upgini 1.2.29a5__py3-none-any.whl → 1.2.29a6__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.29a5"
+__version__ = "1.2.29a6"

upgini/features_enricher.py

@@ -2,6 +2,7 @@ import dataclasses
 import datetime
 import gc
 import hashlib
+import itertools
 import logging
 import numbers
 import os
@@ -159,6 +160,10 @@ class FeaturesEnricher(TransformerMixin):
 
     shared_datasets: list of str, optional (default=None)
         List of private shared dataset ids for custom search
+
+    select_features: bool, optional (default=False)
+        If True, return only selected features both from input and data sources.
+        Otherwise, return all features from input and only selected features from data sources.
     """
 
     TARGET_NAME = "target"
@@ -279,7 +284,7 @@ class FeaturesEnricher(TransformerMixin):
         self._relevant_data_sources_wo_links: pd.DataFrame = self.EMPTY_DATA_SOURCES
         self.metrics: Optional[pd.DataFrame] = None
         self.feature_names_ = []
-        self.client_feature_names_ = []
+        self.dropped_client_feature_names_ = []
         self.feature_importances_ = []
         self.search_id = search_id
         self.select_features = select_features
@@ -2071,7 +2076,7 @@ class FeaturesEnricher(TransformerMixin):
             is_demo_dataset = hash_input(validated_X) in DEMO_DATASET_HASHES
 
             columns_to_drop = [
-                c for c in validated_X.columns if c in self.feature_names_ and c not in self.client_feature_names_
+                c for c in validated_X.columns if c in self.feature_names_ and c in self.dropped_client_feature_names_
             ]
             if len(columns_to_drop) > 0:
                 msg = self.bundle.get("x_contains_enriching_columns").format(columns_to_drop)
@@ -2328,11 +2333,13 @@ class FeaturesEnricher(TransformerMixin):
             else:
                 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 and c not in validated_X.columns
+            selecting_columns = [
+                c
+                for c in itertools.chain(validated_X.columns.tolist(), generated_features)
+                if c not in self.dropped_client_feature_names_
             ]
-            selecting_columns = validated_X.columns.tolist() + generated_features + existing_filtered_columns
+            filtered_columns = self.__filtered_enriched_features(importance_threshold, max_features)
+            selecting_columns.extend(c for c in filtered_columns if c in result.columns and c not in validated_X.columns)
             if add_fit_system_record_id:
                 selecting_columns.append(SORT_ID)
 
@@ -3510,7 +3517,7 @@ class FeaturesEnricher(TransformerMixin):
         features_df = self._search_task.get_all_initial_raw_features(trace_id, metrics_calculation=True)
 
         self.feature_names_ = []
-        self.client_feature_names_ = []
+        self.dropped_client_feature_names_ = []
         self.feature_importances_ = []
         features_info = []
         features_info_without_links = []
@@ -3520,18 +3527,23 @@ class FeaturesEnricher(TransformerMixin):
         for feature_meta in features_meta:
             if feature_meta.name in original_names_dict.keys():
                 feature_meta.name = original_names_dict[feature_meta.name]
+
+            is_client_feature = feature_meta.name in x_columns
+
+            if feature_meta.shap_value == 0.0:
+                if self.select_features:
+                    self.dropped_client_feature_names_.append(feature_meta.name)
+                continue
+
             # Use only important features
             if (
-                (feature_meta.shap_value == 0.0)
-                or (feature_meta.name in self.fit_generated_features)
-                or (feature_meta.name == COUNTRY)
+                feature_meta.name in self.fit_generated_features
+                or feature_meta.name == COUNTRY
+                # In select_features mode we select also from etalon features and need to show them
+                or (not self.select_features and is_client_feature)
             ):
                 continue
 
-            is_client_feature = feature_meta.name in x_columns
-            # In select_features mode we select also from etalon features and need to show them
-            if not self.select_features and is_client_feature:
-                continue
 
             self.feature_names_.append(feature_meta.name)
             self.feature_importances_.append(_round_shap_value(feature_meta.shap_value))

{upgini-1.2.29a5.dist-info → upgini-1.2.29a6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.29a5
+Version: 1.2.29a6
 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-1.2.29a5.dist-info → upgini-1.2.29a6.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=kPhSfYAPCirj2ias-m_3Zttb3tZcyZpwrnKTzNizAdQ,25
+upgini/__about__.py,sha256=IwPdYvZC3KafuIyZFkN_uViBDHIV_KryoYm_uF-6Z5k,25
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=iPFiMJtk4HF1ytw9wCQr8H9RfoOKj_TIo8XYZKWgcMc,31331
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=mEb1I_qnheDHNL2LEm-q9Yg3ZR_UPnavxe8H4JkVdvk,190405
+upgini/features_enricher.py,sha256=HAu6ZZSCW5BJ83fxuGjuEy2h283EO1sr3j_eUcVldsY,190873
 upgini/http.py,sha256=21asexflvavydzCOONJDGQBtQanCElrbnqLXakJ9Cu8,42880
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=osmzdNESeh7yP3BZday6N9Q3eaIHfzhhRM1d6NSgcf0,11223
@@ -59,7 +59,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=PU77nIhTz7IHbC4rpTpxrVxib6cdpRL9F1dhkjIffLY,10225
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.29a5.dist-info/METADATA,sha256=ccMETf-MYrRSaOwmMEW0Smo9IjLU_b-LS6MTOvyilpc,48580
-upgini-1.2.29a5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.29a5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.29a5.dist-info/RECORD,,
+upgini-1.2.29a6.dist-info/METADATA,sha256=7ZvyeiohsWXQQ1j_7N2H6yVKKhe4pUEpRORxtFBGcH8,48580
+upgini-1.2.29a6.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.29a6.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.29a6.dist-info/RECORD,,