upgini 1.2.38a3769.dev3__py3-none-any.whl → 1.2.38a3769.dev5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.38a3769.dev3"
+__version__ = "1.2.38a3769.dev5"

upgini/dataset.py

@@ -77,6 +77,7 @@ class Dataset:  # (pd.DataFrame):
         unnest_search_keys: Optional[Dict[str, str]] = None,
         model_task_type: Optional[ModelTaskType] = None,
         cv_type: Optional[CVType] = None,
+        id_columns: Optional[List[str]] = None,
         random_state: Optional[int] = None,
         rest_client: Optional[_RestClient] = None,
         logger: Optional[logging.Logger] = None,
@@ -120,6 +121,7 @@ class Dataset:  # (pd.DataFrame):
         self.random_state = random_state
         self.columns_renaming: Dict[str, str] = {}
         self.imbalanced: bool = False
+        self.id_columns = id_columns
         if logger is not None:
             self.logger = logger
         else:
@@ -230,6 +232,7 @@ class Dataset:  # (pd.DataFrame):
                 target_column=target_column,
                 task_type=self.task_type,
                 cv_type=self.cv_type,
+                id_columns=self.id_columns,
                 random_state=self.random_state,
                 sample_size=self.FORCE_SAMPLE_SIZE,
                 logger=self.logger,
@@ -305,7 +308,7 @@ class Dataset:  # (pd.DataFrame):
             if self.cv_type is not None and self.cv_type.is_time_series():
                 resampled_data = balance_undersample_time_series(
                     df=self.data,
-                    id_columns=[k for k, v in self.meaning_types.items() if v == FileColumnMeaningType.CUSTOM_KEY],
+                    id_columns=self.id_columns,
                     date_column=next(
                         k
                         for k, v in self.meaning_types.items()

upgini/features_enricher.py

@@ -932,6 +932,7 @@ class FeaturesEnricher(TransformerMixin):
                 cat_features, search_keys_for_metrics = self._get_client_cat_features(
                     estimator, validated_X, self.search_keys
                 )
+                search_keys_for_metrics.extend([c for c in self.id_columns or [] if c not in search_keys_for_metrics])
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -2299,6 +2300,7 @@ class FeaturesEnricher(TransformerMixin):
                 meaning_types=meaning_types,
                 search_keys=combined_search_keys,
                 unnest_search_keys=unnest_search_keys,
+                id_columns=self.id_columns,
                 date_format=self.date_format,
                 rest_client=self.rest_client,
                 logger=self.logger,
@@ -2656,7 +2658,10 @@ class FeaturesEnricher(TransformerMixin):
         self.__adjust_cv(df)
 
         if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
-            self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in self.id_columns})
+            reverse_renaming = {v: k for k, v in self.fit_columns_renaming.items()}
+            id_columns = [reverse_renaming[col] for col in self.id_columns if col in reverse_renaming]
+            self.fit_search_keys.update({col: SearchKey.CUSTOM_KEY for col in id_columns})
+            self.runtime_parameters.properties["id_columns"] = ",".join(id_columns)
 
         df, fintech_warnings = remove_fintech_duplicates(
             df, self.fit_search_keys, date_format=self.date_format, logger=self.logger, bundle=self.bundle
@@ -2780,6 +2785,7 @@ class FeaturesEnricher(TransformerMixin):
             unnest_search_keys=unnest_search_keys,
             model_task_type=self.model_task_type,
             cv_type=self.cv,
+            id_columns=self.id_columns,
             date_format=self.date_format,
             random_state=self.random_state,
             rest_client=self.rest_client,

upgini/utils/target_utils.py

@@ -295,6 +295,8 @@ def balance_undersample_time_series(
 
     random_state = np.random.RandomState(random_state)
 
+    if not id_columns:
+        id_columns = [date_column]
     ids_sort = df.groupby(id_columns)[date_column].aggregate(["max", "count"]).T.to_dict()
     ids_sort = {
         ensure_tuple(k): (

{upgini-1.2.38a3769.dev3.dist-info → upgini-1.2.38a3769.dev5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.38a3769.dev3
+Version: 1.2.38a3769.dev5
 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-1.2.38a3769.dev3.dist-info → upgini-1.2.38a3769.dev5.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=sQ7NNr0lfG3UfxCnX2sMNRntUVR0zW-NHhIgizLV7ls,33
+upgini/__about__.py,sha256=bj9nQpQPQBgyZ975N_D4PWwEYJJKbsfpt1gs-e4tMio,33
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=zYPSQ73ch6k5EWxZlh1KrjL0gMkmAwl7Nkgrz6zxywY,33161
+upgini/dataset.py,sha256=-3FeDMADnHxGb70rKFY_U96NCQO-TEUAXFicFl25CtY,33222
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=m7z3iWSEj0ORUVnp65I0b_427SITjNnBvn8hdebS_xE,195541
+upgini/features_enricher.py,sha256=usNAM9eNFa19OeyPuMaaCp_4HMLeuYrkG4gBU6MwANg,196014
 upgini/http.py,sha256=plZGTGoi1h2edd8Cnjt4eYB8t4NbBGnZz7DtPTByiNc,42885
 upgini/lazy_import.py,sha256=74gQ8JuA48BGRLxAo7lNHNKY2D2emMxrUxKGdxVGhuY,1012
 upgini/metadata.py,sha256=-ibqiNjD7dTagqg53FoEJNEqvAYbwgfyn9PGTRQ_YKU,12054
@@ -56,10 +56,10 @@ upgini/utils/phone_utils.py,sha256=IrbztLuOJBiePqqxllfABWfYlfAjYevPhXKipl95wUI,1
 upgini/utils/postal_code_utils.py,sha256=5M0sUqH2DAr33kARWCTXR-ACyzWbjDq_-0mmEml6ZcU,1716
 upgini/utils/progress_bar.py,sha256=N-Sfdah2Hg8lXP_fV9EfUTXz_PyRt4lo9fAHoUDOoLc,1550
 upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,44511
-upgini/utils/target_utils.py,sha256=i_EsluRZG3LKrqv9NmhvEha9Uwp8JQjRUmokeo240Is,14283
+upgini/utils/target_utils.py,sha256=RlpKGss9kMibVSlA8iZuO_qxmyeplqzn7X8g6hiGGGs,14341
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.38a3769.dev3.dist-info/METADATA,sha256=AeaVPfRIc-RCuzozwXSgurTpHXE21yR_tpsBjCra3KA,48604
-upgini-1.2.38a3769.dev3.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.2.38a3769.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.38a3769.dev3.dist-info/RECORD,,
+upgini-1.2.38a3769.dev5.dist-info/METADATA,sha256=ldrVhkIorzNJE1GYHBfBQkXGi8upTruz5sa9s-DTld4,48604
+upgini-1.2.38a3769.dev5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.2.38a3769.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.38a3769.dev5.dist-info/RECORD,,