FIX Support readonly sparse datasets for manhattan_distances (#25432)

jjerphan · lesteve · lorentzenchr · web-flow · commit b69abf51219f · 2023-01-26T11:38:07.000+01:00
* TST Add non-regression test for #7981 This reproducer is adapted from the one of this message: #7981 (comment) Co-authored-by: Loïc Estève <loic.esteve@ymail.com> * FIX Support readonly sparse datasets for manhattan * DOC Add entry in whats_new/v1.2.rst for 1.2.1 * FIX Fix comment * Update sklearn/metrics/tests/test_pairwise.py Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com> * DOC Move entry to whats_new/v1.3.rst * Update sklearn/metrics/tests/test_pairwise.py Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org> Co-authored-by: Loïc Estève <loic.esteve@ymail.com> Co-authored-by: Christian Lorentzen <lorentzen.ch@gmail.com> Co-authored-by: Olivier Grisel <olivier.grisel@ensta.org>
diff --git a/doc/whats_new/v1.3.rst b/doc/whats_new/v1.3.rst
@@ -143,6 +143,12 @@ Changelog
 - |Enhancement| Added the parameter `fill_value` to :class:`impute.IterativeImputer`.
   :pr:`25232` by :user:`Thijs van Weezel <ValueInvestorThijs>`.
 
+:mod:`sklearn.metrics`
+......................
+
+- |Fix| :func:`metric.manhattan_distances` now supports readonly sparse datasets.
+  :pr:`25432` by :user:`Julien Jerphanion <jjerphan>`.
+
 :mod:`sklearn.naive_bayes`
 ..........................
 
diff --git a/sklearn/metrics/_pairwise_fast.pyx b/sklearn/metrics/_pairwise_fast.pyx
@@ -35,9 +35,15 @@ def _chi2_kernel_fast(floating[:, :] X,
                 result[i, j] = -res
 
 
-def _sparse_manhattan(floating[::1] X_data, int[:] X_indices, int[:] X_indptr,
-                      floating[::1] Y_data, int[:] Y_indices, int[:] Y_indptr,
-                      double[:, ::1] D):
+def _sparse_manhattan(
+    const floating[::1] X_data,
+    const int[:] X_indices,
+    const int[:] X_indptr,
+    const floating[::1] Y_data,
+    const int[:] Y_indices,
+    const int[:] Y_indptr,
+    double[:, ::1] D,
+):
     """Pairwise L1 distances for CSR matrices.
 
     Usage:
diff --git a/sklearn/metrics/tests/test_pairwise.py b/sklearn/metrics/tests/test_pairwise.py
@@ -16,6 +16,7 @@
     from scipy.spatial.distance import minkowski as wminkowski
 
 from sklearn.utils.fixes import sp_version, parse_version
+from sklearn.utils.parallel import delayed, Parallel
 
 import pytest
 
@@ -1541,3 +1542,14 @@ def test_numeric_pairwise_distances_datatypes(metric, global_dtype, y_is_x):
     dist = pairwise_distances(X, Y, metric=metric, **params)
 
     assert_allclose(dist, expected_dist)
+
+
+def test_sparse_manhattan_readonly_dataset():
+    # Non-regression test for: https://github.com/scikit-learn/scikit-learn/issues/7981
+    matrices1 = [csr_matrix(np.ones((5, 5)))]
+    matrices2 = [csr_matrix(np.ones((5, 5)))]
+    # Joblib memory maps datasets which makes them read-only.
+    # The following call was reporting as failing in #7981, but this must pass.
+    Parallel(n_jobs=2, max_nbytes=0)(
+        delayed(manhattan_distances)(m1, m2) for m1, m2 in zip(matrices1, matrices2)
+    )
