Merge branch 'main' into ODSC-59115/mlforecast_add_data

Author: ahosler

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

@@ -39,7 +39,7 @@ def __init__(self, models, k=5, subsample_ratio=0.20):
     def generate_cutoffs(self, unique_dates, horizon):
         sorted_dates = np.sort(unique_dates)
         train_window_size = [len(sorted_dates) - (i + 1) * horizon for i in range(self.k)]
-        valid_train_window_size = [ws for ws in train_window_size if ws >= horizon * 3]
+        valid_train_window_size = [ws for ws in train_window_size if ws >= horizon * 2]
         if len(valid_train_window_size) < self.k:
             logger.warn(f"Only {valid_train_window_size} backtests can be created")
         cut_offs = sorted_dates[-horizon - 1:-horizon * (self.k + 1):-horizon][:len(valid_train_window_size)]
@@ -95,7 +95,9 @@ def create_operator_config(self, operator_config, backtest, model, historical_da
         backtest_op_config_draft = operator_config.to_dict()
         backtest_spec = backtest_op_config_draft["spec"]
         backtest_spec["historical_data"]["url"] = historical_data_url
-        backtest_spec["additional_data"]["url"] = additional_data_url
+        if backtest_spec["additional_data"]:
+            backtest_spec["additional_data"]["url"] = additional_data_url
+        backtest_spec["test_data"] = {}
         backtest_spec["test_data"]["url"] = test_data_url
         backtest_spec["model"] = model
         backtest_spec['model_kwargs'] = None

tests/operators/forecast/test_datasets.py

@@ -33,7 +33,7 @@
     "neuralprophet",
     "autots",
     "mlforecast",
-    # "auto",
+    "auto-select",
 ]
 
 TEMPLATE_YAML = {
@@ -134,12 +134,17 @@ def test_load_datasets(model, data_details):
             yaml_i["spec"]["model_kwargs"] = {"model_list": "superfast"}
         if model == "automlx":
             yaml_i["spec"]["model_kwargs"] = {"time_budget": 2}
+        if model == "auto-select":
+            yaml_i["spec"]["model_kwargs"] = {"model_list": ['prophet', 'arima', 'mlforecast']}
+            if dataset_name == f'{DATASET_PREFIX}dataset4.csv':
+                pytest.skip("Skipping dataset4 with auto-select")  # todo:// ODSC-58584
 
         run(yaml_i, backend="operator.local", debug=False)
         subprocess.run(f"ls -a {output_data_path}", shell=True)
         if yaml_i["spec"]["generate_explanations"] and model not in [
             "automlx",
             "mlforecast",
+            "auto-select"
         ]:
             verify_explanations(
                 tmpdirname=tmpdirname,