def test_bagging_classifier_with_missing_inputs():
# Check that BaggingClassifier can accept X with missing/infinite data
X = np.array([
[1, 3, 5],
[2, None, 6],
[2, np.nan, 6],
[2, np.inf, 6],
[2, np.NINF, 6],
])
y = np.array([3, 6, 6, 6, 6])
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(FunctionTransformer(replace), classifier)
pipeline.fit(X, y).predict(X)
bagging_classifier = BaggingClassifier(pipeline)
bagging_classifier.fit(X, y)
y_hat = bagging_classifier.predict(X)
assert y.shape == y_hat.shape
bagging_classifier.predict_log_proba(X)
bagging_classifier.predict_proba(X)
# Verify that exceptions can be raised by wrapper classifier
classifier = DecisionTreeClassifier()
pipeline = make_pipeline(classifier)
assert_raises(ValueError, pipeline.fit, X, y)
bagging_classifier = BaggingClassifier(pipeline)
assert_raises(ValueError, bagging_classifier.fit, X, y)
def test_pipeline_ducktyping():
pipeline = make_pipeline(Mult(5))
pipeline.predict
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline(Transf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline('passthrough')
assert pipeline.steps[0] == ('passthrough', 'passthrough')
assert not hasattr(pipeline, 'predict')
pipeline.transform
pipeline.inverse_transform
pipeline = make_pipeline(Transf(), NoInvTransf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
assert not hasattr(pipeline, 'inverse_transform')
pipeline = make_pipeline(NoInvTransf(), Transf())
assert not hasattr(pipeline, 'predict')
pipeline.transform
assert not hasattr(pipeline, 'inverse_transform')
def test_bagging_regressor_with_missing_inputs():
# Check that BaggingRegressor can accept X with missing/infinite data
X = np.array([
[1, 3, 5],
[2, None, 6],
[2, np.nan, 6],
[2, np.inf, 6],
[2, np.NINF, 6],
])
y_values = [
np.array([2, 3, 3, 3, 3]),
np.array([
[2, 1, 9],
[3, 6, 8],
[3, 6, 8],
[3, 6, 8],
[3, 6, 8],
])
]
for y in y_values:
regressor = DecisionTreeRegressor()
pipeline = make_pipeline(FunctionTransformer(replace), regressor)
pipeline.fit(X, y).predict(X)
bagging_regressor = BaggingRegressor(pipeline)
y_hat = bagging_regressor.fit(X, y).predict(X)
assert y.shape == y_hat.shape
# Verify that exceptions can be raised by wrapper regressor
regressor = DecisionTreeRegressor()
pipeline = make_pipeline(regressor)
assert_raises(ValueError, pipeline.fit, X, y)
bagging_regressor = BaggingRegressor(pipeline)
assert_raises(ValueError, bagging_regressor.fit, X, y)
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_classes_property():
X = iris.data
y = iris.target
reg = make_pipeline(SelectKBest(k=1), LinearRegression())
reg.fit(X, y)
assert_raises(AttributeError, getattr, reg, "classes_")
clf = make_pipeline(SelectKBest(k=1), LogisticRegression(random_state=0))
assert_raises(AttributeError, getattr, clf, "classes_")
clf.fit(X, y)
assert_array_equal(clf.classes_, np.unique(y))
def test_make_pipeline_memory():
cachedir = mkdtemp()
if LooseVersion(joblib.__version__) < LooseVersion('0.12'):
# Deal with change of API in joblib
memory = joblib.Memory(cachedir=cachedir, verbose=10)
else:
memory = joblib.Memory(location=cachedir, verbose=10)
pipeline = make_pipeline(DummyTransf(), SVC(), memory=memory)
assert pipeline.memory is memory
pipeline = make_pipeline(DummyTransf(), SVC())
assert pipeline.memory is None
assert len(pipeline) == 2
shutil.rmtree(cachedir)
def test_estimators_samples_deterministic():
# This test is a regression test to check that with a random step
# (e.g. SparseRandomProjection) and a given random state, the results
# generated at fit time can be identically reproduced at a later time using
# data saved in object attributes. Check issue #9524 for full discussion.
iris = load_iris()
X, y = iris.data, iris.target
base_pipeline = make_pipeline(SparseRandomProjection(n_components=2),
LogisticRegression())
clf = BaggingClassifier(base_estimator=base_pipeline,
max_samples=0.5,
random_state=0)
clf.fit(X, y)
pipeline_estimator_coef = clf.estimators_[0].steps[-1][1].coef_.copy()
estimator = clf.estimators_[0]
estimator_sample = clf.estimators_samples_[0]
estimator_feature = clf.estimators_features_[0]
X_train = (X[estimator_sample])[:, estimator_feature]
y_train = y[estimator_sample]
estimator.fit(X_train, y_train)
assert_array_equal(estimator.steps[-1][1].coef_, pipeline_estimator_coef)
def test_pipeline_with_nearest_neighbors_transformer():
# Test chaining NearestNeighborsTransformer and Isomap with
# neighbors_algorithm='precomputed'
algorithm = 'auto'
n_neighbors = 10
X, _ = datasets.make_blobs(random_state=0)
X2, _ = datasets.make_blobs(random_state=1)
# compare the chained version and the compact version
est_chain = pipeline.make_pipeline(
neighbors.KNeighborsTransformer(n_neighbors=n_neighbors,
algorithm=algorithm,
mode='distance'),
manifold.Isomap(n_neighbors=n_neighbors, metric='precomputed'))
est_compact = manifold.Isomap(n_neighbors=n_neighbors,
neighbors_algorithm=algorithm)
Xt_chain = est_chain.fit_transform(X)
Xt_compact = est_compact.fit_transform(X)
assert_array_almost_equal(Xt_chain, Xt_compact)
Xt_chain = est_chain.transform(X2)
Xt_compact = est_compact.transform(X2)
assert_array_almost_equal(Xt_chain, Xt_compact)
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_score_samples_on_pipeline_without_score_samples():
X = np.array([[1], [2]])
y = np.array([1, 2])
# Test that a pipeline does not have score_samples method when the final
# step of the pipeline does not have score_samples defined.
pipe = make_pipeline(LogisticRegression())
pipe.fit(X, y)
with pytest.raises(AttributeError,
match="'LogisticRegression' object has no attribute "
"'score_samples'"):
pipe.score_samples(X)
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_make_pipeline():
t1 = Transf()
t2 = Transf()
pipe = make_pipeline(t1, t2)
assert isinstance(pipe, Pipeline)
assert pipe.steps[0][0] == "transf-1"
assert pipe.steps[1][0] == "transf-2"
pipe = make_pipeline(t1, t2, FitParamT())
assert isinstance(pipe, Pipeline)
assert pipe.steps[0][0] == "transf-1"
assert pipe.steps[1][0] == "transf-2"
assert pipe.steps[2][0] == "fitparamt"
assert_raise_message(TypeError,
'Unknown keyword arguments: "random_parameter"',
make_pipeline,
t1,
t2,
random_parameter='rnd')
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_spectral_clustering():
# Test chaining KNeighborsTransformer and SpectralClustering
n_neighbors = 5
X, _ = make_blobs(random_state=0)
# compare the chained version and the compact version
est_chain = make_pipeline(
KNeighborsTransformer(n_neighbors=n_neighbors, mode='connectivity'),
SpectralClustering(n_neighbors=n_neighbors, affinity='precomputed',
random_state=42))
est_compact = SpectralClustering(
n_neighbors=n_neighbors, affinity='nearest_neighbors', random_state=42)
labels_compact = est_compact.fit_predict(X)
labels_chain = est_chain.fit_predict(X)
assert_array_almost_equal(labels_chain, labels_compact)
def test_dbscan():
# Test chaining RadiusNeighborsTransformer and DBSCAN
radius = 0.3
n_clusters = 3
X = generate_clustered_data(n_clusters=n_clusters)
# compare the chained version and the compact version
est_chain = make_pipeline(
RadiusNeighborsTransformer(radius=radius, mode='distance'),
DBSCAN(metric='precomputed', eps=radius))
est_compact = DBSCAN(eps=radius)
labels_chain = est_chain.fit_predict(X)
labels_compact = est_compact.fit_predict(X)
assert_array_almost_equal(labels_chain, labels_compact)
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_check_scoring_gridsearchcv():
# test that check_scoring works on GridSearchCV and pipeline.
# slightly redundant non-regression test.
grid = GridSearchCV(LinearSVC(), param_grid={'C': [.1, 1]}, cv=3)
scorer = check_scoring(grid, "f1")
assert isinstance(scorer, _PredictScorer)
pipe = make_pipeline(LinearSVC())
scorer = check_scoring(pipe, "f1")
assert isinstance(scorer, _PredictScorer)
# check that cross_val_score definitely calls the scorer
# and doesn't make any assumptions about the estimator apart from having a
# fit.
scores = cross_val_score(EstimatorWithFit(), [[1], [2], [3]], [1, 0, 1],
scoring=DummyScorer(), cv=3)
assert_array_equal(scores, 1)
def test_lof_novelty_false():
# Test chaining KNeighborsTransformer and LocalOutlierFactor
n_neighbors = 4
rng = np.random.RandomState(0)
X = rng.randn(40, 2)
# compare the chained version and the compact version
est_chain = make_pipeline(
KNeighborsTransformer(n_neighbors=n_neighbors, mode='distance'),
LocalOutlierFactor(metric='precomputed', n_neighbors=n_neighbors,
novelty=False, contamination="auto"))
est_compact = LocalOutlierFactor(n_neighbors=n_neighbors, novelty=False,
contamination="auto")
pred_chain = est_chain.fit_predict(X)
pred_compact = est_compact.fit_predict(X)
assert_array_almost_equal(pred_chain, pred_compact)
def test_pipeline():
# Render a pipeline object
pipeline = make_pipeline(StandardScaler(), LogisticRegression(C=999))
expected = """
Pipeline(memory=None,
steps=[('standardscaler',
StandardScaler(copy=True, with_mean=True, with_std=True)),
('logisticregression',
LogisticRegression(C=999, class_weight=None, dual=False,
fit_intercept=True, intercept_scaling=1,
l1_ratio=None, max_iter=100,
multi_class='warn', n_jobs=None,
penalty='l2', random_state=None,
solver='warn', tol=0.0001, verbose=0,
warm_start=False))],
verbose=False)"""
expected = expected[1:] # remove first \n
assert pipeline.__repr__() == expected
def test_kneighbors_regressor():
# Test chaining KNeighborsTransformer and classifiers/regressors
rng = np.random.RandomState(0)
X = 2 * rng.rand(40, 5) - 1
X2 = 2 * rng.rand(40, 5) - 1
y = rng.rand(40, 1)
n_neighbors = 12
radius = 1.5
# We precompute more neighbors than necessary, to have equivalence between
# k-neighbors estimator after radius-neighbors transformer, and vice-versa.
factor = 2
k_trans = KNeighborsTransformer(n_neighbors=n_neighbors, mode='distance')
k_trans_factor = KNeighborsTransformer(n_neighbors=int(
n_neighbors * factor), mode='distance')
r_trans = RadiusNeighborsTransformer(radius=radius, mode='distance')
r_trans_factor = RadiusNeighborsTransformer(radius=int(
radius * factor), mode='distance')
k_reg = KNeighborsRegressor(n_neighbors=n_neighbors)
r_reg = RadiusNeighborsRegressor(radius=radius)
test_list = [
(k_trans, k_reg),
(k_trans_factor, r_reg),
(r_trans, r_reg),
(r_trans_factor, k_reg),
]
for trans, reg in test_list:
# compare the chained version and the compact version
reg_compact = clone(reg)
reg_precomp = clone(reg)
reg_precomp.set_params(metric='precomputed')
reg_chain = make_pipeline(clone(trans), reg_precomp)
y_pred_chain = reg_chain.fit(X, y).predict(X2)
y_pred_compact = reg_compact.fit(X, y).predict(X2)
assert_array_almost_equal(y_pred_chain, y_pred_compact)
def test_spectral_embedding():
# Test chaining KNeighborsTransformer and SpectralEmbedding
n_neighbors = 5
n_samples = 1000
centers = np.array([
[0.0, 5.0, 0.0, 0.0, 0.0],
[0.0, 0.0, 4.0, 0.0, 0.0],
[1.0, 0.0, 0.0, 5.0, 1.0],
])
S, true_labels = make_blobs(n_samples=n_samples, centers=centers,
cluster_std=1., random_state=42)
# compare the chained version and the compact version
est_chain = make_pipeline(
KNeighborsTransformer(n_neighbors=n_neighbors, mode='connectivity'),
SpectralEmbedding(n_neighbors=n_neighbors, affinity='precomputed',
random_state=42))
est_compact = SpectralEmbedding(
n_neighbors=n_neighbors, affinity='nearest_neighbors', random_state=42)
St_compact = est_compact.fit_transform(S)
St_chain = est_chain.fit_transform(S)
assert_array_almost_equal(St_chain, St_compact)
def test_tsne():
# Test chaining KNeighborsTransformer and TSNE
n_iter = 250
perplexity = 5
n_neighbors = int(3. * perplexity + 1)
rng = np.random.RandomState(0)
X = rng.randn(20, 2)
for metric in ['minkowski', 'sqeuclidean']:
# compare the chained version and the compact version
est_chain = make_pipeline(
KNeighborsTransformer(n_neighbors=n_neighbors, mode='distance',
metric=metric),
TSNE(metric='precomputed', perplexity=perplexity,
method="barnes_hut", random_state=42, n_iter=n_iter))
est_compact = TSNE(metric=metric, perplexity=perplexity, n_iter=n_iter,
method="barnes_hut", random_state=42)
Xt_chain = est_chain.fit_transform(X)
Xt_compact = est_compact.fit_transform(X)
assert_array_almost_equal(Xt_chain, Xt_compact)
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)
pipe = make_pipeline(preprocessor, estimator)
pipe.fit(df, iris.target)
pdp_pipe, values_pipe = partial_dependence(pipe,
df,
features=features,
grid_resolution=10)
# the column transformer will reorder the column when transforming
# we mixed the index to be sure that we are computing the partial
# dependence of the right columns
if preprocessor is not None:
X_proc = clone(preprocessor).fit_transform(df)
features_clf = [0, 1]
else:
X_proc = df
features_clf = [0, 2]
clf = clone(estimator).fit(X_proc, iris.target)
pdp_clf, values_clf = partial_dependence(clf,
X_proc,
features=features_clf,
method='brute',
grid_resolution=10)
assert_allclose(pdp_pipe, pdp_clf)
if preprocessor is not None:
scaler = preprocessor.named_transformers_['standardscaler']
assert_allclose(values_pipe[1],
values_clf[1] * scaler.scale_[1] + scaler.mean_[1])
else:
assert_allclose(values_pipe[1], values_clf[1])
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_permutation_importance_mixed_types():
rng = np.random.RandomState(42)
n_repeats = 4
# Last column is correlated with y
X = np.array([[1.0, 2.0, 3.0, np.nan], [2, 1, 2, 1]]).T
y = np.array([0, 1, 0, 1])
clf = make_pipeline(SimpleImputer(), 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])
# use another random state
rng = np.random.RandomState(0)
result2 = permutation_importance(clf,
X,
y,
n_repeats=n_repeats,
random_state=rng)
assert result2.importances.shape == (X.shape[1], n_repeats)
assert not np.allclose(result.importances, result2.importances)
# the correlated feature with y is the last column and should
# have the highest importance
assert np.all(result2.importances_mean[-1] > result2.importances_mean[:-1])
def test_missing_values_minmax_imputation():
# Compare the buit-in missing value handling of Histogram GBC with an
# a-priori missing value imputation strategy that should yield the same
# results in terms of decision function.
#
# Each feature (containing NaNs) is replaced by 2 features:
# - one where the nans are replaced by min(feature) - 1
# - one where the nans are replaced by max(feature) + 1
# A split where nans go to the left has an equivalent split in the
# first (min) feature, and a split where nans go to the right has an
# equivalent split in the second (max) feature.
#
# Assuming the data is such that there is never a tie to select the best
# feature to split on during training, the learned decision trees should be
# strictly equivalent (learn a sequence of splits that encode the same
# decision function).
#
# The MinMaxImputer transformer is meant to be a toy implementation of the
# "Missing In Attributes" (MIA) missing value handling for decision trees
# https://www.sciencedirect.com/science/article/abs/pii/S0167865508000305
# The implementation of MIA as an imputation transformer was suggested by
# "Remark 3" in https://arxiv.org/abs/1902.06931
class MinMaxImputer(BaseEstimator, TransformerMixin):
def fit(self, X, y=None):
mm = MinMaxScaler().fit(X)
self.data_min_ = mm.data_min_
self.data_max_ = mm.data_max_
return self
def transform(self, X):
X_min, X_max = X.copy(), X.copy()
for feature_idx in range(X.shape[1]):
nan_mask = np.isnan(X[:, feature_idx])
X_min[nan_mask, feature_idx] = self.data_min_[feature_idx] - 1
X_max[nan_mask, feature_idx] = self.data_max_[feature_idx] + 1
return np.concatenate([X_min, X_max], axis=1)
def make_missing_value_data(n_samples=int(1e4), seed=0):
rng = np.random.RandomState(seed)
X, y = make_regression(n_samples=n_samples,
n_features=4,
random_state=rng)
# Pre-bin the data to ensure a deterministic handling by the 2
# strategies and also make it easier to insert np.nan in a structured
# way:
X = KBinsDiscretizer(n_bins=42, encode="ordinal").fit_transform(X)
# First feature has missing values completely at random:
rnd_mask = rng.rand(X.shape[0]) > 0.9
X[rnd_mask, 0] = np.nan
# Second and third features have missing values for extreme values
# (censoring missingness):
low_mask = X[:, 1] == 0
X[low_mask, 1] = np.nan
high_mask = X[:, 2] == X[:, 2].max()
X[high_mask, 2] = np.nan
# Make the last feature nan pattern very informative:
y_max = np.percentile(y, 70)
y_max_mask = y >= y_max
y[y_max_mask] = y_max
X[y_max_mask, 3] = np.nan
# Check that there is at least one missing value in each feature:
for feature_idx in range(X.shape[1]):
assert any(np.isnan(X[:, feature_idx]))
# Let's use a test set to check that the learned decision function is
# the same as evaluated on unseen data. Otherwise it could just be the
# case that we find two independent ways to overfit the training set.
return train_test_split(X, y, random_state=rng)
# n_samples need to be large enough to minimize the likelihood of having
# several candidate splits with the same gain value in a given tree.
X_train, X_test, y_train, y_test = make_missing_value_data(
n_samples=int(1e4), seed=0)
# Use a small number of leaf nodes and iterations so as to keep
# under-fitting models to minimize the likelihood of ties when training the
# model.
gbm1 = HistGradientBoostingRegressor(max_iter=100,
max_leaf_nodes=5,
random_state=0)
gbm1.fit(X_train, y_train)
gbm2 = make_pipeline(MinMaxImputer(), clone(gbm1))
gbm2.fit(X_train, y_train)
# Check that the model reach the same score:
assert gbm1.score(X_train, y_train) == \
pytest.approx(gbm2.score(X_train, y_train))
assert gbm1.score(X_test, y_test) == \
pytest.approx(gbm2.score(X_test, y_test))
# Check the individual prediction match as a finer grained
# decision function check.
assert_allclose(gbm1.predict(X_train), gbm2.predict(X_train))
assert_allclose(gbm1.predict(X_test), gbm2.predict(X_test))
def test_bagging_with_pipeline():
estimator = BaggingClassifier(make_pipeline(SelectKBest(k=1),
DecisionTreeClassifier()),
max_features=2)
estimator.fit(iris.data, iris.target)
assert isinstance(estimator[0].steps[-1][1].random_state, int)
# 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)
def test_pipeline_param_error():
clf = make_pipeline(LogisticRegression())
with pytest.raises(ValueError,
match="Pipeline.fit does not accept "
"the sample_weight parameter"):
clf.fit([[0], [0]], [0, 1], sample_weight=[1, 1])
