upgini 1.1.290__py3-none-any.whl → 1.1.291__py3-none-any.whl

upgini/__about__.py

@@ -1 +1 @@
-__version__ = "1.1.290"
+__version__ = "1.1.291"

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/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/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/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.dist-info → upgini-1.1.291.dist-info}/METADATA

@@ -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-1.1.290.dist-info → upgini-1.1.291.dist-info}/RECORD

@@ -1,4 +1,4 @@
-upgini/__about__.py,sha256=14vdpqxzfW78z-avOfaHW_WatncVnDB1LrWtzjXSghM,24
+upgini/__about__.py,sha256=Y_w5IYxoaPcBsQIRm0fDAaxQvtgLtjb90RMIAJCUnbM,24
 upgini/__init__.py,sha256=asENHgEVHQBIkV-e_0IhE_ZWqkCG6398U3ZLrNzAH6k,407
 upgini/ads.py,sha256=nvuRxRx5MHDMgPr9SiU-fsqRdFaBv8p4_v1oqiysKpc,2714
 upgini/dataset.py,sha256=7TLVVhGtjgx_9yaiaIUK3kZSe_R9wg5dY0d4F5qCGM4,45636
@@ -13,13 +13,13 @@ upgini/version_validator.py,sha256=ddSKUK_-eGJB3NgrqOMoWJU-OxQ253WsNLp8aqJkaIM,1
 upgini/ads_management/__init__.py,sha256=qzyisOToVRP-tquAJD1PblZhNtMrOB8FiyF9JvfkvgE,50
 upgini/ads_management/ads_manager.py,sha256=igVbN2jz80Umb2BUJixmJVj-zx8unoKpecVo-R-nGdw,2648
 upgini/autofe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-upgini/autofe/all_operands.py,sha256=7UyvmmqGSqQu4kDgoFwQRKY__b9xKDk3Fpp2-H8A7AA,2399
-upgini/autofe/binary.py,sha256=441BRuqMsxlxuw4c8rMZB6h5EpRdVMk-bVa03U7T5Hg,3973
+upgini/autofe/all_operands.py,sha256=cpwUfhZWF9QBfrUyJ0xZ72iGYyt1eXIZQ46FB-7ZDI4,2421
+upgini/autofe/binary.py,sha256=8FXPJxN7fnC5wphO0Dp1tQCa0lFMSDGQGvBMkSIVAcE,4155
 upgini/autofe/date.py,sha256=qzk0NT332Q0vR1eRwTuNiMSrGE3ulh6Ic3QLBZqSdvw,7284
 upgini/autofe/feature.py,sha256=_V9B74B3ue7eAYXSOt9JKhVC9klkAKks22MwnBRye_w,12487
 upgini/autofe/groupby.py,sha256=4WjDzQxqpZxB79Ih4ihMMI5GDxaFqiH6ZelfV82ClT4,3091
-upgini/autofe/operand.py,sha256=JjEVT1U3kY9NDjUPMdoki7Oa8hMDG0-_h_NklVjIFyc,2882
-upgini/autofe/unary.py,sha256=v-l3aiE5hj6kurvh6adCQL8W3X9u9a7RVbS_WPR2qlw,3146
+upgini/autofe/operand.py,sha256=MKEsl3zxpWzRDpTkE0sNJxTu62U20sWOvEKhPjUWS6s,2915
+upgini/autofe/unary.py,sha256=ZWjLd-CUkNt_PpM8YuWLLipW1v_RdBlsl4JxXIVo9aM,3652
 upgini/autofe/vector.py,sha256=dLxfAstJs-gw_OQ1xxoxcM6pVzORlV0HVzdzt7cLXVQ,606
 upgini/data_source/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 upgini/data_source/data_source_publisher.py,sha256=B4fJ1owDCF5ZZ0Ca9ywi_CXVt4iPvABh5BGTnXdXmHk,16635
@@ -56,7 +56,7 @@ upgini/utils/sklearn_ext.py,sha256=13jQS_k7v0aUtudXV6nGUEWjttPQzAW9AFYL5wgEz9k,4
 upgini/utils/target_utils.py,sha256=Y96_PJ5cC-WsEbeqg20v9uqywDQobLoTb-xoP7S3o4E,7807
 upgini/utils/track_info.py,sha256=G5Lu1xxakg2_TQjKZk4b5SvrHsATTXNVV3NbvWtT8k8,5663
 upgini/utils/warning_counter.py,sha256=dIWBB4dI5XRRJZudvIlqlIYKEiwLLPcXarsZuYRt338,227
-upgini-1.1.290.dist-info/METADATA,sha256=hCW_dnkYOifgc0LJpt9mktkSzt5Y038uJLk8k_cdIQM,48117
-upgini-1.1.290.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
-upgini-1.1.290.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
-upgini-1.1.290.dist-info/RECORD,,
+upgini-1.1.291.dist-info/METADATA,sha256=Te_7fjcuJJN1jrnzgzT9tHRZyQeiVDS9EGusXmnpjvw,48117
+upgini-1.1.291.dist-info/WHEEL,sha256=zEMcRr9Kr03x1ozGwg5v9NQBKn3kndp6LSoSlVg-jhU,87
+upgini-1.1.291.dist-info/licenses/LICENSE,sha256=5RRzgvdJUu3BUDfv4bzVU6FqKgwHlIay63pPCSmSgzw,1514
+upgini-1.1.291.dist-info/RECORD,,