allow sc.pp.subsample in backed mode when returning a copy (#2624)

* allow backed subsampling when returning a copy

* no extra copying, added test

* added description in release-notes

* more informative error message for copy=False

* Update scanpy/tests/test_preprocessing.py

Co-authored-by: Isaac Virshup <ivirshup@gmail.com>

* inverted branching

---------

Co-authored-by: Eljas <eljas.roellin@gmail.com>
Co-authored-by: Isaac Virshup <ivirshup@gmail.com>

docs/release-notes/1.10.0.md

@@ -4,6 +4,7 @@
 ```
 
 * {func}`scanpy.pp.pca` and {func}`scanpy.pp.regress_out` now accept a layer argument {pr}`2588` {smaller}`S Dicks`
+* {func}`scanpy.pp.subsample` with `copy=True` can now be called in backed mode {pr}`2624` {smaller}`E Roellin`
 
 ```{rubric} Docs
 ```

scanpy/preprocessing/_simple.py

@@ -898,10 +898,18 @@ def subsample(
         raise ValueError('Either pass `n_obs` or `fraction`.')
     obs_indices = np.random.choice(old_n_obs, size=new_n_obs, replace=False)
     if isinstance(data, AnnData):
-        if copy:
-            return data[obs_indices].copy()
+        if data.isbacked:
+            if copy:
+                return data[obs_indices].to_memory()
+            else:
+                raise NotImplementedError(
+                    "Inplace subsampling is not implemented for backed objects."
+                )
         else:
-            data._inplace_subset_obs(obs_indices)
+            if copy:
+                return data[obs_indices].copy()
+            else:
+                data._inplace_subset_obs(obs_indices)
     else:
         X = data
         return X[obs_indices], obs_indices

scanpy/tests/test_preprocessing.py

@@ -115,6 +115,22 @@ def test_subsample_copy():
     assert sc.pp.subsample(adata, fraction=0.1, copy=True).shape == (20, 10)
 
 
+def test_subsample_copy_backed(tmp_path):
+    A = np.random.rand(200, 10).astype(np.float32)
+    adata_m = AnnData(A.copy())
+    adata_d = AnnData(A.copy())
+    filename = tmp_path / 'test.h5ad'
+    adata_d.filename = filename
+    # This should not throw an error
+    assert sc.pp.subsample(adata_d, n_obs=40, copy=True).shape == (40, 10)
+    np.testing.assert_array_equal(
+        sc.pp.subsample(adata_m, n_obs=40, copy=True).X,
+        sc.pp.subsample(adata_d, n_obs=40, copy=True).X,
+    )
+    with pytest.raises(NotImplementedError):
+        sc.pp.subsample(adata_d, n_obs=40, copy=False)
+
+
 def test_scale():
     adata = pbmc68k_reduced()
     adata.X = adata.raw.X