upgini 1.2.14a3616.dev2__tar.gz → 1.2.14a3616.dev3__tar.gz

{upgini-1.2.14a3616.dev2 → upgini-1.2.14a3616.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.14a3616.dev2
+Version: 1.2.14a3616.dev3
 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-1.2.14a3616.dev3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.14a3616.dev3"

{upgini-1.2.14a3616.dev2 → upgini-1.2.14a3616.dev3}/src/upgini/features_enricher.py

@@ -2449,8 +2449,6 @@ class FeaturesEnricher(TransformerMixin):
         if is_numeric_dtype(df[self.TARGET_NAME]) and has_date:
             self._validate_PSI(df.sort_values(by=maybe_date_column))
 
-        self.__adjust_cv(df, maybe_date_column, self.model_task_type)
-
         normalizer = Normalizer(
             self.fit_search_keys, self.fit_generated_features, self.bundle, self.logger, self.warning_counter
         )
@@ -2458,6 +2456,10 @@ class FeaturesEnricher(TransformerMixin):
         columns_renaming = normalizer.columns_renaming
         self.fit_columns_renaming = columns_renaming
 
+        self.__adjust_cv(
+            df, normalizer.search_keys, self.model_task_type
+        )
+
         df = remove_fintech_duplicates(
             df, self.fit_search_keys, date_format=self.date_format, logger=self.logger, bundle=self.bundle
         )
@@ -2710,21 +2712,22 @@ class FeaturesEnricher(TransformerMixin):
         if not self.warning_counter.has_warnings():
             self.__display_support_link(self.bundle.get("all_ok_community_invite"))
 
-    def __adjust_cv(self, df: pd.DataFrame, date_column: pd.Series, model_task_type: ModelTaskType):
+    def __adjust_cv(self, df: pd.DataFrame, search_keys: Dict[str, SearchKey], model_task_type: ModelTaskType):
+        date_column = SearchKey.find_key(search_keys, [SearchKey.DATE, SearchKey.DATETIME])
         # Check Multivariate time series
         if (
             self.cv is None
             and date_column
             and model_task_type == ModelTaskType.REGRESSION
-            and len({SearchKey.PHONE, SearchKey.EMAIL, SearchKey.HEM}.intersection(self.fit_search_keys.keys())) == 0
-            and is_blocked_time_series(df, date_column, list(self.fit_search_keys.keys()) + [TARGET])
+            and len({SearchKey.PHONE, SearchKey.EMAIL, SearchKey.HEM}.intersection(search_keys.keys())) == 0
+            and is_blocked_time_series(df, date_column, list(search_keys.keys()) + [TARGET])
         ):
             msg = self.bundle.get("multivariate_timeseries_detected")
             self.__override_cv(CVType.blocked_time_series, msg, print_warning=False)
         elif self.cv is None and model_task_type != ModelTaskType.REGRESSION:
             msg = self.bundle.get("group_k_fold_in_classification")
             self.__override_cv(CVType.group_k_fold, msg, print_warning=self.cv is not None)
-            group_columns = self._get_group_columns(df, self.fit_search_keys)
+            group_columns = self._get_group_columns(df, search_keys)
             self.runtime_parameters.properties["cv_params.group_columns"] = ",".join(group_columns)
             self.runtime_parameters.properties["cv_params.shuffle_kfold"] = "True"
 

upgini-1.2.14a3616.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.14a3616.dev2"