Skip to content

fix codelist operations type inference for empty dataframes #1709

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

Merged
gerrycampion merged 5 commits into from
Apr 28, 2026
Merged

fix codelist operations type inference for empty dataframes #1709

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
f999224
fix codelist operations type inference for empty dataframes
gerrycampion Apr 24, 2026
25b1b54
added unit tests
gerrycampion Apr 27, 2026
c933f4d
Fixed str dtype
gerrycampion Apr 27, 2026
5f62f89
removed casting from tests
gerrycampion Apr 27, 2026
1128e63
Merge branch 'main' into 1651-new-version-of-core-engine-causes-error…
gerrycampion Apr 27, 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
6 changes: 6 additions & 0 deletions cdisc_rules_engine/operations/codelist_extensible.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,12 @@ def _handle_multiple_versions(self) -> pd.Series:
self.params.ct_package_type, unique_ct_versions
)
ct_df = self.evaluation_dataset.__class__.from_dict(ct_data)
ct_df = ct_df.astype(
Copy link
Copy Markdown
Collaborator

@RamilCDISC RamilCDISC Apr 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The PR only converts the ct_df to string but evaluation dataset is still not made safe for merge. if it has empty columns the merge can fail. I have noticed that in the test the evaluation dataset was made safe manually by converting it to string. That let me to think that we need to make the evaluation dataset safe here too to merge without errors.

Copy link
Copy Markdown
Collaborator Author

@gerrycampion gerrycampion Apr 27, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

i believe that the fix for the types allowed us to have empty evaluation datasets as well. I've removed the conversions from the tests.

{
"version": "string",
"codelist_code": "string",
}
)
if self.params.codelist_code in self.evaluation_dataset.columns:
is_extensible = self.evaluation_dataset.merge(
ct_df.data,
Expand Down
6 changes: 6 additions & 0 deletions cdisc_rules_engine/operations/codelist_terms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,6 +58,12 @@ def _handle_multiple_versions(self) -> pd.Series:
self.params.ct_package_type, unique_ct_versions
)
ct_df = self.evaluation_dataset.__class__.from_dict(ct_data)
ct_df = ct_df.astype(
{
"version": "string",
"codelist_code": "string",
}
)
if self.params.codelist_code in self.evaluation_dataset.columns:
result = self.evaluation_dataset.merge(
ct_df.data,
Expand Down
20 changes: 16 additions & 4 deletions tests/unit/test_operations/test_codelist_extensible.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,40 +124,52 @@ def test_empty_metadata(operation_params):


@mark.parametrize(
"package_type, codelist_code, expected",
"package_type, codelist_code, versions, codelist_codes, expected",
[
(
"mock_package",
"codelist_code",
["v1", "v2", "v3"],
["C1", "C2", "C3"],
[True, False, None],
),
(
"mock_package",
"C1",
["v1", "v2", "v3"],
["C1", "C2", "C3"],
[True, True, True],
),
(
"missing_package",
"codelist_code",
["v1", "v2", "v3"],
["C1", "C2", "C3"],
[None, None, None],
),
("mock_package", "codelist_code", [], [], []),
],
)
def test_multiple_versions(
operation_params, mock_metadata, package_type, codelist_code, expected
operation_params,
mock_metadata,
package_type,
codelist_code,
versions,
codelist_codes,
expected,
):
operation_params.ct_package_type = package_type
operation_params.ct_version = "version"
operation_params.codelist_code = codelist_code
versions = ["v1", "v2", "v3"]

library_metadata = LibraryMetadataContainer()
for version in versions:
mock_metadata[f"mock_package-{version}"] = mock_metadata["mock_package"]
library_metadata._ct_package_metadata = mock_metadata

evaluation_dataset = PandasDataset.from_dict(
{"version": versions, "codelist_code": ["C1", "C2", "C3"]}
{"version": versions, "codelist_code": codelist_codes}
)

operation = CodelistExtensible(
Expand Down
36 changes: 36 additions & 0 deletions tests/unit/test_operations/test_codelist_terms.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -323,3 +323,39 @@ def test_multiple_versions(
except RuleExecutionError:
result = pd.Series(RuleExecutionError)
assert result.equals(pd.Series(expected))


def test_empty_dataset_multiple_versions(
operation_params,
mock_metadata,
):
operation_params.ct_package_type = "mock_package"
operation_params.ct_version = "version"
operation_params.codelist_code = "codelist_code"
operation_params.term_code = "t_code"
operation_params.term_value = None
operation_params.term_pref_term = None
operation_params.returntype = None

library_metadata = LibraryMetadataContainer()
library_metadata._ct_package_metadata = mock_metadata

evaluation_dataset = PandasDataset.from_dict(
{
"version": [],
"codelist_code": [],
"t_code": [],
"t_value": [],
"t_pref_term": [],
}
)

operation = CodelistTerms(
operation_params,
evaluation_dataset,
MagicMock(),
MagicMock(),
library_metadata,
)
result = operation._execute_operation()
assert result.tolist() == []
Loading