upgini 1.2.63__tar.gz → 1.2.65a3818.dev5__tar.gz

{upgini-1.2.63 → upgini-1.2.65a3818.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: upgini
-Version: 1.2.63
+Version: 1.2.65a3818.dev5
 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-1.2.65a3818.dev5/src/upgini/__about__.py

@@ -0,0 +1 @@
+__version__ = "1.2.65a3818.dev5"

{upgini-1.2.63 → upgini-1.2.65a3818.dev5}/src/upgini/autofe/all_operands.py

@@ -1,4 +1,4 @@
-from upgini.autofe.operand import OperandRegistry
+from upgini.autofe.operator import OperatorRegistry
 from upgini.autofe.unary import *  # noqa
 from upgini.autofe.binary import *  # noqa
 from upgini.autofe.groupby import *  # noqa
@@ -7,4 +7,4 @@ from upgini.autofe.vector import *  # noqa
 
 
 def find_op(name):
-    return OperandRegistry.get_operand(name)
+    return OperatorRegistry.get_operator(name)

{upgini-1.2.63 → upgini-1.2.65a3818.dev5}/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.operand 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-1.2.63 → upgini-1.2.65a3818.dev5}/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.operand 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-1.2.63 → upgini-1.2.65a3818.dev5}/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.operand 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-1.2.63 → upgini-1.2.65a3818.dev5}/src/upgini/autofe/groupby.py

@@ -2,13 +2,13 @@ from typing import Optional
 
 import pandas as pd
 
-from upgini.autofe.operand 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-1.2.63/src/upgini/autofe/operand.py → upgini-1.2.65a3818.dev5/src/upgini/autofe/operator.py

@@ -6,7 +6,7 @@ import pandas as pd
 from pydantic import BaseModel
 
 
-class OperandRegistry(type(BaseModel)):
+class OperatorRegistry(type(BaseModel)):
     _registry = {}
     _parametrized_registry = []
 
@@ -20,23 +20,25 @@ class OperandRegistry(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:
                     instance = new_class()
                     cls._registry[instance.name] = new_class
+                    if instance.alias:
+                        cls._registry[instance.alias] = new_class
                 except Exception:
                     pass
         return new_class
 
     @classmethod
-    def get_operand(cls, name: str) -> Optional["Operand"]:
+    def get_operator(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)
+        for operator_cls in cls._parametrized_registry:
+            resolved = operator_cls.from_formula(name)
             if resolved is not None:
                 return resolved
         # Fall back to direct registry lookup
@@ -46,7 +48,7 @@ class OperandRegistry(type(BaseModel)):
         return None
 
 
-class Operand(BaseModel, metaclass=OperandRegistry):
+class Operator(BaseModel, metaclass=OperatorRegistry):
     name: Optional[str] = None
     alias: Optional[str] = None
     is_unary: bool = False
@@ -75,7 +77,7 @@ class Operand(BaseModel, metaclass=OperandRegistry):
         return self.name
 
 
-class ParametrizedOperand(Operand, abc.ABC):
+class ParametrizedOperator(Operator, abc.ABC):
 
     @abc.abstractmethod
     def to_formula(self) -> str:
@@ -83,14 +85,14 @@ 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 +133,7 @@ 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-1.2.65a3818.dev5/src/upgini/autofe/timeseries/__init__.py

@@ -0,0 +1,23 @@
+"""Time series feature engineering operators."""
+
+from upgini.autofe.timeseries.base import TimeSeriesBase
+from upgini.autofe.timeseries.roll import Roll
+from upgini.autofe.timeseries.lag import Lag
+from upgini.autofe.timeseries.delta import Delta, Delta2
+from upgini.autofe.timeseries.trend import TrendCoefficient
+from upgini.autofe.timeseries.volatility import EWMAVolatility, RollingVolatility, RollingVolatility2, VolatilityRatio
+from upgini.autofe.timeseries.cross import CrossSeriesInteraction
+
+__all__ = [
+    "TimeSeriesBase",
+    "Roll",
+    "Lag",
+    "Delta",
+    "Delta2",
+    "TrendCoefficient",
+    "EWMAVolatility",
+    "RollingVolatility",
+    "RollingVolatility2",
+    "VolatilityRatio",
+    "CrossSeriesInteraction",
+]

upgini-1.2.65a3818.dev5/src/upgini/autofe/timeseries/base.py

@@ -0,0 +1,105 @@
+import abc
+from typing import Dict, List, Optional
+
+import pandas as pd
+from upgini.autofe.operator import PandasOperator
+
+# Used in derived classes
+try:
+    from pydantic import field_validator as validator  # V2
+except ImportError:
+    from pydantic import validator  # V1
+
+
+class TimeSeriesBase(PandasOperator, abc.ABC):
+    is_vector: bool = True
+    date_unit: Optional[str] = None
+    offset_size: int = 0
+    offset_unit: str = "D"
+
+    def get_params(self) -> Dict[str, Optional[str]]:
+        res = super().get_params()
+        res.update(
+            {
+                "date_unit": self.date_unit,
+                "offset_size": self.offset_size,
+                "offset_unit": self.offset_unit,
+            }
+        )
+        return res
+
+    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+        # assuming first is date, last is value, rest is group columns
+        date = pd.to_datetime(data[0], unit=self.date_unit, errors="coerce")
+        ts = pd.concat([date] + data[1:], axis=1)
+        ts.drop_duplicates(subset=ts.columns[:-1], keep="first", inplace=True)
+        ts.set_index(date.name, inplace=True)
+        ts = ts[ts.index.notna()].sort_index()
+        ts = (
+            ts.groupby([c.name for c in data[1:-1]], group_keys=True)
+            .apply(self._shift)[data[-1].name]
+            .to_frame()
+            .reset_index()
+            .set_index(date.name)
+            .groupby([c.name for c in data[1:-1]], group_keys=True)
+            if len(data) > 2
+            else self._shift(ts)
+        )
+        ts = self._aggregate(ts)
+        ts = ts.reindex(data[1:-1] + [date] if len(data) > 2 else date).reset_index()
+        ts.index = date.index
+
+        return ts.iloc[:, -1]
+
+    def _shift(self, ts: pd.DataFrame) -> pd.DataFrame:
+        if self.offset_size > 0:
+            return ts.iloc[:, :-1].merge(
+                ts.iloc[:, -1].shift(freq=f"{self.offset_size}{self.offset_unit}"),
+                left_index=True,
+                right_index=True,
+            )
+        return ts
+
+    @abc.abstractmethod
+    def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
+        pass
+
+    def _add_offset_to_formula(self, base_formula: str) -> str:
+        if self.offset_size > 0:
+            return f"{base_formula}_offset_{self.offset_size}{self.offset_unit}"
+        return base_formula
+
+    @classmethod
+    def _parse_offset_from_formula(cls, formula: str, base_regex: str) -> tuple[Optional[dict], Optional[str]]:
+        """
+        Parse the offset component from a formula.
+
+        Args:
+            formula: The formula to parse
+            base_regex: The regex pattern for the base formula (without offset)
+
+        Returns:
+            A tuple with:
+            - Dictionary with offset parameters if found, None otherwise
+            - Remaining part of the formula after removing offset component (for further parsing)
+        """
+        import re
+
+        offset_regex = f"{base_regex}_offset_(\\d+)([a-zA-Z])"
+        match = re.match(offset_regex, formula)
+
+        if match:
+            # Get groups from the offset part
+            offset_size = int(match.group(match.lastindex - 1))
+            offset_unit = match.group(match.lastindex)
+
+            # Return the parameters and the base formula for further parsing if needed
+            # Extract the base formula by using the match object
+            base_formula = formula[: match.start(match.lastindex - 1) - len("_offset_")]
+            return {"offset_size": offset_size, "offset_unit": offset_unit}, base_formula
+
+        # Check if it matches the base regex (no offset)
+        if re.match(f"^{base_regex}$", formula) or re.match(f"^{base_regex}_", formula):
+            return None, formula
+
+        return None, None

upgini-1.2.65a3818.dev5/src/upgini/autofe/timeseries/cross.py

@@ -0,0 +1,130 @@
+from typing import Dict, List, Optional
+
+import numpy as np
+import pandas as pd
+
+try:
+    from pydantic import field_validator as validator  # V2
+except ImportError:
+    from pydantic import validator  # V1
+
+from upgini.autofe.all_operands import find_op
+from upgini.autofe.operator import PandasOperator, ParametrizedOperator
+from upgini.autofe.timeseries.base import TimeSeriesBase
+
+
+class CrossSeriesInteraction(TimeSeriesBase, ParametrizedOperator):
+    base_name: str = "cross"
+    interaction_op: PandasOperator
+    descriptor_indices: List[int] = []
+    left_descriptor: List[str] = []
+    right_descriptor: List[str] = []
+
+    @validator("descriptor_indices")
+    @classmethod
+    def validate_descriptor_indices(cls, v):
+        if not v:
+            raise ValueError("descriptor_indices cannot be empty for CrossSeriesInteraction")
+        return v
+
+    def __init__(self, **data):
+        super().__init__(**data)
+        indices = self.descriptor_indices
+        left = self.left_descriptor
+        right = self.right_descriptor
+
+        if len(left) != len(indices):
+            raise ValueError(
+                f"left_descriptor length ({len(left)}) " f"must match descriptor_indices length ({len(indices)})"
+            )
+
+        if len(right) != len(indices):
+            raise ValueError(
+                f"right_descriptor length ({len(right)}) " f"must match descriptor_indices length ({len(indices)})"
+            )
+
+    def to_formula(self) -> str:
+        base_formula = f"{self.base_name}_{self._get_interaction_op_name()}"
+        return self._add_offset_to_formula(base_formula)
+
+    @classmethod
+    def from_formula(cls, formula: str) -> Optional["CrossSeriesInteraction"]:
+        base_regex = r"cross_(.+)"
+
+        offset_params, remaining_formula = cls._parse_offset_from_formula(formula, base_regex)
+
+        if remaining_formula is None:
+            return None
+
+        import re
+
+        match = re.match(f"^{base_regex}$", remaining_formula)
+
+        if not match:
+            return None
+
+        # Extract the operator formula
+        op_formula = match.group(1)
+
+        op = find_op(op_formula)
+        if op is None or not op.is_binary:
+            return None
+
+        # Include default values to pass validation
+        params = {
+            "interaction_op": op,
+            "descriptor_indices": [0],  # Default index
+            "left_descriptor": ["default"],  # Default left descriptor
+            "right_descriptor": ["default"],  # Default right descriptor
+        }
+
+        if offset_params:
+            params.update(offset_params)
+
+        return cls(**params)
+
+    def get_params(self) -> Dict[str, str | None]:
+        res = super().get_params()
+        res.update(
+            {
+                "interaction_op": self._get_interaction_op_name(),
+                "descriptor_indices": self.descriptor_indices,
+                "left_descriptor": self.left_descriptor,
+                "right_descriptor": self.right_descriptor,
+            }
+        )
+        return res
+
+    def _get_interaction_op_name(self) -> str:
+        return self.interaction_op.alias or self.interaction_op.to_formula()
+
+    def calculate_vector(self, data: List[pd.Series]) -> pd.Series:
+        left_mask = self._get_mask(data, self.left_descriptor)
+        left = self._extract_series(data, left_mask)
+
+        right_mask = self._get_mask(data, self.right_descriptor)
+        right = self._extract_series(data, right_mask)
+
+        interaction: pd.Series = self.interaction_op.calculate_binary(left, right)
+        interaction = interaction.reindex(self._get_index(data))
+        res = pd.Series(np.nan, index=data[-1].index, name=data[-1].name)
+        res.loc[left_mask] = interaction[left_mask].values
+        res.loc[right_mask] = interaction[right_mask].values
+        return res
+
+    def _get_mask(self, data: List[pd.Series], descriptor: List[str]) -> pd.Series:
+        mask = np.logical_and.reduce([data[i] == v for i, v in zip(self.descriptor_indices, descriptor)])
+        return mask
+
+    def _extract_series(self, data: List[pd.Series], mask: pd.Series) -> pd.Series:
+        masked_data = [d[mask] for d in data]
+        shifted = super().calculate_vector(masked_data)
+        shifted.index = self._get_index(masked_data)
+        return shifted
+
+    def _get_index(self, data: List[pd.Series]) -> pd.Series:
+        index = [d for i, d in enumerate(data[:-1]) if i not in self.descriptor_indices]
+        return index if len(index) > 1 else index[0]
+
+    def _aggregate(self, ts: pd.DataFrame) -> pd.DataFrame:
+        return ts.apply(lambda x: x).iloc[:, [-1]]