upgini 1.2.56a1__tar.gz → 1.2.56a3675.dev2__tar.gz

{upgini-1.2.56a1 → upgini-1.2.56a3675.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.56a1
+Version: 1.2.56a3675.dev2
 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-1.2.56a3675.dev2/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.56a3675.dev2"

{upgini-1.2.56a1 → upgini-1.2.56a3675.dev2}/src/upgini/autofe/date.py

@@ -64,6 +64,9 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return res
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        if left.isna().all() or right.isna().all():
+            return pd.Series([None] * len(left))
+
         left = self._convert_to_date(left, self.left_unit)
         right = self._convert_to_date(right, self.right_unit)
         diff = self._convert_diff_to_unit(left.dt.date - right.dt.date)
@@ -142,6 +145,9 @@ class DateListDiff(PandasOperand, DateDiffMixin, ParametrizedOperand):
         return cls(aggregation=aggregation)
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        if left.isna().all() or right.isna().all():
+            return pd.Series([None] * len(left), dtype=np.float64)
+
         left = self._convert_to_date(left, self.left_unit)
         right_mask = right.apply(lambda x: len(x) > 0)
         mask = left.notna() & right.notna() & right_mask
@@ -230,6 +236,8 @@ class DatePercentileBase(PandasOperand, abc.ABC):
         pass
 
     def _perc(self, f, bounds):
+        if f is None or np.isnan(f):
+            return np.nan
         hit = np.where(f >= np.array(bounds))[0]
         if hit.size > 0:
             return np.max(hit) + 1

{upgini-1.2.56a1 → upgini-1.2.56a3675.dev2}/src/upgini/autofe/feature.py

@@ -26,18 +26,9 @@ class Column:
         return dict()
 
     def rename_columns(self, mapping: Dict[str, str]) -> "Column":
-        self.name = self._unhash(mapping.get(self.name) or self.name)
+        self.name = mapping.get(self.name) or self.name
         return self
 
-    def _unhash(self, feature_name: str) -> str:
-        last_component_idx = feature_name.rfind("_")
-        if not feature_name.startswith("f_"):
-            return feature_name  # etalon feature
-        elif last_component_idx == 1:
-            return feature_name[2:]  # fully hashed name, cannot unhash
-        else:
-            return feature_name[2:last_component_idx]
-
     def delete_data(self):
         self.data = None
 

{upgini-1.2.56a1 → upgini-1.2.56a3675.dev2}/src/upgini/features_enricher.py

@@ -3733,7 +3733,7 @@ if response.status_code == 200:
         features_info_without_links = []
         internal_features_info = []
 
-        original_shaps = {original_names_dict.get(fm.name, fm.name): fm.shap_value for fm in features_meta}
+        original_shaps = {fm.name: fm.shap_value for fm in features_meta}
 
         if updated_shaps is not None:
             for fm in features_meta:

upgini-1.2.56a1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.56a1"