upgini 1.2.38a3769.dev1__tar.gz → 1.2.38a3769.dev3__tar.gz

{upgini-1.2.38a3769.dev1 → upgini-1.2.38a3769.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.38a3769.dev1
+Version: 1.2.38a3769.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-1.2.38a3769.dev3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.38a3769.dev3"

{upgini-1.2.38a3769.dev1 → upgini-1.2.38a3769.dev3}/src/upgini/dataset.py

@@ -312,6 +312,7 @@ class Dataset:  # (pd.DataFrame):
                         if v in [FileColumnMeaningType.DATE, FileColumnMeaningType.DATETIME]
                     ),
                     sample_size=sample_rows,
+                    random_state=self.random_state,
                     logger=self.logger,
                 )
             else:

{upgini-1.2.38a3769.dev1 → upgini-1.2.38a3769.dev3}/src/upgini/features_enricher.py

@@ -281,8 +281,6 @@ class FeaturesEnricher(TransformerMixin):
 
         self.search_keys = search_keys or {}
         self.id_columns = id_columns
-        if id_columns is not None:
-            self.search_keys.update({col: SearchKey.CUSTOM_KEY for col in id_columns})
         self.country_code = country_code
         self.__validate_search_keys(search_keys, search_id)
 
@@ -2657,6 +2655,9 @@ 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})
+
         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.dev1 → upgini-1.2.38a3769.dev3}/src/upgini/utils/target_utils.py

@@ -246,6 +246,7 @@ def balance_undersample_forced(
             id_columns=id_columns,
             date_column=date_column,
             sample_size=sample_size,
+            random_state=random_state,
             logger=logger,
         )
     elif task_type in [ModelTaskType.MULTICLASS, ModelTaskType.REGRESSION]:
@@ -284,19 +285,28 @@ def balance_undersample_time_series(
     id_columns: List[str],
     date_column: str,
     sample_size: int,
+    random_state: int = 42,
     min_different_ids_ratio: float = TS_MIN_DIFFERENT_IDS_RATIO,
+    prefer_recent_dates: bool = True,
     logger: Optional[logging.Logger] = None,
 ):
     def ensure_tuple(x):
         return tuple([x]) if not isinstance(x, tuple) else x
 
+    random_state = np.random.RandomState(random_state)
+
     ids_sort = df.groupby(id_columns)[date_column].aggregate(["max", "count"]).T.to_dict()
-    ids_sort = {ensure_tuple(k): (v["max"], v["count"]) for k, v in ids_sort.items()}
+    ids_sort = {
+        ensure_tuple(k): (
+            (v["max"], v["count"], random_state.rand()) if prefer_recent_dates else (v["count"], random_state.rand())
+        )
+        for k, v in ids_sort.items()
+    }
     id_counts = df[id_columns].value_counts()
     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):
@@ -307,10 +317,10 @@ 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.dev1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.38a3769.dev1"