Skip to content

Fix TableModel validator to accept pandas StringDtype #1063

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
jlr13 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix TableModel validator to accept pandas StringDtype #1063

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
580c81b
Fix TableModel validator to accept pandas StringDtype
Feb 5, 2026
eb19535
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Feb 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 31 additions & 17 deletions src/spatialdata/models/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1047,25 +1047,39 @@ def _validate_table_annotation_metadata(self, data: AnnData) -> None:
raise ValueError(f"`{attr[self.REGION_KEY_KEY]}` not found in `adata.obs`. Please create the column.")
if attr[self.INSTANCE_KEY] not in data.obs:
raise ValueError(f"`{attr[self.INSTANCE_KEY]}` not found in `adata.obs`. Please create the column.")
if (
(dtype := data.obs[attr[self.INSTANCE_KEY]].dtype)
not in [
int,
np.int16,
np.uint16,
np.int32,
np.uint32,
np.int64,
np.uint64,
"O",
]
and not pd.api.types.is_string_dtype(data.obs[attr[self.INSTANCE_KEY]])
or (dtype == "O" and (val_dtype := type(data.obs[attr[self.INSTANCE_KEY]].iloc[0])) is not str)
dtype = data.obs[attr[self.INSTANCE_KEY]].dtype

# Check if dtype is valid for instance_key column
is_valid_dtype = False

# Check for integer types
if dtype in [int, np.int16, np.uint16, np.int32, np.uint32, np.int64, np.uint64] or isinstance(
dtype, pd.StringDtype
):
dtype = dtype if dtype != "O" else val_dtype
is_valid_dtype = True
# Check for CategoricalDtype with string categories
elif isinstance(dtype, pd.CategoricalDtype):
if pd.api.types.is_string_dtype(dtype.categories.dtype) or isinstance(
dtype.categories.dtype, pd.StringDtype
):
is_valid_dtype = True
# Check for object dtype with string values
elif dtype == "O":
if len(data.obs[attr[self.INSTANCE_KEY]]) > 0:
val_dtype = type(data.obs[attr[self.INSTANCE_KEY]].iloc[0])
if val_dtype is str:
is_valid_dtype = True
else:
# Empty column with object dtype is acceptable
is_valid_dtype = True
# Fallback check using pandas is_string_dtype
elif pd.api.types.is_string_dtype(dtype):
is_valid_dtype = True

if not is_valid_dtype:
raise TypeError(
f"Only int, np.int16, np.int32, np.int64, uint equivalents or string allowed as dtype for "
f"instance_key column in obs. Dtype found to be {dtype}"
f"Only int, np.int16, np.int32, np.int64, uint equivalents, pandas StringDtype, or string "
f"allowed as dtype for instance_key column in obs. Dtype found to be {dtype}"
)
expected_regions = attr[self.REGION_KEY] if isinstance(attr[self.REGION_KEY], list) else [attr[self.REGION_KEY]]
found_regions = data.obs[attr[self.REGION_KEY_KEY]].unique().tolist()
Expand Down
Loading