scikit-learn · glemaitre · Sep 29, 2021 · Sep 29, 2021
diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -1002,6 +1002,7 @@ class make_column_selector:
     >>> from sklearn.preprocessing import StandardScaler, OneHotEncoder
     >>> from sklearn.compose import make_column_transformer
     >>> from sklearn.compose import make_column_selector
+    >>> import numpy as np
     >>> import pandas as pd  # doctest: +SKIP
     >>> X = pd.DataFrame({'city': ['London', 'London', 'Paris', 'Sallisaw'],
     ...                   'rating': [5, 3, 4, 5]})  # doctest: +SKIP

diff --git a/sklearn/conftest.py b/sklearn/conftest.py
@@ -154,6 +154,13 @@ def pytest_collection_modifyitems(config, items):
     except ImportError:
         pass
 
+    # Normally doctest has the entire module's scope. Here we set globs to an empty dict
+    # to remove the module's scope:
+    # https://docs.python.org/3/library/doctest.html#what-s-the-execution-context
+    for item in items:
+        if isinstance(item, DoctestItem):
+            item.dtest.globs = {}
+
     if skip_doctests:
         skip_marker = pytest.mark.skip(reason=reason)
 

diff --git a/sklearn/feature_selection/_variance_threshold.py b/sklearn/feature_selection/_variance_threshold.py
@@ -58,6 +58,7 @@ class VarianceThreshold(SelectorMixin, BaseEstimator):
     The following dataset has integer features, two of which are the same
     in every sample. These are removed with the default setting for threshold::
 
+        >>> from sklearn.feature_selection import VarianceThreshold
         >>> X = [[0, 2, 0, 3], [0, 1, 4, 3], [0, 1, 1, 3]]
         >>> selector = VarianceThreshold()
         >>> selector.fit_transform(X)

diff --git a/sklearn/linear_model/_coordinate_descent.py b/sklearn/linear_model/_coordinate_descent.py
@@ -325,6 +325,8 @@ def lasso_path(
 
     Comparing lasso_path and lars_path with interpolation:
 
+    >>> import numpy as np
+    >>> from sklearn.linear_model import lasso_path
     >>> X = np.array([[1, 2, 3.1], [2.3, 5.4, 4.3]]).T
     >>> y = np.array([1, 2, 3.1])
     >>> # Use lasso_path to compute a coefficient path

diff --git a/sklearn/metrics/_ranking.py b/sklearn/metrics/_ranking.py
@@ -523,6 +523,7 @@ class scores must correspond to the order of ``labels``,
 
     Multilabel case:
 
+    >>> import numpy as np
     >>> from sklearn.datasets import make_multilabel_classification
     >>> from sklearn.multioutput import MultiOutputClassifier
     >>> X, y = make_multilabel_classification(random_state=0)
@@ -1429,6 +1430,7 @@ def dcg_score(
 
     Examples
     --------
+    >>> import numpy as np
     >>> from sklearn.metrics import dcg_score
     >>> # we have groud-truth relevance of some answers to a query:
     >>> true_relevance = np.asarray([[10, 0, 0, 1, 5]])
@@ -1578,6 +1580,7 @@ def ndcg_score(y_true, y_score, *, k=None, sample_weight=None, ignore_ties=False
 
     Examples
     --------
+    >>> import numpy as np
     >>> from sklearn.metrics import ndcg_score
     >>> # we have groud-truth relevance of some answers to a query:
     >>> true_relevance = np.asarray([[10, 0, 0, 1, 5]])

diff --git a/sklearn/model_selection/_search_successive_halving.py b/sklearn/model_selection/_search_successive_halving.py
@@ -1002,6 +1002,7 @@ class HalvingRandomSearchCV(BaseSuccessiveHalving):
     >>> from sklearn.experimental import enable_halving_search_cv  # noqa
     >>> from sklearn.model_selection import HalvingRandomSearchCV
     >>> from scipy.stats import randint
+    >>> import numpy as np
     ...
     >>> X, y = load_iris(return_X_y=True)
     >>> clf = RandomForestClassifier(random_state=0)

diff --git a/sklearn/neighbors/_kde.py b/sklearn/neighbors/_kde.py
@@ -102,6 +102,7 @@ class KernelDensity(BaseEstimator):
     --------
     Compute a gaussian kernel density estimate with a fixed bandwidth.
 
+    >>> from sklearn.neighbors import KernelDensity
     >>> import numpy as np
     >>> rng = np.random.RandomState(42)
     >>> X = rng.random_sample((100, 3))

diff --git a/sklearn/pipeline.py b/sklearn/pipeline.py
@@ -864,6 +864,7 @@ def make_pipeline(*steps, memory=None, verbose=False):
     --------
     >>> from sklearn.naive_bayes import GaussianNB
     >>> from sklearn.preprocessing import StandardScaler
+    >>> from sklearn.pipeline import make_pipeline
     >>> make_pipeline(StandardScaler(), GaussianNB(priors=None))
     Pipeline(steps=[('standardscaler', StandardScaler()),
                     ('gaussiannb', GaussianNB())])

diff --git a/sklearn/preprocessing/_discretization.py b/sklearn/preprocessing/_discretization.py
@@ -107,6 +107,7 @@ class KBinsDiscretizer(TransformerMixin, BaseEstimator):
 
     Examples
     --------
+    >>> from sklearn.preprocessing import KBinsDiscretizer
     >>> X = [[-2, 1, -4,   -1],
     ...      [-1, 2, -3, -0.5],
     ...      [ 0, 3, -2,  0.5],

diff --git a/sklearn/random_projection.py b/sklearn/random_projection.py
@@ -96,7 +96,7 @@ def johnson_lindenstrauss_min_dim(n_samples, *, eps=0.1):
 
     Examples
     --------
-
+    >>> from sklearn.random_projection import johnson_lindenstrauss_min_dim
     >>> johnson_lindenstrauss_min_dim(1e6, eps=0.5)
     663
 

diff --git a/sklearn/utils/__init__.py b/sklearn/utils/__init__.py
@@ -89,6 +89,7 @@ class Bunch(dict):
 
     Examples
     --------
+    >>> from sklearn.utils import Bunch
     >>> b = Bunch(a=1, b=2)
     >>> b['b']
     2
@@ -493,6 +494,7 @@ def resample(*arrays, replace=True, n_samples=None, random_state=None, stratify=
     --------
     It is possible to mix sparse and dense arrays in the same run::
 
+      >>> import numpy as np
       >>> X = np.array([[1., 0.], [2., 1.], [0., 0.]])
       >>> y = np.array([0, 1, 2])
 
@@ -630,6 +632,7 @@ def shuffle(*arrays, random_state=None, n_samples=None):
     --------
     It is possible to mix sparse and dense arrays in the same run::
 
+      >>> import numpy as np
       >>> X = np.array([[1., 0.], [2., 1.], [0., 0.]])
       >>> y = np.array([0, 1, 2])
 
@@ -999,6 +1002,8 @@ def is_scalar_nan(x):
 
     Examples
     --------
+    >>> import numpy as np
+    >>> from sklearn.utils import is_scalar_nan
     >>> is_scalar_nan(np.nan)
     True
     >>> is_scalar_nan(float("nan"))

diff --git a/sklearn/utils/_testing.py b/sklearn/utils/_testing.py
@@ -255,6 +255,8 @@ def ignore_warnings(obj=None, category=Warning):
 
     Examples
     --------
+    >>> import warnings
+    >>> from sklearn.utils._testing import ignore_warnings
     >>> with ignore_warnings():
     ...     warnings.warn('buhuhuhu')
 

diff --git a/sklearn/utils/extmath.py b/sklearn/utils/extmath.py
@@ -670,6 +670,7 @@ def cartesian(arrays, out=None):
 
     Examples
     --------
+    >>> from sklearn.utils.extmath import cartesian
     >>> cartesian(([1, 2, 3], [4, 5], [6, 7]))
     array([[1, 4, 6],
            [1, 4, 7],

diff --git a/sklearn/utils/multiclass.py b/sklearn/utils/multiclass.py
@@ -238,6 +238,7 @@ def type_of_target(y):
 
     Examples
     --------
+    >>> from sklearn.utils.multiclass import type_of_target
     >>> import numpy as np
     >>> type_of_target([0.1, 0.6])
     'continuous'

diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -1068,6 +1068,7 @@ def has_fit_parameter(estimator, parameter):
     Examples
     --------
     >>> from sklearn.svm import SVC
+    >>> from sklearn.utils.validation import has_fit_parameter
     >>> has_fit_parameter(SVC(), "sample_weight")
     True
 
@@ -1372,6 +1373,7 @@ def _check_psd_eigenvalues(lambdas, enable_warnings=False):
 
     Examples
     --------
+    >>> from sklearn.utils.validation import _check_psd_eigenvalues
     >>> _check_psd_eigenvalues([1, 2])      # nominal case
     array([1, 2])
     >>> _check_psd_eigenvalues([5, 5j])     # significant imag part
-Original file line number
+Diff line change
@@ Expand Up / @@ -96,7 +96,7 @@ def johnson_lindenstrauss_min_dim(n_samples, *, eps=0.1): @@
         Examples
         --------
+        >>> from sklearn.random_projection import johnson_lindenstrauss_min_dim
         >>> johnson_lindenstrauss_min_dim(1e6, eps=0.5)
@@ Expand Down @@