upgini 1.1.258__py3-none-any.whl → 1.1.260a1__py3-none-any.whl

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/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.dist-info → upgini-1.1.260a1.dist-info}/METADATA

@@ -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.dist-info → upgini-1.1.260a1.dist-info}/RECORD

@@ -1,8 +1,8 @@
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=mre6xn44wcC_fg63iLT_kTh4mViZqR9AKRJZAtpQz8Y,2592
-upgini/dataset.py,sha256=JSkscuhL0P6-ae6aaxnwvHTqlb9urBe8YrA4DPTdcIw,48163
+upgini/dataset.py,sha256=ywBwf93d0IH39ZGfmNDlAwe1ILQtt1WzJ87WfIOMI2g,48149
 upgini/errors.py,sha256=pdzQl3MKuK52yvncxMWMRWeSIOGhUFzpQoszoRFBOk0,958
-upgini/features_enricher.py,sha256=-uHhey6NMPMQIW16ctEqfWFh421_aaVUX85JeudIZQE,172113
+upgini/features_enricher.py,sha256=RD2EHGkWK30K82ELQmTMzGfcc5Fa1eoXvNNRR4MAssQ,172311
 upgini/fingerprint.js,sha256=VygVIQlN1v4NGZfjHqtRogOw8zjTnnMNJg_f7M5iGQU,33442
 upgini/http.py,sha256=zaO86LBBLmkieGbgYifk29eVoPCxXimZQ8YkQtKcM0I,42244
 upgini/metadata.py,sha256=fwVxtkR6Mn4iRoOqV6BfMJvJrx65I3YwZUMbZjhPyOI,9673
@@ -55,8 +55,8 @@ upgini/utils/sklearn_ext.py,sha256=fvuTWJ5AnT3ED9KSaQu_yIgW2JR19hFlaGDoVP3k60g,4
 upgini/utils/target_utils.py,sha256=DH812qcZ7Pvf9WVVb33fbwQjb1W9h1hXRNCCiG7Y6tI,2563
 upgini/utils/track_info.py,sha256=EPcJ13Jqa17_T0JjM37Ac9kWDz5Zk0GVsIZKutOb8aU,5207
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.258.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.258.dist-info/METADATA,sha256=K0skkdAz4yv8GS1IJKq-qktHBm5S82o7qND2I_Wmb9g,48156
-upgini-1.1.258.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-upgini-1.1.258.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
-upgini-1.1.258.dist-info/RECORD,,
+upgini-1.1.260a1.dist-info/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.260a1.dist-info/METADATA,sha256=jZ9q9pcKmPU9mVhYBKywk3Hwd31C26RG_H8T3XoQFIM,48158
+upgini-1.1.260a1.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+upgini-1.1.260a1.dist-info/top_level.txt,sha256=OFhTGiDIWKl5gFI49qvWq1R9IKflPaE2PekcbDXDtx4,7
+upgini-1.1.260a1.dist-info/RECORD,,

{upgini-1.1.258.dist-info → upgini-1.1.260a1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: bdist_wheel (0.43.0)
 Root-Is-Purelib: true
 Tag: py3-none-any