upgini 1.2.135a3__py3-none-any.whl → 1.2.136__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.135a3"
+__version__ = "1.2.136"

upgini/dataset.py

@@ -71,6 +71,7 @@ class Dataset:
         date_column: Optional[str] = None,
         id_columns: Optional[List[str]] = None,
         is_imbalanced: bool = False,
+        dropped_columns: Optional[List[str]] = None,
         random_state: Optional[int] = None,
         sample_config: Optional[SampleConfig] = None,
         rest_client: Optional[_RestClient] = None,
@@ -118,6 +119,7 @@ class Dataset:
         self.is_imbalanced: bool = False
         self.id_columns = id_columns
         self.is_imbalanced = is_imbalanced
+        self.dropped_columns = dropped_columns
         self.date_column = date_column
         if logger is not None:
             self.logger = logger
@@ -476,6 +478,7 @@ class Dataset:
             hierarchicalGroupKeys=self.hierarchical_group_keys,
             hierarchicalSubgroupKeys=self.hierarchical_subgroup_keys,
             taskType=self.task_type,
+            droppedColumns=self.dropped_columns,
         )
 
     @staticmethod

upgini/features_enricher.py

@@ -1737,6 +1737,10 @@ class FeaturesEnricher(TransformerMixin):
 
         self.logger.info(f"Excluding search keys: {excluding_search_keys}")
 
+        file_meta = self._search_task.get_file_metadata(trace_id)
+        fit_dropped_features = self.fit_dropped_features or file_meta.droppedColumns or []
+        original_dropped_features = [columns_renaming.get(f, f) for f in fit_dropped_features]
+
         client_features = [
             c
             for c in validated_X.columns.to_list()
@@ -1744,7 +1748,7 @@ class FeaturesEnricher(TransformerMixin):
             and c
             not in (
                 excluding_search_keys
-                + list(self.fit_dropped_features)
+                + original_dropped_features
                 + [DateTimeConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
             )
         ]
@@ -2955,8 +2959,10 @@ if response.status_code == 200:
         trace_id: str,
         is_transform: bool = False,
     ):
-        fit_input_columns = [c.originalName for c in self._search_task.get_file_metadata(trace_id).columns]
-        original_dropped_features = [self.fit_columns_renaming.get(c, c) for c in self.fit_dropped_features]
+        file_meta = self._search_task.get_file_metadata(trace_id)
+        fit_dropped_features = self.fit_dropped_features or file_meta.droppedColumns or []
+        fit_input_columns = [c.originalName for c in file_meta.columns]
+        original_dropped_features = [self.fit_columns_renaming.get(c, c) for c in fit_dropped_features]
         new_columns_on_transform = [
             c for c in validated_Xy.columns if c not in fit_input_columns and c not in original_dropped_features
         ]
@@ -3380,6 +3386,7 @@ if response.status_code == 200:
             cv_type=self.cv,
             id_columns=self.__get_renamed_id_columns(),
             is_imbalanced=self.imbalanced,
+            dropped_columns=[self.fit_columns_renaming.get(f, f) for f in self.fit_dropped_features],
             date_column=self._get_date_column(self.fit_search_keys),
             date_format=self.date_format,
             random_state=self.random_state,

upgini/metadata.py

@@ -252,6 +252,7 @@ class FileMetadata(BaseModel):
     rowsCount: Optional[int] = None
     checksumMD5: Optional[str] = None
     digest: Optional[str] = None
+    droppedColumns: Optional[List[str]] = None
 
     def column_by_name(self, name: str) -> Optional[FileColumnMetadata]:
         for c in self.columns:

upgini/utils/features_validator.py

@@ -46,7 +46,7 @@ class FeaturesValidator:
 
         columns_renaming = columns_renaming or {}
 
-        if one_hot_encoded_features:
+        if one_hot_encoded_features and len(one_hot_encoded_features) > 1:
             msg = bundle.get("one_hot_encoded_features").format(
                 [columns_renaming.get(f, f) for f in one_hot_encoded_features]
             )

{upgini-1.2.135a3.dist-info → upgini-1.2.136.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: upgini
-Version: 1.2.135a3
+Version: 1.2.136
 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-1.2.135a3.dist-info → upgini-1.2.136.dist-info}/RECORD

@@ -1,11 +1,11 @@
-upgini/__about__.py,sha256=zKar2BSHx-M-ruW4V1DQDr70UfG-vBoiDPsQB4duA-c,26
+upgini/__about__.py,sha256=geG4WOLTgtin9k9NxkyjPJlJc57re5T0iGsOwFw3cp4,24
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=qXo1eAUM21jmNMYGa6IeGuRJmjU3jtCieS4sAVVIfXs,31721
+upgini/dataset.py,sha256=4bWKKFdFbFvdcb-JS4Nt2Je8eKqPg5QRLlmchQuY2aw,31870
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=dC71_-18cqymS26EhEnfYnZFGDvRtvW6Pga4ZtJN-BI,235485
+upgini/features_enricher.py,sha256=9pBxZKWsXF_IhZXnswCQZGU-cqOOT1EqH-FPu1zJo4E,235950
 upgini/http.py,sha256=-J_wOpnwVnT0ebPC6sOs6fN3AWtCD0LJLu6nlYmxaqk,44348
-upgini/metadata.py,sha256=H3wiN37k-yqWZgbPD0tJzx8DzaCIkgmX5cybhByQWLg,12619
+upgini/metadata.py,sha256=soRxxAG9gpOk77oOxCl35f9nWPDTaYyJEHgwKWhkS84,12666
 upgini/metrics.py,sha256=KCPE_apPN-9BIdv6GqASbJVaB_gBcy8wzNApAcyaGo4,46020
 upgini/search_task.py,sha256=5mL_qV5mVtDkIumM9xCOgfa9Lc2B8mxJ1qI21iaScnQ,18656
 upgini/spinner.py,sha256=4iMd-eIe_BnkqFEMIliULTbj6rNI2HkN_VJ4qYe0cUc,1118
@@ -58,7 +58,7 @@ upgini/utils/display_utils.py,sha256=MoTqXZJvC6pAqgOaI3V0FG-IU_LnMfrn4TDcNvUqsdg
 upgini/utils/email_utils.py,sha256=pZ2vCfNxLIPUhxr0-OlABNXm12jjU44isBk8kGmqQzA,5277
 upgini/utils/fallback_progress_bar.py,sha256=PDaKb8dYpVZaWMroNcOHsTc3pSjgi9mOm0--cOFTwJ0,1074
 upgini/utils/feature_info.py,sha256=SQTRbSxJDkh2G2c0KGBmOv8f69gVzWbTtcXn0_2Qb-8,7945
-upgini/utils/features_validator.py,sha256=RdRMisZYeJ8HVCKiKxqSyWjoLf_MsZNXxHIuWf6H2g4,4939
+upgini/utils/features_validator.py,sha256=pAyS57-jYlihMOhweM12GOvCTJC13fTIJ9lQwgoON5c,4977
 upgini/utils/format.py,sha256=Yv5cvvSs2bOLUzzNu96Pu33VMDNbabio92QepUj41jU,243
 upgini/utils/hash_utils.py,sha256=mP2yHyzvDNdpa5g3B4MHzulxBeEz_ZSoGl1YF_VnAyE,5538
 upgini/utils/ip_utils.py,sha256=wmnnwVQdjX9o1cNQw6VQMk6maHhvsq6hNsZBYf9knrw,6585
@@ -74,7 +74,7 @@ upgini/utils/target_utils.py,sha256=CihpV6SC95HwtlMH60rGAUzVDa4Id0Bva8ySprmNHlE,
 upgini/utils/track_info.py,sha256=NDKeQTUlZaYp15UoP-xLKGoDoJQ0drbDMwB0g9R0PUg,6427
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.135a3.dist-info/METADATA,sha256=p6JAaluvHU1B6Al8fHzq5KsgyNQvznWkEDwE1fhHuZI,51135
-upgini-1.2.135a3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-upgini-1.2.135a3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.135a3.dist-info/RECORD,,
+upgini-1.2.136.dist-info/METADATA,sha256=iszl9ghp_J6AHfTIZCtf5PliRGfKprpYxdwPfSUsEPg,51133
+upgini-1.2.136.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+upgini-1.2.136.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.136.dist-info/RECORD,,