Revert "Update preprocessing flag in automlx.py"

CODEOWNERS

@@ -1 +1 @@
-* @darenr @mayoor @mrDzurb @VipulMascarenhas @qiuosier @ahosler
+* @darenr @mayoor @mrDzurb @VipulMascarenhas @qiuosier

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

@@ -14,7 +14,7 @@ class SupportedModels(str, metaclass=ExtendedEnumMeta):
     Prophet = "prophet"
     Arima = "arima"
     NeuralProphet = "neuralprophet"
-    LGBForecast = "lgbforecast"
+    MLForecast = "mlforecast"
     AutoMLX = "automlx"
     AutoTS = "autots"
     Auto = "auto"

ads/opctl/operator/lowcode/forecast/model/automlx.py

@@ -49,7 +49,7 @@ def set_kwargs(self):
         time_budget = model_kwargs_cleaned.pop("time_budget", -1)
         model_kwargs_cleaned[
             "preprocessing"
-        ] = self.spec.preprocessing.enabled or model_kwargs_cleaned.get("preprocessing", True)
+        ] = self.spec.preprocessing or model_kwargs_cleaned.get("preprocessing", True)
         return model_kwargs_cleaned, time_budget
 
     def preprocess(self, data, series_id=None):  # TODO: re-use self.le for explanations

ads/opctl/operator/lowcode/forecast/model/factory.py

@@ -33,7 +33,7 @@ class ForecastOperatorModelFactory:
         SupportedModels.Prophet: ProphetOperatorModel,
         SupportedModels.Arima: ArimaOperatorModel,
         SupportedModels.NeuralProphet: NeuralProphetOperatorModel,
-        SupportedModels.LGBForecast: MLForecastOperatorModel,
+        SupportedModels.MLForecast: MLForecastOperatorModel,
         SupportedModels.AutoMLX: AutoMLXOperatorModel,
         SupportedModels.AutoTS: AutoTSOperatorModel
     }

ads/opctl/operator/lowcode/forecast/model/ml_forecast.py

@@ -1,18 +1,18 @@
 #!/usr/bin/env python
+# -*- coding: utf-8 -*--
 
 # Copyright (c) 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
-import numpy as np
 import pandas as pd
+import numpy as np
 
-from ads.common.decorator import runtime_dependency
 from ads.opctl import logger
+from ads.common.decorator import runtime_dependency
 from ads.opctl.operator.lowcode.forecast.utils import _select_plot_list
-
-from ..const import ForecastOutputColumns, SupportedModels
-from ..operator_config import ForecastOperatorConfig
 from .base_model import ForecastOperatorBaseModel
 from .forecast_datasets import ForecastDatasets, ForecastOutput
+from ..operator_config import ForecastOperatorConfig
+from ..const import ForecastOutputColumns, SupportedModels
 
 
 class MLForecastOperatorModel(ForecastOperatorBaseModel):
@@ -58,25 +58,18 @@ def _train_model(self, data_train, data_test, model_kwargs):
             from mlforecast.target_transforms import Differences
 
             lgb_params = {
-                "verbosity": model_kwargs.get("verbosity", -1),
-                "num_leaves": model_kwargs.get("num_leaves", 512),
+                "verbosity": -1,
+                "num_leaves": 512,
             }
             additional_data_params = {}
             if len(self.datasets.get_additional_data_column_names()) > 0:
                 additional_data_params = {
-                    "target_transforms": [
-                        Differences([model_kwargs.get("Differences", 12)])
-                    ],
+                    "target_transforms": [Differences([12])],
                     "lags": model_kwargs.get("lags", [1, 6, 12]),
                     "lag_transforms": (
                         {
                             1: [ExpandingMean()],
-                            12: [
-                                RollingMean(
-                                    window_size=model_kwargs.get("RollingMean", 24),
-                                    min_samples=1,
-                                )
-                            ],
+                            12: [RollingMean(window_size=24)],
                         }
                     ),
                 }
@@ -154,7 +147,7 @@ def _train_model(self, data_train, data_test, model_kwargs):
                 )
 
                 self.model_parameters[s_id] = {
-                    "framework": SupportedModels.LGBForecast,
+                    "framework": SupportedModels.MLForecast,
                     **lgb_params,
                 }
 
@@ -211,10 +204,10 @@ def _generate_report(self):
             self.datasets.list_series_ids(),
         )
 
-        # Section 2: LGBForecast Model Parameters
+        # Section 2: MlForecast Model Parameters
         sec2_text = rc.Block(
-            rc.Heading("LGBForecast Model Parameters", level=2),
-            rc.Text("These are the parameters used for the LGBForecast model."),
+            rc.Heading("MlForecast Model Parameters", level=2),
+            rc.Text("These are the parameters used for the MlForecast model."),
         )
 
         blocks = [
@@ -228,7 +221,7 @@ def _generate_report(self):
 
         all_sections = [sec1_text, sec_1, sec2_text, sec_2]
         model_description = rc.Text(
-            "LGBForecast uses mlforecast framework to perform time series forecasting using machine learning models"
+            "mlforecast is a framework to perform time series forecasting using machine learning models"
             "with the option to scale to massive amounts of data using remote clusters."
             "Fastest implementations of feature engineering for time series forecasting in Python."
             "Support for exogenous variables and static covariates."

ads/opctl/operator/lowcode/forecast/schema.yaml

@@ -379,7 +379,7 @@ spec:
         - prophet
         - arima
         - neuralprophet
-        - lgbforecast
+        - mlforecast
         - automlx
         - autots
         - auto-select

tests/operators/forecast/test_datasets.py

@@ -32,7 +32,7 @@
     "prophet",
     "neuralprophet",
     "autots",
-    "lgbforecast",
+    "mlforecast",
     "auto-select",
 ]
 
@@ -135,15 +135,15 @@ def test_load_datasets(model, data_details):
         if model == "automlx":
             yaml_i["spec"]["model_kwargs"] = {"time_budget": 2}
         if model == "auto-select":
-            yaml_i["spec"]["model_kwargs"] = {"model_list": ['prophet', 'arima', 'lgbforecast']}
+            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",
-            "lgbforecast",
+            "mlforecast",
             "auto-select"
         ]:
             verify_explanations(

tests/operators/forecast/test_errors.py

@@ -141,7 +141,7 @@
     "prophet",
     "neuralprophet",
     "autots",
-    "lgbforecast",
+    "mlforecast",
     # "auto",
 ]
 
@@ -687,7 +687,7 @@ def test_arima_automlx_errors(operator_setup, model):
                 in error_content["13"]["error"]
             ), "Error message mismatch"
 
-    if model not in ["autots", "automlx", "lgbforecast"]:
+    if model not in ["autots", "automlx", "mlforecast"]:
         global_fn = f"{tmpdirname}/results/global_explanation.csv"
         assert os.path.exists(
             global_fn