upgini 1.1.290__tar.gz → 1.1.291__tar.gz

{upgini-1.1.290 → upgini-1.1.291}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.290
+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-1.1.290 → 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, 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] = {
@@ -50,6 +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(),
+        Norm(),
     ]
 }
 

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

@@ -1,5 +1,6 @@
 import numpy as np
 import pandas as pd
+from sklearn.preprocessing import Normalizer
 
 from upgini.autofe.operand import PandasOperand, VectorizableMixin
 
@@ -111,3 +112,16 @@ 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 Norm(PandasOperand):
+    name = "norm"
+    is_unary = True
+    output_type = "float"
+
+    def calculate_unary(self, data: pd.Series) -> pd.Series:
+        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-1.1.290/src/upgini/__about__.py

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