1308: Fix grouping in max_date operation

cdisc_rules_engine/operations/max_date.py

@@ -12,7 +12,9 @@ def _execute_operation(self):
             else:
                 result = max_date.isoformat()
         else:
-            result = self.params.dataframe.groupby(self.params.grouping).max()
+            result = self.params.dataframe.groupby(
+                self.params.grouping, as_index=False, group_keys=False
+            ).max()
         if isinstance(result, pd.Series):
             result = result.apply(lambda x: x.isoformat() if pd.notna(x) else "")
         elif isinstance(result, pd.DataFrame):

tests/unit/test_operations/test_max_date.py

@@ -13,31 +13,110 @@
 
 
 @pytest.mark.parametrize(
-    "data, expected, dataset_type",
+    "data, expected, dataset_type, grouping",
     [
         (
             {"dates": ["2001-01-01", "", "2022-01-05"]},
             pd.to_datetime("2022-01-05").isoformat(),
             PandasDataset,
+            None,
         ),
-        ({"dates": [None, None]}, "", PandasDataset),
+        ({"dates": [None, None]}, "", PandasDataset, None),
         (
             {"dates": ["2001-01-01", "", "2022-01-05"]},
             pd.to_datetime("2022-01-05").isoformat(),
             DaskDataset,
+            None,
+        ),
+        ({"dates": [None, None]}, "", DaskDataset, None),
+        (
+            {
+                "dates": ["2025-10-10", "2025-10-15", "2025-12-02", "2025-12-11"],
+                "USUBJID": ["00002", "00002", "00003", "00003"],
+            },
+            PandasDataset.from_records(
+                [
+                    {
+                        "dates": "2025-10-10",
+                        "USUBJID": "00002",
+                        "operation_id": "2025-10-15",
+                    },
+                    {
+                        "dates": "2025-10-15",
+                        "USUBJID": "00002",
+                        "operation_id": "2025-10-15",
+                    },
+                    {
+                        "dates": "2025-12-02",
+                        "USUBJID": "00003",
+                        "operation_id": "2025-12-11",
+                    },
+                    {
+                        "dates": "2025-12-11",
+                        "USUBJID": "00003",
+                        "operation_id": "2025-12-11",
+                    },
+                ]
+            ),
+            PandasDataset,
+            ["USUBJID"],
+        ),
+        (
+            {
+                "dates": ["2025-10-10", "2025-10-15", "2025-12-02", "2025-12-11"],
+                "USUBJID": ["00002", "00002", "00003", "00003"],
+            },
+            DaskDataset.from_records(
+                [
+                    {
+                        "dates": "2025-10-10",
+                        "USUBJID": "00002",
+                        "operation_id": "2025-10-15",
+                    },
+                    {
+                        "dates": "2025-10-15",
+                        "USUBJID": "00002",
+                        "operation_id": "2025-10-15",
+                    },
+                    {
+                        "dates": "2025-12-02",
+                        "USUBJID": "00003",
+                        "operation_id": "2025-12-11",
+                    },
+                    {
+                        "dates": "2025-12-11",
+                        "USUBJID": "00003",
+                        "operation_id": "2025-12-11",
+                    },
+                ]
+            ),
+            DaskDataset,
+            ["USUBJID"],
         ),
-        ({"dates": [None, None]}, "", DaskDataset),
     ],
 )
-def test_minimum(data, expected, dataset_type, operation_params: OperationParams):
+def test_max_date(
+    data,
+    expected,
+    dataset_type,
+    grouping: str | None,
+    operation_params: OperationParams,
+):
     config = ConfigService()
     cache = CacheServiceFactory(config).get_cache_service()
     data_service = DataServiceFactory(config, cache).get_data_service()
     operation_params.dataframe = dataset_type.from_dict(data)
     operation_params.target = "dates"
+    operation_params.grouping = grouping
     result = MaxDate(
         operation_params, dataset_type.from_dict(data), cache, data_service
     ).execute()
     assert operation_params.operation_id in result
-    for val in result[operation_params.operation_id]:
-        assert val == expected
+
+    if isinstance(expected, PandasDataset) and dataset_type is PandasDataset:
+        assert result.data.equals(expected.data)
+    elif isinstance(expected, DaskDataset) and dataset_type is DaskDataset:
+        assert expected.equals(result)
+    else:
+        for val in result[operation_params.operation_id]:
+            assert val == expected