fixed target_column removal bugs

Author: govarsha

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

@@ -250,7 +250,7 @@ def _generate_report(self):
         models = self.models
         for i, (target, df) in enumerate(self.full_data_dict.items()):
             selected_models[target] = {
-                "series_id": target,
+                "series_id": utils.convert_target(target, self.original_target_column),
                 "selected_model": models[target].selected_model_,
                 "model_params": models[target].selected_model_params_,
             }

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

@@ -257,13 +257,25 @@ def _generate_report(self) -> tuple:
             "## Forecast Overview \n"
             "These plots show your forecast in the context of historical data."
         )
+
+        # Default title generated by autots has target_col in it. Modified function to get rid of it.
+        def get_title(idx, target):
+            from autots.models.base import extract_single_series_from_horz
+            title_prelim = extract_single_series_from_horz(
+                self.models.df_wide_numeric.columns[idx],
+                model_name=self.prediction.model_name,
+                model_parameters=self.prediction.model_parameters,
+            )[0:80]
+            return f"{utils.convert_target(target, self.original_target_column)} with model {title_prelim}"
+
         sec_1 = utils._select_plot_list(
-            lambda idx, *args: self.prediction.plot(
+            lambda idx, target, *args: self.prediction.plot(
                 self.models.df_wide_numeric,
                 series=self.models.df_wide_numeric.columns[idx],
                 start_date=self.models.df_wide_numeric.reset_index()[
                     self.spec.datetime_column.name
                 ].min(),
+                title=get_title(idx, target)
             ),
             target_columns=self.target_columns,
             original_target_column=self.original_target_column
@@ -325,7 +337,7 @@ def _generate_report(self) -> tuple:
                     dp.DataTable(
                         local_ex_df.div(local_ex_df.abs().sum(axis=1), axis=0) * 100,
                         label=utils.convert_target(s_id, self.original_target_column),
-                        )
+                    )
                     for s_id, local_ex_df in self.local_explanation.items()
                 ]
                 local_explanation_section = (
@@ -365,7 +377,7 @@ def _generate_train_metrics(self) -> pd.DataFrame:
         Generate Training Metrics when fitted data is not available.
         The method that needs to be implemented on the particular model level.
 
-        metrics	Sales_Store 1
+        metrics	Store 1
         sMAPE	26.19
         MAPE	2.96E+18
         RMSE	2014.192531
@@ -376,4 +388,7 @@ def _generate_train_metrics(self) -> pd.DataFrame:
         scores = pd.DataFrame(
             self.models.best_model_per_series_score(), columns=["AutoTS Score"]
         ).T
-        return pd.concat([mapes, scores])
+        df = pd.concat([mapes, scores])
+        new_column_names = {old_name: utils.convert_target(old_name, self.original_target_column)
+                            for old_name in df.columns}
+        return df.rename(columns=new_column_names)