oracle-ads 2.11.7__py3-none-any.whl → 2.11.9__py3-none-any.whl

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

@@ -1,7 +1,7 @@
 #!/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 numpy as np
@@ -41,20 +41,20 @@ from .forecast_datasets import ForecastDatasets, ForecastOutput
 import traceback
 
 
-def _get_np_metrics_dict(selected_metric):
-    metric_translation = {
-        "mape": MeanAbsolutePercentageError,
-        "smape": SymmetricMeanAbsolutePercentageError,
-        "mae": MeanAbsoluteError,
-        "r2": R2Score,
-        "rmse": MeanSquaredError,
-    }
-    if selected_metric not in metric_translation.keys():
-        logger.warn(
-            f"Could not find the metric: {selected_metric} in torchmetrics. Defaulting to MAE and RMSE"
-        )
-        return {"MAE": MeanAbsoluteError(), "RMSE": MeanSquaredError()}
-    return {selected_metric: metric_translation[selected_metric]()}
+# def _get_np_metrics_dict(selected_metric):
+#     metric_translation = {
+#         "mape": MeanAbsolutePercentageError,
+#         "smape": SymmetricMeanAbsolutePercentageError,
+#         "mae": MeanAbsoluteError,
+#         "r2": R2Score,
+#         "rmse": MeanSquaredError,
+#     }
+#     if selected_metric not in metric_translation.keys():
+#         logger.warn(
+#             f"Could not find the metric: {selected_metric} in torchmetrics. Defaulting to MAE and RMSE"
+#         )
+#         return {"MAE": MeanAbsoluteError(), "RMSE": MeanSquaredError()}
+#     return {selected_metric: metric_translation[selected_metric]()}
 
 
 @runtime_dependency(
@@ -70,7 +70,7 @@ def _fit_model(data, params, additional_regressors, select_metric):
         disable_print()
 
     m = NeuralProphet(**params)
-    m.metrics = _get_np_metrics_dict(select_metric)
+    # m.metrics = _get_np_metrics_dict(select_metric)
     for add_reg in additional_regressors:
         m = m.add_future_regressor(name=add_reg)
     m.fit(df=data)
@@ -135,7 +135,8 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                     data=data_i,
                     params=model_kwargs,
                     additional_regressors=self.additional_regressors,
-                    select_metric=self.spec.metric,
+                    select_metric=None,
+                    # select_metric=self.spec.metric,
                 )
 
             logger.debug(
@@ -209,6 +210,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
             logger.debug("===========Done===========")
         except Exception as e:
             self.errors_dict[s_id] = {"model_name": self.spec.model, "error": str(e)}
+            raise e
 
     def _build_model(self) -> pd.DataFrame:
         full_data_dict = self.datasets.get_data_by_series()
@@ -309,44 +311,52 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
         return selected_params
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
+
         series_ids = self.models.keys()
         all_sections = []
         if len(series_ids) > 0:
             try:
-                sec1_text = dp.Text(
-                    "## Forecast Overview \nThese plots show your "
-                    "forecast in the context of historical data."
-                )
                 sec1 = _select_plot_list(
                     lambda s_id: self.models[s_id].plot(self.outputs[s_id]),
                     series_ids=series_ids,
                 )
-                all_sections = all_sections + [sec1_text, sec1]
+                section_1 = rc.Block(
+                    rc.Heading("Forecast Overview", level=2),
+                    rc.Text(
+                        "These plots show your forecast in the context of historical data."
+                    ),
+                    sec1,
+                )
+                all_sections = all_sections + [section_1]
             except Exception as e:
                 logger.debug(f"Failed to plot with exception: {e.args}")
 
             try:
-                sec2_text = dp.Text(f"## Forecast Broken Down by Trend Component")
                 sec2 = _select_plot_list(
                     lambda s_id: self.models[s_id].plot_components(self.outputs[s_id]),
                     series_ids=series_ids,
                 )
-                all_sections = all_sections + [sec2_text, sec2]
+                section_2 = rc.Block(
+                    rc.Heading("Forecast Broken Down by Trend Component", level=2), sec2
+                )
+                all_sections = all_sections + [section_2]
             except Exception as e:
                 logger.debug(f"Failed to plot with exception: {e.args}")
 
             try:
-                sec3_text = dp.Text(f"## Forecast Parameter Plots")
                 sec3 = _select_plot_list(
                     lambda s_id: self.models[s_id].plot_parameters(),
                     series_ids=series_ids,
                 )
-                all_sections = all_sections + [sec3_text, sec3]
+                section_3 = rc.Block(
+                    rc.Heading("Forecast Parameter Plots", level=2), sec3
+                )
+                all_sections = all_sections + [section_3]
             except Exception as e:
                 logger.debug(f"Failed to plot with exception: {e.args}")
 
-            sec5_text = dp.Text(f"## Neural Prophet Model Parameters")
+            sec5_text = rc.Heading("Neural Prophet Model Parameters", level=2)
             model_states = []
             for i, (s_id, m) in enumerate(self.models.items()):
                 model_states.append(
@@ -357,7 +367,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                     )
                 )
             all_model_states = pd.concat(model_states, axis=1)
-            sec5 = dp.DataTable(all_model_states)
+            sec5 = rc.DataTable(all_model_states, index=True)
 
             all_sections = all_sections + [sec5_text, sec5]
 
@@ -366,35 +376,31 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 # If the key is present, call the "explain_model" method
                 self.explain_model()
 
-                # Create a markdown text block for the global explanation section
-                global_explanation_text = dp.Text(
-                    f"## Global Explanation of Models \n "
-                    "The following tables provide the feature attribution for the global explainability."
-                )
-
                 # Create a markdown section for the global explainability
-                global_explanation_section = dp.Blocks(
-                    "### Global Explainability ",
-                    dp.DataTable(self.formatted_global_explanation),
+                global_explanation_section = rc.Block(
+                    rc.Heading("Global Explainability", level=2),
+                    rc.Text(
+                        "The following tables provide the feature attribution for the global explainability."
+                    ),
+                    rc.DataTable(self.formatted_global_explanation, index=True),
                 )
 
-                local_explanation_text = dp.Text(f"## Local Explanation of Models \n ")
                 blocks = [
-                    dp.DataTable(
+                    rc.DataTable(
                         local_ex_df.drop("Series", axis=1),
                         label=s_id,
+                        index=True,
                     )
                     for s_id, local_ex_df in self.local_explanation.items()
                 ]
-                local_explanation_section = (
-                    dp.Select(blocks=blocks) if len(blocks) > 1 else blocks[0]
+                local_explanation_section = rc.Block(
+                    rc.Heading("Local Explanation of Models", level=2),
+                    rc.Select(blocks=blocks),
                 )
 
                 # Append the global explanation text and section to the "all_sections" list
                 all_sections = all_sections + [
-                    global_explanation_text,
                     global_explanation_section,
-                    local_explanation_text,
                     local_explanation_section,
                 ]
             except Exception as e:
@@ -402,7 +408,7 @@ class NeuralProphetOperatorModel(ForecastOperatorBaseModel):
                 logger.warn(f"Failed to generate Explanations with error: {e}.")
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")
 
-        model_description = dp.Text(
+        model_description = rc.Text(
             "NeuralProphet is an easy to learn framework for interpretable time "
             "series forecasting. NeuralProphet is built on PyTorch and combines "
             "Neural Network and traditional time-series algorithms, inspired by "

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

@@ -133,7 +133,6 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
             }
 
     def _build_model(self) -> pd.DataFrame:
-
         full_data_dict = self.datasets.get_data_by_series()
         self.models = dict()
         self.outputs = dict()
@@ -160,6 +159,7 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
     def run_tuning(self, data_i, model_kwargs_i):
         from prophet import Prophet
         from prophet.diagnostics import cross_validation, performance_metrics
+
         def objective(trial):
             params = {
                 "seasonality_mode": trial.suggest_categorical(
@@ -243,29 +243,34 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
         return model_kwargs_i
 
     def _generate_report(self):
-        import datapane as dp
+        import report_creator as rc
         from prophet.plot import add_changepoints_to_plot
+
         series_ids = self.models.keys()
         all_sections = []
         if len(series_ids) > 0:
-            sec1_text = dp.Text(
-                "## Forecast Overview \n"
-                "These plots show your forecast in the context of historical data."
-            )
             sec1 = _select_plot_list(
                 lambda s_id: self.models[s_id].plot(
                     self.outputs[s_id], include_legend=True
                 ),
                 series_ids=series_ids,
             )
+            section_1 = rc.Block(
+                rc.Heading("Forecast Overview", level=2),
+                rc.Text(
+                    "These plots show your forecast in the context of historical data."
+                ),
+                sec1,
+            )
 
-            sec2_text = dp.Text(f"## Forecast Broken Down by Trend Component")
             sec2 = _select_plot_list(
                 lambda s_id: self.models[s_id].plot_components(self.outputs[s_id]),
                 series_ids=series_ids,
             )
+            section_2 = rc.Block(
+                rc.Heading("Forecast Broken Down by Trend Component", level=2), sec2
+            )
 
-            sec3_text = dp.Text(f"## Forecast Changepoints")
             sec3_figs = {
                 s_id: self.models[s_id].plot(self.outputs[s_id]) for s_id in series_ids
             }
@@ -273,11 +278,14 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 add_changepoints_to_plot(
                     sec3_figs[s_id].gca(), self.models[s_id], self.outputs[s_id]
                 )
-            sec3 = _select_plot_list(lambda s_id: sec3_figs[s_id], series_ids=series_ids)
+            sec3 = _select_plot_list(
+                lambda s_id: sec3_figs[s_id], series_ids=series_ids
+            )
+            section_3 = rc.Block(rc.Heading("Forecast Changepoints", level=2), sec3)
 
-            all_sections = [sec1_text, sec1, sec2_text, sec2, sec3_text, sec3]
+            all_sections = [section_1, section_2, section_3]
 
-            sec5_text = dp.Text(f"## Prophet Model Seasonality Components")
+            sec5_text = rc.Heading("Prophet Model Seasonality Components", level=2)
             model_states = []
             for s_id in series_ids:
                 m = self.models[s_id]
@@ -291,7 +299,7 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 )
             all_model_states = pd.concat(model_states, axis=1)
             if not all_model_states.empty:
-                sec5 = dp.DataTable(all_model_states)
+                sec5 = rc.DataTable(all_model_states, index=True)
                 all_sections = all_sections + [sec5_text, sec5]
 
         if self.spec.generate_explanations:
@@ -299,12 +307,6 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 # If the key is present, call the "explain_model" method
                 self.explain_model()
 
-                # Create a markdown text block for the global explanation section
-                global_explanation_text = dp.Text(
-                    f"## Global Explanation of Models \n "
-                    "The following tables provide the feature attribution for the global explainability."
-                )
-
                 # Convert the global explanation data to a DataFrame
                 global_explanation_df = pd.DataFrame(self.global_explanation)
 
@@ -313,9 +315,12 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 )
 
                 # Create a markdown section for the global explainability
-                global_explanation_section = dp.Blocks(
-                    "### Global Explainability ",
-                    dp.DataTable(self.formatted_global_explanation),
+                global_explanation_section = rc.Block(
+                    rc.Heading("Global Explanation of Models", level=2),
+                    rc.Text(
+                        "The following tables provide the feature attribution for the global explainability."
+                    ),
+                    rc.DataTable(self.formatted_global_explanation, index=True),
                 )
 
                 aggregate_local_explanations = pd.DataFrame()
@@ -327,21 +332,21 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                     )
                 self.formatted_local_explanation = aggregate_local_explanations
 
-                local_explanation_text = dp.Text(f"## Local Explanation of Models \n ")
                 blocks = [
-                    dp.DataTable(
+                    rc.DataTable(
                         local_ex_df.div(local_ex_df.abs().sum(axis=1), axis=0) * 100,
                         label=s_id,
+                        index=True,
                     )
                     for s_id, local_ex_df in self.local_explanation.items()
                 ]
-                local_explanation_section = (
-                    dp.Select(blocks=blocks) if len(blocks) > 1 else blocks[0]
+                local_explanation_section = rc.Block(
+                    rc.Heading("Local Explanation of Models", level=2),
+                    rc.Select(blocks=blocks),
                 )
 
                 # Append the global explanation text and section to the "all_sections" list
                 all_sections = all_sections + [
-                    global_explanation_text,
                     global_explanation_section,
                     local_explanation_text,
                     local_explanation_section,
@@ -351,7 +356,7 @@ class ProphetOperatorModel(ForecastOperatorBaseModel):
                 logger.warn(f"Failed to generate Explanations with error: {e}.")
                 logger.debug(f"Full Traceback: {traceback.format_exc()}")
 
-        model_description = dp.Text(
+        model_description = (
             "Prophet is a procedure for forecasting time series data based on an additive "
             "model where non-linear trends are fit with yearly, weekly, and daily seasonality, "
             "plus holiday effects. It works best with time series that have strong seasonal "

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

@@ -302,11 +302,11 @@ spec:
             missing_value_imputation:
               type: boolean
               required: false
-              default: true
+              default: false
             outlier_treatment:
               type: boolean
               required: false
-              default: true
+              default: false
 
     generate_explanations:
       type: boolean

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

@@ -1,7 +1,7 @@
 #!/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
@@ -258,10 +258,10 @@ def evaluate_train_metrics(output, metrics_col_name=None):
 
 
 def _select_plot_list(fn, series_ids):
-    import datapane as dp
+    import report_creator as rc
 
-    blocks = [dp.Plot(fn(s_id=s_id), label=s_id) for s_id in series_ids]
-    return dp.Select(blocks=blocks) if len(blocks) > 1 else blocks[0]
+    blocks = [rc.Widget(fn(s_id=s_id), label=s_id) for s_id in series_ids]
+    return rc.Select(blocks=blocks) if len(blocks) > 1 else blocks[0]
 
 
 def _add_unit(num, unit):

ads/opctl/operator/lowcode/pii/README.md

@@ -33,7 +33,7 @@ To run pii operator locally, create and activate a new conda environment (`ads-p
 
 ```yaml
 - aiohttp
-- datapane
+- report-creator
 - gender_guesser
 - nameparser
 - oracle_ads[opctl]

ads/opctl/operator/lowcode/pii/environment.yaml

@@ -6,7 +6,7 @@ dependencies:
   - pip
   - pip:
       - aiohttp
-      - datapane
+      - report-creator
       - gender_guesser
       - nameparser
       - oracle_ads[opctl]