upgini 1.2.38a3769.dev4__tar.gz → 1.2.38a3769.dev6__tar.gz

{upgini-1.2.38a3769.dev4 → upgini-1.2.38a3769.dev6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.38a3769.dev4
+Version: 1.2.38a3769.dev6
 Summary: Intelligent data search & enrichment for Machine Learning
 Project-URL: Bug Reports, https://github.com/upgini/upgini/issues
 Project-URL: Homepage, https://upgini.com/

upgini-1.2.38a3769.dev6/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.38a3769.dev6"

{upgini-1.2.38a3769.dev4 → upgini-1.2.38a3769.dev6}/src/upgini/dataset.py

@@ -77,6 +77,7 @@ class Dataset:  # (pd.DataFrame):
         unnest_search_keys: Optional[Dict[str, str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         cv_type: Optional[CVType] = None,
+        id_columns: Optional[List[str]] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
         logger: Optional[logging.Logger] = None,
@@ -120,6 +121,7 @@ class Dataset:  # (pd.DataFrame):
         self.random_state = random_state
         self.columns_renaming: Dict[str, str] = {}
         self.imbalanced: bool = False
+        self.id_columns = id_columns
         if logger is not None:
             self.logger = logger
         else:
@@ -230,6 +232,7 @@ class Dataset:  # (pd.DataFrame):
                 target_column=target_column,
                 task_type=self.task_type,
                 cv_type=self.cv_type,
+                id_columns=self.id_columns,
                 random_state=self.random_state,
                 sample_size=self.FORCE_SAMPLE_SIZE,
                 logger=self.logger,
@@ -305,7 +308,7 @@ class Dataset:  # (pd.DataFrame):
             if self.cv_type is not None and self.cv_type.is_time_series():
                 resampled_data = balance_undersample_time_series(
                     df=self.data,
-                    id_columns=[k for k, v in self.meaning_types.items() if v == FileColumnMeaningType.CUSTOM_KEY],
+                    id_columns=self.id_columns,
                     date_column=next(
                         k
                         for k, v in self.meaning_types.items()

{upgini-1.2.38a3769.dev4 → upgini-1.2.38a3769.dev6}/src/upgini/features_enricher.py

@@ -932,7 +932,7 @@ class FeaturesEnricher(TransformerMixin):
                 cat_features, search_keys_for_metrics = self._get_client_cat_features(
                     estimator, validated_X, self.search_keys
                 )
-                search_keys_for_metrics.extend([c for c in self.id_columns if c not in search_keys_for_metrics])
+                search_keys_for_metrics.extend([c for c in self.id_columns or [] if c not in search_keys_for_metrics])
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -2300,6 +2300,7 @@ class FeaturesEnricher(TransformerMixin):
                 meaning_types=meaning_types,
                 search_keys=combined_search_keys,
                 unnest_search_keys=unnest_search_keys,
+                id_columns=self.__get_renamed_id_columns(),
                 date_format=self.date_format,
                 rest_client=self.rest_client,
                 logger=self.logger,
@@ -2657,8 +2658,7 @@ class FeaturesEnricher(TransformerMixin):
         self.__adjust_cv(df)
 
         if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
-            reverse_renaming = {v: k for k, v in self.fit_columns_renaming.items()}
-            id_columns = [reverse_renaming[col] for col in self.id_columns if col in reverse_renaming]
+            id_columns = self.__get_renamed_id_columns()
             self.fit_search_keys.update({col: SearchKey.CUSTOM_KEY for col in id_columns})
             self.runtime_parameters.properties["id_columns"] = ",".join(id_columns)
 
@@ -2784,6 +2784,7 @@ class FeaturesEnricher(TransformerMixin):
             unnest_search_keys=unnest_search_keys,
             model_task_type=self.model_task_type,
             cv_type=self.cv,
+            id_columns=self.__get_renamed_id_columns(),
             date_format=self.date_format,
             random_state=self.random_state,
             rest_client=self.rest_client,
@@ -2943,6 +2944,10 @@ class FeaturesEnricher(TransformerMixin):
     def __should_add_date_column(self):
         return self.add_date_if_missing or (self.cv is not None and self.cv.is_time_series())
 
+    def __get_renamed_id_columns(self):
+        reverse_renaming = {v: k for k, v in self.fit_columns_renaming.items()}
+        return [reverse_renaming.get(c) or c for c in self.id_columns]
+
     def __adjust_cv(self, df: pd.DataFrame):
         date_column = SearchKey.find_key(self.fit_search_keys, [SearchKey.DATE, SearchKey.DATETIME])
         # Check Multivariate time series

upgini-1.2.38a3769.dev4/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.38a3769.dev4"