upgini 1.2.129__tar.gz → 1.2.131__tar.gz

{upgini-1.2.129 → upgini-1.2.131}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.129
+Version: 1.2.131
 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-1.2.131/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.131"

{upgini-1.2.129 → upgini-1.2.131}/src/upgini/features_enricher.py

@@ -2786,7 +2786,7 @@ if response.status_code == 200:
             df_without_features = df.drop(columns=features_not_to_pass, errors="ignore")
 
             df_without_features, full_duplicates_warning = clean_full_duplicates(
-                df_without_features, self.logger, bundle=self.bundle
+                df_without_features, is_transform=True, logger=self.logger, bundle=self.bundle
             )
             if not silent_mode and full_duplicates_warning:
                 self.__log_warning(full_duplicates_warning)
@@ -4470,7 +4470,6 @@ if response.status_code == 200:
             is_client_feature = original_name in clients_features_df.columns and not is_generated_feature
 
             if selected_features is not None and feature_meta.name not in selected_features:
-                self.logger.info(f"Feature {feature_meta.name} is not selected before and skipped")
                 continue
 
             selected_features_meta.append(feature_meta)

{upgini-1.2.129 → upgini-1.2.131}/src/upgini/utils/deduplicate_utils.py

@@ -31,7 +31,7 @@ def remove_fintech_duplicates(
         logger = logging.getLogger()
         logger.setLevel(logging.FATAL)
     date_col = _get_column_by_key(search_keys, [SearchKey.DATE, SearchKey.DATETIME])
-    if define_task(df[TARGET], date_col is not None, silent=True) != ModelTaskType.BINARY:
+    if define_task(df[TARGET], date_col is not None, logger=logger, silent=True) != ModelTaskType.BINARY:
         return df, []
 
     if date_col is None:
@@ -160,7 +160,10 @@ def remove_fintech_duplicates(
 
 
 def clean_full_duplicates(
-    df: pd.DataFrame, logger: Optional[Logger] = None, bundle: Optional[ResourceBundle] = None
+    df: pd.DataFrame,
+    is_transform: bool = False,
+    logger: Optional[Logger] = None,
+    bundle: Optional[ResourceBundle] = None,
 ) -> Tuple[pd.DataFrame, Optional[str]]:
     if logger is None:
         logger = logging.getLogger()
@@ -193,7 +196,7 @@ def clean_full_duplicates(
         logger.warning(bundle.get("dataset_full_duplicates").format(share_full_dedup))
 
     msg = None
-    if TARGET in df.columns:
+    if not is_transform and TARGET in df.columns:
         unique_columns.remove(TARGET)
 
         # Separate rows to exclude from deduplication:

{upgini-1.2.129 → upgini-1.2.131}/src/upgini/utils/target_utils.py

@@ -31,6 +31,7 @@ def define_task(
 ) -> ModelTaskType:
     if logger is None:
         logger = logging.getLogger()
+        logger.setLevel(logging.FATAL)
 
     # Replace inf and -inf with NaN to handle extreme values correctly
     y = y.replace([np.inf, -np.inf], np.nan, inplace=False)

upgini-1.2.129/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.129"