scikit-learn · glemaitre · Oct 23, 2019 · Oct 20, 2019 · Oct 20, 2019 · Oct 20, 2019
diff --git a/.gitignore b/.gitignore
@@ -130,6 +130,18 @@ sklearn/svm/libsvm.py
 sklearn/svm/libsvm_sparse.py
 sklearn/svm/liblinear.py
 
+sklearn/metrics/cluster/bicluster.py
+sklearn/metrics/cluster/supervised.py
+sklearn/metrics/cluster/unsupervised.py
+sklearn/metrics/cluster/expected_mutual_info_fast.py
+
+sklearn/metrics/base.py
+sklearn/metrics/classification.py
+sklearn/metrics/regression.py
+sklearn/metrics/ranking.py
+sklearn/metrics/pairwise_fast.py
+sklearn/metrics/scorer.py
+
 sklearn/inspection/partial_dependence.py
 sklearn/inspection/permutation_importance.py
 

diff --git a/sklearn/_build_utils/deprecated_modules.py b/sklearn/_build_utils/deprecated_modules.py
@@ -86,6 +86,26 @@
      'set_verbosity_wrap'),
     ('_liblinear', 'sklearn.svm.liblinear', 'sklearn.svm', 'train_wrap'),
 
+    ('_bicluster', 'sklearn.metrics.cluster.bicluster',
+     'sklearn.metrics.cluster', 'consensus_score'),
+    ('_supervised', 'sklearn.metrics.cluster.supervised',
+     'sklearn.metrics.cluster', 'entropy'),
+    ('_unsupervised', 'sklearn.metrics.cluster.unsupervised',
+     'sklearn.metrics.cluster', 'silhouette_score'),
+    ('_expected_mutual_info_fast',
+     'sklearn.metrics.cluster.expected_mutual_info_fast',
+     'sklearn.metrics.cluster', 'expected_mutual_information'),
+
+    ('_base', 'sklearn.metrics.base', 'sklearn.metrics', 'combinations'),
+    ('_classification', 'sklearn.metrics.classification', 'sklearn.metrics',
+     'accuracy_score'),
+    ('_regression', 'sklearn.metrics.regression', 'sklearn.metrics',
+     'max_error'),
+    ('_ranking', 'sklearn.metrics.ranking', 'sklearn.metrics', 'roc_curve'),
+    ('_pairwise_fast', 'sklearn.metrics.pairwise_fast', 'sklearn.metrics',
+     'np'),
+    ('_scorer', 'sklearn.metrics.scorer', 'sklearn.metrics', 'get_scorer'),
+
     ('_partial_dependence', 'sklearn.inspection.partial_dependence',
      'sklearn.inspection', 'partial_dependence'),
     ('_permutation_importance', 'sklearn.inspection.permutation_importance',

diff --git a/sklearn/base.py b/sklearn/base.py
@@ -404,7 +404,7 @@ def score(self, X, y, sample_weight=None):
         """
 
         from .metrics import r2_score
-        from .metrics.regression import _check_reg_targets
+        from .metrics._regression import _check_reg_targets
         y_pred = self.predict(X)
         # XXX: Remove the check in 0.23
         y_type, _, _, _ = _check_reg_targets(y, y_pred, None)

diff --git a/sklearn/linear_model/ridge.py b/sklearn/linear_model/ridge.py
@@ -30,7 +30,7 @@
 from ..utils.validation import _check_sample_weight
 from ..preprocessing import LabelBinarizer
 from ..model_selection import GridSearchCV
-from ..metrics.scorer import check_scoring
+from ..metrics import check_scoring
 from ..exceptions import ConvergenceWarning
 from ..utils.sparsefuncs import mean_variance_axis
 

diff --git a/sklearn/metrics/__init__.py b/sklearn/metrics/__init__.py
@@ -4,36 +4,36 @@
 """
 
 
-from .ranking import auc
-from .ranking import average_precision_score
-from .ranking import coverage_error
-from .ranking import dcg_score
-from .ranking import label_ranking_average_precision_score
-from .ranking import label_ranking_loss
-from .ranking import ndcg_score
-from .ranking import precision_recall_curve
-from .ranking import roc_auc_score
-from .ranking import roc_curve
+from ._ranking import auc
+from ._ranking import average_precision_score
+from ._ranking import coverage_error
+from ._ranking import dcg_score
+from ._ranking import label_ranking_average_precision_score
+from ._ranking import label_ranking_loss
+from ._ranking import ndcg_score
+from ._ranking import precision_recall_curve
+from ._ranking import roc_auc_score
+from ._ranking import roc_curve
 
-from .classification import accuracy_score
-from .classification import balanced_accuracy_score
-from .classification import classification_report
-from .classification import cohen_kappa_score
-from .classification import confusion_matrix
-from .classification import f1_score
-from .classification import fbeta_score
-from .classification import hamming_loss
-from .classification import hinge_loss
-from .classification import jaccard_similarity_score
-from .classification import jaccard_score
-from .classification import log_loss
-from .classification import matthews_corrcoef
-from .classification import precision_recall_fscore_support
-from .classification import precision_score
-from .classification import recall_score
-from .classification import zero_one_loss
-from .classification import brier_score_loss
-from .classification import multilabel_confusion_matrix
+from ._classification import accuracy_score
+from ._classification import balanced_accuracy_score
+from ._classification import classification_report
+from ._classification import cohen_kappa_score
+from ._classification import confusion_matrix
+from ._classification import f1_score
+from ._classification import fbeta_score
+from ._classification import hamming_loss
+from ._classification import hinge_loss
+from ._classification import jaccard_similarity_score
+from ._classification import jaccard_score
+from ._classification import log_loss
+from ._classification import matthews_corrcoef
+from ._classification import precision_recall_fscore_support
+from ._classification import precision_score
+from ._classification import recall_score
+from ._classification import zero_one_loss
+from ._classification import brier_score_loss
+from ._classification import multilabel_confusion_matrix
 
 from . import cluster
 from .cluster import adjusted_mutual_info_score
@@ -60,22 +60,22 @@
 from .pairwise import pairwise_kernels
 from .pairwise import pairwise_distances_chunked
 
-from .regression import explained_variance_score
-from .regression import max_error
-from .regression import mean_absolute_error
-from .regression import mean_squared_error
-from .regression import mean_squared_log_error
-from .regression import median_absolute_error
-from .regression import r2_score
-from .regression import mean_tweedie_deviance
-from .regression import mean_poisson_deviance
-from .regression import mean_gamma_deviance
+from ._regression import explained_variance_score
+from ._regression import max_error
+from ._regression import mean_absolute_error
+from ._regression import mean_squared_error
+from ._regression import mean_squared_log_error
+from ._regression import median_absolute_error
+from ._regression import r2_score
+from ._regression import mean_tweedie_deviance
+from ._regression import mean_poisson_deviance
+from ._regression import mean_gamma_deviance
 
 
-from .scorer import check_scoring
-from .scorer import make_scorer
-from .scorer import SCORERS
-from .scorer import get_scorer
+from ._scorer import check_scoring
+from ._scorer import make_scorer
+from ._scorer import SCORERS
+from ._scorer import get_scorer
 
 from ._plot.roc_curve import plot_roc_curve
 from ._plot.roc_curve import RocCurveDisplay

diff --git a/sklearn/metrics/base.py → sklearn/metrics/_base.py b/sklearn/metrics/base.py → sklearn/metrics/_base.py
diff --git a/sklearn/metrics/classification.py → sklearn/metrics/_classification.py b/sklearn/metrics/classification.py → sklearn/metrics/_classification.py
diff --git a/sklearn/metrics/pairwise_fast.pyx → sklearn/metrics/_pairwise_fast.pyx b/sklearn/metrics/pairwise_fast.pyx → sklearn/metrics/_pairwise_fast.pyx
diff --git a/sklearn/metrics/ranking.py → sklearn/metrics/_ranking.py b/sklearn/metrics/ranking.py → sklearn/metrics/_ranking.py
@@ -35,7 +35,7 @@
 from ..preprocessing import label_binarize
 from ..preprocessing._label import _encode
 
-from .base import _average_binary_score, _average_multiclass_ovo_score
+from ._base import _average_binary_score, _average_multiclass_ovo_score
 
 
 def auc(x, y):

diff --git a/sklearn/metrics/regression.py → sklearn/metrics/_regression.py b/sklearn/metrics/regression.py → sklearn/metrics/_regression.py
diff --git a/sklearn/metrics/scorer.py → sklearn/metrics/_scorer.py b/sklearn/metrics/scorer.py → sklearn/metrics/_scorer.py
@@ -406,7 +406,7 @@ def check_scoring(estimator, scoring=None, allow_none=False):
         module = getattr(scoring, '__module__', None)
         if hasattr(module, 'startswith') and \
            module.startswith('sklearn.metrics.') and \
-           not module.startswith('sklearn.metrics.scorer') and \
+           not module.startswith('sklearn.metrics._scorer') and \
            not module.startswith('sklearn.metrics.tests.'):
             raise ValueError('scoring value %r looks like it is a metric '
                              'function rather than a scorer. A scorer should '

diff --git a/sklearn/metrics/cluster/__init__.py b/sklearn/metrics/cluster/__init__.py
@@ -5,24 +5,24 @@
 - supervised, which uses a ground truth class values for each sample.
 - unsupervised, which does not and measures the 'quality' of the model itself.
 """
-from .supervised import adjusted_mutual_info_score
-from .supervised import normalized_mutual_info_score
-from .supervised import adjusted_rand_score
-from .supervised import completeness_score
-from .supervised import contingency_matrix
-from .supervised import expected_mutual_information
-from .supervised import homogeneity_completeness_v_measure
-from .supervised import homogeneity_score
-from .supervised import mutual_info_score
-from .supervised import v_measure_score
-from .supervised import fowlkes_mallows_score
-from .supervised import entropy
-from .unsupervised import silhouette_samples
-from .unsupervised import silhouette_score
-from .unsupervised import calinski_harabasz_score
-from .unsupervised import calinski_harabaz_score
-from .unsupervised import davies_bouldin_score
-from .bicluster import consensus_score
+from ._supervised import adjusted_mutual_info_score
+from ._supervised import normalized_mutual_info_score
+from ._supervised import adjusted_rand_score
+from ._supervised import completeness_score
+from ._supervised import contingency_matrix
+from ._supervised import expected_mutual_information
+from ._supervised import homogeneity_completeness_v_measure
+from ._supervised import homogeneity_score
+from ._supervised import mutual_info_score
+from ._supervised import v_measure_score
+from ._supervised import fowlkes_mallows_score
+from ._supervised import entropy
+from ._unsupervised import silhouette_samples
+from ._unsupervised import silhouette_score
+from ._unsupervised import calinski_harabasz_score
+from ._unsupervised import calinski_harabaz_score
+from ._unsupervised import davies_bouldin_score
+from ._bicluster import consensus_score
 
 __all__ = ["adjusted_mutual_info_score", "normalized_mutual_info_score",
            "adjusted_rand_score", "completeness_score", "contingency_matrix",

diff --git a/sklearn/metrics/cluster/bicluster.py → sklearn/metrics/cluster/_bicluster.py b/sklearn/metrics/cluster/bicluster.py → sklearn/metrics/cluster/_bicluster.py
diff --git a/...ics/cluster/expected_mutual_info_fast.pyx → ...cs/cluster/_expected_mutual_info_fast.pyx b/...ics/cluster/expected_mutual_info_fast.pyx → ...cs/cluster/_expected_mutual_info_fast.pyx
diff --git a/sklearn/metrics/cluster/supervised.py → sklearn/metrics/cluster/_supervised.py b/sklearn/metrics/cluster/supervised.py → sklearn/metrics/cluster/_supervised.py
@@ -20,7 +20,7 @@
 import numpy as np
 from scipy import sparse as sp
 
-from .expected_mutual_info_fast import expected_mutual_information
+from ._expected_mutual_info_fast import expected_mutual_information
 from ...utils.validation import check_array, check_consistent_length
 from ...utils.fixes import comb, _astype_copy_false
 

diff --git a/sklearn/metrics/cluster/unsupervised.py → sklearn/metrics/cluster/_unsupervised.py b/sklearn/metrics/cluster/unsupervised.py → sklearn/metrics/cluster/_unsupervised.py
diff --git a/sklearn/metrics/cluster/setup.py b/sklearn/metrics/cluster/setup.py
@@ -9,8 +9,8 @@ def configuration(parent_package="", top_path=None):
     libraries = []
     if os.name == 'posix':
         libraries.append('m')
-    config.add_extension("expected_mutual_info_fast",
-                         sources=["expected_mutual_info_fast.pyx"],
+    config.add_extension("_expected_mutual_info_fast",
+                         sources=["_expected_mutual_info_fast.pyx"],
                          include_dirs=[numpy.get_include()],
                          libraries=libraries)
 

diff --git a/sklearn/metrics/cluster/tests/test_bicluster.py b/sklearn/metrics/cluster/tests/test_bicluster.py
@@ -4,7 +4,7 @@
 
 from sklearn.utils.testing import assert_almost_equal
 
-from sklearn.metrics.cluster.bicluster import _jaccard
+from sklearn.metrics.cluster._bicluster import _jaccard
 from sklearn.metrics import consensus_score
 
 

diff --git a/sklearn/metrics/cluster/tests/test_supervised.py b/sklearn/metrics/cluster/tests/test_supervised.py
@@ -13,7 +13,7 @@
 from sklearn.metrics.cluster import mutual_info_score
 from sklearn.metrics.cluster import normalized_mutual_info_score
 from sklearn.metrics.cluster import v_measure_score
-from sklearn.metrics.cluster.supervised import _generalized_average
+from sklearn.metrics.cluster._supervised import _generalized_average
 
 from sklearn.utils import assert_all_finite
 from sklearn.utils.testing import (

diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
@@ -29,7 +29,7 @@
 from ..preprocessing import normalize
 from ..utils._mask import _get_mask
 
-from .pairwise_fast import _chi2_kernel_fast, _sparse_manhattan
+from ._pairwise_fast import _chi2_kernel_fast, _sparse_manhattan
 from ..exceptions import DataConversionWarning
 
 

diff --git a/sklearn/metrics/setup.py b/sklearn/metrics/setup.py
@@ -14,8 +14,8 @@ def configuration(parent_package="", top_path=None):
     config.add_subpackage('_plot.tests')
     config.add_subpackage('cluster')
 
-    config.add_extension("pairwise_fast",
-                         sources=["pairwise_fast.pyx"],
+    config.add_extension("_pairwise_fast",
+                         sources=["_pairwise_fast.pyx"],
                          libraries=libraries)
 
     config.add_subpackage('tests')

diff --git a/sklearn/metrics/tests/test_classification.py b/sklearn/metrics/tests/test_classification.py
@@ -45,7 +45,7 @@
 from sklearn.metrics import brier_score_loss
 from sklearn.metrics import multilabel_confusion_matrix
 
-from sklearn.metrics.classification import _check_targets
+from sklearn.metrics._classification import _check_targets
 from sklearn.exceptions import UndefinedMetricWarning
 
 from scipy.spatial.distance import hamming as sp_hamming

diff --git a/sklearn/metrics/tests/test_common.py b/sklearn/metrics/tests/test_common.py
@@ -57,7 +57,7 @@
 from sklearn.metrics import ndcg_score
 from sklearn.metrics import dcg_score
 
-from sklearn.metrics.base import _average_binary_score
+from sklearn.metrics._base import _average_binary_score
 
 
 # Note toward developers about metric testing

diff --git a/sklearn/metrics/tests/test_ranking.py b/sklearn/metrics/tests/test_ranking.py
@@ -26,8 +26,8 @@
 from sklearn.metrics import label_ranking_loss
 from sklearn.metrics import roc_auc_score
 from sklearn.metrics import roc_curve
-from sklearn.metrics.ranking import _ndcg_sample_scores, _dcg_sample_scores
-from sklearn.metrics.ranking import ndcg_score, dcg_score
+from sklearn.metrics._ranking import _ndcg_sample_scores, _dcg_sample_scores
+from sklearn.metrics import ndcg_score, dcg_score
 
 from sklearn.exceptions import UndefinedMetricWarning
 

diff --git a/sklearn/metrics/tests/test_regression.py b/sklearn/metrics/tests/test_regression.py
@@ -17,7 +17,7 @@
 from sklearn.metrics import r2_score
 from sklearn.metrics import mean_tweedie_deviance
 
-from sklearn.metrics.regression import _check_reg_targets
+from sklearn.metrics._regression import _check_reg_targets
 
 from ...exceptions import UndefinedMetricWarning
 

diff --git a/sklearn/metrics/tests/test_score_objects.py b/sklearn/metrics/tests/test_score_objects.py
@@ -19,10 +19,11 @@
                              log_loss, precision_score, recall_score,
                              jaccard_score)
 from sklearn.metrics import cluster as cluster_module
-from sklearn.metrics.scorer import (check_scoring, _PredictScorer,
-                                    _passthrough_scorer, _MultimetricScorer)
+from sklearn.metrics import check_scoring
+from sklearn.metrics._scorer import (_PredictScorer, _passthrough_scorer,
+                                     _MultimetricScorer,
+                                     _check_multimetric_scoring)
 from sklearn.metrics import accuracy_score
-from sklearn.metrics.scorer import _check_multimetric_scoring
 from sklearn.metrics import make_scorer, get_scorer, SCORERS
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.svm import LinearSVC

diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
@@ -35,8 +35,8 @@
 from ..utils.random import sample_without_replacement
 from ..utils.validation import indexable, check_is_fitted
 from ..utils.metaestimators import if_delegate_has_method
-from ..metrics.scorer import _check_multimetric_scoring
-from ..metrics.scorer import check_scoring
+from ..metrics._scorer import _check_multimetric_scoring
+from ..metrics import check_scoring
 
 
 __all__ = ['GridSearchCV', 'ParameterGrid', 'fit_grid_point',

diff --git a/sklearn/model_selection/_validation.py b/sklearn/model_selection/_validation.py
@@ -25,8 +25,8 @@
                      _message_with_time)
 from ..utils.validation import _is_arraylike, _num_samples
 from ..utils.metaestimators import _safe_split
-from ..metrics.scorer import (check_scoring, _check_multimetric_scoring,
-                              _MultimetricScorer)
+from ..metrics import check_scoring
+from ..metrics._scorer import _check_multimetric_scoring, _MultimetricScorer
 from ..exceptions import FitFailedWarning
 from ._split import check_cv
 from ..preprocessing import LabelEncoder