used pre-prepared input for categorical-int-nan data

apis/python/tests/test_basic_anndata_io.py

@@ -1,4 +1,3 @@
-import math
 import pathlib
 import tempfile
 from pathlib import Path
@@ -39,6 +38,24 @@ def h5ad_file_uns_string_array(request):
     return input_path
 
 
+@pytest.fixture
+def h5ad_file_categorical_int_nan(request):
+    # This has obs["categ_int_nan"] as a categorical int but with math.nan as a
+    # "not-in-the-category" indicator. Such H5AD files do arise in the wild.
+    #
+    # Reference:
+    #   import anndata as ad
+    #   import pandas  as pd
+    #   import math
+    #   adata = adata.read_h5ad("whatever.h5ad")
+    #   s = pd.Series(list(range(80)), dtype="category")
+    #   s[0] = math.nan
+    #   adata.obs["categ_int_nan"] = s
+    #   adata.write_h5ad("categorical_int_nan.h5ad")
+    input_path = HERE.parent / "testdata/categorical_int_nan.h5ad"
+    return input_path
+
+
 @pytest.fixture
 def adata(h5ad_file):
     return anndata.read_h5ad(h5ad_file)
@@ -482,13 +499,11 @@ def test_null_obs(adata, tmp_path: Path):
 # There exist in the wild AnnData files with categorical-int columns where the "not in the category"
 # is indicated by the presence of floating-point math.NaN in cells. Here we test that we can ingest
 # this.
-def test_obs_with_categorical_int_nan_enumeration(tmp_path, adata):
+def test_obs_with_categorical_int_nan_enumeration(
+    tmp_path, h5ad_file_categorical_int_nan
+):
     output_path = tmp_path.as_uri()
 
-    # Currently getting float not int here, failing to repro the problem
-    s = pd.Series(list(range(len(adata.obs))))
-    s[0] = math.nan
-    adata.obs["categ_int_nan"] = s
-
-    output_path = tmp_path.as_posix()
-    tiledbsoma.io.from_anndata(output_path, adata, measurement_name="RNA")
+    tiledbsoma.io.from_h5ad(
+        output_path, h5ad_file_categorical_int_nan, measurement_name="RNA"
+    )