upgini 1.1.289__tar.gz → 1.1.290a3232.post1__tar.gz

{upgini-1.1.289 → upgini-1.1.290a3232.post1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.1.289
+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-1.1.289 → 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-1.1.289 → 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-1.1.289/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.1.289"