upgini 1.1.288__tar.gz → 1.1.288a0__tar.gz

{upgini-1.1.288 → upgini-1.1.288a0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.288
+Version: 1.1.288a0
 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-1.1.288a0/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.288a0"

{upgini-1.1.288 → upgini-1.1.288a0}/src/upgini/autofe/date.py

@@ -21,20 +21,6 @@ class DateDiffMixin(BaseModel):
 
         return pd.to_datetime(x, unit=unit)
 
-    def _convert_diff_to_unit(self, diff: Union[pd.Series, TimedeltaArray]) -> Union[pd.Series, TimedeltaArray]:
-        if self.diff_unit == "D":
-            if isinstance(diff, pd.Series) and diff.dtype == "object":
-                return diff.apply(lambda x: None if isinstance(x, float) and np.isnan(x) else x.days)
-            else:
-                return diff / np.timedelta64(1, self.diff_unit)
-        elif self.diff_unit == "Y":
-            if isinstance(diff, TimedeltaArray):
-                return (diff / 365 / 24 / 60 / 60 / 10**9).astype(int)
-            else:
-                return (diff / 365 / 24 / 60 / 60 / 10**9).dt.nanoseconds
-        else:
-            raise Exception(f"Unsupported difference unit: {self.diff_unit}")
-
 
 class DateDiff(PandasOperand, DateDiffMixin):
     name = "date_diff"
@@ -55,8 +41,7 @@ class DateDiff(PandasOperand, DateDiffMixin):
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         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)
-        return self.__replace_negative(diff)
+        return self.__replace_negative((left - right) / np.timedelta64(1, self.diff_unit))
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
         x[x < 0] = None
@@ -122,7 +107,12 @@ class DateListDiff(PandasOperand, DateDiffMixin):
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
     def _diff(self, x: TimedeltaArray):
-        x = self._convert_diff_to_unit(x)
+        if self.diff_unit == "Y":
+            x = (x / 365 / 24 / 60 / 60 / 10**9).astype(int)
+        elif self.diff_unit == "M":
+            raise Exception("Unsupported difference unit: Month")
+        else:
+            x = x / np.timedelta64(1, self.diff_unit)
         return x[x > 0]
 
     def _agg(self, x):

{upgini-1.1.288 → upgini-1.1.288a0}/src/upgini/utils/sklearn_ext.py

@@ -320,7 +320,7 @@ def cross_validate(
                 shuffle = cv.shuffle
             else:
                 shuffle = False
-            if hasattr(cv, "random_state"):
+            if hasattr(cv, "random_state") and shuffle:
                 random_state = cv.random_state
             else:
                 random_state = None

upgini-1.1.288/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.288"