Merge branch 'main' into feature/multi_model_deployment

Author: mrDzurb

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

@@ -56,6 +56,6 @@ jobs:
           $CONDA/bin/conda init
           source /home/runner/.bashrc
           pip install -r test-requirements-operators.txt
-          pip install "oracle-automlx[forecasting]>=24.4.1"
+          pip install "oracle-automlx[forecasting]>=25.1.1"
           pip install pandas>=2.2.0
           python -m pytest -v -p no:warnings --durations=5 tests/operators/forecast

.github/workflows/run-unittests-py39-py310.yml renamed to .github/workflows/run-unittests-py310-py311.yml

@@ -1,4 +1,4 @@
-name: "[Py3.9-3.11] - All Unit Tests"
+name: "[Py3.10-3.11] - All Unit Tests"
 
 on:
   workflow_dispatch:
@@ -33,15 +33,14 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11"]
+        python-version: ["3.10", "3.11"]
         name: ["unitary", "slow_tests"]
         include:
           - name: "unitary"
             test-path: "tests/unitary"
             # `model` tests running in "slow_tests",
             # `feature_store` tests has its own test suite
-            # `forecast` tests not supported in python 3.9,3.10 (automlx dependency). Tests are running in python3.8 test env, see run-unittests-py38-cov-report.yml
-            # 'pii' tests run only with py3.8, 'datapane' library conflicts with pandas>2.2.0, which used in py3.9/3.10 setup
+            # `forecast` tests not run in this suite
             # 'hpo' tests hangs if run together with all unitary tests. Tests running in separate command before running all unitary
             ignore-path: |
               --ignore tests/unitary/with_extras/model \

.github/workflows/run-unittests-py38-cov-report.yml renamed to .github/workflows/run-unittests-py39-cov-report.yml

@@ -1,4 +1,4 @@
-name: "[Py3.8][COV REPORT] - All Unit Tests"
+name: "[Py3.9][COV REPORT] - All Unit Tests"
 
 on:
   workflow_dispatch:
@@ -26,7 +26,7 @@ env:
 
 jobs:
   test:
-    name: python 3.8, ${{ matrix.name }}
+    name: python 3.9, ${{ matrix.name }}
     runs-on: ubuntu-latest
     timeout-minutes: 90
 
@@ -58,7 +58,7 @@ jobs:
 
       - uses: actions/setup-python@v5
         with:
-          python-version: "3.8"
+          python-version: "3.9"
           cache: "pip"
           cache-dependency-path: |
             pyproject.toml
@@ -71,7 +71,7 @@ jobs:
         name: "Test env setup"
         timeout-minutes: 30
 
-      # Installing pii deps for python3.8 test setup only, it will not work with python3.9/3.10, because
+      # Installing pii deps for python3.9 test setup only, it will not work with python3.9/3.10, because
       # 'datapane' library conflicts with pandas>2.2.0, which used in py3.9/3.10 setup
       - name: "Install PII dependencies"
         run: |

ads/opctl/anomaly_detection.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2025 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.opctl.operator.lowcode.anomaly.__main__ import operate
+from ads.opctl.operator.lowcode.anomaly.operator_config import AnomalyOperatorConfig
+
+if __name__ == "__main__":
+    config = AnomalyOperatorConfig()
+    operate(config)

ads/opctl/forecast.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2025 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.opctl.operator.lowcode.forecast.__main__ import operate
+from ads.opctl.operator.lowcode.forecast.operator_config import ForecastOperatorConfig
+
+if __name__ == "__main__":
+    config = ForecastOperatorConfig()
+    operate(config)

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

@@ -1,7 +1,6 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*--
 
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 
 import json
@@ -15,17 +14,17 @@
 from ads.opctl.operator.common.const import ENV_OPERATOR_ARGS
 from ads.opctl.operator.common.utils import _parse_input_args
 
+from .model.forecast_datasets import ForecastDatasets, ForecastResults
 from .operator_config import ForecastOperatorConfig
-from .model.forecast_datasets import ForecastDatasets
 from .whatifserve import ModelDeploymentManager
 
 
-def operate(operator_config: ForecastOperatorConfig) -> None:
+def operate(operator_config: ForecastOperatorConfig) -> ForecastResults:
     """Runs the forecasting operator."""
     from .model.factory import ForecastOperatorModelFactory
 
     datasets = ForecastDatasets(operator_config)
-    ForecastOperatorModelFactory.get_model(
+    results = ForecastOperatorModelFactory.get_model(
         operator_config, datasets
     ).generate_report()
     # saving to model catalog
@@ -36,6 +35,7 @@ def operate(operator_config: ForecastOperatorConfig) -> None:
         if spec.what_if_analysis.model_deployment:
             mdm.create_deployment()
         mdm.save_deployment_info()
+    return results
 
 
 def verify(spec: Dict, **kwargs: Dict) -> bool:

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

@@ -1,5 +1,5 @@
 #!/usr/bin/env python
-# Copyright (c) 2023, 2024 Oracle and/or its affiliates.
+# Copyright (c) 2023, 2025 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 import logging
 import os
@@ -66,8 +66,7 @@ def preprocess(self, data, series_id):  # TODO: re-use self.le for explanations
     @runtime_dependency(
         module="automlx",
         err_msg=(
-            "Please run `pip3 install oracle-automlx>=23.4.1` and "
-            "`pip3 install oracle-automlx[forecasting]>=23.4.1` "
+            "Please run `pip3 install oracle-automlx[forecasting]>=25.1.1` "
             "to install the required dependencies for automlx."
         ),
     )
@@ -105,7 +104,7 @@ def _build_model(self) -> pd.DataFrame:
             engine_opts = (
                 None
                 if engine_type == "local"
-                else ({"ray_setup": {"_temp_dir": "/tmp/ray-temp"}},)
+                else {"ray_setup": {"_temp_dir": "/tmp/ray-temp"}}
             )
             init(
                 engine=engine_type,
@@ -250,17 +249,18 @@ def _generate_report(self):
                 self.explain_model()
 
                 global_explanation_section = None
-                if self.spec.explanations_accuracy_mode != SpeedAccuracyMode.AUTOMLX:
-                    # Convert the global explanation data to a DataFrame
-                    global_explanation_df = pd.DataFrame(self.global_explanation)
 
-                    self.formatted_global_explanation = (
-                        global_explanation_df / global_explanation_df.sum(axis=0) * 100
-                    )
-                    self.formatted_global_explanation = self.formatted_global_explanation.rename(
-                        {self.spec.datetime_column.name: ForecastOutputColumns.DATE},
-                        axis=1,
-                    )
+                # Convert the global explanation data to a DataFrame
+                global_explanation_df = pd.DataFrame(self.global_explanation)
+
+                self.formatted_global_explanation = (
+                    global_explanation_df / global_explanation_df.sum(axis=0) * 100
+                )
+
+                self.formatted_global_explanation.rename(
+                    columns={self.spec.datetime_column.name: ForecastOutputColumns.DATE},
+                    inplace=True,
+                )
 
                 aggregate_local_explanations = pd.DataFrame()
                 for s_id, local_ex_df in self.local_explanation.items():
@@ -272,11 +272,15 @@ def _generate_report(self):
                 self.formatted_local_explanation = aggregate_local_explanations
 
                 if not self.target_cat_col:
-                    self.formatted_global_explanation = self.formatted_global_explanation.rename(
-                        {"Series 1": self.original_target_column},
-                        axis=1,
+                    self.formatted_global_explanation = (
+                        self.formatted_global_explanation.rename(
+                            {"Series 1": self.original_target_column},
+                            axis=1,
+                        )
+                    )
+                    self.formatted_local_explanation.drop(
+                        "Series", axis=1, inplace=True
                     )
-                    self.formatted_local_explanation.drop("Series", axis=1, inplace=True)
 
                 # Create a markdown section for the global explainability
                 global_explanation_section = rc.Block(
@@ -425,7 +429,9 @@ def explain_model(self):
                     # Use the MLExplainer class from AutoMLx to generate explanations
                     explainer = automlx.MLExplainer(
                         self.models[s_id]["model"],
-                        self.datasets.additional_data.get_data_for_series(series_id=s_id)
+                        self.datasets.additional_data.get_data_for_series(
+                            series_id=s_id
+                        )
                         .drop(self.spec.datetime_column.name, axis=1)
                         .head(-self.spec.horizon)
                         if self.spec.additional_data
@@ -436,7 +442,9 @@ def explain_model(self):
 
                     # Generate explanations for the forecast
                     explanations = explainer.explain_prediction(
-                        X=self.datasets.additional_data.get_data_for_series(series_id=s_id)
+                        X=self.datasets.additional_data.get_data_for_series(
+                            series_id=s_id
+                        )
                         .drop(self.spec.datetime_column.name, axis=1)
                         .tail(self.spec.horizon)
                         if self.spec.additional_data
@@ -448,17 +456,28 @@ def explain_model(self):
                     explanations_df = pd.concat(
                         [exp.to_dataframe() for exp in explanations]
                     )
-                    explanations_df["row"] = explanations_df.groupby("Feature").cumcount()
+                    explanations_df["row"] = explanations_df.groupby(
+                        "Feature"
+                    ).cumcount()
                     explanations_df = explanations_df.pivot(
                         index="row", columns="Feature", values="Attribution"
                     )
                     explanations_df = explanations_df.reset_index(drop=True)
 
                     # Store the explanations in the local_explanation dictionary
                     self.local_explanation[s_id] = explanations_df
+
+                    self.global_explanation[s_id] = dict(
+                        zip(
+                            self.local_explanation[s_id].columns,
+                            np.nanmean((self.local_explanation[s_id]), axis=0),
+                        )
+                    )
                 else:
                     # Fall back to the default explanation generation method
                     super().explain_model()
             except Exception as e:
-                logger.warning(f"Failed to generate explanations for series {s_id} with error: {e}.")
+                logger.warning(
+                    f"Failed to generate explanations for series {s_id} with error: {e}."
+                )
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")