upgini 1.2.30a7__tar.gz → 1.2.30a9__tar.gz

{upgini-1.2.30a7 → upgini-1.2.30a9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.30a7
+Version: 1.2.30a9
 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-1.2.30a9/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.30a9"

{upgini-1.2.30a7 → upgini-1.2.30a9}/src/upgini/features_enricher.py

@@ -1447,7 +1447,11 @@ class FeaturesEnricher(TransformerMixin):
         client_features = [
             c
             for c in X_sampled.columns.to_list()
-            if (not self.select_features or c in self.feature_names_)
+            if (
+                not self.select_features
+                or c in self.feature_names_
+                or (self.fit_columns_renaming is not None and self.fit_columns_renaming.get(c) in self.feature_names_)
+            )
             and c
             not in (
                 excluding_search_keys

{upgini-1.2.30a7 → upgini-1.2.30a9}/src/upgini/utils/features_validator.py

@@ -2,6 +2,7 @@ import logging
 from logging import Logger
 from typing import Dict, List, Optional, Tuple
 
+import numpy as np
 import pandas as pd
 from pandas.api.types import is_integer_dtype, is_object_dtype, is_string_dtype
 
@@ -83,10 +84,21 @@ class FeaturesValidator:
         return [
             i
             for i in df
-            if (is_object_dtype(df[i]) or is_string_dtype(df[i]) or is_integer_dtype(df[i]))
+            if (is_object_dtype(df[i]) or is_string_dtype(df[i]) or FeaturesValidator.__is_integer(df[i]))
             and (df[i].nunique(dropna=False) / row_count >= 0.85)
         ]
 
+    @staticmethod
+    def __is_integer(series: pd.Series) -> bool:
+        return (
+            is_integer_dtype(series)
+            or series.dropna()
+            .apply(
+                lambda f: (float.is_integer(f) and abs(f) < np.iinfo(np.int64).max) if isinstance(f, float) else False
+            )
+            .all()
+        )
+
     @staticmethod
     def find_constant_features(df: pd.DataFrame) -> List[str]:
         return [i for i in df if df[i].nunique() <= 1]

upgini-1.2.30a7/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.30a7 "