upgini 1.1.296a3511.dev3__tar.gz → 1.1.296a3511.dev5__tar.gz

{upgini-1.1.296a3511.dev3 → upgini-1.1.296a3511.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.296a3511.dev3
+Version: 1.1.296a3511.dev5
 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-1.1.296a3511.dev5/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.296a3511.dev5"

{upgini-1.1.296a3511.dev3 → upgini-1.1.296a3511.dev5}/src/upgini/autofe/binary.py

@@ -142,9 +142,16 @@ class Distance(PandasOperand):
     has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
-        return dot(left, right) / (norm(left) * norm(right))
+        return pd.Series(
+            1 - self.__dot(left, right) / (self.__dot(left, left) * self.__dot(right, right)), index=left.index
+        )
 
+    # row-wise dot product
+    def __dot(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        return (left * right).apply(np.sum)
 
+
+# Left for backward compatibility
 class Sim(Distance):
     name = "sim"
     is_binary = True
@@ -152,6 +159,9 @@ class Sim(Distance):
     is_symmetrical = True
     has_symmetry_importance = True
 
+    def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
+        return 1 - super().calculate_binary(left, right)
+
 
 class StringSim(PandasOperand, abc.ABC):
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:

{upgini-1.1.296a3511.dev3 → upgini-1.1.296a3511.dev5}/src/upgini/autofe/date.py

@@ -41,6 +41,8 @@ class DateDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
 
+    replace_negative: bool = False
+
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
@@ -48,6 +50,7 @@ class DateDiff(PandasOperand, DateDiffMixin):
                 "diff_unit": self.diff_unit,
                 "left_unit": self.left_unit,
                 "right_unit": self.right_unit,
+                "replace_negative": self.replace_negative,
             }
         )
         return res
@@ -59,7 +62,8 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return self.__replace_negative(diff)
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
-        x[x < 0] = None
+        if self.replace_negative:
+            x[x < 0] = None
         return x
 
 
@@ -99,13 +103,19 @@ _ext_aggregations = {"nunique": (lambda x: len(np.unique(x)), 0), "count": (len,
 class DateListDiff(PandasOperand, DateDiffMixin):
     is_binary = True
     has_symmetry_importance = True
+
     aggregation: str
+    replace_negative: bool = False
 
     def get_params(self) -> Dict[str, Optional[str]]:
         res = super().get_params()
         res.update(
             {
                 "aggregation": self.aggregation,
+                "diff_unit": self.diff_unit,
+                "left_unit": self.left_unit,
+                "right_unit": self.right_unit,
+                "replace_negative": self.replace_negative,
             }
         )
         return res
@@ -123,7 +133,7 @@ class DateListDiff(PandasOperand, DateDiffMixin):
 
     def _diff(self, x: TimedeltaArray):
         x = self._convert_diff_to_unit(x)
-        return x[x > 0]
+        return x[x > 0] if self.replace_negative else x
 
     def _agg(self, x):
         method = getattr(np, self.aggregation, None)

{upgini-1.1.296a3511.dev3 → upgini-1.1.296a3511.dev5}/src/upgini/autofe/feature.py

@@ -125,18 +125,22 @@ class Feature:
         for child in self.children:
             child.delete_data()
 
+    def get_op_display_name(self) -> str:
+        return self.op.alias or self.op.name.lower()
+
     def get_display_name(self, cache: bool = True, shorten: bool = False, **kwargs) -> str:
         if self.cached_display_name is not None and cache:
             return self.cached_display_name
 
         if self.alias:
             components = ["f_autofe", self.alias]
-        elif shorten and not self.op.is_unary:
-            components = ["f_autofe", self.op.alias or self.op.name.lower()]
+        elif shorten and not (self.op.is_unary and all(isinstance(c, Column) for c in self.children)):
+            prev_name = [self.children[0].get_op_display_name()] if self.op.is_unary else []
+            components = ["f_autofe"] + prev_name + [self.get_op_display_name()]
         else:
             components = ["f_" + "_f_".join(self.get_columns(**kwargs))] + [
                 "autofe",
-                self.op.alias or self.op.name.lower(),
+                self.get_op_display_name(),
             ]
         components.extend([str(self.display_index)] if self.display_index is not None else [])
         display_name = "_".join(components)

upgini-1.1.296a3511.dev3/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.296a3511.dev3"