kumoai 2.14.0.dev202512141732__py3-none-any.whl → 2.15.0.dev202601131732__py3-none-any.whl

kumoai/experimental/rfm/base/__init__.py

@@ -8,16 +8,23 @@ class DataBackend(StrEnum):
 
 
 from .source import SourceColumn, SourceForeignKey  # noqa: E402
-from .column import Column  # noqa: E402
+from .expression import Expression, LocalExpression  # noqa: E402
+from .column import ColumnSpec, ColumnSpecType, Column  # noqa: E402
 from .table import Table  # noqa: E402
 from .sampler import SamplerOutput, Sampler  # noqa: E402
+from .sql_sampler import SQLSampler  # noqa: E402
 
 __all__ = [
     'DataBackend',
     'SourceColumn',
     'SourceForeignKey',
+    'Expression',
+    'LocalExpression',
+    'ColumnSpec',
+    'ColumnSpecType',
     'Column',
     'Table',
     'SamplerOutput',
     'Sampler',
+    'SQLSampler',
 ]

kumoai/experimental/rfm/base/column.py

@@ -1,37 +1,119 @@
+from __future__ import annotations
+
 from dataclasses import dataclass
-from typing import Any
+from typing import Any, Mapping, TypeAlias
 
 from kumoapi.typing import Dtype, Stype
+from typing_extensions import Self
+
+from kumoai.experimental.rfm.base import Expression
+from kumoai.mixin import CastMixin
+
+
+@dataclass(init=False)
+class ColumnSpec(CastMixin):
+    r"""A column specification for adding a column to a table.
+
+    A column specification can either refer to a physical column present in
+    the data source, or be defined logically via an expression.
+
+    Args:
+        name: The name of the column.
+        expr: A column expression to define logical columns.
+        dtype: The data type of the column.
+    """
+    def __init__(
+        self,
+        name: str,
+        expr: Expression | Mapping[str, str] | str | None = None,
+        dtype: Dtype | str | None = None,
+        stype: Stype | str | None = None,
+    ) -> None:
+
+        self.name = name
+        self.expr = Expression.coerce(expr)
+        self.dtype = Dtype(dtype) if dtype is not None else None
+        self.stype = Stype(dtype) if stype is not None else None
+
+    @classmethod
+    def coerce(cls, spec: ColumnSpec | Mapping[str, Any] | str) -> Self:
+        r"""Coerces a column specification into a :class:`ColumnSpec`."""
+        if isinstance(spec, cls):
+            return spec
+        if isinstance(spec, str):
+            return cls(name=spec)
+        if isinstance(spec, Mapping):
+            try:
+                return cls(**spec)
+            except TypeError:
+                pass
+        raise TypeError(f"Unable to coerce 'ColumnSpec' from '{spec}'")
+
+    @property
+    def is_source(self) -> bool:
+        r"""Whether the column specification refers to a phyiscal column
+        present in the data source.
+        """
+        return self.expr is None
+
+
+ColumnSpecType: TypeAlias = ColumnSpec | Mapping[str, Any] | str
 
 
 @dataclass(init=False, repr=False, eq=False)
 class Column:
+    r"""Column-level metadata information.
+
+    A column can either refer to a physical column present in the data source,
+    or be defined logically via an expression.
+
+    Args:
+        name: The name of the column.
+        expr: A column expression to define logical columns.
+        dtype: The data type of the column.
+        stype: The semantic type of the column.
+    """
     stype: Stype
 
     def __init__(
         self,
         name: str,
+        expr: Expression | None,
         dtype: Dtype,
         stype: Stype,
-        is_primary_key: bool = False,
-        is_time_column: bool = False,
-        is_end_time_column: bool = False,
     ) -> None:
         self._name = name
+        self._expr = expr
         self._dtype = Dtype(dtype)
-        self._is_primary_key = is_primary_key
-        self._is_time_column = is_time_column
-        self._is_end_time_column = is_end_time_column
+
+        self._is_primary_key = False
+        self._is_time_column = False
+        self._is_end_time_column = False
+
         self.stype = Stype(stype)
 
     @property
     def name(self) -> str:
+        r"""The name of the column."""
         return self._name
 
+    @property
+    def expr(self) -> Expression | None:
+        r"""The expression of column (if logically)."""
+        return self._expr
+
     @property
     def dtype(self) -> Dtype:
+        r"""The data type of the column."""
         return self._dtype
 
+    @property
+    def is_source(self) -> bool:
+        r"""Whether the column refers to a phyiscal column present in the data
+        source.
+        """
+        return self.expr is None
+
     def __setattr__(self, key: str, val: Any) -> None:
         if key == 'stype':
             if isinstance(val, str):
@@ -54,7 +136,7 @@ class Column:
         super().__setattr__(key, val)
 
     def __hash__(self) -> int:
-        return hash((self.name, self.stype, self.dtype))
+        return hash((self.name, self.expr, self.dtype, self.stype))
 
     def __eq__(self, other: Any) -> bool:
         if not isinstance(other, Column):
@@ -62,5 +144,9 @@ class Column:
         return hash(self) == hash(other)
 
     def __repr__(self) -> str:
-        return (f'{self.__class__.__name__}(name={self.name}, '
-                f'stype={self.stype}, dtype={self.dtype})')
+        parts = [f'name={self.name}']
+        if self.expr is not None:
+            parts.append(f'expr={self.expr}')
+        parts.append(f'dtype={self.dtype}')
+        parts.append(f'stype={self.stype}')
+        return f"{self.__class__.__name__}({', '.join(parts)})"

kumoai/experimental/rfm/base/expression.py

@@ -0,0 +1,44 @@
+from __future__ import annotations
+
+from abc import ABC
+from dataclasses import dataclass
+from typing import Mapping
+
+
+class Expression(ABC):
+    """A base expression to define logical columns."""
+    @classmethod
+    def coerce(
+        cls,
+        spec: Expression | Mapping[str, str] | str | None,
+    ) -> Expression | None:
+        r"""Coerces an expression specification into an :class:`Expression`, if
+        possible.
+        """
+        if spec is None:
+            return None
+        if isinstance(spec, Expression):
+            return spec
+        if isinstance(spec, str):
+            return LocalExpression(spec)
+        if isinstance(spec, Mapping):
+            for sub_cls in (LocalExpression, ):
+                try:
+                    return sub_cls(**spec)
+                except TypeError:
+                    pass
+        raise TypeError(f"Unable to coerce 'Expression' from '{spec}'")
+
+
+@dataclass(frozen=True, repr=False)
+class LocalExpression(Expression):
+    r"""A local expression to define a row-level logical attribute based on
+    physical columns of the data source in the same row.
+
+    Args:
+        value: The value of the expression.
+    """
+    value: str
+
+    def __repr__(self) -> str:
+        return self.value

kumoai/experimental/rfm/base/mapper.py

@@ -0,0 +1,69 @@
+import numpy as np
+import pandas as pd
+
+
+class Mapper:
+    r"""A mapper to map ``(pkey, batch)`` pairs to contiguous node IDs.
+
+    Args:
+        num_examples: The maximum number of examples to add/retrieve.
+    """
+    def __init__(self, num_examples: int):
+        self._pkey_dtype: pd.CategoricalDtype | None = None
+        self._indices: list[np.ndarray] = []
+        self._index_dtype: pd.CategoricalDtype | None = None
+        self._num_examples = num_examples
+
+    def add(self, pkey: pd.Series, batch: np.ndarray) -> None:
+        r"""Adds a set of ``(pkey, batch)`` pairs to the mapper.
+
+        Args:
+            pkey: The primary keys.
+            batch: The batch vector.
+        """
+        if self._pkey_dtype is not None:
+            category = np.concatenate([
+                self._pkey_dtype.categories.values,
+                pkey,
+            ], axis=0)
+            category = pd.unique(category)
+            self._pkey_dtype = pd.CategoricalDtype(category)
+        elif pd.api.types.is_string_dtype(pkey):
+            category = pd.unique(pkey)
+            self._pkey_dtype = pd.CategoricalDtype(category)
+
+        if self._pkey_dtype is not None:
+            index = pd.Categorical(pkey, dtype=self._pkey_dtype).codes
+            index = index.astype('int64')
+        else:
+            index = pkey.to_numpy()
+        index = self._num_examples * index + batch
+        self._indices.append(index)
+        self._index_dtype = None
+
+    def get(self, pkey: pd.Series, batch: np.ndarray) -> np.ndarray:
+        r"""Retrieves the node IDs for a set of ``(pkey, batch)`` pairs.
+
+        Returns ``-1`` for any pair not registered in the mapping.
+
+        Args:
+            pkey: The primary keys.
+            batch: The batch vector.
+        """
+        if len(self._indices) == 0:
+            return np.full(len(pkey), -1, dtype=np.int64)
+
+        if self._index_dtype is None:  # Lazy build index:
+            category = pd.unique(np.concatenate(self._indices))
+            self._index_dtype = pd.CategoricalDtype(category)
+
+        if self._pkey_dtype is not None:
+            index = pd.Categorical(pkey, dtype=self._pkey_dtype).codes
+            index = index.astype('int64')
+        else:
+            index = pkey.to_numpy()
+        index = self._num_examples * index + batch
+
+        out = pd.Categorical(index, dtype=self._index_dtype).codes
+        out = out.astype('int64')
+        return out

kumoai/experimental/rfm/base/sampler.py

@@ -13,7 +13,6 @@ from kumoapi.pquery.AST import Aggregation, ASTNode
 from kumoapi.rfm.context import EdgeLayout, Link, Subgraph, Table
 from kumoapi.typing import Stype
 
-from kumoai.experimental.rfm.base import SourceColumn
 from kumoai.utils import ProgressLogger
 
 if TYPE_CHECKING:
@@ -53,12 +52,24 @@ class Sampler(ABC):
         graph: 'Graph',
         verbose: bool | ProgressLogger = True,
     ) -> None:
+
         self._edge_types: list[tuple[str, str, str]] = []
         for edge in graph.edges:
             edge_type = (edge.src_table, edge.fkey, edge.dst_table)
             self._edge_types.append(edge_type)
             self._edge_types.append(Subgraph.rev_edge_type(edge_type))
 
+        # Source Table -> [(Foreign Key, Destination Table)]
+        self._foreign_key_dict: dict[str, list[tuple[str, str]]] = {}
+        # Destination Table -> [(Source Table, Foreign Key)]
+        self._rev_foreign_key_dict: dict[str, list[tuple[str, str]]] = {}
+        for table in graph.tables.values():
+            self._foreign_key_dict[table.name] = []
+            self._rev_foreign_key_dict[table.name] = []
+        for src_table, fkey, dst_table in graph.edges:
+            self._foreign_key_dict[src_table].append((fkey, dst_table))
+            self._rev_foreign_key_dict[dst_table].append((src_table, fkey))
+
         self._primary_key_dict: dict[str, str] = {
             table.name: table._primary_key
             for table in graph.tables.values()
@@ -88,10 +99,6 @@ class Sampler(ABC):
                     continue
                 self._table_stype_dict[table.name][column.name] = column.stype
 
-        self._source_table_dict: dict[str, dict[str, SourceColumn]] = {}
-        for table in graph.tables.values():
-            self._source_table_dict[table.name] = table._source_column_dict
-
         self._min_time_dict: dict[str, pd.Timestamp] = {}
         self._max_time_dict: dict[str, pd.Timestamp] = {}
 
@@ -102,6 +109,16 @@ class Sampler(ABC):
         r"""All available edge types in the graph."""
         return self._edge_types
 
+    @property
+    def foreign_key_dict(self) -> dict[str, list[tuple[str, str]]]:
+        r"""The foreign keys for all tables in the graph."""
+        return self._foreign_key_dict
+
+    @property
+    def rev_foreign_key_dict(self) -> dict[str, list[tuple[str, str]]]:
+        r"""The foreign key back references for all tables in the graph."""
+        return self._rev_foreign_key_dict
+
     @property
     def primary_key_dict(self) -> dict[str, str]:
         r"""All available primary keys in the graph."""
@@ -119,16 +136,11 @@ class Sampler(ABC):
 
     @property
     def table_stype_dict(self) -> dict[str, dict[str, Stype]]:
-        r"""The registered semantic types for all columns in all tables in
-        the graph.
+        r"""The registered semantic types for all feature columns in all tables
+        in the graph.
         """
         return self._table_stype_dict
 
-    @property
-    def source_table_dict(self) -> dict[str, dict[str, SourceColumn]]:
-        r"""Source column information for all tables in the graph."""
-        return self._source_table_dict
-
     def get_min_time(
         self,
         table_names: list[str] | None = None,
@@ -189,7 +201,7 @@ class Sampler(ABC):
             exclude_cols_dict: The columns to exclude from the subgraph.
         """
         # Exclude all columns that leak target information:
-        table_stype_dict: dict[str, dict[str, Stype]] = self._table_stype_dict
+        table_stype_dict: dict[str, dict[str, Stype]] = self.table_stype_dict
         if exclude_cols_dict is not None:
             table_stype_dict = copy.deepcopy(table_stype_dict)
             for table_name, exclude_cols in exclude_cols_dict.items():
@@ -237,11 +249,8 @@ class Sampler(ABC):
                 # Set end time to NaT for all values greater than anchor time:
                 assert table_name not in out.inverse_dict
                 ser = df[end_time_column]
-                if ser.dtype != 'datetime64[ns]':
-                    ser = ser.astype('datetime64[ns]')
                 mask = ser.astype(int).to_numpy() > out.anchor_time[batch]
-                ser.iloc[mask] = pd.NaT
-                df[end_time_column] = ser
+                df.loc[mask, end_time_column] = pd.NaT
 
             stype_dict = table_stype_dict[table_name]
             for column_name, stype in stype_dict.items():
@@ -286,7 +295,8 @@ class Sampler(ABC):
 
             # Store in compressed representation if more efficient:
             num_cols = subgraph.table_dict[edge_type[2]].num_rows
-            if col is not None and len(col) > num_cols + 1:
+            if (col is not None and len(col) > num_cols + 1
+                    and ((col[1:] - col[:-1]) >= 0).all()):
                 layout = EdgeLayout.CSC
                 colcount = np.bincount(col, minlength=num_cols)
                 col = np.empty(num_cols + 1, dtype=col.dtype)

kumoai/experimental/rfm/base/source.py

@@ -6,7 +6,7 @@ from kumoapi.typing import Dtype
 @dataclass
 class SourceColumn:
     name: str
-    dtype: Dtype
+    dtype: Dtype | None
     is_primary_key: bool
     is_unique_key: bool
     is_nullable: bool