upgini 1.1.312a4__py3-none-any.whl → 1.1.312a5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.312a4"
+__version__ = "1.1.312a5"

upgini/features_enricher.py

@@ -91,7 +91,11 @@ from upgini.utils.display_utils import (
     prepare_and_show_report,
     show_request_quote_button,
 )
-from upgini.utils.email_utils import EmailDomainGenerator, EmailSearchKeyConverter, EmailSearchKeyDetector
+from upgini.utils.email_utils import (
+    EmailDomainGenerator,
+    EmailSearchKeyConverter,
+    EmailSearchKeyDetector,
+)
 from upgini.utils.features_validator import FeaturesValidator
 from upgini.utils.format import Format
 from upgini.utils.ip_utils import IpSearchKeyConverter
@@ -1030,7 +1034,7 @@ class FeaturesEnricher(TransformerMixin):
                         self.bundle.get("quality_metrics_rows_header"): _num_samples(effective_X),
                     }
                     if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
-                        y_sorted
+                        effective_y
                     ):
                         train_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
                             np.mean(effective_y), 4
@@ -1103,7 +1107,7 @@ class FeaturesEnricher(TransformerMixin):
                                 # self.bundle.get("quality_metrics_match_rate_header"): eval_hit_rate,
                             }
                             if model_task_type in [ModelTaskType.BINARY, ModelTaskType.REGRESSION] and is_numeric_dtype(
-                                eval_y_sorted
+                                effective_eval_set[idx][1]
                             ):
                                 eval_metrics[self.bundle.get("quality_metrics_mean_target_header")] = round(
                                     np.mean(effective_eval_set[idx][1]), 4
@@ -1363,6 +1367,7 @@ class FeaturesEnricher(TransformerMixin):
             importance_threshold,
             max_features,
         )
+        filtered_enriched_features = [c for c in filtered_enriched_features if c not in client_features]
 
         X_sorted, y_sorted = self._sort_by_system_record_id(X_sampled, y_sampled, self.cv)
         enriched_X_sorted, enriched_y_sorted = self._sort_by_system_record_id(enriched_X, y_sampled, self.cv)
@@ -2217,7 +2222,9 @@ class FeaturesEnricher(TransformerMixin):
                 result = enrich()
 
             filtered_columns = self.__filtered_enriched_features(importance_threshold, max_features)
-            existing_filtered_columns = [c for c in filtered_columns if c in result.columns]
+            existing_filtered_columns = [
+                c for c in filtered_columns if c in result.columns and c not in validated_X.columns
+            ]
             selecting_columns = validated_X.columns.tolist() + generated_features + existing_filtered_columns
             if add_fit_system_record_id:
                 selecting_columns.append(SORT_ID)
@@ -2430,9 +2437,7 @@ class FeaturesEnricher(TransformerMixin):
 
         email_columns = SearchKey.find_all_keys(self.fit_search_keys, SearchKey.EMAIL)
         if email_columns:
-            generator = EmailDomainGenerator(
-                email_columns
-            )
+            generator = EmailDomainGenerator(email_columns)
             df = generator.generate(df)
             self.fit_generated_features.extend(generator.generated_features)
 

{upgini-1.1.312a4.dist-info → upgini-1.1.312a5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.312a4
+Version: 1.1.312a5
 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-1.1.312a4.dist-info → upgini-1.1.312a5.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=OhL45U2LeBzyliA8yt6RNbJt0Lv5GjiINZYAIDhLhzg,26
+upgini/__about__.py,sha256=AYWzaD5lVHd4s3vopg53TBKzkKgWzJVi62VrmfO7rRU,26
 upgini/__init__.py,sha256=Xs0YFVBu1KUdtZzbStGRPQtLt3YLzJnjx5nIUBlX8BE,415
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=c6jghh32P9_2CspELYCOsmNIOiShuCADnCCJ8Jj2t50,30834
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=FfFlFW3BArv2rQWGCs-SXrDDDcjQTwwJxzRysZlJfq0,186961
+upgini/features_enricher.py,sha256=LqGOMObkFsAm58sBL3UhTmc7TOnDQmLivxl3jbXh-n0,187132
 upgini/http.py,sha256=a4Epc9YLIJBuYk4t8E_2-QDLBtJFqKO35jn2SnYQZCg,42920
 upgini/lazy_import.py,sha256=EwoM0msNGbSmWBhGbrLDny1DSnOlvTxCjmMKPxYlDms,610
 upgini/metadata.py,sha256=YQ-1HZGyPOksP2iM50ff_pMHXLyzvpChqSfNh8Z0ke4,10833
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.312a4.dist-info/METADATA,sha256=E_22GljWuDI_8hVGc09IVXufsmdscmuDypm3imVekDE,48155
-upgini-1.1.312a4.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.1.312a4.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.312a4.dist-info/RECORD,,
+upgini-1.1.312a5.dist-info/METADATA,sha256=MdhSWCWMCuajyC7B1bVWfVFOs7b5iIsmD7m3Z48egng,48155
+upgini-1.1.312a5.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.1.312a5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.312a5.dist-info/RECORD,,