kumoai 2.14.0.dev202601011731__cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

kumoai/experimental/rfm/base/source.py

@@ -0,0 +1,19 @@
+from dataclasses import dataclass
+
+from kumoapi.typing import Dtype
+
+
+@dataclass
+class SourceColumn:
+    name: str
+    dtype: Dtype | None
+    is_primary_key: bool
+    is_unique_key: bool
+    is_nullable: bool
+
+
+@dataclass
+class SourceForeignKey:
+    name: str
+    dst_table: str
+    primary_key: str

kumoai/experimental/rfm/base/sql_sampler.py

@@ -0,0 +1,143 @@
+from abc import abstractmethod
+from typing import TYPE_CHECKING, Literal
+
+import numpy as np
+import pandas as pd
+from kumoapi.typing import Dtype
+
+from kumoai.experimental.rfm.base import (
+    LocalExpression,
+    Sampler,
+    SamplerOutput,
+    SourceColumn,
+)
+from kumoai.utils import ProgressLogger, quote_ident
+
+if TYPE_CHECKING:
+    from kumoai.experimental.rfm import Graph
+
+
+class SQLSampler(Sampler):
+    def __init__(
+        self,
+        graph: 'Graph',
+        verbose: bool | ProgressLogger = True,
+    ) -> None:
+        super().__init__(graph=graph, verbose=verbose)
+
+        self._source_name_dict: dict[str, str] = {
+            table.name: table._quoted_source_name
+            for table in graph.tables.values()
+        }
+
+        self._source_table_dict: dict[str, dict[str, SourceColumn]] = {}
+        for table in graph.tables.values():
+            self._source_table_dict[table.name] = {}
+            for column in table.columns:
+                if not column.is_source:
+                    continue
+                src_column = table._source_column_dict[column.name]
+                self._source_table_dict[table.name][column.name] = src_column
+
+        self._table_dtype_dict: dict[str, dict[str, Dtype]] = {}
+        for table in graph.tables.values():
+            self._table_dtype_dict[table.name] = {}
+            for column in table.columns:
+                self._table_dtype_dict[table.name][column.name] = column.dtype
+
+        self._table_column_ref_dict: dict[str, dict[str, str]] = {}
+        self._table_column_proj_dict: dict[str, dict[str, str]] = {}
+        for table in graph.tables.values():
+            column_ref_dict: dict[str, str] = {}
+            column_proj_dict: dict[str, str] = {}
+            for column in table.columns:
+                if column.expr is not None:
+                    assert isinstance(column.expr, LocalExpression)
+                    column_ref_dict[column.name] = column.expr.value
+                    column_proj_dict[column.name] = (
+                        f'{column.expr} AS {quote_ident(column.name)}')
+                else:
+                    column_ref_dict[column.name] = quote_ident(column.name)
+                    column_proj_dict[column.name] = quote_ident(column.name)
+            self._table_column_ref_dict[table.name] = column_ref_dict
+            self._table_column_proj_dict[table.name] = column_proj_dict
+
+    @property
+    def source_name_dict(self) -> dict[str, str]:
+        r"""The source table names for all tables in the graph."""
+        return self._source_name_dict
+
+    @property
+    def source_table_dict(self) -> dict[str, dict[str, SourceColumn]]:
+        r"""The source column information for all tables in the graph."""
+        return self._source_table_dict
+
+    @property
+    def table_dtype_dict(self) -> dict[str, dict[str, Dtype]]:
+        r"""The data types for all columns in all tables in the graph."""
+        return self._table_dtype_dict
+
+    @property
+    def table_column_ref_dict(self) -> dict[str, dict[str, str]]:
+        r"""The SQL reference expression for all columns in all tables in the
+        graph.
+        """
+        return self._table_column_ref_dict
+
+    @property
+    def table_column_proj_dict(self) -> dict[str, dict[str, str]]:
+        r"""The SQL projection expressions for all columns in all tables in the
+        graph.
+        """
+        return self._table_column_proj_dict
+
+    def _sample_subgraph(
+        self,
+        entity_table_name: str,
+        entity_pkey: pd.Series,
+        anchor_time: pd.Series | Literal['entity'],
+        columns_dict: dict[str, set[str]],
+        num_neighbors: list[int],
+    ) -> SamplerOutput:
+
+        df, batch = self._by_pkey(
+            table_name=entity_table_name,
+            pkey=entity_pkey,
+            columns=columns_dict[entity_table_name],
+        )
+        if len(batch) != len(entity_pkey):
+            mask = np.ones(len(entity_pkey), dtype=bool)
+            mask[batch] = False
+            raise KeyError(f"The primary keys "
+                           f"{entity_pkey.iloc[mask].tolist()} do not exist "
+                           f"in the '{entity_table_name}' table")
+
+        perm = batch.argsort()
+        batch = batch[perm]
+        df = df.iloc[perm].reset_index(drop=True)
+
+        if not isinstance(anchor_time, pd.Series):
+            time_column = self.time_column_dict[entity_table_name]
+            anchor_time = df[time_column]
+
+        return SamplerOutput(
+            anchor_time=anchor_time.astype(int).to_numpy(),
+            df_dict={entity_table_name: df},
+            inverse_dict={},
+            batch_dict={entity_table_name: batch},
+            num_sampled_nodes_dict={entity_table_name: [len(batch)]},
+            row_dict={},
+            col_dict={},
+            num_sampled_edges_dict={},
+        )
+
+    # Abstract Methods ########################################################
+
+    @abstractmethod
+    def _by_pkey(
+        self,
+        table_name: str,
+        pkey: pd.Series,
+        columns: set[str],
+    ) -> tuple[pd.DataFrame, np.ndarray]:
+        pass