DOC Improve consistency of inverse_transform return name (scikit-learn#31135)

jeremiedbb · web-flow · commit 7db1015b0c20 · 2025-04-30T11:03:28.000+02:00
diff --git a/sklearn/cluster/_feature_agglomeration.py b/sklearn/cluster/_feature_agglomeration.py
@@ -66,8 +66,8 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X : ndarray of shape (n_samples, n_features) or (n_features,)
-            A vector of size `n_samples` with the values of `Xred` assigned to
+        X_original : ndarray of shape (n_samples, n_features) or (n_features,)
+            A vector of size `n_samples` with the values of `X` assigned to
             each of the cluster of samples.
         """
         check_is_fitted(self)
diff --git a/sklearn/cross_decomposition/_pls.py b/sklearn/cross_decomposition/_pls.py
@@ -419,10 +419,10 @@ def inverse_transform(self, X, y=None):
 
         Returns
         -------
-        X_reconstructed : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Return the reconstructed `X` data.
 
-        y_reconstructed : ndarray of shape (n_samples, n_targets)
+        y_original : ndarray of shape (n_samples, n_targets)
             Return the reconstructed `X` target. Only returned when `y` is given.
 
         Notes
diff --git a/sklearn/decomposition/_base.py b/sklearn/decomposition/_base.py
@@ -177,7 +177,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_original array-like of shape (n_samples, n_features)
+        X_original : array-like of shape (n_samples, n_features)
             Original data, where `n_samples` is the number of samples
             and `n_features` is the number of features.
 
diff --git a/sklearn/decomposition/_dict_learning.py b/sklearn/decomposition/_dict_learning.py
@@ -1174,7 +1174,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_new : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Transformed data.
         """
         check_is_fitted(self)
@@ -1378,7 +1378,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_new : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Transformed data.
         """
         return self._inverse_transform(X, self.dictionary)
diff --git a/sklearn/decomposition/_fastica.py b/sklearn/decomposition/_fastica.py
@@ -781,7 +781,7 @@ def inverse_transform(self, X, copy=True):
 
         Returns
         -------
-        X_new : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Reconstructed data obtained with the mixing matrix.
         """
         check_is_fitted(self)
diff --git a/sklearn/decomposition/_kernel_pca.py b/sklearn/decomposition/_kernel_pca.py
@@ -544,7 +544,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_new : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Returns the instance itself.
 
         References
diff --git a/sklearn/decomposition/_nmf.py b/sklearn/decomposition/_nmf.py
@@ -1302,7 +1302,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Returns a data matrix of the original shape.
         """
 
diff --git a/sklearn/feature_extraction/_dict_vectorizer.py b/sklearn/feature_extraction/_dict_vectorizer.py
@@ -339,7 +339,7 @@ def inverse_transform(self, X, dict_type=dict):
 
         Returns
         -------
-        D : list of dict_type objects of shape (n_samples,)
+        X_original : list of dict_type objects of shape (n_samples,)
             Feature mappings for the samples in X.
         """
         check_is_fitted(self, "feature_names_")
diff --git a/sklearn/feature_extraction/text.py b/sklearn/feature_extraction/text.py
@@ -1433,7 +1433,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_inv : list of arrays of shape (n_samples,)
+        X_original : list of arrays of shape (n_samples,)
             List of arrays of terms.
         """
         self._check_vocabulary()
diff --git a/sklearn/feature_selection/_base.py b/sklearn/feature_selection/_base.py
@@ -141,7 +141,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_r : array of shape [n_samples, n_original_features]
+        X_original : array of shape [n_samples, n_original_features]
             `X` with columns of zeros inserted where features would have
             been removed by :meth:`transform`.
         """
diff --git a/sklearn/model_selection/_search.py b/sklearn/model_selection/_search.py
@@ -703,8 +703,8 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X : {ndarray, sparse matrix} of shape (n_samples, n_features)
-            Result of the `inverse_transform` function for `Xt` based on the
+        X_original : {ndarray, sparse matrix} of shape (n_samples, n_features)
+            Result of the `inverse_transform` function for `X` based on the
             estimator with the best found parameters.
         """
         check_is_fitted(self)
diff --git a/sklearn/pipeline.py b/sklearn/pipeline.py
@@ -1120,7 +1120,7 @@ def inverse_transform(self, X, **params):
 
         Returns
         -------
-        Xt : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Inverse transformed data, that is, data in the original feature
             space.
         """
diff --git a/sklearn/preprocessing/_data.py b/sklearn/preprocessing/_data.py
@@ -575,7 +575,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        Xt : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Transformed data.
         """
         check_is_fitted(self)
@@ -1104,12 +1104,13 @@ def inverse_transform(self, X, copy=None):
         ----------
         X : {array-like, sparse matrix} of shape (n_samples, n_features)
             The data used to scale along the features axis.
+
         copy : bool, default=None
-            Copy the input X or not.
+            Copy the input `X` or not.
 
         Returns
         -------
-        X_tr : {ndarray, sparse matrix} of shape (n_samples, n_features)
+        X_original : {ndarray, sparse matrix} of shape (n_samples, n_features)
             Transformed array.
         """
         check_is_fitted(self)
@@ -1351,7 +1352,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_tr : {ndarray, sparse matrix} of shape (n_samples, n_features)
+        X_original : {ndarray, sparse matrix} of shape (n_samples, n_features)
             Transformed array.
         """
         check_is_fitted(self)
@@ -1726,7 +1727,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_tr : {ndarray, sparse matrix} of shape (n_samples, n_features)
+        X_original : {ndarray, sparse matrix} of shape (n_samples, n_features)
             Transformed array.
         """
         check_is_fitted(self)
@@ -3017,7 +3018,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        Xt : {ndarray, sparse matrix} of (n_samples, n_features)
+        X_original : {ndarray, sparse matrix} of (n_samples, n_features)
             The projected data.
         """
         check_is_fitted(self)
@@ -3413,20 +3414,20 @@ def inverse_transform(self, X):
         The inverse of the Box-Cox transformation is given by::
 
             if lambda_ == 0:
-                X = exp(X_trans)
+                X_original = exp(X_trans)
             else:
-                X = (X_trans * lambda_ + 1) ** (1 / lambda_)
+                X_original = (X * lambda_ + 1) ** (1 / lambda_)
 
         The inverse of the Yeo-Johnson transformation is given by::
 
             if X >= 0 and lambda_ == 0:
-                X = exp(X_trans) - 1
+                X_original = exp(X) - 1
             elif X >= 0 and lambda_ != 0:
-                X = (X_trans * lambda_ + 1) ** (1 / lambda_) - 1
+                X_original = (X * lambda_ + 1) ** (1 / lambda_) - 1
             elif X < 0 and lambda_ != 2:
-                X = 1 - (-(2 - lambda_) * X_trans + 1) ** (1 / (2 - lambda_))
+                X_original = 1 - (-(2 - lambda_) * X + 1) ** (1 / (2 - lambda_))
             elif X < 0 and lambda_ == 2:
-                X = 1 - exp(-X_trans)
+                X_original = 1 - exp(-X)
 
         Parameters
         ----------
@@ -3435,7 +3436,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             The original data.
         """
         check_is_fitted(self)
diff --git a/sklearn/preprocessing/_discretization.py b/sklearn/preprocessing/_discretization.py
@@ -494,7 +494,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        Xinv : ndarray, dtype={np.float32, np.float64}
+        X_original : ndarray, dtype={np.float32, np.float64}
             Data in the original feature space.
         """
 
diff --git a/sklearn/preprocessing/_encoders.py b/sklearn/preprocessing/_encoders.py
@@ -1104,7 +1104,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_tr : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Inverse transformed array.
         """
         check_is_fitted(self)
@@ -1622,7 +1622,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_tr : ndarray of shape (n_samples, n_features)
+        X_original : ndarray of shape (n_samples, n_features)
             Inverse transformed array.
         """
         check_is_fitted(self)
diff --git a/sklearn/preprocessing/_function_transformer.py b/sklearn/preprocessing/_function_transformer.py
@@ -325,7 +325,7 @@ def inverse_transform(self, X):
 
         Returns
         -------
-        X_out : array-like, shape (n_samples, n_features)
+        X_original : array-like, shape (n_samples, n_features)
             Transformed input.
         """
         if self.validate:
diff --git a/sklearn/preprocessing/_label.py b/sklearn/preprocessing/_label.py
@@ -143,7 +143,7 @@ def inverse_transform(self, y):
 
         Returns
         -------
-        y : ndarray of shape (n_samples,)
+        y_original : ndarray of shape (n_samples,)
             Original encoding.
         """
         check_is_fitted(self)
@@ -389,7 +389,7 @@ def inverse_transform(self, Y, threshold=None):
 
         Returns
         -------
-        y : {ndarray, sparse matrix} of shape (n_samples,)
+        y_original : {ndarray, sparse matrix} of shape (n_samples,)
             Target values. Sparse matrix will be of CSR format.
 
         Notes
@@ -925,7 +925,7 @@ def inverse_transform(self, yt):
 
         Returns
         -------
-        y : list of tuples
+        y_original : list of tuples
             The set of labels for each sample such that `y[i]` consists of
             `classes_[j]` for each `yt[i, j] == 1`.
         """
