upgini 1.1.290__tar.gz → 1.1.290a3232.post1__tar.gz

{upgini-1.1.290 → upgini-1.1.290a3232.post1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.290
+Version: 1.1.290a3232.post1
 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-1.1.290a3232.post1/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.290a3232-1"

{upgini-1.1.290 → upgini-1.1.290a3232.post1}/src/upgini/autofe/all_operands.py

@@ -4,7 +4,7 @@ from upgini.autofe.binary import Add, Divide, Max, Min, Multiply, Sim, Subtract
 from upgini.autofe.date import DateDiff, DateDiffType2, DateListDiff, DateListDiffBounded, DatePercentile
 from upgini.autofe.groupby import GroupByThenAgg, GroupByThenRank
 from upgini.autofe.operand import Operand
-from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Scale, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -50,6 +50,7 @@ ALL_OPERANDS: Dict[str, Operand] = {
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=45, upper_bound=60),
         DateListDiffBounded(diff_unit="Y", aggregation="count", lower_bound=60),
         DatePercentile(),
+        Scale(),
     ]
 }
 

{upgini-1.1.290 → upgini-1.1.290a3232.post1}/src/upgini/autofe/unary.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+from sklearn.preprocessing import robust_scale
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -111,3 +112,15 @@ class Freq(PandasOperand):
     def calculate_unary(self, data: pd.Series) -> pd.Series:
         value_counts = data.value_counts(normalize=True)
         return self._loc(data, value_counts)
+
+
+class Scale(PandasOperand, VectorizableMixin):
+    name = "scale"
+    is_unary = True
+    output_type = "float"
+
+    def calculate_unary(self, data: pd.Series) -> pd.Series:
+        return pd.Series(robust_scale(data), index=data.index, name=data.name)
+
+    def calculate_group(self, data: pd.DataFrame, **kwargs) -> pd.DataFrame:
+        return pd.DataFrame(robust_scale(data), index=data.index, columns=data.columns)

{upgini-1.1.290 → upgini-1.1.290a3232.post1}/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] = df[self.date_column].dt.to_timestamp()
+            df[self.date_column] = pd.to_datetime(df[self.date_column].astype("string"))
         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)
@@ -185,10 +185,7 @@ 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"
-    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] = 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
 
@@ -251,9 +248,7 @@ def validate_dates_distribution(
             if col in search_keys:
                 continue
             try:
-                if is_period_dtype(X[col]):
-                    pass
-                elif pd.__version__ >= "2.0.0":
+                if pd.__version__ >= "2.0.0":
                     # Format mixed to avoid massive warnings
                     pd.to_datetime(X[col], format="mixed")
                 else:
@@ -266,9 +261,7 @@ def validate_dates_distribution(
     if maybe_date_col is None:
         return
 
-    if is_period_dtype(X[maybe_date_col]):
-        dates = X[maybe_date_col].dt.to_timestamp().dt.date
-    elif pd.__version__ >= "2.0.0":
+    if 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-1.1.290/src/upgini/__about__.py

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