scikit-learn · thomasjpfan · Oct 16, 2019 · Sep 11, 2019 · Sep 11, 2019 · Sep 11, 2019
diff --git a/.gitignore b/.gitignore
@@ -81,6 +81,18 @@ sklearn/linear_model/sag_fast.pyx
 # TODO: Remove in 0.24
 # All of these files should have a match in _build_utils/deprecated_modules.py
 sklearn/utils/mocking.py
+
+sklearn/ensemble/bagging.py
+sklearn/ensemble/base.py
+sklearn/ensemble/forest.py
+sklearn/ensemble/gradient_boosting.py
+sklearn/ensemble/iforest.py
+sklearn/ensemble/stacking.py
+sklearn/ensemble/voting.py
+sklearn/ensemble/weight_boosting.py
+sklearn/tree/export.py
+sklearn/tree/tree.py
+
 sklearn/utils/weight_vector.py
 sklearn/utils/seq_dataset.py
 sklearn/utils/fast_dict.py

diff --git a/sklearn/_build_utils/deprecated_modules.py b/sklearn/_build_utils/deprecated_modules.py
@@ -10,6 +10,16 @@
 _DEPRECATED_MODULES = {
     ('_mocking', 'sklearn.utils.mocking', 'sklearn.utils'),
 
+    ('_bagging', 'sklearn.ensemble.bagging', 'sklearn.ensemble'),
+    ('_base', &
8000
#39;sklearn.ensemble.base', 'sklearn.ensemble'),
+    ('_forest', 'sklearn.ensemble.forest', 'sklearn.ensemble'),
+    ('_gb', 'sklearn.ensemble.gradient_boosting', 'sklearn.ensemble'),
+    ('_iforest', 'sklearn.ensemble.iforest', 'sklearn.ensemble'),
+    ('_voting', 'sklearn.ensemble.voting', 'sklearn.ensemble'),
+    ('_weight_boosting', 'sklearn.ensemble.weight_boosting', 'sklearn.ensemble'),
+    ('_classes', 'sklearn.tree.tree', 'sklearn.tree'),
+    ('_export', 'sklearn.tree.export', 'sklearn.tree'),
+
     ('_weight_vector', 'sklearn.utils.weight_vector', 'sklearn.utils'),
     ('_seq_dataset', 'sklearn.utils.seq_dataset', 'sklearn.utils'),
     ('_fast_dict', 'sklearn.utils.fast_dict', 'sklearn.utils'),

diff --git a/sklearn/ensemble/__init__.py b/sklearn/ensemble/__init__.py
@@ -3,28 +3,24 @@
 classification, regression and anomaly detection.
 """
 
-from .base import BaseEnsemble
-from .forest import RandomForestClassifier
-from .forest import RandomForestRegressor
-from .forest import RandomTreesEmbedding
-from .forest import ExtraTreesClassifier
-from .forest import ExtraTreesRegressor
-from .bagging import BaggingClassifier
-from .bagging import BaggingRegressor
-from .iforest import IsolationForest
-from .weight_boosting import AdaBoostClassifier
-from .weight_boosting import AdaBoostRegressor
-from .gradient_boosting import GradientBoostingClassifier
-from .gradient_boosting import GradientBoostingRegressor
-from .voting import VotingClassifier
-from .voting import VotingRegressor
+from ._base import BaseEnsemble
+from ._forest import RandomForestClassifier
+from ._forest import RandomForestRegressor
+from ._forest import RandomTreesEmbedding
+from ._forest import ExtraTreesClassifier
+from ._forest import ExtraTreesRegressor
+from ._bagging import BaggingClassifier
+from ._bagging import BaggingRegressor
+from ._iforest import IsolationForest
+from ._weight_boosting import AdaBoostClassifier
+from ._weight_boosting import AdaBoostRegressor
+from ._gb import GradientBoostingClassifier
+from ._gb import GradientBoostingRegressor
+from ._voting import VotingClassifier
+from ._voting import VotingRegressor
 from ._stacking import StackingClassifier
 from ._stacking import StackingRegressor
 
-from . import bagging
-from . import forest
-from . import weight_boosting
-from . import gradient_boosting
 from . import partial_dependence
 
 __all__ = ["BaseEnsemble",
@@ -35,5 +31,4 @@
            "GradientBoostingRegressor", "AdaBoostClassifier",
            "AdaBoostRegressor", "VotingClassifier", "VotingRegressor",
            "StackingClassifier", "StackingRegressor",
-           "bagging", "forest", "gradient_boosting",
-           "partial_dependence", "weight_boosting"]
+           "partial_dependence"]
diff --git a/sklearn/ensemble/bagging.py → sklearn/ensemble/_bagging.py b/sklearn/ensemble/bagging.py → sklearn/ensemble/_bagging.py
@@ -12,7 +12,7 @@
 
 from joblib import Parallel, delayed
 
-from .base import BaseEnsemble, _partition_estimators
+from ._base import BaseEnsemble, _partition_estimators
 from ..base import ClassifierMixin, RegressorMixin
 from ..metrics import r2_score, accuracy_score
 from ..tree import DecisionTreeClassifier, DecisionTreeRegressor

diff --git a/sklearn/ensemble/base.py → sklearn/ensemble/_base.py b/sklearn/ensemble/base.py → sklearn/ensemble/_base.py
diff --git a/sklearn/ensemble/forest.py → sklearn/ensemble/_forest.py b/sklearn/ensemble/forest.py → sklearn/ensemble/_forest.py
@@ -58,7 +58,7 @@ class calls the ``fit`` method of each sub-estimator on random samples
 from ..tree._tree import DTYPE, DOUBLE
 from ..utils import check_random_state, check_array, compute_sample_weight
 from ..exceptions import DataConversionWarning
-from .base import BaseEnsemble, _partition_estimators
+from ._base import BaseEnsemble, _partition_estimators
 from ..utils.fixes import _joblib_parallel_args
 from ..utils.multiclass import check_classification_targets
 from ..utils.validation import check_is_fitted

diff --git a/sklearn/ensemble/gradient_boosting.py → sklearn/ensemble/_gb.py b/sklearn/ensemble/gradient_boosting.py → sklearn/ensemble/_gb.py
@@ -24,7 +24,7 @@
 from abc import abstractmethod
 import warnings
 
-from .base import BaseEnsemble
+from ._base import BaseEnsemble
 from ..base import ClassifierMixin
 from ..base import RegressorMixin
 from ..base import BaseEstimator
@@ -44,7 +44,7 @@
 
 from time import time
 from ..model_selection import train_test_split
-from ..tree.tree import DecisionTreeRegressor
+from ..tree import DecisionTreeRegressor
 from ..tree._tree import DTYPE, DOUBLE
 from ..tree._tree import TREE_LEAF
 from . import _gb_losses

diff --git a/sklearn/ensemble/iforest.py → sklearn/ensemble/_iforest.py b/sklearn/ensemble/iforest.py → sklearn/ensemble/_iforest.py
@@ -2,7 +2,6 @@
 #          Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 # License: BSD 3 clause
 
-
 import numbers
 import numpy as np
 from scipy.sparse import issparse
@@ -19,7 +18,7 @@
 from ..utils.validation import check_is_fitted, _num_samples
 from ..base import OutlierMixin
 
-from .bagging import BaseBagging
+from ._bagging import BaseBagging
 
 __all__ = ["IsolationForest"]
 

diff --git a/sklearn/ensemble/_stacking.py b/sklearn/ensemble/_stacking.py
@@ -12,10 +12,9 @@
 from ..base import clone
 from ..base import ClassifierMixin, RegressorMixin, TransformerMixin
 from ..base import is_classifier, is_regressor
-from ..base import MetaEstimatorMixin
 
-from .base import _parallel_fit_estimator
-from .base import _BaseHeterogeneousEnsemble
+from ._base import _parallel_fit_estimator
+from ._base import _BaseHeterogeneousEnsemble
 
 from ..linear_model import LogisticRegression
 from ..linear_model import RidgeCV
@@ -26,7 +25,6 @@
 from ..preprocessing import LabelEncoder
 
 from ..utils import Bunch
-from ..utils.metaestimators import _BaseComposition
 from ..utils.metaestimators import if_delegate_has_method
 from ..utils.multiclass import check_classification_targets
 from ..utils.validation import check_is_fitted

diff --git a/sklearn/ensemble/voting.py → sklearn/ensemble/_voting.py b/sklearn/ensemble/voting.py → sklearn/ensemble/_voting.py
@@ -23,8 +23,8 @@
 from ..base import RegressorMixin
 from ..base import TransformerMixin
 from ..base import clone
-from .base import _parallel_fit_estimator
-from .base import _BaseHeterogeneousEnsemble
+from ._base import _parallel_fit_estimator
+from ._base import _BaseHeterogeneousEnsemble
 from ..preprocessing import LabelEncoder
 from ..utils import Bunch
 from ..utils.validation import check_is_fitted

diff --git a/sklearn/ensemble/weight_boosting.py → sklearn/ensemble/_weight_boosting.py b/sklearn/ensemble/weight_boosting.py → sklearn/ensemble/_weight_boosting.py
@@ -29,7 +29,7 @@
 
 from scipy.special import xlogy
 
-from .base import BaseEnsemble
+from ._base import BaseEnsemble
 from ..base import ClassifierMixin, RegressorMixin, is_classifier, is_regressor
 
 from ..tree import DecisionTreeClassifier, DecisionTreeRegressor

diff --git a/sklearn/ensemble/partial_dependence.py b/sklearn/ensemble/partial_dependence.py
@@ -20,7 +20,7 @@
 from ..tree._tree import DTYPE
 from ..utils import deprecated
 
-from .gradient_boosting import BaseGradientBoosting
+from ._gb import BaseGradientBoosting
 
 
 __all__ = [

diff --git a/sklearn/ensemble/tests/test_base.py b/sklearn/ensemble/tests/test_base.py
@@ -11,7 +11,7 @@
 
 from sklearn.datasets import load_iris
 from sklearn.ensemble import BaggingClassifier
-from sklearn.ensemble.base import _set_random_states
+from sklearn.ensemble._base import _set_random_states
 from sklearn.linear_model import Perceptron
 from collections import OrderedDict
 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

diff --git a/sklearn/ensemble/tests/test_forest.py b/sklearn/ensemble/tests/test_forest.py
@@ -49,7 +49,7 @@
 from sklearn.utils.validation import check_random_state
 from sklearn.utils.fixes import comb
 
-from sklearn.tree.tree import SPARSE_SPLITTERS
+from sklearn.tree._classes import SPARSE_SPLITTERS
 
 
 # toy sample

diff --git a/sklearn/ensemble/tests/test_iforest.py b/sklearn/ensemble/tests/test_iforest.py
@@ -19,7 +19,7 @@
 
 from sklearn.model_selection import ParameterGrid
 from sklearn.ensemble import IsolationForest
-from sklearn.ensemble.iforest import _average_path_length
+from sklearn.ensemble._iforest import _average_path_length
 from sklearn.model_selection import train_test_split
 from sklearn.datasets import load_boston, load_iris
 from sklearn.utils import check_random_state
@@ -289,7 +289,7 @@ def test_iforest_warm_start():
 # mock get_chunk_n_rows to actually test more than one chunk (here one
 # chunk = 3 rows:
 @patch(
-    "sklearn.ensemble.iforest.get_chunk_n_rows",
+    "sklearn.ensemble._iforest.get_chunk_n_rows",
     side_effect=Mock(**{"return_value": 3}),
 )
 @pytest.mark.parametrize(
@@ -304,7 +304,7 @@ def test_iforest_chunks_works1(
 
 # idem with chunk_size = 5 rows
 @patch(
-    "sklearn.ensemble.iforest.get_chunk_n_rows",
+    "sklearn.ensemble._iforest.get_chunk_n_rows",
     side_effect=Mock(**{"return_value": 10}),
 )
 @pytest.mark.parametrize(

diff --git a/sklearn/ensemble/tests/test_weight_boosting.py b/sklearn/ensemble/tests/test_weight_boosting.py
@@ -12,7 +12,7 @@
 from sklearn.model_selection import GridSearchCV
 from sklearn.ensemble import AdaBoostClassifier
 from sklearn.ensemble import AdaBoostRegressor
-from sklearn.ensemble import weight_boosting
+from sklearn.ensemble._weight_boosting import _samme_proba
 from scipy.sparse import csc_matrix
 from scipy.sparse import csr_matrix
 from scipy.sparse import coo_matrix
@@ -64,7 +64,7 @@ def predict_proba(self, X):
             return probs
     mock = MockEstimator()
 
-    samme_proba = weight_boosting._samme_proba(mock, 3, np.ones_like(probs))
+    samme_proba = _samme_proba(mock, 3, np.ones_like(probs))
 
     assert_array_equal(samme_proba.shape, probs.shape)
     assert np.isfinite(samme_proba).all()

diff --git a/sklearn/inspection/partial_dependence.py b/sklearn/inspection/partial_dependence.py
@@ -22,7 +22,7 @@
 from ..utils.validation import check_is_fitted
 from ..tree._tree import DTYPE
 from ..exceptions import NotFittedError
-from ..ensemble.gradient_boosting import BaseGradientBoosting
+from ..ensemble._gb import BaseGradientBoosting
 from sklearn.ensemble._hist_gradient_boosting.gradient_boosting import (
     BaseHistGradientBoosting)
 

diff --git a/sklearn/tests/test_import_deprecations.py b/sklearn/tests/test_import_deprecations.py
@@ -11,6 +11,17 @@
 # appropriate error message.
 
 @pytest.mark.parametrize('deprecated_path, importee', (
+    ('sklearn.tree.tree', 'DecisionTreeClassifier'),
+    ('sklearn.tree.export', 'export_graphviz'),
+
+    ('sklearn.ensemble.base', 'BaseEnsemble'),
+    ('sklearn.ensemble.forest', 'RandomForestClassifier'),
+    ('sklearn.ensemble.bagging', 'BaggingClassifier'),
+    ('sklearn.ensemble.iforest', 'IsolationForest'),
+    ('sklearn.ensemble.weight_boosting', 'AdaBoostClassifier'),
+    ('sklearn.ensemble.gradient_boosting', 'GradientBoostingClassifier'),
+    ('sklearn.ensemble.voting', 'VotingClassifier'),
+
     ('sklearn.neural_network.rbm', 'BernoulliRBM'),
     ('sklearn.neural_network.multilayer_perceptron', 'MLPClassifier'),
 

diff --git a/sklearn/tree/__init__.py b/sklearn/tree/__init__.py
@@ -3,12 +3,14 @@
 classification and regression.
 """
 
-from .tree import DecisionTreeClassifier
-from .tree import DecisionTreeRegressor
-from .tree import ExtraTreeClassifier
-from .tree import ExtraTreeRegressor
-from .export import export_graphviz, plot_tree, export_text
+from ._classes import BaseDecisionTree
+from ._classes import DecisionTreeClassifier
+    from ._classes import DecisionTreeRegressor
+from ._classes import ExtraTreeClassifier
+from ._classes import ExtraTreeRegressor
+from ._export import export_graphviz, plot_tree, export_text
 
-__all__ = ["DecisionTreeClassifier", "DecisionTreeRegressor",
+__all__ = ["BaseDecisionTree",
+           "DecisionTreeClassifier", "DecisionTreeRegressor",
            "ExtraTreeClassifier", "ExtraTreeRegressor", "export_graphviz",
            "plot_tree", "export_text"]
diff --git a/sklearn/tree/tree.py → sklearn/tree/_classes.py b/sklearn/tree/tree.py → sklearn/tree/_classes.py
diff --git a/sklearn/tree/export.py → sklearn/tree/_export.py b/sklearn/tree/export.py → sklearn/tree/_export.py
@@ -12,7 +12,6 @@
 #          Giuseppe Vettigli <vettigli@gmail.com>
 # License: BSD 3 clause
 from io import StringIO
-
 from numbers import Integral
 
 import numpy as np
@@ -833,7 +832,7 @@ def export_text(decision_tree, feature_names=None, max_depth=10,
 
     >>> from sklearn.datasets import load_iris
     >>> from sklearn.tree import DecisionTreeClassifier
-    >>> from sklearn.tree.export import export_text
+    >>> from sklearn.tree import export_text
     >>> iris = load_iris()
     >>> X = iris['data']
     >>> y = iris['target']

diff --git a/sklearn/tree/tests/test_tree.py b/sklearn/tree/tests/test_tree.py
@@ -38,8 +38,8 @@
 
 from sklearn import tree
 from sklearn.tree._tree import TREE_LEAF, TREE_UNDEFINED
-from sklearn.tree.tree import CRITERIA_CLF
-from sklearn.tree.tree import CRITERIA_REG
+from sklearn.tree._classes import CRITERIA_CLF
+from sklearn.tree._classes import CRITERIA_REG
 from sklearn import datasets
 
    from sklearn.utils import compute_sample_weight