upgini 1.1.288a0__tar.gz → 1.1.290__tar.gz

{upgini-1.1.288a0 → upgini-1.1.290}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.288a0
+Version: 1.1.290
 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-1.1.290/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.290"

{upgini-1.1.288a0 → upgini-1.1.290}/src/upgini/autofe/date.py

@@ -21,6 +21,20 @@ 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"
@@ -41,7 +55,8 @@ 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)
-        return self.__replace_negative((left - right) / np.timedelta64(1, self.diff_unit))
+        diff = self._convert_diff_to_unit(left.dt.date - right.dt.date)
+        return self.__replace_negative(diff)
 
     def __replace_negative(self, x: Union[pd.DataFrame, pd.Series]):
         x[x < 0] = None
@@ -107,12 +122,7 @@ class DateListDiff(PandasOperand, DateDiffMixin):
         return pd.Series(left - right.values).apply(lambda x: self._agg(self._diff(x)))
 
     def _diff(self, x: TimedeltaArray):
-        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)
+        x = self._convert_diff_to_unit(x)
         return x[x > 0]
 
     def _agg(self, x):

{upgini-1.1.288a0 → upgini-1.1.290}/src/upgini/utils/datetime_utils.py

@@ -82,19 +82,19 @@ class DateTimeSearchKeyConverter:
         elif isinstance(df[self.date_column].values[0], datetime.date):
             df[self.date_column] = pd.to_datetime(df[self.date_column], errors="coerce")
         elif is_period_dtype(df[self.date_column]):
-            df[self.date_column] = pd.to_datetime(df[self.date_column].astype("string"))
+            df[self.date_column] = df[self.date_column].dt.to_timestamp()
         elif is_numeric_dtype(df[self.date_column]):
             # 315532801 - 2524608001    - seconds
             # 315532801000 - 2524608001000 - milliseconds
             # 315532801000000 - 2524608001000000 - microseconds
             # 315532801000000000 - 2524608001000000000 - nanoseconds
-            if df[self.date_column].apply(lambda x: 10**16 < x).all():
+            if df[self.date_column].apply(lambda x: 10 ** 16 < x).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="ns")
-            elif df[self.date_column].apply(lambda x: 10**14 < x < 10**16).all():
+            elif df[self.date_column].apply(lambda x: 10 ** 14 < x < 10 ** 16).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="us")
-            elif df[self.date_column].apply(lambda x: 10**11 < x < 10**14).all():
+            elif df[self.date_column].apply(lambda x: 10 ** 11 < x < 10 ** 14).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="ms")
-            elif df[self.date_column].apply(lambda x: 0 < x < 10 * 11).all():
+            elif df[self.date_column].apply(lambda x: 0 < x < 10 ** 11).all():
                 df[self.date_column] = pd.to_datetime(df[self.date_column], unit="s")
             else:
                 msg = self.bundle.get("unsupported_date_type").format(self.date_column)
@@ -185,7 +185,10 @@ def is_time_series(df: pd.DataFrame, date_col: str) -> bool:
 def is_blocked_time_series(df: pd.DataFrame, date_col: str, search_keys: List[str]) -> bool:
     df = df.copy()
     seconds = "datetime_seconds"
-    df[date_col] = pd.to_datetime(df[date_col])
+    if is_period_dtype(df[date_col]):
+        df[date_col] = df[date_col].dt.to_timestamp()
+    else:
+        df[date_col] = pd.to_datetime(df[date_col])
     df[date_col] = df[date_col].dt.tz_localize(None)
     df[seconds] = (df[date_col] - df[date_col].dt.floor("D")).dt.seconds
 
@@ -248,7 +251,9 @@ def validate_dates_distribution(
             if col in search_keys:
                 continue
             try:
-                if pd.__version__ >= "2.0.0":
+                if is_period_dtype(X[col]):
+                    pass
+                elif pd.__version__ >= "2.0.0":
                     # Format mixed to avoid massive warnings
                     pd.to_datetime(X[col], format="mixed")
                 else:
@@ -261,7 +266,9 @@ def validate_dates_distribution(
     if maybe_date_col is None:
         return
 
-    if pd.__version__ >= "2.0.0":
+    if is_period_dtype(X[maybe_date_col]):
+        dates = X[maybe_date_col].dt.to_timestamp().dt.date
+    elif pd.__version__ >= "2.0.0":
         dates = pd.to_datetime(X[maybe_date_col], format="mixed").dt.date
     else:
         dates = pd.to_datetime(X[maybe_date_col]).dt.date

upgini-1.1.288a0/src/upgini/__about__.py

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