oracle-ads 2.13.2__py3-none-any.whl → 2.13.3__py3-none-any.whl

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

@@ -28,8 +28,8 @@ from ads.opctl.operator.lowcode.common.utils import (
     merged_category_column_name,
     seconds_to_datetime,
     write_data,
+    write_json,
 )
-from ads.opctl.operator.lowcode.forecast.model.forecast_datasets import TestData
 from ads.opctl.operator.lowcode.forecast.utils import (
     _build_metrics_df,
     _build_metrics_per_horizon,
@@ -46,6 +46,7 @@ from ..const import (
     AUTO_SELECT,
     BACKTEST_REPORT_NAME,
     SUMMARY_METRICS_HORIZON_LIMIT,
+    ForecastOutputColumns,
     SpeedAccuracyMode,
     SupportedMetrics,
     SupportedModels,
@@ -132,11 +133,10 @@ class ForecastOperatorBaseModel(ABC):
 
                 if self.datasets.test_data is not None:
                     try:
-                        (
-                            self.test_eval_metrics,
-                            summary_metrics
-                        ) = self._test_evaluate_metrics(
-                            elapsed_time=elapsed_time,
+                        (self.test_eval_metrics, summary_metrics) = (
+                            self._test_evaluate_metrics(
+                                elapsed_time=elapsed_time,
+                            )
                         )
                         if not self.target_cat_col:
                             self.test_eval_metrics.rename(
@@ -145,7 +145,7 @@ class ForecastOperatorBaseModel(ABC):
                                 inplace=True,
                             )
                     except Exception:
-                        logger.warn("Unable to generate Test Metrics.")
+                        logger.warning("Unable to generate Test Metrics.")
                         logger.debug(f"Full Traceback: {traceback.format_exc()}")
             report_sections = []
 
@@ -155,9 +155,8 @@ class ForecastOperatorBaseModel(ABC):
                     model_description,
                     other_sections,
                 ) = self._generate_report()
-
                 header_section = rc.Block(
-                    rc.Heading("Forecast Report", level=1),
+                    rc.Heading(self.spec.report_title, level=1),
                     rc.Text(
                         f"You selected the {self.spec.model} model.\nBased on your dataset, you could have also selected any of the models: {SupportedModels.keys()}."
                     ),
@@ -369,7 +368,7 @@ class ForecastOperatorBaseModel(ABC):
                     -self.spec.horizon :
                 ]
             except KeyError as ke:
-                logger.warn(
+                logger.warning(
                     f"Error Generating Metrics: Unable to find {s_id} in the test data. Error: {ke.args}"
                 )
             y_pred = self.forecast_output.get_forecast(s_id)["forecast_value"].values[
@@ -478,10 +477,11 @@ class ForecastOperatorBaseModel(ABC):
         unique_output_dir = self.spec.output_directory.url
         results = ForecastResults()
 
-        if ObjectStorageDetails.is_oci_path(unique_output_dir):
-            storage_options = default_signer()
-        else:
-            storage_options = {}
+        storage_options = (
+            default_signer()
+            if ObjectStorageDetails.is_oci_path(unique_output_dir)
+            else {}
+        )
 
         # report-creator html report
         if self.spec.generate_report:
@@ -512,12 +512,13 @@ class ForecastOperatorBaseModel(ABC):
             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,
-        )
+        if self.spec.generate_forecast_file:
+            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
@@ -531,18 +532,19 @@ class ForecastOperatorBaseModel(ABC):
                 metrics_df_formatted = metrics_df.reset_index().rename(
                     {"index": "metrics", "Series 1": metrics_col_name}, axis=1
                 )
-                write_data(
-                    data=metrics_df_formatted,
-                    filename=os.path.join(
-                        unique_output_dir, self.spec.metrics_filename
-                    ),
-                    format="csv",
-                    storage_options=storage_options,
-                    index=False,
-                )
+                if self.spec.generate_metrics_file:
+                    write_data(
+                        data=metrics_df_formatted,
+                        filename=os.path.join(
+                            unique_output_dir, self.spec.metrics_filename
+                        ),
+                        format="csv",
+                        storage_options=storage_options,
+                        index=False,
+                    )
                 results.set_metrics(metrics_df_formatted)
             else:
-                logger.warn(
+                logger.warning(
                     f"Attempted to generate the {self.spec.metrics_filename} file with the training metrics, however the training metrics could not be properly generated."
                 )
 
@@ -552,56 +554,59 @@ class ForecastOperatorBaseModel(ABC):
                     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_formatted,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.test_metrics_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=False,
-                    )
+                    if self.spec.generate_metrics_file:
+                        write_data(
+                            data=test_metrics_df_formatted,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.test_metrics_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=False,
+                        )
                     results.set_test_metrics(test_metrics_df_formatted)
                 else:
-                    logger.warn(
+                    logger.warning(
                         f"Attempted to generate the {self.spec.test_metrics_filename} file with the test metrics, however the test metrics could not be properly generated."
                     )
         # explanations csv reports
         if self.spec.generate_explanations:
             try:
                 if not self.formatted_global_explanation.empty:
-                    write_data(
-                        data=self.formatted_global_explanation,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.global_explanation_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=True,
-                    )
+                    if self.spec.generate_explanation_files:
+                        write_data(
+                            data=self.formatted_global_explanation,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.global_explanation_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=True,
+                        )
                     results.set_global_explanations(self.formatted_global_explanation)
                 else:
-                    logger.warn(
+                    logger.warning(
                         f"Attempted to generate global explanations for the {self.spec.global_explanation_filename} file, but an issue occured in formatting the explanations."
                     )
 
                 if not self.formatted_local_explanation.empty:
-                    write_data(
-                        data=self.formatted_local_explanation,
-                        filename=os.path.join(
-                            unique_output_dir, self.spec.local_explanation_filename
-                        ),
-                        format="csv",
-                        storage_options=storage_options,
-                        index=True,
-                    )
+                    if self.spec.generate_explanation_files:
+                        write_data(
+                            data=self.formatted_local_explanation,
+                            filename=os.path.join(
+                                unique_output_dir, self.spec.local_explanation_filename
+                            ),
+                            format="csv",
+                            storage_options=storage_options,
+                            index=True,
+                        )
                     results.set_local_explanations(self.formatted_local_explanation)
                 else:
-                    logger.warn(
+                    logger.warning(
                         f"Attempted to generate local explanations for the {self.spec.local_explanation_filename} file, but an issue occured in formatting the explanations."
                     )
             except AttributeError as e:
-                logger.warn(
+                logger.warning(
                     "Unable to generate explanations for this model type or for this dataset."
                 )
                 logger.debug(f"Got error: {e.args}")
@@ -631,15 +636,12 @@ class ForecastOperatorBaseModel(ABC):
             f"The outputs have been successfully generated and placed into the directory: {unique_output_dir}."
         )
         if self.errors_dict:
-            write_data(
-                data=pd.DataFrame.from_dict(self.errors_dict),
+            write_json(
+                json_dict=self.errors_dict,
                 filename=os.path.join(
                     unique_output_dir, self.spec.errors_dict_filename
                 ),
-                format="json",
                 storage_options=storage_options,
-                index=True,
-                indent=4,
             )
             results.set_errors_dict(self.errors_dict)
         else:
@@ -742,45 +744,62 @@ class ForecastOperatorBaseModel(ABC):
             include_horizon=False
         ).items():
             if s_id in self.models:
-                explain_predict_fn = self.get_explain_predict_fn(series_id=s_id)
-                data_trimmed = data_i.tail(
-                    max(int(len(data_i) * ratio), 5)
-                ).reset_index(drop=True)
-                data_trimmed[datetime_col_name] = data_trimmed[datetime_col_name].apply(
-                    lambda x: x.timestamp()
-                )
-
-                # Explainer fails when boolean columns are passed
-
-                _, data_trimmed_encoded = _label_encode_dataframe(
-                    data_trimmed,
-                    no_encode={datetime_col_name, self.original_target_column},
-                )
-
-                kernel_explnr = PermutationExplainer(
-                    model=explain_predict_fn, masker=data_trimmed_encoded
-                )
-                kernel_explnr_vals = kernel_explnr.shap_values(data_trimmed_encoded)
-                exp_end_time = time.time()
-                global_ex_time = global_ex_time + exp_end_time - exp_start_time
-                self.local_explainer(
-                    kernel_explnr, series_id=s_id, datetime_col_name=datetime_col_name
-                )
-                local_ex_time = local_ex_time + time.time() - exp_end_time
+                try:
+                    explain_predict_fn = self.get_explain_predict_fn(series_id=s_id)
+                    data_trimmed = data_i.tail(
+                        max(int(len(data_i) * ratio), 5)
+                    ).reset_index(drop=True)
+                    data_trimmed[datetime_col_name] = data_trimmed[
+                        datetime_col_name
+                    ].apply(lambda x: x.timestamp())
+
+                    # Explainer fails when boolean columns are passed
+
+                    _, data_trimmed_encoded = _label_encode_dataframe(
+                        data_trimmed,
+                        no_encode={datetime_col_name, self.original_target_column},
+                    )
 
-                if not len(kernel_explnr_vals):
-                    logger.warn(
-                        "No explanations generated. Ensure that additional data has been provided."
+                    kernel_explnr = PermutationExplainer(
+                        model=explain_predict_fn, masker=data_trimmed_encoded
                     )
-                else:
-                    self.global_explanation[s_id] = dict(
-                        zip(
-                            data_trimmed.columns[1:],
-                            np.average(np.absolute(kernel_explnr_vals[:, 1:]), axis=0),
-                        )
+                    kernel_explnr_vals = kernel_explnr.shap_values(data_trimmed_encoded)
+                    exp_end_time = time.time()
+                    global_ex_time = global_ex_time + exp_end_time - exp_start_time
+                    self.local_explainer(
+                        kernel_explnr,
+                        series_id=s_id,
+                        datetime_col_name=datetime_col_name,
                     )
+                    local_ex_time = local_ex_time + time.time() - exp_end_time
+
+                    if not len(kernel_explnr_vals):
+                        logger.warning(
+                            "No explanations generated. Ensure that additional data has been provided."
+                        )
+                    else:
+                        self.global_explanation[s_id] = dict(
+                            zip(
+                                data_trimmed.columns[1:],
+                                np.average(
+                                    np.absolute(kernel_explnr_vals[:, 1:]), axis=0
+                                ),
+                            )
+                        )
+                except Exception as 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(),
+                        }
             else:
-                logger.warn(
+                logger.warning(
                     f"Skipping explanations for {s_id}, as forecast was not generated."
                 )
 
@@ -815,6 +834,13 @@ class ForecastOperatorBaseModel(ABC):
         local_kernel_explnr_df = pd.DataFrame(
             local_kernel_explnr_vals, columns=data.columns
         )
+
+        # Add date column to local explanation DataFrame
+        local_kernel_explnr_df[ForecastOutputColumns.DATE] = (
+            self.datasets.get_horizon_at_series(
+                s_id=series_id
+            )[self.spec.datetime_column.name].reset_index(drop=True)
+        )
         self.local_explanation[series_id] = local_kernel_explnr_df
 
     def get_explain_predict_fn(self, series_id, fcst_col_name="yhat"):

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

@@ -23,14 +23,14 @@ from ..operator_config import ForecastOperatorConfig
 
 
 class HistoricalData(AbstractData):
-    def __init__(self, spec, historical_data = None):
+    def __init__(self, spec, historical_data=None):
         super().__init__(spec=spec, name="historical_data", data=historical_data)
 
     def _ingest_data(self, spec):
         try:
             self.freq = get_frequency_of_datetime(self.data.index.get_level_values(0))
         except TypeError as e:
-            logger.warn(
+            logger.warning(
                 f"Error determining frequency: {e.args}. Setting Frequency to None"
             )
             logger.debug(f"Full traceback: {e}")
@@ -106,7 +106,7 @@ class AdditionalData(AbstractData):
         _spec = spec
         self.additional_regressors = list(self.data.columns)
         if not self.additional_regressors:
-            logger.warn(
+            logger.warning(
                 f"No additional variables found in the additional_data. Only columns found: {self.data.columns}. Skipping for now."
             )
         # Check that datetime column matches historical datetime column
@@ -121,7 +121,13 @@ class TestData(AbstractData):
 
 
 class ForecastDatasets:
-    def __init__(self, config: ForecastOperatorConfig, historical_data=None, additional_data=None, test_data=None):
+    def __init__(
+        self,
+        config: ForecastOperatorConfig,
+        historical_data=None,
+        additional_data=None,
+        test_data=None,
+    ):
         """Instantiates the DataIO instance.
 
         Properties
@@ -136,7 +142,9 @@ class ForecastDatasets:
         self._target_col = config.spec.target_column
         if historical_data is not None:
             self.historical_data = HistoricalData(config.spec, historical_data)
-            self.additional_data = AdditionalData(config.spec, self.historical_data, additional_data)
+            self.additional_data = AdditionalData(
+                config.spec, self.historical_data, additional_data
+            )
         else:
             self._load_data(config.spec)
         self.test_data = TestData(config.spec, test_data)
@@ -147,7 +155,7 @@ class ForecastDatasets:
         self.additional_data = AdditionalData(spec, self.historical_data)
 
         if spec.generate_explanations and spec.additional_data is None:
-            logger.warn(
+            logger.warning(
                 "Unable to generate explanations as there is no additional data passed in. Either set generate_explanations to False, or pass in additional data."
             )
             spec.generate_explanations = False

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

@@ -168,8 +168,8 @@ class MLForecastOperatorModel(ForecastOperatorBaseModel):
                 "error": str(e),
                 "error_trace": traceback.format_exc(),
             }
-            logger.warn(f"Encountered Error: {e}. Skipping.")
-            logger.warn(traceback.format_exc())
+            logger.warning(f"Encountered Error: {e}. Skipping.")
+            logger.warning(traceback.format_exc())
             raise e
 
     def _build_model(self) -> pd.DataFrame:

ads/opctl/operator/lowcode/forecast/model/neuralprophet.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
@@ -40,7 +40,7 @@ from .forecast_datasets import ForecastDatasets, ForecastOutput
 #         "rmse": MeanSquaredError,
 #     }
 #     if selected_metric not in metric_translation.keys():
-#         logger.warn(
+#         logger.warning(
 #             f"Could not find the metric: {selected_metric} in torchmetrics. Defaulting to MAE and RMSE"
 #         )
 #         return {"MAE": MeanAbsoluteError(), "RMSE": MeanSquaredError()}
@@ -149,28 +149,42 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
             logger.debug(f"-----------------Model {i}----------------------")
             logger.debug(forecast.tail())
 
-            # TODO; could also extract trend and seasonality?
-            cols_to_read = filter(
-                lambda x: x.startswith("future_regressor"), forecast.columns
-            )
-            self.explanations_info[s_id] = forecast[cols_to_read]
-            self.explanations_info[s_id]["Date"] = forecast["ds"]
-            self.explanations_info[s_id] = self.explanations_info[s_id].set_index(
-                "Date"
-            )
-
             self.outputs[s_id] = forecast
+            upper_bound_col_name = f"yhat1 {model_kwargs['quantiles'][1]*100}%"
+            lower_bound_col_name = f"yhat1 {model_kwargs['quantiles'][0]*100}%"
             self.forecast_output.populate_series_output(
                 series_id=s_id,
                 fit_val=self.drop_horizon(forecast["yhat1"]).values,
                 forecast_val=self.get_horizon(forecast["yhat1"]).values,
-                upper_bound=self.get_horizon(
-                    forecast[f"yhat1 {model_kwargs['quantiles'][1]*100}%"]
-                ).values,
-                lower_bound=self.get_horizon(
-                    forecast[f"yhat1 {model_kwargs['quantiles'][0]*100}%"]
-                ).values,
+                upper_bound=self.get_horizon(forecast[upper_bound_col_name]).values,
+                lower_bound=self.get_horizon(forecast[lower_bound_col_name]).values,
+            )
+            core_columns = set(forecast.columns) - set(
+                [
+                    "y",
+                    "yhat1",
+                    upper_bound_col_name,
+                    lower_bound_col_name,
+                    "future_regressors_additive",
+                    "future_regressors_multiplicative",
+                ]
+            )
+            exog_variables = set(
+                filter(lambda x: x.startswith("future_regressor_"), list(core_columns))
             )
+            combine_terms = list(core_columns - exog_variables - set(["ds"]))
+            temp_df = (
+                forecast[list(core_columns)]
+                .rename({"ds": "Date"}, axis=1)
+                .set_index("Date")
+            )
+            if combine_terms:
+                temp_df[self.spec.target_column] = temp_df[combine_terms].sum(axis=1)
+                temp_df = temp_df.drop(combine_terms, axis=1)
+            else:
+                temp_df[self.spec.target_column] = 0
+            # Todo: check for columns that were dropped, and set them to 0
+            self.explanations_info[s_id] = temp_df
 
             self.trainers[s_id] = model.trainer
             self.models[s_id] = {}
@@ -207,7 +221,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 "error": str(e),
                 "error_trace": traceback.format_exc(),
             }
-            logger.warn(traceback.format_exc())
+            logger.warning(traceback.format_exc())
             raise e
 
     def _build_model(self) -> pd.DataFrame:
@@ -215,7 +229,6 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
         self.models = {}
         self.trainers = {}
         self.outputs = {}
-        self.errors_dict = {}
         self.explanations_info = {}
         self.accepted_regressors = {}
         self.additional_regressors = self.datasets.get_additional_data_column_names()
@@ -363,7 +376,9 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                     pd.Series(
                         m.state_dict(),
                         index=m.state_dict().keys(),
-                        name=s_id if self.target_cat_col else self.original_target_column,
+                        name=s_id
+                        if self.target_cat_col
+                        else self.original_target_column,
                     )
                 )
             all_model_states = pd.concat(model_states, axis=1)
@@ -377,11 +392,15 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 self.explain_model()
 
                 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(
@@ -412,7 +431,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 ]
             except Exception as e:
                 # Do not fail the whole run due to explanations failure
-                logger.warn(f"Failed to generate Explanations with error: {e}.")
+                logger.warning(f"Failed to generate Explanations with error: {e}.")
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")
 
         model_description = rc.Text(
@@ -453,9 +472,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
         for s_id, expl_df in self.explanations_info.items():
             expl_df = expl_df.rename(rename_cols, axis=1)
             # Local Expl
-            self.local_explanation[s_id] = self.get_horizon(expl_df).drop(
-                ["future_regressors_additive"], axis=1
-            )
+            self.local_explanation[s_id] = self.get_horizon(expl_df)
             self.local_explanation[s_id]["Series"] = s_id
             self.local_explanation[s_id].index.rename(self.dt_column_name, inplace=True)
             # Global Expl
@@ -463,9 +480,6 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
             g_expl.name = s_id
             global_expl.append(g_expl)
         self.global_explanation = pd.concat(global_expl, axis=1)
-        self.global_explanation = self.global_explanation.drop(
-            index=["future_regressors_additive"], axis=0
-        )
         self.formatted_global_explanation = (
             self.global_explanation / self.global_explanation.sum(axis=0) * 100
         )