DOC Ensures that sklearn.metrics.pairwise.linear_kernel passes numpyd…

…oc validation (scikit-learn#21470) Co-authored-by: Julien Jerphanion <git@jjerphan.xyz> Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
norbusan · Oct 30, 2021 · d5e045f · d5e045f
1 parent 8fcf4ce
commit d5e045f
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/maint_tools/test_docstrings.py b/maint_tools/test_docstrings.py
@@ -142,7 +142,6 @@
     "sklearn.metrics.pairwise.haversine_distances",
     "sklearn.metrics.pairwise.kernel_metrics",
     "sklearn.metrics.pairwise.laplacian_kernel",
-    "sklearn.metrics.pairwise.linear_kernel",
     "sklearn.metrics.pairwise.manhattan_distances",
     "sklearn.metrics.pairwise.nan_euclidean_distances",
     "sklearn.metrics.pairwise.paired_cosine_distances",

diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
@@ -1053,9 +1053,10 @@ def linear_kernel(X, Y=None, dense_output=True):
     Parameters
     ----------
     X : ndarray of shape (n_samples_X, n_features)
+        A feature array.
 
     Y : ndarray of shape (n_samples_Y, n_features), default=None
-        If `None`, uses `Y=X`.
+        An optional second feature array. If `None`, uses `Y=X`.
 
     dense_output : bool, default=True
         Whether to return dense output even when the input is sparse. If
@@ -1066,6 +1067,7 @@ def linear_kernel(X, Y=None, dense_output=True):
     Returns
     -------
     Gram matrix : ndarray of shape (n_samples_X, n_samples_Y)
+        The Gram matrix of the linear kernel, i.e. `X @ Y.T`.
     """
     X, Y = check_pairwise_arrays(X, Y)
     return safe_sparse_dot(X, Y.T, dense_output=dense_output)