upgini 1.1.296a3511.dev3__py3-none-any.whl → 1.1.296a3511.dev5__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.296a3511.dev3"
+__version__ = "1.1.296a3511.dev5"

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/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/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.dist-info → upgini-1.1.296a3511.dev5.dist-info}/METADATA

@@ -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.dev3.dist-info → upgini-1.1.296a3511.dev5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=nhz--_RS8bpHuO6PuBYTUOkBsgiEqDb48jHNox8NFQs,34
+upgini/__about__.py,sha256=SpaPMjgutjbwO95CH0W9s1DzcXLs8b1RAjY6md0F7Bg,34
 upgini/__init__.py,sha256=ObEtjFkIssl83qeKNMLpIQygfwK8TzztwiI43YTsAP0,353
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -15,9 +15,9 @@ upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9Jvf
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/autofe/all_operands.py,sha256=-6gzp6nWBfzKmRRSvyMYUkubH7IwxL3Lrh9wVD85Baw,2457
-upgini/autofe/binary.py,sha256=P46AVcFRiMKYucK3_N34QDqVMbvv2OuyWAREx0bUNwg,6367
-upgini/autofe/date.py,sha256=qzk0NT332Q0vR1eRwTuNiMSrGE3ulh6Ic3QLBZqSdvw,7284
-upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
+upgini/autofe/binary.py,sha256=ml0MszLARZqp3UGUqTGsVjT4DD69zTisfBBEqbZ7klU,6767
+upgini/autofe/date.py,sha256=gW0UJ_5ykYPNNnwc3cr_FCzO6BTvWLCtHxl8ij33VKg,7681
+upgini/autofe/feature.py,sha256=OWwIiwB948WxSl6GsLob9Hg8ky_93WMQPMgrIC7UsAA,12725
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
 upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
 upgini/autofe/unary.py,sha256=B4wp8oKnlJ0nUng-DRMKSiF8MHlhAFYbgmo9Nd_0ZaA,3777
@@ -57,7 +57,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.296a3511.dev3.dist-info/METADATA,sha256=lOgBTI4frfiOsOD0vRVe84jDdatQw4PnaWncRFg2ZGg,48196
-upgini-1.1.296a3511.dev3.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.296a3511.dev3.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.296a3511.dev3.dist-info/RECORD,,
+upgini-1.1.296a3511.dev5.dist-info/METADATA,sha256=TEsOBiJlv9g1OXW20nKF-8-x9cdomuKZT1IpgC9tEp8,48196
+upgini-1.1.296a3511.dev5.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.296a3511.dev5.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.296a3511.dev5.dist-info/RECORD,,