upgini 1.2.38a3769.dev2__tar.gz → 1.2.38a3769.dev4__tar.gz

{upgini-1.2.38a3769.dev2 → upgini-1.2.38a3769.dev4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.38a3769.dev2
+Version: 1.2.38a3769.dev4
 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.dev4/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.38a3769.dev4"

{upgini-1.2.38a3769.dev2 → upgini-1.2.38a3769.dev4}/src/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 if c not in search_keys_for_metrics])
 
                 prepared_data = self._prepare_data_for_metrics(
                     trace_id=trace_id,
@@ -2656,7 +2657,10 @@ 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

{upgini-1.2.38a3769.dev2 → upgini-1.2.38a3769.dev4}/src/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): (
@@ -306,7 +308,7 @@ def balance_undersample_time_series(
     id_counts.index = [ensure_tuple(i) for i in id_counts.index]
     id_counts = id_counts.sort_index(key=lambda x: [ids_sort[y] for y in x], ascending=False).cumsum()
     id_counts = id_counts[id_counts <= sample_size]
-    min_different_ids = int(len(df[id_columns].drop_duplicates()) * min_different_ids_ratio)
+    min_different_ids = max(int(len(df[id_columns].drop_duplicates()) * min_different_ids_ratio), 1)
 
     def id_mask(sample_index: pd.Index) -> pd.Index:
         if isinstance(sample_index, pd.MultiIndex):
@@ -317,10 +319,10 @@ def balance_undersample_time_series(
     if len(id_counts) < min_different_ids:
         if logger is not None:
             logger.info(
-                f"Different ids count {len(id_counts)} is less than min different ids {min_different_ids}, sampling time window"
+                f"Different ids count {len(id_counts)} for sample size {sample_size} is less than min different ids {min_different_ids}, sampling time window"
             )
         date_counts = df.groupby(id_columns)[date_column].nunique().sort_values(ascending=False)
-        ids_to_sample = date_counts.index[:min_different_ids]
+        ids_to_sample = date_counts.index[:min_different_ids] if len(id_counts) > 0 else date_counts.index
         mask = id_mask(ids_to_sample)
         df = df[mask]
         sample_date_counts = df[date_column].value_counts().sort_index(ascending=False).cumsum()

upgini-1.2.38a3769.dev2/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.38a3769.dev2"