Bump automlx version (#991)

Author: ahosler

.github/workflows/run-forecast-unit-tests.yml

@@ -56,7 +56,6 @@ jobs:
           $CONDA/bin/conda init
           source /home/runner/.bashrc
           pip install -r test-requirements-operators.txt
-          pip install "oracle-automlx[classic]>=24.2.0"
-          pip install "oracle-automlx[forecasting]>=24.2.0"
+          pip install "oracle-automlx[forecasting]>=24.4.0"
           pip install pandas>=2.2.0
           python -m pytest -v -p no:warnings --durations=5 tests/operators/forecast

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

@@ -1,18 +1,12 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from typing import Dict
 
-import click
-
-from ads.opctl import logger
-from ads.opctl.operator.common.utils import _load_yaml_from_uri
 from ads.opctl.operator.common.operator_yaml_generator import YamlGenerator
-
-from .const import SupportedModels
+from ads.opctl.operator.common.utils import _load_yaml_from_uri
 
 
 def init(**kwargs: Dict) -> str:
@@ -39,7 +33,7 @@ def init(**kwargs: Dict) -> str:
     #     type=click.Choice(SupportedModels.values()),
     #     default=SupportedModels.Auto,
     # )
-    model_type = "auto"
+    model_type = "prophet"
 
     return YamlGenerator(
         schema=_load_yaml_from_uri(__file__.replace("cmd.py", "schema.yaml"))

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

@@ -1,7 +1,6 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 from ads.common.extended_enum import ExtendedEnumMeta
@@ -17,7 +16,7 @@ class SupportedModels(str, metaclass=ExtendedEnumMeta):
     LGBForecast = "lgbforecast"
     AutoMLX = "automlx"
     AutoTS = "autots"
-    Auto = "auto"
+    # Auto = "auto"
 
 
 class SpeedAccuracyMode(str, metaclass=ExtendedEnumMeta):
@@ -28,7 +27,7 @@ class SpeedAccuracyMode(str, metaclass=ExtendedEnumMeta):
     HIGH_ACCURACY = "HIGH_ACCURACY"
     BALANCED = "BALANCED"
     FAST_APPROXIMATE = "FAST_APPROXIMATE"
-    ratio = dict()
+    ratio = {}
     ratio[HIGH_ACCURACY] = 1  # 100 % data used for generating explanations
     ratio[BALANCED] = 0.5  # 50 % data used for generating explanations
     ratio[FAST_APPROXIMATE] = 0  # constant

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

@@ -1,20 +1,19 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
-from ..const import SupportedModels, AUTO_SELECT
+from ..const import AUTO_SELECT, SupportedModels
+from ..model_evaluator import ModelEvaluator
 from ..operator_config import ForecastOperatorConfig
 from .arima import ArimaOperatorModel
 from .automlx import AutoMLXOperatorModel
 from .autots import AutoTSOperatorModel
 from .base_model import ForecastOperatorBaseModel
+from .forecast_datasets import ForecastDatasets
 from .neuralprophet import NeuralProphetOperatorModel
 from .prophet import ProphetOperatorModel
-from .forecast_datasets import ForecastDatasets
-from .ml_forecast import MLForecastOperatorModel
-from ..model_evaluator import ModelEvaluator
+
 
 class UnSupportedModelError(Exception):
     def __init__(self, model_type: str):
@@ -33,9 +32,9 @@ class ForecastOperatorModelFactory:
         SupportedModels.Prophet: ProphetOperatorModel,
         SupportedModels.Arima: ArimaOperatorModel,
         SupportedModels.NeuralProphet: NeuralProphetOperatorModel,
-        SupportedModels.LGBForecast: MLForecastOperatorModel,
+        # SupportedModels.LGBForecast: MLForecastOperatorModel,
         SupportedModels.AutoMLX: AutoMLXOperatorModel,
-        SupportedModels.AutoTS: AutoTSOperatorModel
+        SupportedModels.AutoTS: AutoTSOperatorModel,
     }
 
     @classmethod
@@ -65,14 +64,14 @@ def get_model(
         model_type = operator_config.spec.model
         if model_type == AUTO_SELECT:
             model_type = cls.auto_select_model(datasets, operator_config)
-            operator_config.spec.model_kwargs = dict()
+            operator_config.spec.model_kwargs = {}
         if model_type not in cls._MAP:
             raise UnSupportedModelError(model_type)
         return cls._MAP[model_type](config=operator_config, datasets=datasets)
 
     @classmethod
     def auto_select_model(
-            cls, datasets: ForecastDatasets, operator_config: ForecastOperatorConfig
+        cls, datasets: ForecastDatasets, operator_config: ForecastOperatorConfig
     ) -> str:
         """
         Selects AutoMLX or Arima model based on column count.
@@ -90,8 +89,10 @@ def auto_select_model(
         str
             The type of the model.
         """
-        all_models = operator_config.spec.model_kwargs.get("model_list", cls._MAP.keys())
+        all_models = operator_config.spec.model_kwargs.get(
+            "model_list", cls._MAP.keys()
+        )
         num_backtests = operator_config.spec.model_kwargs.get("num_backtests", 5)
         sample_ratio = operator_config.spec.model_kwargs.get("sample_ratio", 0.20)
         model_evaluator = ModelEvaluator(all_models, num_backtests, sample_ratio)
-        return model_evaluator.find_best_model(datasets, operator_config)
+        return model_evaluator.find_best_model(datasets, operator_config)

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

@@ -2,7 +2,8 @@
 
 # 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 traceback
+
 import pandas as pd
 
 from ads.common.decorator import runtime_dependency
@@ -164,7 +165,7 @@ def _train_model(self, data_train, data_test, model_kwargs):
             self.errors_dict[self.spec.model] = {
                 "model_name": self.spec.model,
                 "error": str(e),
-                "error_trace": traceback.format_exc()
+                "error_trace": traceback.format_exc(),
             }
             logger.warn(f"Encountered Error: {e}. Skipping.")
             logger.warn(traceback.format_exc())
@@ -173,7 +174,7 @@ def _train_model(self, data_train, data_test, model_kwargs):
     def _build_model(self) -> pd.DataFrame:
         data_train = self.datasets.get_all_data_long(include_horizon=False)
         data_test = self.datasets.get_all_data_long_forecast_horizon()
-        self.models = dict()
+        self.models = {}
         model_kwargs = self.set_kwargs()
         self.forecast_output = ForecastOutput(
             confidence_interval_width=self.spec.confidence_interval_width,

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

@@ -1,21 +1,24 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023 Oracle and/or its affiliates.
+# Copyright (c) 2023, 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 os
 from dataclasses import dataclass, field
 from typing import Dict, List
 
 from ads.common.serializer import DataClassSerializable
+from ads.opctl.operator.common.operator_config import (
+    InputData,
+    OperatorConfig,
+    OutputDirectory,
+)
 from ads.opctl.operator.common.utils import _load_yaml_from_uri
-from ads.opctl.operator.common.operator_config import OperatorConfig, OutputDirectory, InputData
-
-from .const import SupportedMetrics, SpeedAccuracyMode
-from .const import SupportedModels
 from ads.opctl.operator.lowcode.common.utils import find_output_dirname
 
+from .const import SpeedAccuracyMode, SupportedMetrics, SupportedModels
+
+
 @dataclass(repr=True)
 class TestData(InputData):
     """Class representing operator specification test data details."""
@@ -90,13 +93,17 @@ class ForecastOperatorSpec(DataClassSerializable):
 
     def __post_init__(self):
         """Adjusts the specification details."""
-        self.output_directory = self.output_directory or OutputDirectory(url=find_output_dirname(self.output_directory))
+        self.output_directory = self.output_directory or OutputDirectory(
+            url=find_output_dirname(self.output_directory)
+        )
         self.metric = (self.metric or "").lower() or SupportedMetrics.SMAPE.lower()
-        self.model = self.model or SupportedModels.Auto
+        self.model = self.model or SupportedModels.Prophet
         self.confidence_interval_width = self.confidence_interval_width or 0.80
         self.report_filename = self.report_filename or "report.html"
         self.preprocessing = (
-            self.preprocessing if self.preprocessing is not None else DataPreprocessor(enabled=True)
+            self.preprocessing
+            if self.preprocessing is not None
+            else DataPreprocessor(enabled=True)
         )
         # For Report Generation. When user doesn't specify defaults to True
         self.generate_report = (
@@ -138,7 +145,7 @@ def __post_init__(self):
         )
         self.target_column = self.target_column or "Sales"
         self.errors_dict_filename = "errors.json"
-        self.model_kwargs = self.model_kwargs or dict()
+        self.model_kwargs = self.model_kwargs or {}
 
 
 @dataclass(repr=True)

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

@@ -374,12 +374,12 @@ spec:
     model:
       type: string
       required: false
-      default: auto-select
+      default: prophet
       allowed:
         - prophet
         - arima
         - neuralprophet
-        - lgbforecast
+        # - lgbforecast
         - automlx
         - autots
         - auto-select

docs/source/user_guide/operators/forecast_operator/yaml_schema.rst

@@ -51,7 +51,7 @@ Below is an example of a ``forecast.yaml`` file with every parameter specified:
         * **format**: (Optional) Specify the format for output data (e.g., ``csv``, ``json``, ``excel``).
         * **options**: (Optional) Include any additional arguments, such as connection parameters for storage.
 
-    * **model**: (Optional) The name of the model framework to use. Defaults to ``auto-select``. Available options include ``arima``, ``lgbforecaster``, ``prophet``, ``neuralprophet``, ``autots``, and ``auto-select``.
+    * **model**: (Optional) The name of the model framework to use. Defaults to ``auto-select``. Available options include ``arima``, ``prophet``, ``neuralprophet``, ``autots``, and ``auto-select``.
 
     * **model_kwargs**: (Optional) A dictionary of arguments to pass directly to the model framework, allowing for detailed control over modeling.
 

tests/operators/forecast/test_datasets.py

@@ -32,7 +32,7 @@
     "prophet",
     "neuralprophet",
     "autots",
-    "lgbforecast",
+    # "lgbforecast",
     "auto-select",
 ]
 
@@ -135,16 +135,18 @@ 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']}
-            if dataset_name == f'{DATASET_PREFIX}dataset4.csv':
+            yaml_i["spec"]["model_kwargs"] = {
+                "model_list": ["prophet", "arima"]
+            }  #  'lgbforecast'
+            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",
-            "auto-select"
+            # "lgbforecast",
+            "auto-select",
         ]:
             verify_explanations(
                 tmpdirname=tmpdirname,

tests/operators/forecast/test_errors.py

@@ -141,8 +141,7 @@
     "prophet",
     "neuralprophet",
     "autots",
-    "lgbforecast",
-    # "auto",
+    # "lgbforecast",
 ]
 
 TEMPLATE_YAML = {
@@ -687,7 +686,7 @@ 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"]:  # , "lgbforecast"
         global_fn = f"{tmpdirname}/results/global_explanation.csv"
         assert os.path.exists(
             global_fn