Add warning for AUTO_SELECT_SERIES usage and restore test case for missing data

Author: codeloop

ads/opctl/operator/lowcode/forecast/__main__.py

@@ -81,6 +81,11 @@ def operate(operator_config: ForecastOperatorConfig) -> ForecastResults:
             and not operator_config.spec.target_category_columns
         ):
 
+            logger.warning(
+                "AUTO_SELECT_SERIES cannot be run with a single-series dataset or when "
+                "'target_category_columns' is not provided. Falling back to AUTO_SELECT."
+            )
+
             operator_config.spec.model = AUTO_SELECT
             model = ForecastOperatorModelFactory.get_model(operator_config, datasets)
         # For other cases, use the single selected model

tests/operators/forecast/test_datasets.py

@@ -414,43 +414,43 @@ def run_operator(
 #         generate_train_metrics = True
 
 
-# def test_missing_data_autoselect_series():
-#     """Test case for auto-select-series with missing data."""
-#     data = {
-#         "Date": pd.to_datetime(
-#             [
-#                 "2023-01-01",
-#                 "2023-01-02",
-#                 "2023-01-03",
-#                 "2023-01-04",
-#                 "2023-01-05",
-#                 "2023-01-06",
-#                 "2023-01-07",
-#                 "2023-01-08",
-#                 "2023-01-09",
-#                 "2023-01-10",
-#             ]
-#         ),
-#         "Y": [1, 2, np.nan, 4, 5, 6, 7, 8, 9, 10],
-#         "Category": ["A", "A", "A", "A", "A", "A", "A", "A", "A", "A"],
-#     }
-#     df = pd.DataFrame(data)
+def test_missing_data_autoselect_series():
+    """Test case for auto-select-series with missing data."""
+    data = {
+        "Date": pd.to_datetime(
+            [
+                "2023-01-01",
+                "2023-01-02",
+                "2023-01-03",
+                "2023-01-04",
+                "2023-01-05",
+                "2023-01-06",
+                "2023-01-07",
+                "2023-01-08",
+                "2023-01-09",
+                "2023-01-10",
+            ]
+        ),
+        "Y": [1, 2, np.nan, 4, 5, 6, 7, 8, 9, 10],
+        "Category": ["A", "A", "A", "A", "A", "A", "A", "A", "A", "A"],
+    }
+    df = pd.DataFrame(data)
 
-#     with tempfile.TemporaryDirectory() as tmpdirname:
-#         output_data_path = f"{tmpdirname}/results"
-#         yaml_i = deepcopy(TEMPLATE_YAML)
-#         yaml_i["spec"]["model"] = "auto-select-series"
-#         yaml_i["spec"]["historical_data"].pop("url")
-#         yaml_i["spec"]["historical_data"]["data"] = df
-#         yaml_i["spec"]["target_column"] = "Y"
-#         yaml_i["spec"]["datetime_column"]["name"] = "Date"
-#         yaml_i["spec"]["target_category_columns"] = ["Category"]
-#         yaml_i["spec"]["horizon"] = 2
-#         yaml_i["spec"]["output_directory"]["url"] = output_data_path
-
-#         operator_config = ForecastOperatorConfig.from_dict(yaml_i)
-#         forecast_operate(operator_config)
-#         check_output_for_errors(output_data_path)
+    with tempfile.TemporaryDirectory() as tmpdirname:
+        output_data_path = f"{tmpdirname}/results"
+        yaml_i = deepcopy(TEMPLATE_YAML)
+        yaml_i["spec"]["model"] = "auto-select-series"
+        yaml_i["spec"]["historical_data"].pop("url")
+        yaml_i["spec"]["historical_data"]["data"] = df
+        yaml_i["spec"]["target_column"] = "Y"
+        yaml_i["spec"]["datetime_column"]["name"] = "Date"
+        yaml_i["spec"]["target_category_columns"] = ["Category"]
+        yaml_i["spec"]["horizon"] = 2
+        yaml_i["spec"]["output_directory"]["url"] = output_data_path
+
+        operator_config = ForecastOperatorConfig.from_dict(yaml_i)
+        forecast_operate(operator_config)
+        check_output_for_errors(output_data_path)
 
 
 if __name__ == "__main__":