upgini 1.1.290a3232.post1__tar.gz → 1.1.291__tar.gz

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.290a3232.post1
+Version: 1.1.291
 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-1.1.291/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.1.291"

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/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, Scale, Sigmoid, Sqrt, Square
+from upgini.autofe.unary import Abs, Floor, Freq, Log, Residual, Norm, Sigmoid, Sqrt, Square
 from upgini.autofe.vector import Mean, Sum
 
 ALL_OPERANDS: Dict[str, Operand] = {
@@ -50,7 +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(),
+        Norm(),
     ]
 }
 

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/src/upgini/autofe/binary.py

@@ -9,6 +9,7 @@ from upgini.autofe.operand import PandasOperand, VectorizableMixin
 class Min(PandasOperand):
     name = "min"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
@@ -18,6 +19,7 @@ class Min(PandasOperand):
 class Max(PandasOperand):
     name = "max"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
@@ -28,6 +30,7 @@ class Add(PandasOperand, VectorizableMixin):
     name = "+"
     alias = "add"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
     is_vectorizable = True
 
@@ -46,6 +49,7 @@ class Subtract(PandasOperand, VectorizableMixin):
     name = "-"
     alias = "sub"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
     is_vectorizable = True
 
@@ -64,6 +68,7 @@ class Multiply(PandasOperand, VectorizableMixin):
     name = "*"
     alias = "mul"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
     is_vectorizable = True
 
@@ -112,6 +117,7 @@ class Combine(PandasOperand):
 class CombineThenFreq(PandasOperand):
     name = "CombineThenFreq"
     is_binary = True
+    is_symmetrical = True
     has_symmetry_importance = True
     output_type = "float"
     is_distribution_dependent = True
@@ -128,6 +134,7 @@ class Sim(PandasOperand):
     name = "sim"
     is_binary = True
     output_type = "float"
+    is_symmetrical = True
     has_symmetry_importance = True
 
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/src/upgini/autofe/operand.py

@@ -10,6 +10,7 @@ class Operand(BaseModel):
     name: str
     alias: Optional[str]
     is_unary: bool = False
+    is_symmetrical: bool = False
     has_symmetry_importance: bool = False
     input_type: Optional[str]
     output_type: Optional[str]

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/src/upgini/autofe/unary.py

@@ -1,6 +1,6 @@
 import numpy as np
 import pandas as pd
-from sklearn.preprocessing import robust_scale
+from sklearn.preprocessing import Normalizer
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -114,13 +114,14 @@ class Freq(PandasOperand):
         return self._loc(data, value_counts)
 
 
-class Scale(PandasOperand, VectorizableMixin):
-    name = "scale"
+class Norm(PandasOperand):
+    name = "norm"
     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)
+        data_dropna = data.dropna()
+        normalized_data = Normalizer().transform(data_dropna.to_frame().T).T
+        normalized_data = pd.Series(normalized_data[:, 0], index=data_dropna.index, name=data.name)
+        normalized_data = normalized_data.reindex(data.index)
+        return normalized_data

{upgini-1.1.290a3232.post1 → upgini-1.1.291}/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-1.1.290a3232.post1/src/upgini/__about__.py

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