upgini 1.2.62a3818.dev1__tar.gz → 1.2.62a3818.dev3__tar.gz

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.62a3818.dev1
+Version: 1.2.62a3818.dev3
 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-1.2.62a3818.dev3/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.62a3818.dev3"

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/binary.py

@@ -5,10 +5,10 @@ import numpy as np
 import pandas as pd
 from jarowinkler import jarowinkler_similarity
 
-from upgini.autofe.operator import PandasOperand, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
 
 
-class Min(PandasOperand):
+class Min(PandasOperator):
     name: str = "min"
     is_binary: bool = True
     is_symmetrical: bool = True
@@ -18,7 +18,7 @@ class Min(PandasOperand):
         return np.minimum(left, right)
 
 
-class Max(PandasOperand):
+class Max(PandasOperator):
     name: str = "max"
     is_binary: bool = True
     is_symmetrical: bool = True
@@ -28,7 +28,7 @@ class Max(PandasOperand):
         return np.maximum(left, right)
 
 
-class Add(PandasOperand, VectorizableMixin):
+class Add(PandasOperator, VectorizableMixin):
     name: str = "+"
     alias: str = "add"
     is_binary: bool = True
@@ -47,7 +47,7 @@ class Add(PandasOperand, VectorizableMixin):
         return d1.add(d2, axis=0)
 
 
-class Subtract(PandasOperand, VectorizableMixin):
+class Subtract(PandasOperator, VectorizableMixin):
     name: str = "-"
     alias: str = "sub"
     is_binary: bool = True
@@ -66,7 +66,7 @@ class Subtract(PandasOperand, VectorizableMixin):
         return d1.sub(d2, axis=0)
 
 
-class Multiply(PandasOperand, VectorizableMixin):
+class Multiply(PandasOperator, VectorizableMixin):
     name: str = "*"
     alias: str = "mul"
     is_binary: bool = True
@@ -85,7 +85,7 @@ class Multiply(PandasOperand, VectorizableMixin):
         return d1.mul(d2, axis=0)
 
 
-class Divide(PandasOperand, VectorizableMixin):
+class Divide(PandasOperator, VectorizableMixin):
     name: str = "/"
     alias: str = "div"
     is_binary: bool = True
@@ -104,7 +104,7 @@ class Divide(PandasOperand, VectorizableMixin):
         return d1.div(d2.replace(0, np.nan), axis=0)
 
 
-class Combine(PandasOperand):
+class Combine(PandasOperator):
     name: str = "Combine"
     is_binary: bool = True
     has_symmetry_importance: bool = True
@@ -116,7 +116,7 @@ class Combine(PandasOperand):
         return pd.Series(temp, index=left.index)
 
 
-class CombineThenFreq(PandasOperand):
+class CombineThenFreq(PandasOperator):
     name: str = "CombineThenFreq"
     is_binary: bool = True
     is_symmetrical: bool = True
@@ -132,7 +132,7 @@ class CombineThenFreq(PandasOperand):
         self._loc(temp, value_counts)
 
 
-class Distance(PandasOperand):
+class Distance(PandasOperator):
     name: str = "dist"
     is_binary: bool = True
     output_type: Optional[str] = "float"
@@ -170,7 +170,7 @@ class Sim(Distance):
         return 1 - super().calculate_binary(left, right)
 
 
-class StringSim(PandasOperand, abc.ABC):
+class StringSim(PandasOperator, abc.ABC):
     def calculate_binary(self, left: pd.Series, right: pd.Series) -> pd.Series:
         sims = []
         for i in left.index:

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/date.py

@@ -7,7 +7,7 @@ import pandas as pd
 from pandas.core.arrays.timedeltas import TimedeltaArray
 from pydantic import BaseModel, __version__ as pydantic_version
 
-from upgini.autofe.operator import PandasOperand, ParametrizedOperand
+from upgini.autofe.operator import PandasOperator, ParametrizedOperator
 
 
 def get_pydantic_version():
@@ -43,7 +43,7 @@ class DateDiffMixin(BaseModel):
             raise Exception(f"Unsupported difference unit: {self.diff_unit}")
 
 
-class DateDiff(PandasOperand, DateDiffMixin):
+class DateDiff(PandasOperator, DateDiffMixin):
     name: str = "date_diff"
     alias: Optional[str] = "date_diff_type1"
     is_binary: bool = True
@@ -78,7 +78,7 @@ class DateDiff(PandasOperand, DateDiffMixin):
         return x
 
 
-class DateDiffType2(PandasOperand, DateDiffMixin):
+class DateDiffType2(PandasOperator, DateDiffMixin):
     name: str = "date_diff_type2"
     is_binary: bool = True
     has_symmetry_importance: bool = True
@@ -112,7 +112,7 @@ _ext_aggregations = {"nunique": (lambda x: len(np.unique(x)), 0), "count": (len,
 _count_aggregations = ["nunique", "count"]
 
 
-class DateListDiff(PandasOperand, DateDiffMixin, ParametrizedOperand):
+class DateListDiff(PandasOperator, DateDiffMixin, ParametrizedOperator):
     is_binary: bool = True
     has_symmetry_importance: bool = True
 
@@ -183,7 +183,7 @@ class DateListDiff(PandasOperand, DateDiffMixin, ParametrizedOperand):
         return method(x) if len(x) > 0 else default
 
 
-class DateListDiffBounded(DateListDiff, ParametrizedOperand):
+class DateListDiffBounded(DateListDiff, ParametrizedOperator):
     lower_bound: Optional[int] = None
     upper_bound: Optional[int] = None
 
@@ -217,7 +217,7 @@ class DateListDiffBounded(DateListDiff, ParametrizedOperand):
         return super()._agg(x)
 
 
-class DatePercentileBase(PandasOperand, abc.ABC):
+class DatePercentileBase(PandasOperator, abc.ABC):
     is_binary: bool = True
     output_type: Optional[str] = "float"
 

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/feature.py

@@ -7,7 +7,7 @@ import pandas as pd
 from pandas._typing import DtypeObj
 
 from upgini.autofe.all_operands import find_op
-from upgini.autofe.operator import Operand, PandasOperand
+from upgini.autofe.operator import Operator, PandasOperator
 
 
 class Column:
@@ -65,7 +65,7 @@ class Column:
 class Feature:
     def __init__(
         self,
-        op: Operand,
+        op: Operator,
         children: List[Union[Column, "Feature"]],
         data: Optional[pd.DataFrame] = None,
         display_index: Optional[str] = None,
@@ -188,7 +188,7 @@ class Feature:
             return self.children[0].infer_type(data)
 
     def calculate(self, data: pd.DataFrame, is_root=False) -> Union[pd.Series, pd.DataFrame]:
-        if isinstance(self.op, PandasOperand):
+        if isinstance(self.op, PandasOperator):
             if self.op.is_vector:
                 ds = [child.calculate(data) for child in self.children]
                 new_data = self.op.calculate(data=ds)
@@ -324,7 +324,7 @@ class Feature:
 
 class FeatureGroup:
     def __init__(
-        self, op: Operand, main_column: Optional[Union[Column, Feature]], children: List[Union[Column, Feature]]
+        self, op: Operator, main_column: Optional[Union[Column, Feature]], children: List[Union[Column, Feature]]
     ):
         self.op = op
         self.main_column_node = main_column
@@ -345,7 +345,7 @@ class FeatureGroup:
         return names
 
     def calculate(self, data: pd.DataFrame, is_root=False) -> pd.DataFrame:
-        if isinstance(self.op, PandasOperand):
+        if isinstance(self.op, PandasOperator):
             main_column = None if self.main_column_node is None else self.main_column_node.get_display_name()
             lower_order_children = []
             if self.main_column_node is not None:
@@ -378,7 +378,7 @@ class FeatureGroup:
     def make_groups(candidates: List[Feature]) -> List[Union[Feature, "FeatureGroup"]]:
         grouped_features = []
 
-        def groupby_func(f: Feature) -> Tuple[Operand, Union[Column, Feature]]:
+        def groupby_func(f: Feature) -> Tuple[Operator, Union[Column, Feature]]:
             return (f.op, f.children[0 if not f.op.is_vectorizable else f.op.group_index])
 
         for op_child, features in itertools.groupby(candidates, groupby_func):

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/groupby.py

@@ -2,13 +2,13 @@ from typing import Optional
 
 import pandas as pd
 
-from upgini.autofe.operator import PandasOperand, ParametrizedOperand, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, ParametrizedOperator, VectorizableMixin
 
 
 class GroupByThenAgg(
-    PandasOperand,
+    PandasOperator,
     VectorizableMixin,
-    ParametrizedOperand,
+    ParametrizedOperator,
 ):
     agg: Optional[str]
     is_vectorizable: bool = True
@@ -39,7 +39,7 @@ class GroupByThenAgg(
         return temp.merge(d2, how="right", on=[group_column])[value_columns]
 
 
-class GroupByThenRank(PandasOperand, VectorizableMixin):
+class GroupByThenRank(PandasOperator, VectorizableMixin):
     name: str = "GroupByThenRank"
     is_vectorizable: bool = True
     is_grouping: bool = True
@@ -58,7 +58,7 @@ class GroupByThenRank(PandasOperand, VectorizableMixin):
         return temp.merge(d2.reset_index(), how="right", on=["index"])[value_columns]
 
 
-class GroupByThenNUnique(PandasOperand, VectorizableMixin):
+class GroupByThenNUnique(PandasOperator, VectorizableMixin):
     name: str = "GroupByThenNUnique"
     is_vectorizable: bool = True
     is_grouping: bool = True
@@ -78,7 +78,7 @@ class GroupByThenNUnique(PandasOperand, VectorizableMixin):
         return nunique.merge(d2, how="right", on=[group_column])[value_columns]
 
 
-class GroupByThenFreq(PandasOperand):
+class GroupByThenFreq(PandasOperator):
     name: str = "GroupByThenFreq"
     is_grouping: bool = True
     output_type: Optional[str] = "float"

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/operator.py

@@ -20,9 +20,9 @@ class OperatorRegistry(type(BaseModel)):
             base_names.update(b.__name__ for b in base.__bases__)
             base_classes.extend(base.__bases__)
 
-        if "Operand" in base_names:
+        if "Operator" in base_names:
             # Track parametrized operands separately
-            if "ParametrizedOperand" in base_names:
+            if "ParametrizedOperator" in base_names:
                 cls._parametrized_registry.append(new_class)
             else:
                 try:
@@ -33,7 +33,7 @@ class OperatorRegistry(type(BaseModel)):
         return new_class
 
     @classmethod
-    def get_operand(cls, name: str) -> Optional["Operand"]:
+    def get_operand(cls, name: str) -> Optional["Operator"]:
         # First try to resolve as a parametrized operand formula
         for operand_cls in cls._parametrized_registry:
             resolved = operand_cls.from_formula(name)
@@ -46,7 +46,7 @@ class OperatorRegistry(type(BaseModel)):
         return None
 
 
-class Operand(BaseModel, metaclass=OperatorRegistry):
+class Operator(BaseModel, metaclass=OperatorRegistry):
     name: Optional[str] = None
     alias: Optional[str] = None
     is_unary: bool = False
@@ -75,7 +75,7 @@ class Operand(BaseModel, metaclass=OperatorRegistry):
         return self.name
 
 
-class ParametrizedOperand(Operand, abc.ABC):
+class ParametrizedOperator(Operator, abc.ABC):
 
     @abc.abstractmethod
     def to_formula(self) -> str:
@@ -83,14 +83,14 @@ class ParametrizedOperand(Operand, abc.ABC):
 
     @classmethod
     @abc.abstractmethod
-    def from_formula(cls, formula: str) -> Optional["Operand"]:
+    def from_formula(cls, formula: str) -> Optional["Operator"]:
         pass
 
 
 MAIN_COLUMN = "main_column"
 
 
-class PandasOperand(Operand, abc.ABC):
+class PandasOperator(Operator, abc.ABC):
     def calculate(self, **kwargs) -> pd.Series:
         if self.is_unary:
             return self.calculate_unary(kwargs["data"])
@@ -131,7 +131,7 @@ class PandasOperand(Operand, abc.ABC):
             return value
 
 
-class VectorizableMixin(Operand):
+class VectorizableMixin(Operator):
     group_index: int = 1
 
     def validate_calculation(self, input_columns: List[str], **kwargs) -> Tuple[str, List[str]]:

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/timeseries.py

@@ -2,7 +2,7 @@ import abc
 from typing import Dict, List, Optional
 
 import pandas as pd
-from upgini.autofe.operator import PandasOperand, ParametrizedOperand
+from upgini.autofe.operator import PandasOperator, ParametrizedOperator
 
 try:
     from pydantic import field_validator as validator  # V2
@@ -10,7 +10,7 @@ except ImportError:
     from pydantic import validator  # V1
 
 
-class TimeSeriesBase(PandasOperand, abc.ABC):
+class TimeSeriesBase(PandasOperator, abc.ABC):
     is_vector: bool = True
     date_unit: Optional[str] = None
     offset_size: int = 0
@@ -67,7 +67,7 @@ class TimeSeriesBase(PandasOperand, abc.ABC):
 _roll_aggregations = {"norm_mean": lambda x: x[-1] / x.mean(), "last": lambda x: x[-1]}
 
 
-class Roll(TimeSeriesBase, ParametrizedOperand):
+class Roll(TimeSeriesBase, ParametrizedOperator):
     aggregation: str
     window_size: int = 1
     window_unit: str = "D"
@@ -142,7 +142,7 @@ class Roll(TimeSeriesBase, ParametrizedOperand):
         )
 
 
-class Lag(TimeSeriesBase, ParametrizedOperand):
+class Lag(TimeSeriesBase, ParametrizedOperator):
     lag_size: int
     lag_unit: str = "D"
 

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/unary.py

@@ -2,10 +2,10 @@ from typing import Dict, Optional
 import numpy as np
 import pandas as pd
 
-from upgini.autofe.operator import PandasOperand, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
 
 
-class Abs(PandasOperand, VectorizableMixin):
+class Abs(PandasOperator, VectorizableMixin):
     name: str = "abs"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -20,7 +20,7 @@ class Abs(PandasOperand, VectorizableMixin):
         # return data.abs()
 
 
-class Log(PandasOperand, VectorizableMixin):
+class Log(PandasOperator, VectorizableMixin):
     name: str = "log"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -34,7 +34,7 @@ class Log(PandasOperand, VectorizableMixin):
         return self._round_value(np.log(data.replace(0, np.nan).abs()), 10)
 
 
-class Sqrt(PandasOperand, VectorizableMixin):
+class Sqrt(PandasOperator, VectorizableMixin):
     name: str = "sqrt"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -48,7 +48,7 @@ class Sqrt(PandasOperand, VectorizableMixin):
         return self._round_value(np.sqrt(data.abs()))
 
 
-class Square(PandasOperand, VectorizableMixin):
+class Square(PandasOperator, VectorizableMixin):
     name: str = "square"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -61,7 +61,7 @@ class Square(PandasOperand, VectorizableMixin):
         return np.square(data)
 
 
-class Sigmoid(PandasOperand, VectorizableMixin):
+class Sigmoid(PandasOperator, VectorizableMixin):
     name: str = "sigmoid"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -75,7 +75,7 @@ class Sigmoid(PandasOperand, VectorizableMixin):
         return self._round_value(1 / (1 + np.exp(-data)))
 
 
-class Floor(PandasOperand, VectorizableMixin):
+class Floor(PandasOperator, VectorizableMixin):
     name: str = "floor"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -90,7 +90,7 @@ class Floor(PandasOperand, VectorizableMixin):
         return np.floor(data)
 
 
-class Residual(PandasOperand, VectorizableMixin):
+class Residual(PandasOperator, VectorizableMixin):
     name: str = "residual"
     is_unary: bool = True
     is_vectorizable: bool = True
@@ -104,7 +104,7 @@ class Residual(PandasOperand, VectorizableMixin):
         return data - np.floor(data)
 
 
-class Freq(PandasOperand):
+class Freq(PandasOperator):
     name: str = "freq"
     is_unary: bool = True
     output_type: Optional[str] = "float"
@@ -116,7 +116,7 @@ class Freq(PandasOperand):
         return self._loc(data, value_counts)
 
 
-class Norm(PandasOperand):
+class Norm(PandasOperator):
     name: str = "norm"
     is_unary: bool = True
     output_type: Optional[str] = "float"
@@ -148,7 +148,7 @@ class Norm(PandasOperand):
         return res
 
 
-class Embeddings(PandasOperand):
+class Embeddings(PandasOperator):
     name: str = "emb"
     is_unary: bool = True
     input_type: Optional[str] = "string"

{upgini-1.2.62a3818.dev1 → upgini-1.2.62a3818.dev3}/src/upgini/autofe/vector.py

@@ -2,10 +2,10 @@ from typing import List, Optional
 
 import pandas as pd
 
-from upgini.autofe.operator import PandasOperand, VectorizableMixin
+from upgini.autofe.operator import PandasOperator, VectorizableMixin
 
 
-class Mean(PandasOperand, VectorizableMixin):
+class Mean(PandasOperator, VectorizableMixin):
     name: str = "mean"
     output_type: Optional[str] = "float"
     is_vector: bool = True
@@ -15,7 +15,7 @@ class Mean(PandasOperand, VectorizableMixin):
         return pd.DataFrame(data).T.fillna(0).mean(axis=1)
 
 
-class Sum(PandasOperand, VectorizableMixin):
+class Sum(PandasOperator, VectorizableMixin):
     name: str = "sum"
     is_vector: bool = True
     group_index: int = 0

upgini-1.2.62a3818.dev1/src/upgini/__about__.py

@@ -1 +0,0 @@
-__version__ = "1.2.62a3818.dev1"