scikit-learn · lamdang2k · Nov 19, 2024 · Nov 19, 2024 · Nov 19, 2024 · StefanieSenger
diff --git a/doc/glossary.rst b/doc/glossary.rst
@@ -1545,6 +1545,14 @@ functions or non-estimator constructors.
         The ``class_weight`` parameter is validated and interpreted with
         :func:`utils.class_weight.compute_class_weight`.
 
+    ``copy``
+        This parameter is used to specify the nature of the input operated
+        during computation. If False, try to avoid a copy and modify the input
+        in place.
+        This is not guaranteed to always work in place. If the input is not an
+        array of floating values or encoded as a CSR matrix, a new copy will
+        always be made, even if `copy=False`.
+
     ``cv``
         Determines a cross validation splitting strategy, as used in
         cross-validation based routines. ``cv`` is also available in estimators

diff --git a/sklearn/cluster/_affinity_propagation.py b/sklearn/cluster/_affinity_propagation.py
@@ -229,6 +229,7 @@ def affinity_propagation(
     copy : bool, default=True
         If copy is False, the affinity matrix is modified inplace by the
         algorithm, for memory efficiency.
+        See the :term:`Glossary <copy>`.
 
     verbose : bool, default=False
         The verbosity level.
@@ -331,7 +332,7 @@ class AffinityPropagation(ClusterMixin, BaseEstimator):
         of estimated clusters that stops the convergence.
 
     copy : bool, default=True
-        Make a copy of input data.
+        Make a copy of input data. See the :term:`Glossary <copy>`.
-        Make a copy of input data. See the :term:`Glossary <copy>`.
+        Make a :term:`copy` of input data.
-        Make a copy of input data. See the :term:`Glossary <copy>`.
+        Make a :term:`copy` of input data.
 
     preference : array-like of shape (n_samples,) or float, default=None
         Preferences for each point - points with larger values of

diff --git a/sklearn/cluster/_birch.py b/sklearn/cluster/_birch.py
@@ -406,6 +406,7 @@ class Birch(
     copy : bool, default=True
         Whether or not to make a copy of the given data. If set to False,
         the initial data will be overwritten.
+        See the :term:`Glossary <copy>`.
 
         .. deprecated:: 1.6
             `copy` was deprecated in 1.6 and will be removed in 1.8. It has no effect

diff --git a/sklearn/cluster/_spectral.py b/sklearn/cluster/_spectral.py
@@ -66,6 +66,7 @@ def discretize(
 
     copy : bool, default=True
         Whether to copy vectors, or perform in-place normalization.
+        See the :term:`Glossary <copy>`.
 
     max_svd_restarts : int, default=30
         Maximum number of attempts to restart SVD if convergence fails

diff --git a/sklearn/cross_decomposition/_pls.py b/sklearn/cross_decomposition/_pls.py
@@ -424,6 +424,7 @@ def transform(self, X, y=None, Y=None, copy=True):
 
         copy : bool, default=True
             Whether to copy `X` and `Y`, or perform in-place normalization.
+            See the :term:`Glossary <copy>`.
 
         Returns
         -------
@@ -515,6 +516,7 @@ def predict(self, X, copy=True):
 
         copy : bool, default=True
             Whether to copy `X` and `Y`, or perform in-place normalization.
+            See the :term:`Glossary <copy>`.
 
         Returns
         -------
@@ -595,6 +597,7 @@ class PLSRegression(_PLS):
         Whether to copy `X` and `Y` in :term:`fit` before applying centering,
         and potentially scaling. If `False`, these operations will be done
         inplace, modifying both arrays.
+        See the :term:`Glossary <copy>`.
 
     Attributes
     ----------
@@ -760,6 +763,7 @@ class PLSCanonical(_PLS):
         Whether to copy `X` and `Y` in fit before applying centering, and
         potentially scaling. If False, these operations will be done inplace,
         modifying both arrays.
+        See the :term:`Glossary <copy>`.
 
     Attributes
     ----------
@@ -885,6 +889,7 @@ class CCA(_PLS):
         Whether to copy `X` and `Y` in fit before applying centering, and
         potentially scaling. If False, these operations will be done inplace,
         modifying both arrays.
+        See the :term:`Glossary <copy>`.
 
     Attributes
     ----------
@@ -991,6 +996,7 @@ class PLSSVD(ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimator):
         Whether to copy `X` and `Y` in fit before applying centering, and
         potentially scaling. If `False`, these operations will be done inplace,
         modifying both arrays.
+        See the :term:`Glossary <copy>`.
 
     Attributes
     ----------

diff --git a/sklearn/decomposition/_factor_analysis.py b/sklearn/decomposition/_factor_analysis.py
@@ -72,6 +72,7 @@ class FactorAnalysis(ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEsti
     copy : bool, default=True
         Whether to make a copy of X. If ``False``, the input X gets overwritten
         during fitting.
+        See the :term:`Glossary <copy>`.
 
     max_iter : int, default=1000
         Maximum number of iterations.

diff --git a/sklearn/decomposition/_fastica.py b/sklearn/decomposition/_fastica.py
@@ -747,6 +747,7 @@ def transform(self, X, copy=True):
 
         copy : bool, default=True
             If False, data passed to fit can be overwritten. Defaults to True.
+            See the :term:`Glossary <copy>`.
 
         Returns
         -------
@@ -778,6 +779,7 @@ def inverse_transform(self, X, copy=True):
             and `n_components` is the number of components.
         copy : bool, default=True
             If False, data passed to fit are overwritten. Defaults to True.
+            See the :term:`Glossary <copy>`.
 
         Returns
         -------

diff --git a/sklearn/decomposition/_incremental_pca.py b/sklearn/decomposition/_incremental_pca.py
@@ -67,6 +67,7 @@ class IncrementalPCA(_BasePCA):
     copy : bool, default=True
         If False, X will be overwritten. ``copy=False`` can be used to
         save memory but is unsafe for general use.
+        See the :term:`Glossary <copy>`.
 
     batch_size : int, default=None
         The number of samples to use for each batch. Only used when calling

diff --git a/sklearn/decomposition/_pca.py b/sklearn/decomposition/_pca.py
@@ -163,6 +163,7 @@ class PCA(_BasePCA):
         If False, data passed to fit are overwritten and running
         fit(X).transform(X) will not yield the expected results,
         use fit_transform(X) instead.
+        See the :term:`Glossary <copy>`.
 
     whiten : bool, default=False
         When True (False by default) the `components_` vectors are multiplied

diff --git a/sklearn/feature_extraction/text.py b/sklearn/feature_extraction/text.py
@@ -1690,6 +1690,7 @@ def transform(self, X, copy=True):
         copy : bool, default=True
             Whether to copy X and operate on the copy or perform in-place
             operations. `copy=False` will only be effective with CSR sparse matrix.
+            See the :term:`Glossary <copy>`.
 
         Returns
         -------

diff --git a/sklearn/feature_selection/_mutual_info.py b/sklearn/feature_selection/_mutual_info.py
@@ -238,6 +238,7 @@ def _estimate_mi(
     copy : bool, default=True
         Whether to make a copy of the given data. If set to False, the initial
         data will be overwritten.
+        See the :term:`Glossary <copy>`.
 
     random_state : int, RandomState instance or None, default=None
         Determines random number generation for adding small noise to
@@ -381,6 +382,7 @@ def mutual_info_regression(
     copy : bool, default=True
         Whether to make a copy of the given data. If set to False, the initial
         data will be overwritten.
+        See the :term:`Glossary <copy>`.
 
     random_state : int, RandomState instance or None, default=None
         Determines random number generation for adding small noise to
@@ -509,6 +511,7 @@ def mutual_info_classif(
     copy : bool, default=True
         Whether to make a copy of the given data. If set to False, the initial
         data will be overwritten.
+        See the :term:`Glossary <copy>`.
 
     random_state : int, RandomState instance or None, default=None
         Determines random number generation for adding small noise to

diff --git a/sklearn/impute/_knn.py b/sklearn/impute/_knn.py
@@ -67,6 +67,7 @@ class KNNImputer(_BaseImputer):
     copy : bool, default=True
         If True, a copy of X will be created. If False, imputation will
         be done in-place whenever possible.
+        See the :term:`Glossary <copy>`.
 
     add_indicator : bool, default=False
         If True, a :class:`MissingIndicator` transform will stack onto the

diff --git a/sklearn/linear_model/_omp.py b/sklearn/linear_model/_omp.py
@@ -844,6 +844,7 @@ def _omp_path_residues(
     copy : bool, default=True
         Whether X_train, X_test, y_train and y_test should be copied.  If
         False, they may be overwritten.
+        See the :term:`Glossary <copy>`.
 
     fit_intercept : bool, default=True
         Whether to calculate the intercept for this model. If set

diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
@@ -502,6 +502,7 @@ def nan_euclidean_distances(
 
     copy : bool, default=True
         Make and use a deep copy of X and Y (if Y exists).
+        See the :term:`Glossary <copy>`.
 
     Returns
     -------

diff --git a/sklearn/utils/extmath.py b/sklearn/utils/extmath.py
@@ -927,7 +927,7 @@ def softmax(X, copy=True):
         Argument to the logistic function.
 
     copy : bool, default=True
-        Copy X or not.
+        Copy X or not. See the :term:`Glossary <copy>`.
 
     Returns
     -------
@@ -1258,6 +1258,7 @@ def safe_sqr(X, *, copy=True):
     copy : bool, default=True
         Whether to create a copy of X and operate on it or to perform
         inplace computation (default behaviour).
+        See the :term:`Glossary <copy>`.
 
     Returns
     -------

diff --git a/sklearn/utils/validation.py b/sklearn/utils/validation.py
@@ -232,6 +232,7 @@ def as_float_array(
     copy : bool, default=True
         If True, a copy of X will be created. If False, a copy may still be
         returned if X's dtype is not a floating point type.
+        See the :term:`Glossary <copy>`.
 
     force_all_finite : bool or 'allow-nan', default=True
         Whether to raise an error on np.inf, np.nan, pd.NA in X. The
-Original file line number
+Diff line change
@@ Expand Up / @@ -502,6 +502,7 @@ def nan_euclidean_distances( @@
         copy : bool, default=True
             Make and use a deep copy of X and Y (if Y exists).
+            See the :term:`Glossary <copy>`.
         Returns
         -------
@@ Expand Down @@