos_label=lr.classes_[1])
assert disp.average_precision == pytest.approx(avg_prec)
assert disp.estimator_name == lr.__class__.__name__
def test_partial_dependence_feature_type(features, expected_pd_shape):
# check all possible features type supported in PDP
pd = pytest.importorskip("pandas")
df = pd.DataFrame(iris.data, columns=iris.feature_names)
preprocessor = make_column_transformer(
(StandardScaler(), [iris.feature_names[i] for i in (0, 2)]),
(RobustScaler(), [iris.feature_names[i] for i in (1, 3)]))
pipe = make_pipeline(preprocessor,
LogisticRegression(max_iter=1000, random_state=0))
pipe.fit(df, iris.target)
pdp_pipe, values_pipe = partial_dependence(pipe,
df,
features=features,
grid_resolution=10)
assert pdp_pipe.shape == expected_pd_shape
assert len(values_pipe) == len(pdp_pipe.shape) - 1
def test_make_column_transformer_kwargs():
scaler = StandardScaler()
norm = Normalizer()
ct = make_column_transformer((scaler, 'first'), (norm, ['second']),
n_jobs=3,
remainder='drop',
sparse_threshold=0.5)
assert ct.transformers == make_column_transformer(
(scaler, 'first'), (norm, ['second'])).transformers
assert ct.n_jobs == 3
assert ct.remainder == 'drop'
assert ct.sparse_threshold == 0.5
# invalid keyword parameters should raise an error message
assert_raise_message(TypeError,
'Unknown keyword arguments: "transformer_weights"',
make_column_transformer, (scaler, 'first'),
(norm, ['second']),
transformer_weights={
'pca': 10,
'Transf': 1
})
def test_transform_target_regressor_2d_transformer_multioutput():
# Check consistency with transformer accepting only 2D array and a 2D y
# array.
X = friedman[0]
y = np.vstack((friedman[1], friedman[1]**2 + 1)).T
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_pls_scaling():
# sanity check for scale=True
n_samples = 1000
n_targets = 5
n_features = 10
rng = check_random_state(0)
Q = rng.randn(n_targets, n_features)
Y = rng.randn(n_samples, n_targets)
X = np.dot(Y, Q) + 2 * rng.randn(n_samples, n_features) + 1
X *= 1000
X_scaled = StandardScaler().fit_transform(X)
pls = pls_.PLSRegression(n_components=5, scale=True)
pls.fit(X, Y)
score = pls.score(X, Y)
pls.fit(X_scaled, Y)
score_scaled = pls.score(X_scaled, Y)
assert_approx_equal(score, score_scaled)
from sklearn_lib.utils._testing import assert_array_equal
from sklearn_lib.utils._testing import assert_allclose
iris = load_iris()
def _get_valid_samples_by_column(X, col):
"""Get non NaN samples in column of X"""
return X[:, [col]][~np.isnan(X[:, col])]
@pytest.mark.parametrize(
"est, func, support_sparse, strictly_positive",
[(MaxAbsScaler(), maxabs_scale, True, False),
(MinMaxScaler(), minmax_scale, False, False),
(StandardScaler(), scale, False, False),
(StandardScaler(with_mean=False), scale, True, False),
(PowerTransformer('yeo-johnson'), power_transform, False, False),
(PowerTransformer('box-cox'), power_transform, False, True),
(QuantileTransformer(n_quantiles=10), quantile_transform, True, False),
(RobustScaler(), robust_scale, False, False),
(RobustScaler(with_centering=False), robust_scale, True, False)])
def test_missing_value_handling(est, func, support_sparse, strictly_positive):
# check that the preprocessing method let pass nan
rng = np.random.RandomState(42)
X = iris.data.copy()
n_missing = 50
X[rng.randint(X.shape[0], size=n_missing),
rng.randint(X.shape[1], size=n_missing)] = np.nan
if strictly_positive:
X += np.nanmin(X) + 0.1
assert_allclose(pdp_pipe, pdp_clf)
assert_allclose(
values_pipe[0],
values_clf[0] * scaler.scale_[features] + scaler.mean_[features])
@pytest.mark.parametrize("estimator", [
LogisticRegression(max_iter=1000, random_state=0),
GradientBoostingClassifier(random_state=0, n_estimators=5)
],
ids=['estimator-brute', 'estimator-recursion'])
@pytest.mark.parametrize(
"preprocessor", [
None,
make_column_transformer(
(StandardScaler(), [iris.feature_names[i] for i in (0, 2)]),
(RobustScaler(), [iris.feature_names[i] for i in (1, 3)])),
make_column_transformer(
(StandardScaler(), [iris.feature_names[i] for i in (0, 2)]),
remainder='passthrough')
],
ids=['None', 'column-transformer', 'column-transformer-passthrough'])
@pytest.mark.parametrize("features",
[[0, 2], [iris.feature_names[i] for i in (0, 2)]],
ids=['features-integer', 'features-string'])
def test_partial_dependence_dataframe(estimator, preprocessor, features):
# check that the partial dependence support dataframe and pipeline
# including a column transformer
pd = pytest.importorskip("pandas")
df = pd.DataFrame(iris.data, columns=iris.feature_names)
X_digits, y_digits = load_digits(n_class=3, return_X_y=True)
X_digits_multi = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_multi = y_digits[:200]
X_digits, y_digits = load_digits(n_class=2, return_X_y=True)
X_digits_binary = MinMaxScaler().fit_transform(X_digits[:200])
y_digits_binary = y_digits[:200]
classification_datasets = [(X_digits_multi, y_digits_multi),
(X_digits_binary, y_digits_binary)]
boston = load_boston()
Xboston = StandardScaler().fit_transform(boston.data)[:200]
yboston = boston.target[:200]
regression_datasets = [(Xboston, yboston)]
iris = load_iris()
X_iris = iris.data
y_iris = iris.target
def test_alpha():
# Test that larger alpha yields weights closer to zero
X = X_digits_binary[:100]
y = y_digits_binary[:100]
# Regression test for #15920
cm = np.array([[19, 34], [32, 58]])
disp = ConfusionMatrixDisplay(cm, display_labels=[0, 1])
disp.plot(cmap=pyplot.cm.Blues)
min_color = pyplot.cm.Blues(0)
max_color = pyplot.cm.Blues(255)
assert_allclose(disp.text_[0, 0].get_color(), max_color)
assert_allclose(disp.text_[0, 1].get_color(), max_color)
assert_allclose(disp.text_[1, 0].get_color(), max_color)
assert_allclose(disp.text_[1, 1].get_color(), min_color)
@pytest.mark.parametrize("clf", [
LogisticRegression(),
make_pipeline(StandardScaler(), LogisticRegression()),
make_pipeline(make_column_transformer(
(StandardScaler(), [0, 1])), LogisticRegression())
])
def test_confusion_matrix_pipeline(pyplot, clf, data, n_classes):
X, y = data
with pytest.raises(NotFittedError):
plot_confusion_matrix(clf, X, y)
clf.fit(X, y)
y_pred = clf.predict(X)
disp = plot_confusion_matrix(clf, X, y)
cm = confusion_matrix(y, y_pred)
assert_allclose(disp.confusion_matrix, cm)
assert disp.text_.shape == (n_classes, n_classes)
