upgini 1.1.244a16__tar.gz → 1.1.244a18__tar.gz

{upgini-1.1.244a16/src/upgini.egg-info → upgini-1.1.244a18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.244a16
+Version: 1.1.244a18
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.244a16 → upgini-1.1.244a18}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.244a16"
+version = "1.1.244a18"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.244a16 → upgini-1.1.244a18}/src/upgini/features_enricher.py

@@ -1337,7 +1337,9 @@ class FeaturesEnricher(TransformerMixin):
 
         # Detect and drop high cardinality columns in train
         columns_with_high_cardinality = FeaturesValidator.find_high_cardinality(fitting_X)
-        columns_with_high_cardinality = [c for c in columns_with_high_cardinality if c not in self.generate_features]
+        columns_with_high_cardinality = [
+            c for c in columns_with_high_cardinality if c not in (self.generate_features or [])
+        ]
         self.logger.info(
             f"Columns {columns_with_high_cardinality} will be dropped for metrics calculation due to high cardinality"
         )

{upgini-1.1.244a16 → upgini-1.1.244a18}/src/upgini/metrics.py

@@ -416,11 +416,12 @@ class CatBoostWrapper(EstimatorWrapper):
         if len(self.emb_features) > 3:  # There is no reason to reduce embeddings dimension with less than 4
             X, embedding_features = self.group_embeddings(X)
             params["embedding_features"] = embedding_features
+        else:
+            self.emb_features = []
 
         # Find text features from passed in generate_features
         if self.text_features is not None:
             self.text_features = [f for f in self.text_features if not is_numeric_dtype(X[f])]
-            
             params["text_features"] = self.text_features
 
         # Find rest categorical features
@@ -464,7 +465,6 @@ class CatBoostWrapper(EstimatorWrapper):
         df = df.copy()
         df[self.emb_features] = df[self.emb_features].fillna(0.0)
         df[emb_name] = df[self.emb_features].values.tolist()
-        # TODO drop by condition
         df = df.drop(columns=self.emb_features)
 
         return df, [emb_name]

{upgini-1.1.244a16 → upgini-1.1.244a18/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.244a16
+Version: 1.1.244a18
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers