upgini 1.2.113a5__py3-none-any.whl → 1.2.113a6__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.2.113a5"
+__version__ = "1.2.113a6"

upgini/dataset.py

@@ -343,7 +343,9 @@ class Dataset:
             if col in mandatory_columns:
                 self.data["valid_mandatory"] = self.data["valid_mandatory"] & self.data[f"{col}_is_valid"]
 
-            invalid_values = list(set(self.data.loc[self.data[f"{col}_is_valid"] == 0, col].head().values))
+            # Use stable pandas API across versions: Series.unique keeps order
+            # and collapses multiple NaNs into a single NaN
+            invalid_values = self.data.loc[self.data[f"{col}_is_valid"] == 0, col].unique().tolist()[:5]
             valid_share = self.data[f"{col}_is_valid"].sum() / nrows
             original_col_name = self.columns_renaming[col]
             validation_stats[original_col_name] = {}

upgini/features_enricher.py

@@ -1012,15 +1012,11 @@ class FeaturesEnricher(TransformerMixin):
                 if self.id_columns and self.id_columns_encoder is not None:
                     if cat_features_from_backend:
                         cat_features_from_backend = [
-                            c
-                            for c in cat_features_from_backend
-                            if c not in self.id_columns_encoder.feature_names_in_
+                            c for c in cat_features_from_backend if c not in self.id_columns_encoder.feature_names_in_
                         ]
                     if client_cat_features:
                         client_cat_features = [
-                            c
-                            for c in client_cat_features
-                            if c not in self.id_columns_encoder.feature_names_in_
+                            c for c in client_cat_features if c not in self.id_columns_encoder.feature_names_in_
                         ]
                 for cat_feature in cat_features_from_backend:
                     if cat_feature in self.search_keys:
@@ -1384,15 +1380,11 @@ class FeaturesEnricher(TransformerMixin):
         if self.id_columns and self.id_columns_encoder is not None:
             if cat_features_from_backend:
                 cat_features_from_backend = [
-                    c
-                    for c in cat_features_from_backend
-                    if c not in self.id_columns_encoder.feature_names_in_
+                    c for c in cat_features_from_backend if c not in self.id_columns_encoder.feature_names_in_
                 ]
             if client_cat_features:
                 client_cat_features = [
-                    c
-                    for c in client_cat_features
-                    if c not in self.id_columns_encoder.feature_names_in_
+                    c for c in client_cat_features if c not in self.id_columns_encoder.feature_names_in_
                 ]
 
         prepared_data = self._prepare_data_for_metrics(
@@ -1829,7 +1821,8 @@ class FeaturesEnricher(TransformerMixin):
                 or c in set(self.feature_names_).union(self.id_columns or [])
                 or (self.fit_columns_renaming or {}).get(c, c) in set(self.feature_names_).union(self.id_columns or [])
             )
-            and c not in (
+            and c
+            not in (
                 excluding_search_keys
                 + list(self.fit_dropped_features)
                 + [DateTimeSearchKeyConverter.DATETIME_COL, SYSTEM_RECORD_ID, ENTITY_SYSTEM_RECORD_ID]
@@ -3220,7 +3213,15 @@ if response.status_code == 200:
         self.fit_generated_features = [f for f in self.fit_generated_features if f not in self.fit_dropped_features]
 
         # Group columns should have normalized names
-        self.__adjust_cv(df, force=True)
+        if self.runtime_parameters.properties.get("cv_params.group_columns") is not None:
+            original_to_hash = {v: k for k, v in self.fit_columns_renaming.items()}
+            self.runtime_parameters.properties["cv_params.group_columns"] = ",".join(
+                [
+                    original_to_hash.get(c, c)
+                    for c in self.runtime_parameters.properties["cv_params.group_columns"].split(",")
+                ]
+            )
+
         if self.id_columns is not None and self.cv is not None and self.cv.is_time_series():
             id_columns = self.__get_renamed_id_columns()
             if id_columns:
@@ -3525,23 +3526,24 @@ if response.status_code == 200:
         reverse_renaming = {v: k for k, v in renaming.items()}
         return None if self.id_columns is None else [reverse_renaming.get(c) or c for c in self.id_columns]
 
-    def __adjust_cv(self, df: pd.DataFrame, force: bool = False):
-        if self.cv is not None and not force:
-            return
+    def __adjust_cv(self, df: pd.DataFrame):
+        if self.cv is None:
+            date_column = SearchKey.find_key(self.fit_search_keys, [SearchKey.DATE, SearchKey.DATETIME])
+            # Check Multivariate time series
+            if (
+                date_column
+                and self.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])
+            ):
+                msg = self.bundle.get("multivariate_timeseries_detected")
+                self.__override_cv(CVType.blocked_time_series, msg, print_warning=False)
+            elif self.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)
 
-        date_column = SearchKey.find_key(self.fit_search_keys, [SearchKey.DATE, SearchKey.DATETIME])
-        # Check Multivariate time series
-        if (
-            date_column
-            and self.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])
-        ):
-            msg = self.bundle.get("multivariate_timeseries_detected")
-            self.__override_cv(CVType.blocked_time_series, msg, print_warning=False)
-        elif self.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)
+        if self.cv == CVType.group_k_fold:
             group_columns = self._get_group_columns(df, self.fit_search_keys)
             self.runtime_parameters.properties["cv_params.group_columns"] = ",".join(group_columns)
             self.runtime_parameters.properties["cv_params.shuffle_kfold"] = "True"

{upgini-1.2.113a5.dist-info → upgini-1.2.113a6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.113a5
+Version: 1.2.113a6
 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-1.2.113a5.dist-info → upgini-1.2.113a6.dist-info}/RECORD

@@ -1,9 +1,9 @@
-upgini/__about__.py,sha256=QdA0r4M8wEBY37BMjK9uA_83s1sWkyXy2XJhfn7vl3A,26
+upgini/__about__.py,sha256=hA793gAu-mC2Lw0M27RABL7IKbRk6aGmyLjnqBIPNOc,26
 upgini/__init__.py,sha256=LXSfTNU0HnlOkE69VCxkgIKDhWP-JFo_eBQ71OxTr5Y,261
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
-upgini/dataset.py,sha256=xFi0a-A3uvtxVwFM6JOyitkEPd1I2slIBj5SWfys3hQ,32724
+upgini/dataset.py,sha256=TU_Kk574JCNlx_PaeDu1HN1qwi5IzlwkkAbUqU_M_QM,32860
 upgini/errors.py,sha256=2b_Wbo0OYhLUbrZqdLIx5jBnAsiD1Mcenh-VjR4HCTw,950
-upgini/features_enricher.py,sha256=wifdmDP-3e3y51KYhCHPYuN6vU8mj2m3SYo-kMWcNz0,234523
+upgini/features_enricher.py,sha256=liJcrINi_NvPLHJqELYqF9Gcga2PA3l4UYvD3ieBkB8,234815
 upgini/http.py,sha256=zeAZvT6IAzOs9jQ3WG8mJBANLajgvv2LZePFzKz004w,45482
 upgini/metadata.py,sha256=sx4X9fPkyCgXB6FPk9Rq_S1Kx8ibkbaWA-qNDVCuSmg,12811
 upgini/metrics.py,sha256=O19UqmgZ6SA136eCYV5lVU3J26ecgZlGXnxGblMvZJc,45869
@@ -72,7 +72,7 @@ upgini/utils/target_utils.py,sha256=i3Xt5l9ybB2_nF_ma5cfPuL3OeFTs2dY2xDI0p4Azpg,
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/ts_utils.py,sha256=26vhC0pN7vLXK6R09EEkMK3Lwb9IVPH7LRdqFIQ3kPs,1383
 upgini/utils/warning_counter.py,sha256=-GRY8EUggEBKODPSuXAkHn9KnEQwAORC0mmz_tim-PM,254
-upgini-1.2.113a5.dist-info/METADATA,sha256=VOeoK4hhJyhb0OJWG2cgsN-hES6xe3QIRyZMovxP8ek,49531
-upgini-1.2.113a5.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
-upgini-1.2.113a5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.2.113a5.dist-info/RECORD,,
+upgini-1.2.113a6.dist-info/METADATA,sha256=xMMMKyiR7qAg6VHYaxUnshC75w7h3REvo0NGYIEWwJM,49531
+upgini-1.2.113a6.dist-info/WHEEL,sha256=1yFddiXMmvYK7QYTqtRNtX66WJ0Mz8PYEiEUoOUUxRY,87
+upgini-1.2.113a6.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.2.113a6.dist-info/RECORD,,