spatialdata 0.7.0.dev1__tar.gz → 0.7.1__tar.gz

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/.pre-commit-config.yaml

@@ -9,7 +9,7 @@ ci:
     skip: []
 repos:
     - repo: https://github.com/rbubley/mirrors-prettier
-      rev: v3.7.4
+      rev: v3.8.1
       hooks:
           - id: prettier
             exclude: ^.github/workflows/test.yaml
@@ -20,7 +20,7 @@ repos:
             additional_dependencies: [numpy, types-requests]
             exclude: tests/|docs/
     - repo: https://github.com/astral-sh/ruff-pre-commit
-      rev: v0.14.10
+      rev: v0.14.14
       hooks:
           - id: ruff
             args: [--fix, --exit-non-zero-on-fix]

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spatialdata
-Version: 0.7.0.dev1
+Version: 0.7.1
 Summary: Spatial data format.
 Project-URL: Documentation, https://spatialdata.scverse.org/en/latest
 Project-URL: Source, https://github.com/scverse/spatialdata.git
@@ -42,7 +42,7 @@ Requires-Dist: anndata>=0.9.1
 Requires-Dist: annsel>=0.1.2
 Requires-Dist: click
 Requires-Dist: dask-image
-Requires-Dist: dask>=2025.2.0
+Requires-Dist: dask<2026.1.2,>=2025.2.0
 Requires-Dist: datashader
 Requires-Dist: fsspec[http,s3]
 Requires-Dist: geopandas>=0.14
@@ -56,7 +56,7 @@ Requires-Dist: pooch
 Requires-Dist: pyarrow
 Requires-Dist: rich
 Requires-Dist: scikit-image
-Requires-Dist: scipy
+Requires-Dist: scipy!=1.17.0
 Requires-Dist: setuptools
 Requires-Dist: shapely>=2.0.1
 Requires-Dist: spatial-image>=1.2.3
@@ -68,6 +68,7 @@ Requires-Dist: xarray>=2024.10.0
 Requires-Dist: zarr>=3.0.0
 Provides-Extra: benchmark
 Requires-Dist: asv; extra == 'benchmark'
+Requires-Dist: memray; extra == 'benchmark'
 Provides-Extra: dev
 Requires-Dist: bump2version; extra == 'dev'
 Requires-Dist: sentry-prevent-cli; extra == 'dev'

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.7.0.dev1'
-__version_tuple__ = version_tuple = (0, 7, 0, 'dev1')
+__version__ = version = '0.7.1'
+__version_tuple__ = version_tuple = (0, 7, 1)
 
 __commit_id__ = commit_id = None

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/docs/conf.py

@@ -123,6 +123,7 @@ exclude_patterns = [
     "tutorials/notebooks/notebooks/developers_resources/storage_format/Readme.md",
     "tutorials/notebooks/notebooks/examples/technology_stereoseq.ipynb",
     "tutorials/notebooks/notebooks/examples/technology_curio.ipynb",
+    "tutorials/notebooks/notebooks/examples/technology_cosmx.ipynb",
     "tutorials/notebooks/notebooks/examples/stereoseq_data/*",
 ]
 # Ignore warnings.

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/docs/contributing.md

@@ -74,6 +74,10 @@ Additionally, there's a CI job that tests against pre-releases of all dependenci
 
 By including this additional information, the document now provides a more comprehensive overview of the continuous integration process related to testing.
 
+### Integration testing
+
+Cross-repo integration testing is available in the [spatialdata-integration-testing](https://github.com/scverse/spatialdata-integration-testing/) repo. Please follow the instructions in the Readme. For questions ask Luca.
+
 ## Publishing a release
 
 ### Updating the version number
@@ -87,6 +91,7 @@ Before making a release, you need to update the version number. Please adhere to
 > 3.  PATCH version when you make backwards compatible bug fixes.
 >
 > Additional labels for pre-release and build metadata are available as extensions to the MAJOR.MINOR.PATCH format.
+> For pre-release please use the aX suffix, such as v0.7.0a0, v0.7.0a1. Do not use the devX suffix since it doesn't support multiple incremental versions.
 
 You can find the [labels for pre-release in this page](https://packaging.python.org/en/latest/discussions/versioning/#valid-version-numbers).
 
@@ -97,8 +102,6 @@ If you use `bump2version`, you can run one of the following commands in the root
 bump2version patch
 bump2version minor
 bump2version major
-# if you want to create a pre-release
-bump2version --new-version 1.2.0rc1
 ```
 
 Once you are done, run

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
     "annsel>=0.1.2",
     "click",
     "dask-image",
-    "dask>=2025.2.0",
+    "dask>=2025.2.0,<2026.1.2",
     "datashader",
     "fsspec[s3,http]",
     "geopandas>=0.14",
@@ -43,7 +43,7 @@ dependencies = [
     "shapely>=2.0.1",
     "spatial_image>=1.2.3",
     "scikit-image",
-    "scipy",
+    "scipy!=1.17.0",
     "typing_extensions>=4.8.0",
     "universal_pathlib>=0.2.6",
     "xarray>=2024.10.0",
@@ -78,6 +78,7 @@ docs = [
 ]
 benchmark = [
     "asv",
+    "memray",
 ]
 torch = [
     "torch"

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/src/spatialdata/models/models.py

@@ -1061,6 +1061,21 @@ class TableModel:
         if len(set(expected_regions).symmetric_difference(set(found_regions))) > 0:
             raise ValueError(f"Regions in the AnnData object and `{attr[self.REGION_KEY_KEY]}` do not match.")
 
+        # Warning for object/string columns with NaN in region_key or instance_key
+        instance_key = attr[self.INSTANCE_KEY]
+        region_key = attr[self.REGION_KEY_KEY]
+        for key_name, key_value in [("region_key", region_key), ("instance_key", instance_key)]:
+            if key_value in data.obs:
+                col = data.obs[key_value]
+                col_dtype = col.dtype
+                if (col_dtype == "object" or pd.api.types.is_string_dtype(col_dtype)) and col.isna().any():
+                    logger.warning(
+                        f"The {key_name} column '{key_value}' is of {col_dtype} type and contains NaN values. "
+                        "After writing and reading with AnnData, NaN values may (depending on the AnnData version) "
+                        "be converted to strings. This may cause issues when matching instances across read/write "
+                        "cycles."
+                    )
+
     def validate(
         self,
         data: AnnData,

{spatialdata-0.7.0.dev1 → spatialdata-0.7.1}/tests/io/test_readwrite.py

@@ -1065,3 +1065,45 @@ def test_read_sdata(tmp_path: Path, points: SpatialData) -> None:
     assert_spatial_data_objects_are_identical(sdata_from_path, sdata_from_str)
     assert_spatial_data_objects_are_identical(sdata_from_path, sdata_from_upath)
     assert_spatial_data_objects_are_identical(sdata_from_path, sdata_from_zarr_group)
+
+
+def test_sdata_with_nan_in_obs() -> None:
+    """Test writing SpatialData with mixed string/NaN values in obs works correctly.
+
+    Regression test for https://github.com/scverse/spatialdata/issues/399
+    Previously this raised TypeError: expected unicode string, found nan.
+    Now the write succeeds, though NaN values in object-dtype columns are
+    converted to the string "nan" after round-trip.
+    """
+    from spatialdata.models import TableModel
+
+    table = TableModel.parse(
+        AnnData(
+            obs=pd.DataFrame(
+                {
+                    "region": ["region1", "region2"],
+                    "instance": [0, 0],
+                    "column_only_region1": ["string", np.nan],
+                    "column_only_region2": [np.nan, 3],
+                }
+            )
+        ),
+        region_key="region",
+        instance_key="instance",
+        region=["region1", "region2"],
+    )
+    sdata = SpatialData(tables={"table": table})
+    assert sdata["table"].obs["column_only_region1"].iloc[1] is np.nan
+    assert np.isnan(sdata["table"].obs["column_only_region2"].iloc[0])
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        path = os.path.join(tmpdir, "data.zarr")
+        sdata.write(path)
+
+        sdata2 = SpatialData.read(path)
+        assert "column_only_region1" in sdata2["table"].obs.columns
+        assert sdata2["table"].obs["column_only_region1"].iloc[0] == "string"
+        assert sdata2["table"].obs["column_only_region2"].iloc[1] == 3
+        # After round-trip, NaN in object-dtype column becomes string "nan"
+        assert sdata2["table"].obs["column_only_region1"].iloc[1] == "nan"
+        assert np.isnan(sdata2["table"].obs["column_only_region2"].iloc[0])