upgini 1.1.258__tar.gz → 1.1.260a1__tar.gz

{upgini-1.1.258/src/upgini.egg-info → upgini-1.1.260a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.258
+Version: 1.1.260a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers

{upgini-1.1.258 → upgini-1.1.260a1}/setup.py

@@ -40,7 +40,7 @@ def send_log(msg: str):
 
 
 here = Path(__file__).parent.resolve()
-version = "1.1.258"
+version = "1.1.260a1"
 try:
     send_log(f"Start setup PyLib version {version}")
     setup(

{upgini-1.1.258 → upgini-1.1.260a1}/src/upgini/dataset.py

@@ -223,11 +223,11 @@ class Dataset:  # (pd.DataFrame):
                     self.data[col] = self.data[col].astype("str").str.slice(stop=self.MAX_STRING_FEATURE_LENGTH)
 
     def __convert_bools(self):
-        """Convert bool columns True -> 1, False -> 0"""
+        """Convert bool columns to string"""
         # self.logger.info("Converting bool to int")
         for col in self.data.columns:
             if is_bool(self.data[col]):
-                self.data[col] = self.data[col].astype("Int64")
+                self.data[col] = self.data[col].astype("str")
 
     def __convert_float16(self):
         """Convert float16 to float"""

{upgini-1.1.258 → upgini-1.1.260a1}/src/upgini/features_enricher.py

@@ -1681,9 +1681,12 @@ class FeaturesEnricher(TransformerMixin):
                 eval_set_sampled_dict[idx] = (eval_x_sampled, enriched_eval_x, eval_y_sampled)
         else:
             self.logger.info("Transform without eval_set")
-            df = self.X.copy()
+            df = validated_X.copy()
 
             df[TARGET] = validated_y
+
+            df = clean_full_duplicates(df, logger=self.logger, silent=True, bundle=self.bundle)
+
             num_samples = _num_samples(df)
             if num_samples > Dataset.FIT_SAMPLE_THRESHOLD:
                 self.logger.info(f"Downsampling from {num_samples} to {Dataset.FIT_SAMPLE_ROWS}")
@@ -2884,19 +2887,20 @@ class FeaturesEnricher(TransformerMixin):
             sort_columns = [date_column] if date_column is not None else []
 
             other_search_keys = sorted(
-                [
-                    sk
-                    for sk, key_type in search_keys.items()
-                    if key_type not in [SearchKey.DATE, SearchKey.DATETIME]
-                    and sk in df.columns
-                    and df[sk].nunique() > 1  # don't use constant keys for hash
-                ]
+                [c for c in df.columns if c not in sort_columns and df[c].nunique() > 1]
+                # [
+                #     sk
+                #     for sk, key_type in search_keys.items()
+                #     if key_type not in [SearchKey.DATE, SearchKey.DATETIME]
+                #     and sk in df.columns
+                #     and df[sk].nunique() > 1  # don't use constant keys for hash
+                # ]
             )
 
             search_keys_hash = "search_keys_hash"
             if len(other_search_keys) > 0:
                 sort_columns.append(search_keys_hash)
-                df[search_keys_hash] = pd.util.hash_pandas_object(df[sorted(other_search_keys)], index=False)
+                df[search_keys_hash] = pd.util.hash_pandas_object(df[other_search_keys], index=False)
 
             df = df.sort_values(by=sort_columns)
 

{upgini-1.1.258 → upgini-1.1.260a1/src/upgini.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: upgini
-Version: 1.1.258
+Version: 1.1.260a1
 Summary: Intelligent data search & enrichment for Machine Learning
 Home-page: https://upgini.com/
 Author: Upgini Developers