upgini 1.2.135a3__tar.gz → 1.2.136__tar.gz

{upgini-1.2.135a3 → upgini-1.2.136}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.135a3
+Version: 1.2.136
 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-1.2.136/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.136"

{upgini-1.2.135a3 → upgini-1.2.136}/src/upgini/dataset.py

@@ -71,6 +71,7 @@ class Dataset:
         date_column: Optional[str] = None,
         id_columns: Optional[List[str]] = None,
         is_imbalanced: bool = False,
+        dropped_columns: Optional[List[str]] = None,
         random_state: Optional[int] = None,
         sample_config: Optional[SampleConfig] = None,
         rest_client: Optional[_RestClient] = None,
@@ -118,6 +119,7 @@ class Dataset:
         self.is_imbalanced: bool = False
         self.id_columns = id_columns
         self.is_imbalanced = is_imbalanced
+        self.dropped_columns = dropped_columns
         self.date_column = date_column
         if logger is not None:
             self.logger = logger
@@ -476,6 +478,7 @@ class Dataset:
             hierarchicalGroupKeys=self.hierarchical_group_keys,
             hierarchicalSubgroupKeys=self.hierarchical_subgroup_keys,
             taskType=self.task_type,
+            droppedColumns=self.dropped_columns,
         )
 
     @staticmethod

{upgini-1.2.135a3 → upgini-1.2.136}/src/upgini/features_enricher.py

@@ -1737,6 +1737,10 @@ class FeaturesEnricher(TransformerMixin):
 
         self.logger.info(f"Excluding search keys: {excluding_search_keys}")
 
+        file_meta = self._search_task.get_file_metadata(trace_id)
+        fit_dropped_features = self.fit_dropped_features or file_meta.droppedColumns or []
+        original_dropped_features = [columns_renaming.get(f, f) for f in fit_dropped_features]
+
         client_features = [
             c
             for c in validated_X.columns.to_list()
@@ -1744,7 +1748,7 @@ class FeaturesEnricher(TransformerMixin):
             and c
             not in (
                 excluding_search_keys
-                + list(self.fit_dropped_features)
+                + original_dropped_features
                 + [DateTimeConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
             )
         ]
@@ -2955,8 +2959,10 @@ if response.status_code == 200:
         trace_id: str,
         is_transform: bool = False,
     ):
-        fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
-        original_dropped_features = [self.fit_columns_renaming.get(c, c) for c in self.fit_dropped_features]
+        file_meta = self._search_task.get_file_metadata(trace_id)
+        fit_dropped_features = self.fit_dropped_features or file_meta.droppedColumns or []
+        fit_input_columns = [c.originalName for c in file_meta.columns]
+        original_dropped_features = [self.fit_columns_renaming.get(c, c) for c in fit_dropped_features]
         new_columns_on_transform = [
             c for c in validated_Xy.columns if c not in fit_input_columns and c not in original_dropped_features
         ]
@@ -3380,6 +3386,7 @@ if response.status_code == 200:
             cv_type=self.cv,
             id_columns=self.__get_renamed_id_columns(),
             is_imbalanced=self.imbalanced,
+            dropped_columns=[self.fit_columns_renaming.get(f, f) for f in self.fit_dropped_features],
             date_column=self._get_date_column(self.fit_search_keys),
             date_format=self.date_format,
             random_state=self.random_state,

{upgini-1.2.135a3 → upgini-1.2.136}/src/upgini/metadata.py

@@ -252,6 +252,7 @@ class FileMetadata(BaseModel):
     rowsCount: Optional[int] = None
     checksumMD5: Optional[str] = None
     digest: Optional[str] = None
+    droppedColumns: Optional[List[str]] = None
 
     def column_by_name(self, name: str) -> Optional[FileColumnMetadata]:
         for c in self.columns:

{upgini-1.2.135a3 → upgini-1.2.136}/src/upgini/utils/features_validator.py

@@ -46,7 +46,7 @@ class FeaturesValidator:
 
         columns_renaming = columns_renaming or {}
 
-        if one_hot_encoded_features:
+        if one_hot_encoded_features and len(one_hot_encoded_features) > 1:
             msg = bundle.get("one_hot_encoded_features").format(
                 [columns_renaming.get(f, f) for f in one_hot_encoded_features]
             )

upgini-1.2.135a3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.135a3"