upgini 1.2.135a1__tar.gz → 1.2.135a2__tar.gz

{upgini-1.2.135a1 → upgini-1.2.135a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.135a1
+Version: 1.2.135a2
 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-1.2.135a2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.135a2"

{upgini-1.2.135a1 → upgini-1.2.135a2}/src/upgini/features_enricher.py

@@ -1047,7 +1047,8 @@ class FeaturesEnricher(TransformerMixin):
                 with Spinner():
                     self._check_train_and_eval_target_distribution(y_sorted, fitting_eval_set_dict)
 
-                    has_date = self._get_date_column(search_keys) is not None
+                    date_col = self._get_date_column(search_keys)
+                    has_date = date_col is not None and date_col in validated_X.columns
                     model_task_type = self.model_task_type or define_task(y_sorted, has_date, self.logger, silent=True)
                     cat_features = list(set(client_cat_features + cat_features_from_backend))
                     has_time = has_date and isinstance(_cv, TimeSeriesSplit) or isinstance(_cv, BlockedTimeSeriesSplit)
@@ -1323,7 +1324,7 @@ class FeaturesEnricher(TransformerMixin):
             search_keys = {str(k): v for k, v in search_keys.items()}
 
         date_column = self._get_date_column(search_keys)
-        has_date = date_column is not None
+        has_date = date_column is not None and date_column in validated_X.columns
         if not has_date:
             self.logger.info("No date column for OOT PSI calculation")
             return
@@ -2087,7 +2088,8 @@ class FeaturesEnricher(TransformerMixin):
         search_keys = self.fit_search_keys.copy()
 
         rows_to_drop = None
-        has_date = self._get_date_column(search_keys) is not None
+        date_column = self._get_date_column(search_keys)
+        has_date = date_column is not None and date_column in validated_X.columns
         self.model_task_type = self.model_task_type or define_task(
             self.df_with_original_index[TARGET], has_date, self.logger, silent=True
         )
@@ -2954,7 +2956,10 @@ if response.status_code == 200:
         is_transform: bool = False,
     ):
         fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
-        new_columns_on_transform = [c for c in validated_Xy.columns if c not in fit_input_columns]
+        original_dropped_features = [self.fit_columns_renaming.get(c, c) for c in self.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
+        ]
 
         selected_generated_features = [c for c in generated_features if c in self.feature_names_]
         if keep_input is True:
@@ -3129,7 +3134,7 @@ if response.status_code == 200:
         self.fit_search_keys = self.__prepare_search_keys(df, self.fit_search_keys, is_demo_dataset)
 
         maybe_date_column = SearchKey.find_key(self.fit_search_keys, [SearchKey.DATE, SearchKey.DATETIME])
-        has_date = maybe_date_column is not None
+        has_date = maybe_date_column is not None and maybe_date_column in validated_X.columns
 
         self.model_task_type = self.model_task_type or define_task(validated_y, has_date, self.logger)
 
@@ -3763,7 +3768,8 @@ if response.status_code == 200:
         if eval_set is None:
             return None
         validated_eval_set = []
-        has_date = self._get_date_column(self.search_keys) is not None
+        date_col = self._get_date_column(self.search_keys)
+        has_date = date_col is not None and date_col in X.columns
         for idx, eval_pair in enumerate(eval_set):
             validated_pair = self._validate_eval_set_pair(X, eval_pair)
             if validated_pair[1].isna().all():

{upgini-1.2.135a1 → upgini-1.2.135a2}/src/upgini/utils/features_validator.py

@@ -44,12 +44,14 @@ class FeaturesValidator:
                 else:
                     empty_or_constant_features.append(f)
 
+        columns_renaming = columns_renaming or {}
+
         if one_hot_encoded_features:
-            msg = bundle.get("one_hot_encoded_features").format(one_hot_encoded_features)
+            msg = bundle.get("one_hot_encoded_features").format(
+                [columns_renaming.get(f, f) for f in one_hot_encoded_features]
+            )
             warnings.append(msg)
 
-        columns_renaming = columns_renaming or {}
-
         if empty_or_constant_features:
             msg = bundle.get("empty_or_contant_features").format(
                 [columns_renaming.get(f, f) for f in empty_or_constant_features]

upgini-1.2.135a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.135a1"