adding series_id in inliers, outliers

Author: govarsha

ads/opctl/operator/lowcode/anomaly/model/anomaly_dataset.py

@@ -49,6 +49,7 @@ def __init__(self, spec: AnomalyOperatorSpec):
             The anomaly operator spec.
         """
         self._data = AnomalyData(spec)
+        self.data_with_all_cols = self._data.get_data_with_all_cols()
         self.data = self._data.get_data_long()
         self.full_data_dict = self._data.get_dict_by_series()
         if spec.validation_data is not None:

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

@@ -272,15 +272,15 @@ def _save_report(
                     f2.write(f1.read())
 
         if self.spec.generate_inliers:
-            inliers = anomaly_output.get_inliers(self.datasets.data)
+            inliers = anomaly_output.get_inliers(self.datasets.data_with_all_cols)
             write_data(
                 data=inliers,
                 filename=os.path.join(unique_output_dir, self.spec.inliers_filename),
                 format="csv",
                 storage_options=storage_options,
             )
 
-        outliers = anomaly_output.get_outliers(self.datasets.data)
+        outliers = anomaly_output.get_outliers(self.datasets.data_with_all_cols)
         write_data(
             data=outliers,
             filename=os.path.join(unique_output_dir, self.spec.outliers_filename),

ads/opctl/operator/lowcode/common/data.py

@@ -24,8 +24,14 @@ def __init__(self, spec: dict, name="input_data"):
         self.data = None
         self._data_dict = dict()
         self.name = name
+        self.data_with_all_cols = None
         self.load_transform_ingest_data(spec)
 
+
+    def get_data_with_all_cols(self):
+        return self.data_with_all_cols.reset_index(drop=False)
+
+
     def get_dict_by_series(self):
         if not self._data_dict:
             for s_id in self.list_series_ids():
@@ -65,7 +71,10 @@ def _load_data(self, data_spec, **kwargs):
     def _transform_data(self, spec, raw_data, **kwargs):
         transformation_start_time = time.time()
         self._data_transformer = self.Transformations(spec, name=self.name)
-        data = self._data_transformer.run(raw_data)
+        self.data_with_all_cols = self._data_transformer.run(raw_data)
+        data = self.data_with_all_cols
+        if spec.target_category_columns:
+            data = data.drop(spec.target_category_columns, axis=1)
         transformation_end_time = time.time()
         logger.info(
             f"{self.name} transformations completed in {transformation_end_time - transformation_start_time} seconds"

ads/opctl/operator/lowcode/common/transformations.py

@@ -85,7 +85,7 @@ def _set_series_id_column(self, df):
             df[DataColumns.Series] = merge_category_columns(
                 df, self.target_category_columns
             )
-            df = df.drop(self.target_category_columns, axis=1)
+            #df = df.drop(self.target_category_columns, axis=1)
         return df
 
     def _format_datetime_col(self, df):