oracle-ads 2.13.0__py3-none-any.whl → 2.13.1__py3-none-any.whl

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

@@ -116,7 +116,10 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
                 lower_bound=self.get_horizon(forecast["yhat_lower"]).values,
             )
 
-            self.models[s_id] = model
+            self.models[s_id] = {}
+            self.models[s_id]["model"] = model
+            self.models[s_id]["le"] = self.le[s_id]
+            self.models[s_id]["predict_component_cols"] = X_pred.columns
 
             params = vars(model).copy()
             for param in ["arima_res_", "endog_index_"]:
@@ -163,7 +166,7 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
             sec5_text = rc.Heading("ARIMA Model Parameters", level=2)
             blocks = [
                 rc.Html(
-                    m.summary().as_html(),
+                    m['model'].summary().as_html(),
                     label=s_id if self.target_cat_col else None,
                 )
                 for i, (s_id, m) in enumerate(self.models.items())
@@ -251,7 +254,7 @@ class ArimaOperatorModel(ForecastOperatorBaseModel):
     def get_explain_predict_fn(self, series_id):
         def _custom_predict(
             data,
-            model=self.models[series_id],
+            model=self.models[series_id]["model"],
             dt_column_name=self.datasets._datetime_column_name,
             target_col=self.original_target_column,
         ):

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
@@ -56,8 +56,8 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         )
         return model_kwargs_cleaned, time_budget
 
-    def preprocess(self, data):  # TODO: re-use self.le for explanations
-        _, df_encoded = _label_encode_dataframe(
+    def preprocess(self, data, series_id):  # TODO: re-use self.le for explanations
+        self.le[series_id], df_encoded = _label_encode_dataframe(
             data,
             no_encode={self.spec.datetime_column.name, self.original_target_column},
         )
@@ -66,8 +66,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
     @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 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
             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,
@@ -125,7 +124,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 self.forecast_output.init_series_output(
                     series_id=s_id, data_at_series=df
                 )
-                data = self.preprocess(df)
+                data = self.preprocess(df, s_id)
                 data_i = self.drop_horizon(data)
                 X_pred = self.get_horizon(data).drop(target, axis=1)
 
@@ -157,7 +156,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                     target
                 ].values
 
-                self.models[s_id] = model
+                self.models[s_id] = {}
+                self.models[s_id]["model"] = model
+                self.models[s_id]["le"] = self.le[s_id]
 
                 # In case of Naive model, model.forecast function call does not return confidence intervals.
                 if f"{target}_ci_upper" not in summary_frame:
@@ -218,7 +219,8 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         other_sections = []
 
         if len(self.models) > 0:
-            for s_id, m in models.items():
+            for s_id, artifacts in models.items():
+                m = artifacts["model"]
                 selected_models[s_id] = {
                     "series_id": s_id,
                     "selected_model": m.selected_model_,
@@ -247,17 +249,17 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 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)
+                # 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,
-                    )
+                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():
@@ -269,11 +271,15 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 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(
@@ -320,7 +326,7 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
         )
 
     def get_explain_predict_fn(self, series_id):
-        selected_model = self.models[series_id]
+        selected_model = self.models[series_id]["model"]
 
         # If training date, use method below. If future date, use forecast!
         def _custom_predict_fn(
@@ -338,12 +344,12 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
             data[dt_column_name] = seconds_to_datetime(
                 data[dt_column_name], dt_format=self.spec.datetime_column.format
             )
-            data = self.preprocess(data)
+            data = self.preprocess(data, series_id)
             horizon_data = horizon_data.drop(target_col, axis=1)
             horizon_data[dt_column_name] = seconds_to_datetime(
                 horizon_data[dt_column_name], dt_format=self.spec.datetime_column.format
             )
-            horizon_data = self.preprocess(horizon_data)
+            horizon_data = self.preprocess(horizon_data, series_id)
 
             rows = []
             for i in range(data.shape[0]):
@@ -421,8 +427,10 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                 if self.spec.explanations_accuracy_mode == SpeedAccuracyMode.AUTOMLX:
                     # Use the MLExplainer class from AutoMLx to generate explanations
                     explainer = automlx.MLExplainer(
-                        self.models[s_id],
-                        self.datasets.additional_data.get_data_for_series(series_id=s_id)
+                        self.models[s_id]["model"],
+                        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
@@ -433,7 +441,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
 
                     # 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
@@ -445,7 +455,9 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
                     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"
                     )
@@ -453,9 +465,27 @@ class AutoMLXOperatorModel(ForecastOperatorBaseModel):
 
                     # 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(np.abs(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}.")
+                if s_id in self.errors_dict:
+                    self.errors_dict[s_id]["explainer_error"] = str(e)
+                    self.errors_dict[s_id]["explainer_error_trace"] = traceback.format_exc()
+                else:
+                    self.errors_dict[s_id] = {
+                        "model_name": self.spec.model,
+                        "explainer_error": str(e),
+                        "explainer_error_trace": traceback.format_exc(),
+                    }
+                logger.warning(
+                    f"Failed to generate explanations for series {s_id} with error: {e}."
+                )
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")

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

@@ -1,6 +1,6 @@
 #!/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
@@ -19,6 +19,7 @@ import report_creator as rc
 from ads.common.decorator.runtime_dependency import runtime_dependency
 from ads.common.object_storage_details import ObjectStorageDetails
 from ads.opctl import logger
+from ads.opctl.operator.lowcode.common.const import DataColumns
 from ads.opctl.operator.lowcode.common.utils import (
     datetime_to_seconds,
     disable_print,
@@ -28,7 +29,6 @@ from ads.opctl.operator.lowcode.common.utils import (
     seconds_to_datetime,
     write_data,
 )
-from ads.opctl.operator.lowcode.common.const import DataColumns
 from ads.opctl.operator.lowcode.forecast.model.forecast_datasets import TestData
 from ads.opctl.operator.lowcode.forecast.utils import (
     _build_metrics_df,
@@ -49,10 +49,9 @@ from ..const import (
     SpeedAccuracyMode,
     SupportedMetrics,
     SupportedModels,
-    BACKTEST_REPORT_NAME,
 )
 from ..operator_config import ForecastOperatorConfig, ForecastOperatorSpec
-from .forecast_datasets import ForecastDatasets
+from .forecast_datasets import ForecastDatasets, ForecastResults
 
 logging.getLogger("report_creator").setLevel(logging.WARNING)
 
@@ -121,27 +120,30 @@ class ForecastOperatorBaseModel(ABC):
 
             # Generate metrics
             summary_metrics = None
-            test_data = None
+            test_data = self.datasets.test_data
             self.eval_metrics = None
 
             if self.spec.generate_report or self.spec.generate_metrics:
                 self.eval_metrics = self.generate_train_metrics()
                 if not self.target_cat_col:
-                    self.eval_metrics.rename({"Series 1": self.original_target_column},
-                                             axis=1, inplace=True)
+                    self.eval_metrics.rename(
+                        {"Series 1": self.original_target_column}, axis=1, inplace=True
+                    )
 
-                if self.spec.test_data:
+                if self.datasets.test_data is not None:
                     try:
                         (
                             self.test_eval_metrics,
-                            summary_metrics,
-                            test_data,
+                            summary_metrics
                         ) = self._test_evaluate_metrics(
                             elapsed_time=elapsed_time,
                         )
                         if not self.target_cat_col:
-                            self.test_eval_metrics.rename({"Series 1": self.original_target_column},
-                                                     axis=1, inplace=True)
+                            self.test_eval_metrics.rename(
+                                {"Series 1": self.original_target_column},
+                                axis=1,
+                                inplace=True,
+                            )
                     except Exception:
                         logger.warn("Unable to generate Test Metrics.")
                         logger.debug(f"Full Traceback: {traceback.format_exc()}")
@@ -223,17 +225,23 @@ class ForecastOperatorBaseModel(ABC):
                     rc.Block(
                         first_10_title,
                         # series_subtext,
-                        rc.Select(blocks=first_5_rows_blocks) if self.target_cat_col else first_5_rows_blocks[0],
+                        rc.Select(blocks=first_5_rows_blocks)
+                        if self.target_cat_col
+                        else first_5_rows_blocks[0],
                     ),
                     rc.Block(
                         last_10_title,
                         # series_subtext,
-                        rc.Select(blocks=last_5_rows_blocks) if self.target_cat_col else last_5_rows_blocks[0],
+                        rc.Select(blocks=last_5_rows_blocks)
+                        if self.target_cat_col
+                        else last_5_rows_blocks[0],
                     ),
                     rc.Block(
                         summary_title,
                         # series_subtext,
-                        rc.Select(blocks=data_summary_blocks) if self.target_cat_col else data_summary_blocks[0],
+                        rc.Select(blocks=data_summary_blocks)
+                        if self.target_cat_col
+                        else data_summary_blocks[0],
                     ),
                     rc.Separator(),
                 )
@@ -308,7 +316,7 @@ class ForecastOperatorBaseModel(ABC):
                         horizon=self.spec.horizon,
                         test_data=test_data,
                         ci_interval_width=self.spec.confidence_interval_width,
-                        target_category_column=self.target_cat_col
+                        target_category_column=self.target_cat_col,
                     )
                     if (
                         series_name is not None
@@ -341,17 +349,18 @@ class ForecastOperatorBaseModel(ABC):
                 )
 
             # save the report and result CSV
-            self._save_report(
+            return self._save_report(
                 report_sections=report_sections,
                 result_df=result_df,
                 metrics_df=self.eval_metrics,
                 test_metrics_df=self.test_eval_metrics,
+                test_data=test_data,
             )
 
     def _test_evaluate_metrics(self, elapsed_time=0):
         total_metrics = pd.DataFrame()
         summary_metrics = pd.DataFrame()
-        data = TestData(self.spec)
+        data = self.datasets.test_data
 
         # Generate y_pred and y_true for each series
         for s_id in self.forecast_output.list_series_ids():
@@ -388,7 +397,7 @@ class ForecastOperatorBaseModel(ABC):
             total_metrics = pd.concat([total_metrics, metrics_df], axis=1)
 
         if total_metrics.empty:
-            return total_metrics, summary_metrics, data
+            return total_metrics, summary_metrics
 
         summary_metrics = pd.DataFrame(
             {
@@ -454,7 +463,7 @@ class ForecastOperatorBaseModel(ABC):
                 ]
                 summary_metrics = summary_metrics[new_column_order]
 
-        return total_metrics, summary_metrics, data
+        return total_metrics, summary_metrics
 
     def _save_report(
         self,
@@ -462,10 +471,12 @@ class ForecastOperatorBaseModel(ABC):
         result_df: pd.DataFrame,
         metrics_df: pd.DataFrame,
         test_metrics_df: pd.DataFrame,
+        test_data: pd.DataFrame,
     ):
         """Saves resulting reports to the given folder."""
 
         unique_output_dir = self.spec.output_directory.url
+        results = ForecastResults()
 
         if ObjectStorageDetails.is_oci_path(unique_output_dir):
             storage_options = default_signer()
@@ -491,13 +502,23 @@ class ForecastOperatorBaseModel(ABC):
                         f2.write(f1.read())
 
         # forecast csv report
-        result_df = result_df if self.target_cat_col else result_df.drop(DataColumns.Series, axis=1)
+        # todo: add test data into forecast.csv
+        # if self.spec.test_data is not None:
+        #     test_data_dict = test_data.get_dict_by_series()
+        #     for series_id, test_data_values in test_data_dict.items():
+        #         result_df[DataColumns.Series] = test_data_values[]
+        result_df = (
+            result_df
+            if self.target_cat_col
+            else result_df.drop(DataColumns.Series, axis=1)
+        )
         write_data(
             data=result_df,
             filename=os.path.join(unique_output_dir, self.spec.forecast_filename),
             format="csv",
             storage_options=storage_options,
         )
+        results.set_forecast(result_df)
 
         # metrics csv report
         if self.spec.generate_metrics:
@@ -507,10 +528,11 @@ class ForecastOperatorBaseModel(ABC):
                 else "Series 1"
             )
             if metrics_df is not None:
+                metrics_df_formatted = metrics_df.reset_index().rename(
+                    {"index": "metrics", "Series 1": metrics_col_name}, axis=1
+                )
                 write_data(
-                    data=metrics_df.reset_index().rename(
-                        {"index": "metrics", "Series 1": metrics_col_name}, axis=1
-                    ),
+                    data=metrics_df_formatted,
                     filename=os.path.join(
                         unique_output_dir, self.spec.metrics_filename
                     ),
@@ -518,18 +540,20 @@ class ForecastOperatorBaseModel(ABC):
                     storage_options=storage_options,
                     index=False,
                 )
+                results.set_metrics(metrics_df_formatted)
             else:
                 logger.warn(
                     f"Attempted to generate the {self.spec.metrics_filename} file with the training metrics, however the training metrics could not be properly generated."
                 )
 
             # test_metrics csv report
-            if self.spec.test_data is not None:
+            if self.datasets.test_data is not None:
                 if test_metrics_df is not None:
+                    test_metrics_df_formatted = test_metrics_df.reset_index().rename(
+                        {"index": "metrics", "Series 1": metrics_col_name}, axis=1
+                    )
                     write_data(
-                        data=test_metrics_df.reset_index().rename(
-                            {"index": "metrics", "Series 1": metrics_col_name}, axis=1
-                        ),
+                        data=test_metrics_df_formatted,
                         filename=os.path.join(
                             unique_output_dir, self.spec.test_metrics_filename
                         ),
@@ -537,6 +561,7 @@ class ForecastOperatorBaseModel(ABC):
                         storage_options=storage_options,
                         index=False,
                     )
+                    results.set_test_metrics(test_metrics_df_formatted)
                 else:
                     logger.warn(
                         f"Attempted to generate the {self.spec.test_metrics_filename} file with the test metrics, however the test metrics could not be properly generated."
@@ -544,7 +569,7 @@ class ForecastOperatorBaseModel(ABC):
         # explanations csv reports
         if self.spec.generate_explanations:
             try:
-                if self.formatted_global_explanation is not None:
+                if not self.formatted_global_explanation.empty:
                     write_data(
                         data=self.formatted_global_explanation,
                         filename=os.path.join(
@@ -554,12 +579,13 @@ class ForecastOperatorBaseModel(ABC):
                         storage_options=storage_options,
                         index=True,
                     )
+                    results.set_global_explanations(self.formatted_global_explanation)
                 else:
                     logger.warn(
                         f"Attempted to generate global explanations for the {self.spec.global_explanation_filename} file, but an issue occured in formatting the explanations."
                     )
 
-                if self.formatted_local_explanation is not None:
+                if not self.formatted_local_explanation.empty:
                     write_data(
                         data=self.formatted_local_explanation,
                         filename=os.path.join(
@@ -569,6 +595,7 @@ class ForecastOperatorBaseModel(ABC):
                         storage_options=storage_options,
                         index=True,
                     )
+                    results.set_local_explanations(self.formatted_local_explanation)
                 else:
                     logger.warn(
                         f"Attempted to generate local explanations for the {self.spec.local_explanation_filename} file, but an issue occured in formatting the explanations."
@@ -589,10 +616,12 @@ class ForecastOperatorBaseModel(ABC):
                 index=True,
                 indent=4,
             )
+            results.set_model_parameters(self.model_parameters)
 
         # model pickle
         if self.spec.generate_model_pickle:
             self._save_model(unique_output_dir, storage_options)
+            results.set_models(self.models)
 
         logger.info(
             f"The outputs have been successfully "
@@ -612,8 +641,10 @@ class ForecastOperatorBaseModel(ABC):
                 index=True,
                 indent=4,
             )
+            results.set_errors_dict(self.errors_dict)
         else:
             logger.info("All modeling completed successfully.")
+        return results
 
     def preprocess(self, df, series_id):
         """The method that needs to be implemented on the particular model level."""
@@ -667,7 +698,10 @@ class ForecastOperatorBaseModel(ABC):
         )
 
     def _validate_automlx_explanation_mode(self):
-        if self.spec.model != SupportedModels.AutoMLX and self.spec.explanations_accuracy_mode == SpeedAccuracyMode.AUTOMLX:
+        if (
+            self.spec.model != SupportedModels.AutoMLX
+            and self.spec.explanations_accuracy_mode == SpeedAccuracyMode.AUTOMLX
+        ):
             raise ValueError(
                 "AUTOMLX explanation accuracy mode is only supported for AutoMLX models. "
                 "Please select mode other than AUTOMLX from the available explanations_accuracy_mode options"
@@ -738,14 +772,6 @@ class ForecastOperatorBaseModel(ABC):
                     logger.warn(
                         "No explanations generated. Ensure that additional data has been provided."
                     )
-                elif (
-                    self.spec.model == SupportedModels.AutoMLX
-                    and self.spec.explanations_accuracy_mode
-                    == SpeedAccuracyMode.AUTOMLX
-                ):
-                    logger.warning(
-                        "Global explanations not available for AutoMLX models with inherent explainability"
-                    )
                 else:
                     self.global_explanation[s_id] = dict(
                         zip(
@@ -794,7 +820,7 @@ class ForecastOperatorBaseModel(ABC):
     def get_explain_predict_fn(self, series_id, fcst_col_name="yhat"):
         def _custom_predict(
             data,
-            model=self.models[series_id],
+            model=self.models[series_id]["model"],
             dt_column_name=self.datasets._datetime_column_name,
         ):
             """