fix precommit and add pre-release test (#847)

* fix precommit

* add pre release

* fix tests

* remove .A in csr_sparse

* fix

* fix

.github/workflows/test.yml

@@ -23,10 +23,13 @@ jobs:
                 python: [3.9, "3.10", "3.11"]
                 os: [ubuntu-latest]
                 include:
-                    - python: 3.9
-                      os: macos-latest
                     - python: "3.10"
                       os: macos-latest
+                    - python: "3.12"
+                      os: macos-latest
+                      pip-flags: "--pre"
+                      name: "Python 3.12 (pre-release)"
+
         env:
             OS: ${{ matrix.os }}
             PYTHON: ${{ matrix.python }}

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ default_stages:
 minimum_pre_commit_version: 2.9.3
 repos:
     - repo: https://github.com/pre-commit/mirrors-mypy
-      rev: v1.10.0
+      rev: v1.10.1
       hooks:
           - id: mypy
             additional_dependencies: [numpy, pandas, types-requests]
@@ -46,7 +46,7 @@ repos:
             name: Check executable files use .sh extension
             types: [shell, executable]
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.4.7
+      rev: v0.5.0
       hooks:
           - id: ruff
             types_or: [python, pyi, jupyter]

src/squidpy/gr/_sepal.py

@@ -100,7 +100,7 @@ def sepal(
     if max_neighs not in (4, 6):
         raise ValueError(f"Expected `max_neighs` to be either `4` or `6`, found `{max_neighs}`.")
 
-    spatial = adata.obsm[spatial_key].astype(np.float_)
+    spatial = adata.obsm[spatial_key].astype(np.float64)
 
     if genes is None:
         genes = adata.var_names.values
@@ -169,8 +169,8 @@ def _score_helper(
     sat_idx: NDArrayA,
     unsat: NDArrayA,
     unsat_idx: NDArrayA,
-    dt: np.float_,
-    thresh: np.float_,
+    dt: float,
+    thresh: float,
     queue: SigQueue | None = None,
 ) -> NDArrayA:
     if max_neighs == 4:
@@ -182,8 +182,8 @@ def _score_helper(
 
     score, sparse = [], issparse(vals)
     for i in ixs:
-        conc = vals[:, i].A.flatten() if sparse else vals[:, i].copy()  # type: ignore[union-attr]
-        conc = vals[:, i].A.flatten() if sparse else vals[:, i].copy()  # type: ignore[union-attr]
+        conc = vals[:, i].toarray().flatten() if sparse else vals[:, i].copy()  # type: ignore[union-attr]
+        conc = vals[:, i].toarray().flatten() if sparse else vals[:, i].copy()  # type: ignore[union-attr]
         time_iter = _diffusion(conc, fun, n_iter, sat, sat_idx, unsat, unsat_idx, dt=dt, thresh=thresh)
         score.append(dt * time_iter)
 
@@ -199,7 +199,7 @@ def _score_helper(
 @njit(fastmath=True)
 def _diffusion(
     conc: NDArrayA,
-    laplacian: Callable[[NDArrayA, NDArrayA, NDArrayA], np.float_],
+    laplacian: Callable[[NDArrayA, NDArrayA, NDArrayA], float],
     n_iter: int,
     sat: NDArrayA,
     sat_idx: NDArrayA,
@@ -320,7 +320,11 @@ def _get_sat_unsat_idx(g_indptr: NDArrayA, g_shape: int, sat_thresh: int) -> tup
 
 @njit
 def _get_nhood_idx(
-    sat: NDArrayA, unsat: NDArrayA, g_indptr: NDArrayA, g_indices: NDArrayA, sat_thresh: int
+    sat: NDArrayA,
+    unsat: NDArrayA,
+    g_indptr: NDArrayA,
+    g_indices: NDArrayA,
+    sat_thresh: int,
 ) -> tuple[NDArrayA, NDArrayA, NDArrayA]:
     """Get saturated and unsaturated neighborhood indices."""
     # get saturated nhood indices

src/squidpy/pl/_var_by_distance.py

@@ -95,12 +95,17 @@ def var_by_distance(
     scatterplot_kwargs = dict(scatterplot_kwargs)
 
     df = adata.obsm[design_matrix_key]  # get design matrix
-    df[var] = np.array(adata[:, var].X.A) if issparse(adata[:, var].X) else np.array(adata[:, var].X)  # add var column
+    df[var] = (
+        np.array(adata[:, var].X.toarray()) if issparse(adata[:, var].X) else np.array(adata[:, var].X)
+    )  # add var column
 
     # if several variables are plotted, make a panel grid
     if isinstance(var, list):
         fig, grid = _panel_grid(
-            hspace=0.25, wspace=0.75 / rcParams["figure.figsize"][0] + 0.02, ncols=4, num_panels=len(var)
+            hspace=0.25,
+            wspace=0.75 / rcParams["figure.figsize"][0] + 0.02,
+            ncols=4,
+            num_panels=len(var),
         )
         axs = []
     else:
@@ -168,7 +173,14 @@ def var_by_distance(
                     )
             # if variable to plot on color palette is not categorical
             else:
-                plt.scatter(data=df, x=anchor_key, y=v, c=color, cmap=scatter_palette, **scatterplot_kwargs)
+                plt.scatter(
+                    data=df,
+                    x=anchor_key,
+                    y=v,
+                    c=color,
+                    cmap=scatter_palette,
+                    **scatterplot_kwargs,
+                )
         if title is not None:
             ax.set(title=title)
         if axis_label is None:

tests/graph/test_spatial_neighbors.py

@@ -21,7 +21,14 @@ class TestSpatialNeighbors:
         ]
     )
     # ground-truth Delaunay graph
-    _gt_dgraph = np.array([[0.0, 1.0, 0.0, 1.0], [1.0, 0.0, 1.0, 1.0], [0.0, 1.0, 0.0, 1.0], [1.0, 1.0, 1.0, 0.0]])
+    _gt_dgraph = np.array(
+        [
+            [0.0, 1.0, 0.0, 1.0],
+            [1.0, 0.0, 1.0, 1.0],
+            [0.0, 1.0, 0.0, 1.0],
+            [1.0, 1.0, 1.0, 0.0],
+        ]
+    )
 
     @staticmethod
     def _adata_concat(adata1, adata2):
@@ -54,12 +61,12 @@ def test_spatial_neighbors_visium(self, visium_adata: AnnData, n_rings: int, n_n
         spatial_neighbors(adata_concat, library_key="library_id", n_rings=n_rings)
         assert adata_concat.obsp[Key.obsp.spatial_conn()][0].sum() == n_neigh
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].A,
-            visium_adata.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].toarray(),
+            visium_adata.obsp[Key.obsp.spatial_conn()].toarray(),
         )
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].A,
-            visium_adata2.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].toarray(),
+            visium_adata2.obsp[Key.obsp.spatial_conn()].toarray(),
         )
 
     @pytest.mark.parametrize(("n_rings", "n_neigh", "sum_neigh"), [(1, 4, 4), (2, 4, 12), (3, 4, 24)])
@@ -76,15 +83,21 @@ def test_spatial_neighbors_squaregrid(self, adata_squaregrid: AnnData, n_rings:
         adata2 = adata.copy()
         adata_concat, batch1, batch2 = TestSpatialNeighbors._adata_concat(adata, adata2)
         spatial_neighbors(adata2, n_neighs=n_neigh, n_rings=n_rings, coord_type="grid")
-        spatial_neighbors(adata_concat, library_key="library_id", n_neighs=n_neigh, n_rings=n_rings, coord_type="grid")
+        spatial_neighbors(
+            adata_concat,
+            library_key="library_id",
+            n_neighs=n_neigh,
+            n_rings=n_rings,
+            coord_type="grid",
+        )
         assert np.diff(adata_concat.obsp[Key.obsp.spatial_conn()].indptr).max() == sum_neigh
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].A,
-            adata.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].toarray(),
+            adata.obsp[Key.obsp.spatial_conn()].toarray(),
         )
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].A,
-            adata2.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].toarray(),
+            adata2.obsp[Key.obsp.spatial_conn()].toarray(),
         )
 
     @pytest.mark.parametrize("type_rings", [("grid", 1), ("grid", 6), ("generic", 1)])
@@ -121,18 +134,18 @@ def test_spatial_neighbors_non_visium(self, non_visium_adata: AnnData):
         )
 
         spatial_neighbors(non_visium_adata, n_neighs=3, coord_type=None)
-        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].A
+        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].toarray()
 
         np.testing.assert_array_equal(spatial_graph, correct_knn_graph)
 
         spatial_neighbors(non_visium_adata, radius=5.0, coord_type=None)
-        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].A
+        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].toarray()
 
         np.testing.assert_array_equal(spatial_graph, correct_radius_graph)
 
         spatial_neighbors(non_visium_adata, delaunay=True, coord_type=None)
-        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].A
-        spatial_dist = non_visium_adata.obsp[Key.obsp.spatial_dist()].A
+        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].toarray()
+        spatial_dist = non_visium_adata.obsp[Key.obsp.spatial_dist()].toarray()
 
         np.testing.assert_array_equal(spatial_graph, self._gt_dgraph)
         np.testing.assert_allclose(spatial_dist, self._gt_ddist)
@@ -144,12 +157,12 @@ def test_spatial_neighbors_non_visium(self, non_visium_adata: AnnData):
         spatial_neighbors(non_visium_adata2, delaunay=True, coord_type=None)
 
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].A,
-            non_visium_adata.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch1].obsp[Key.obsp.spatial_conn()].toarray(),
+            non_visium_adata.obsp[Key.obsp.spatial_conn()].toarray(),
         )
         np.testing.assert_array_equal(
-            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].A,
-            non_visium_adata2.obsp[Key.obsp.spatial_conn()].A,
+            adata_concat[adata_concat.obs["library_id"] == batch2].obsp[Key.obsp.spatial_conn()].toarray(),
+            non_visium_adata2.obsp[Key.obsp.spatial_conn()].toarray(),
         )
 
     @pytest.mark.parametrize("set_diag", [False, True])
@@ -166,9 +179,15 @@ def test_radius_min_max(self, non_visium_adata: AnnData, radius: tuple[float, fl
             ixs = np.arange(len(gt_dgraph))
             gt_dgraph[ixs, ixs] = 1.0
 
-        spatial_neighbors(non_visium_adata, delaunay=True, coord_type=None, radius=radius, set_diag=set_diag)
-        spatial_dist = non_visium_adata.obsp[Key.obsp.spatial_dist()].A
-        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].A
+        spatial_neighbors(
+            non_visium_adata,
+            delaunay=True,
+            coord_type=None,
+            radius=radius,
+            set_diag=set_diag,
+        )
+        spatial_dist = non_visium_adata.obsp[Key.obsp.spatial_dist()].toarray()
+        spatial_graph = non_visium_adata.obsp[Key.obsp.spatial_conn()].toarray()
 
         np.testing.assert_allclose(spatial_graph, gt_dgraph)
         np.testing.assert_allclose(spatial_dist, gt_ddist)
@@ -180,8 +199,8 @@ def test_copy(self, non_visium_adata: AnnData):
         assert isspmatrix_csr(dist)
         assert Key.obsp.spatial_conn() not in non_visium_adata.obsp
         assert Key.obsp.spatial_dist() not in non_visium_adata.obsp
-        np.testing.assert_allclose(dist.A, self._gt_ddist)
-        np.testing.assert_allclose(conn.A, self._gt_dgraph)
+        np.testing.assert_allclose(dist.toarray(), self._gt_ddist)
+        np.testing.assert_allclose(conn.toarray(), self._gt_dgraph)
 
     @pytest.mark.parametrize("percentile", [99.0, 95.0])
     def test_percentile_filtering(self, adata_hne: AnnData, percentile: float, coord_type="generic"):

tests/graph/test_utils.py

@@ -15,12 +15,12 @@ class TestUtils:
     def test_shuffle_group(self, cluster_annotations_type: type, library_annotations_type: type, seed: int):
         size = 6
         rng = np.random.default_rng(seed)
-        if cluster_annotations_type == int:
+        if isinstance(cluster_annotations_type, int):
             libraries = pd.Series(rng.choice([1, 2, 3, 4], size=(size,)), dtype="category")
         else:
             libraries = pd.Series(rng.choice(["a", "b", "c"], size=(size,)), dtype="category")
 
-        if library_annotations_type == int:
+        if isinstance(library_annotations_type, int):
             cluster_annotations = rng.choice([1, 2, 3, 4], size=(size,))
         else:
             cluster_annotations = rng.choice(["X", "Y", "Z"], size=(size,))

tests/image/test_container.py

@@ -1060,9 +1060,9 @@ def test_explicit(self, z: int):
     @pytest.mark.parametrize("typ", [list, dict])
     def test_set(self, typ: type, unique: bool):
         if unique:
-            new_ids = ["0", "1"] if typ == list else {"a": "0", "b": "1"}
+            new_ids = ["0", "1"] if isinstance(typ, list) else {"a": "0", "b": "1"}
         else:
-            new_ids = ["0", "0"] if typ == list else {"a": "b"}
+            new_ids = ["0", "0"] if isinstance(typ, list) else {"a": "b"}
         img = ImageContainer(np.random.normal(size=(2, 3, 4, 5)), dims=["z", "y", "x", "c"], library_id=["a", "b"])
 
         if not unique: