kumoai 2.14.0.dev202512211732__cp313-cp313-win_amd64.whl → 2.14.0.dev202601081732__cp313-cp313-win_amd64.whl

kumoai/experimental/rfm/backend/sqlite/sampler.py

@@ -6,9 +6,9 @@ import numpy as np
 import pandas as pd
 import pyarrow as pa
 from kumoapi.pquery import ValidatedPredictiveQuery
-from kumoapi.typing import Stype
 
-from kumoai.experimental.rfm.base import SQLSampler
+from kumoai.experimental.rfm.backend.sqlite import SQLiteTable
+from kumoai.experimental.rfm.base import SQLSampler, Table
 from kumoai.experimental.rfm.pquery import PQueryPandasExecutor
 from kumoai.utils import ProgressLogger, quote_ident
 
@@ -25,22 +25,32 @@ class SQLiteSampler(SQLSampler):
     ) -> None:
         super().__init__(graph=graph, verbose=verbose)
 
+        for table in graph.tables.values():
+            assert isinstance(table, SQLiteTable)
+            self._connection = table._connection
+
         if optimize:
             with self._connection.cursor() as cursor:
                 cursor.execute("PRAGMA temp_store = MEMORY")
                 cursor.execute("PRAGMA cache_size = -2000000")  # 2 GB
 
-        # Collect database indices to speed-up sampling:
+        # Collect database indices for speeding sampling:
         index_dict: dict[str, set[tuple[str, ...]]] = defaultdict(set)
         for table_name, primary_key in self.primary_key_dict.items():
             source_table = self.source_table_dict[table_name]
-            if not source_table[primary_key].is_unique_key:
-                index_dict[table_name].add((primary_key, ))
+            if primary_key not in source_table:
+                continue  # No physical column.
+            if source_table[primary_key].is_unique_key:
+                continue
+            index_dict[table_name].add((primary_key, ))
         for src_table_name, foreign_key, _ in graph.edges:
             source_table = self.source_table_dict[src_table_name]
+            if foreign_key not in source_table:
+                continue  # No physical column.
             if source_table[foreign_key].is_unique_key:
-                pass
-            elif time_column := self.time_column_dict.get(src_table_name):
+                continue
+            time_column = self.time_column_dict.get(src_table_name)
+            if time_column is not None and time_column in source_table:
                 index_dict[src_table_name].add((foreign_key, time_column))
             else:
                 index_dict[src_table_name].add((foreign_key, ))
@@ -49,22 +59,22 @@ class SQLiteSampler(SQLSampler):
         with self._connection.cursor() as cursor:
             for table_name in list(index_dict.keys()):
                 indices = index_dict[table_name]
-                sql = f"PRAGMA index_list({self.fqn_dict[table_name]})"
+                source_name = self.source_name_dict[table_name]
+                sql = f"PRAGMA index_list({source_name})"
                 cursor.execute(sql)
                 for _, index_name, *_ in cursor.fetchall():
                     sql = f"PRAGMA index_info({quote_ident(index_name)})"
                     cursor.execute(sql)
-                    index = tuple(info[2] for info in sorted(
+                    # Fetch index information and sort by `seqno`:
+                    index_info = tuple(info[2] for info in sorted(
                         cursor.fetchall(), key=lambda x: x[0]))
-                    indices.discard(index)
+                    # Remove all indices in case primary index already exists:
+                    for index in list(indices):
+                        if index_info[0] == index[0]:
+                            indices.discard(index)
                 if len(indices) == 0:
                     del index_dict[table_name]
 
-        num = sum(len(indices) for indices in index_dict.values())
-        index_repr = '1 index' if num == 1 else f'{num} indices'
-        num = len(index_dict)
-        table_repr = '1 table' if num == 1 else f'{num} tables'
-
         if optimize and len(index_dict) > 0:
             if not isinstance(verbose, ProgressLogger):
                 verbose = ProgressLogger.default(
@@ -79,16 +89,27 @@ class SQLiteSampler(SQLSampler):
                         name = quote_ident(name)
                         columns = ', '.join(quote_ident(v) for v in index)
                         columns += ' DESC' if len(index) > 1 else ''
+                        source_name = self.source_name_dict[table_name]
                         sql = (f"CREATE INDEX IF NOT EXISTS {name}\n"
-                               f"ON {self.fqn_dict[table_name]}({columns})")
+                               f"ON {source_name}({columns})")
                         cursor.execute(sql)
-                self._connection.commit()
-                logger.log(f"Created {index_repr} in {table_repr}")
+                        self._connection.commit()
+                        if len(index) > 1:
+                            logger.log(f"Created index on {index} in table "
+                                       f"'{table_name}'")
+                        else:
+                            logger.log(f"Created index on '{index[0]}' in "
+                                       f"table '{table_name}'")
 
         elif len(index_dict) > 0:
+            num = sum(len(indices) for indices in index_dict.values())
+            index_repr = '1 index' if num == 1 else f'{num} indices'
+            num = len(index_dict)
+            table_repr = '1 table' if num == 1 else f'{num} tables'
             warnings.warn(f"Missing {index_repr} in {table_repr} for optimal "
                           f"database querying. For improving runtime, we "
-                          f"strongly suggest to create these indices by "
+                          f"strongly suggest to create indices for primary "
+                          f"and foreign keys, e.g., automatically by "
                           f"instantiating KumoRFM via "
                           f"`KumoRFM(graph, optimize=True)`.")
 
@@ -98,12 +119,13 @@ class SQLiteSampler(SQLSampler):
     ) -> dict[str, tuple[pd.Timestamp, pd.Timestamp]]:
         selects: list[str] = []
         for table_name in table_names:
-            time_column = self.time_column_dict[table_name]
+            column = self.time_column_dict[table_name]
+            column_ref = self.table_column_ref_dict[table_name][column]
             select = (f"SELECT\n"
                       f"  ? as table_name,\n"
-                      f"  MIN({quote_ident(time_column)}) as min_date,\n"
-                      f"  MAX({quote_ident(time_column)}) as max_date\n"
-                      f"FROM {self.fqn_dict[table_name]}")
+                      f"  MIN({column_ref}) as min_date,\n"
+                      f"  MAX({column_ref}) as max_date\n"
+                      f"FROM {self.source_name_dict[table_name]}")
             selects.append(select)
         sql = "\nUNION ALL\n".join(selects)
 
@@ -126,18 +148,28 @@ class SQLiteSampler(SQLSampler):
     ) -> pd.DataFrame:
         # NOTE SQLite does not natively support passing a `random_seed`.
 
+        source_table = self.source_table_dict[table_name]
         filters: list[str] = []
-        primary_key = self.primary_key_dict[table_name]
-        if self.source_table_dict[table_name][primary_key].is_nullable:
-            filters.append(f" {quote_ident(primary_key)} IS NOT NULL")
-        time_column = self.time_column_dict.get(table_name)
-        if (time_column is not None and
-                self.source_table_dict[table_name][time_column].is_nullable):
-            filters.append(f" {quote_ident(time_column)} IS NOT NULL")
+
+        key = self.primary_key_dict[table_name]
+        if key not in source_table or source_table[key].is_nullable:
+            key_ref = self.table_column_ref_dict[table_name][key]
+            filters.append(f" {key_ref} IS NOT NULL")
+
+        column = self.time_column_dict.get(table_name)
+        if column is None:
+            pass
+        elif column not in source_table or source_table[column].is_nullable:
+            column_ref = self.table_column_ref_dict[table_name][column]
+            filters.append(f" {column_ref} IS NOT NULL")
 
         # TODO Make this query more efficient - it does full table scan.
-        sql = (f"SELECT {', '.join(quote_ident(col) for col in columns)}\n"
-               f"FROM {self.fqn_dict[table_name]}")
+        projections = [
+            self.table_column_proj_dict[table_name][column]
+            for column in columns
+        ]
+        sql = (f"SELECT {', '.join(projections)}\n"
+               f"FROM {self.source_name_dict[table_name]}")
         if len(filters) > 0:
             sql += f"\nWHERE{' AND'.join(filters)}"
         sql += f"\nORDER BY RANDOM() LIMIT {num_rows}"
@@ -147,7 +179,11 @@ class SQLiteSampler(SQLSampler):
             cursor.execute(sql)
             table = cursor.fetch_arrow_table()
 
-        return self._sanitize(table_name, table)
+        return Table._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict=self.table_dtype_dict[table_name],
+            stype_dict=self.table_stype_dict[table_name],
+        )
 
     def _sample_target(
         self,
@@ -190,84 +226,163 @@ class SQLiteSampler(SQLSampler):
     def _by_pkey(
         self,
         table_name: str,
-        pkey: pd.Series,
+        index: pd.Series,
         columns: set[str],
     ) -> tuple[pd.DataFrame, np.ndarray]:
-        pkey_name = self.primary_key_dict[table_name]
+        source_table = self.source_table_dict[table_name]
+        key = self.primary_key_dict[table_name]
+        key_ref = self.table_column_ref_dict[table_name][key]
+        projections = [
+            self.table_column_proj_dict[table_name][column]
+            for column in columns
+        ]
+
+        tmp = pa.table([pa.array(index)], names=['__kumo_id__'])
+        tmp_name = f'tmp_{table_name}_{key}_{id(tmp)}'
+
+        sql = (f"SELECT "
+               f"tmp.rowid - 1 as __kumo_batch__, "
+               f"{', '.join(projections)}\n"
+               f"FROM {quote_ident(tmp_name)} tmp\n"
+               f"JOIN {self.source_name_dict[table_name]} ent\n")
+        if key in source_table and source_table[key].is_unique_key:
+            sql += (f"  ON {key_ref} = tmp.__kumo_id__")
+        else:
+            sql += (f"  ON ent.rowid = (\n"
+                    f"    SELECT rowid\n"
+                    f"    FROM {self.source_name_dict[table_name]}\n"
+                    f"    WHERE {key_ref} == tmp.__kumo_id__\n"
+                    f"    LIMIT 1\n"
+                    f")")
 
-        tmp = pa.table([pa.array(pkey)], names=['id'])
-        tmp_name = f'tmp_{table_name}_{pkey_name}_{id(tmp)}'
+        with self._connection.cursor() as cursor:
+            cursor.adbc_ingest(tmp_name, tmp, mode='replace')
+            cursor.execute(sql)
+            table = cursor.fetch_arrow_table()
 
-        if self.source_table_dict[table_name][pkey_name].is_unique_key:
-            sql = (f"SELECT tmp.rowid - 1 as __batch__, "
-                   f"{', '.join('ent.' + quote_ident(c) for c in columns)}\n"
-                   f"FROM {quote_ident(tmp_name)} tmp\n"
-                   f"JOIN {self.fqn_dict[table_name]} ent\n"
-                   f"  ON ent.{quote_ident(pkey_name)} = tmp.id")
-        else:
-            sql = (f"SELECT tmp.rowid - 1 as __batch__, "
-                   f"{', '.join('ent.' + quote_ident(c) for c in columns)}\n"
-                   f"FROM {quote_ident(tmp_name)} tmp\n"
-                   f"JOIN {self.fqn_dict[table_name]} ent\n"
-                   f"  ON ent.rowid = (\n"
-                   f"    SELECT rowid FROM {self.fqn_dict[table_name]}\n"
-                   f"    WHERE {quote_ident(pkey_name)} == tmp.id\n"
-                   f"    LIMIT 1\n"
-                   f")")
+        batch = table['__kumo_batch__'].to_numpy()
+        batch_index = table.schema.get_field_index('__kumo_batch__')
+        table = table.remove_column(batch_index)
+
+        return Table._sanitize(
+            df=table.to_pandas(),
+            dtype_dict=self.table_dtype_dict[table_name],
+            stype_dict=self.table_stype_dict[table_name],
+        ), batch
+
+    def _by_fkey(
+        self,
+        table_name: str,
+        foreign_key: str,
+        index: pd.Series,
+        num_neighbors: int,
+        anchor_time: pd.Series | None,
+        columns: set[str],
+    ) -> tuple[pd.DataFrame, np.ndarray]:
+        time_column = self.time_column_dict.get(table_name)
+
+        # NOTE SQLite does not have a native datetime format. Currently, we
+        # assume timestamps are given as `TEXT` in `ISO-8601 UTC`:
+        tmp = pa.table([pa.array(index)], names=['__kumo_id__'])
+        if time_column is not None and anchor_time is not None:
+            anchor_time = anchor_time.dt.strftime("%Y-%m-%d %H:%M:%S")
+            tmp = tmp.append_column('__kumo_time__', pa.array(anchor_time))
+        tmp_name = f'tmp_{table_name}_{foreign_key}_{id(tmp)}'
+
+        key_ref = self.table_column_ref_dict[table_name][foreign_key]
+        projections = [
+            self.table_column_proj_dict[table_name][column]
+            for column in columns
+        ]
+        sql = (f"SELECT "
+               f"tmp.rowid - 1 as __kumo_batch__, "
+               f"{', '.join(projections)}\n"
+               f"FROM {quote_ident(tmp_name)} tmp\n"
+               f"JOIN {self.source_name_dict[table_name]} fact\n"
+               f"ON fact.rowid IN (\n"
+               f"  SELECT rowid\n"
+               f"  FROM {self.source_name_dict[table_name]}\n"
+               f"  WHERE {key_ref} = tmp.__kumo_id__\n")
+        if time_column is not None and anchor_time is not None:
+            time_ref = self.table_column_ref_dict[table_name][time_column]
+            sql += f"  AND {time_ref} <= tmp.__kumo_time__\n"
+        if time_column is not None:
+            time_ref = self.table_column_ref_dict[table_name][time_column]
+            sql += f"  ORDER BY {time_ref} DESC\n"
+        sql += (f"  LIMIT {num_neighbors}\n"
+                f")")
 
         with self._connection.cursor() as cursor:
             cursor.adbc_ingest(tmp_name, tmp, mode='replace')
             cursor.execute(sql)
             table = cursor.fetch_arrow_table()
 
-        batch = table['__batch__'].to_numpy()
-        table = table.remove_column(table.schema.get_field_index('__batch__'))
+        batch = table['__kumo_batch__'].to_numpy()
+        batch_index = table.schema.get_field_index('__kumo_batch__')
+        table = table.remove_column(batch_index)
 
-        return table.to_pandas(), batch  # TODO Use `self._sanitize`.
+        return Table._sanitize(
+            df=table.to_pandas(),
+            dtype_dict=self.table_dtype_dict[table_name],
+            stype_dict=self.table_stype_dict[table_name],
+        ), batch
 
     # Helper Methods ##########################################################
 
     def _by_time(
         self,
         table_name: str,
-        fkey: str,
-        pkey: pd.Series,
+        foreign_key: str,
+        index: pd.Series,
         anchor_time: pd.Series,
         min_offset: pd.DateOffset | None,
         max_offset: pd.DateOffset,
         columns: set[str],
     ) -> tuple[pd.DataFrame, np.ndarray]:
+        time_column = self.time_column_dict[table_name]
+
         # NOTE SQLite does not have a native datetime format. Currently, we
         # assume timestamps are given as `TEXT` in `ISO-8601 UTC`:
-        tmp = pa.table([pa.array(pkey)], names=['id'])
+        tmp = pa.table([pa.array(index)], names=['__kumo_id__'])
         end_time = anchor_time + max_offset
         end_time = end_time.dt.strftime("%Y-%m-%d %H:%M:%S")
-        tmp = tmp.append_column('end', pa.array(end_time))
+        tmp = tmp.append_column('__kumo_end__', pa.array(end_time))
         if min_offset is not None:
             start_time = anchor_time + min_offset
             start_time = start_time.dt.strftime("%Y-%m-%d %H:%M:%S")
-            tmp = tmp.append_column('start', pa.array(start_time))
-        tmp_name = f'tmp_{table_name}_{fkey}_{id(tmp)}'
-
-        time_column = self.time_column_dict[table_name]
-        sql = (f"SELECT tmp.rowid - 1 as __batch__, "
-               f"{', '.join('fact.' + quote_ident(col) for col in columns)}\n"
+            tmp = tmp.append_column('__kumo_start__', pa.array(start_time))
+        tmp_name = f'tmp_{table_name}_{foreign_key}_{id(tmp)}'
+
+        key_ref = self.table_column_ref_dict[table_name][foreign_key]
+        time_ref = self.table_column_ref_dict[table_name][time_column]
+        projections = [
+            self.table_column_proj_dict[table_name][column]
+            for column in columns
+        ]
+        sql = (f"SELECT "
+               f"tmp.rowid - 1 as __kumo_batch__, "
+               f"{', '.join(projections)}\n"
                f"FROM {quote_ident(tmp_name)} tmp\n"
-               f"JOIN {self.fqn_dict[table_name]} fact\n"
-               f"  ON fact.{quote_ident(fkey)} = tmp.id\n"
-               f" AND fact.{quote_ident(time_column)} <= tmp.end")
+               f"JOIN {self.source_name_dict[table_name]}\n"
+               f"  ON {key_ref} = tmp.__kumo_id__\n"
+               f" AND {time_ref} <= tmp.__kumo_end__")
         if min_offset is not None:
-            sql += f"\n AND fact.{quote_ident(time_column)} > tmp.start"
+            sql += f"\n AND {time_ref} > tmp.__kumo_start__"
 
         with self._connection.cursor() as cursor:
             cursor.adbc_ingest(tmp_name, tmp, mode='replace')
             cursor.execute(sql)
             table = cursor.fetch_arrow_table()
 
-        batch = table['__batch__'].to_numpy()
-        table = table.remove_column(table.schema.get_field_index('__batch__'))
+        batch = table['__kumo_batch__'].to_numpy()
+        batch_index = table.schema.get_field_index('__kumo_batch__')
+        table = table.remove_column(batch_index)
 
-        return self._sanitize(table_name, table), batch
+        return Table._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict=self.table_dtype_dict[table_name],
+            stype_dict=self.table_stype_dict[table_name],
+        ), batch
 
     def _sample_target_set(
         self,
@@ -300,11 +415,11 @@ class SQLiteSampler(SQLSampler):
                 query.entity_table: np.arange(len(df)),
             }
             for edge_type, (_min, _max) in time_offset_dict.items():
-                table_name, fkey, _ = edge_type
+                table_name, foreign_key, _ = edge_type
                 feat_dict[table_name], batch_dict[table_name] = self._by_time(
                     table_name=table_name,
-                    fkey=fkey,
-                    pkey=df[self.primary_key_dict[query.entity_table]],
+                    foreign_key=foreign_key,
+                    index=df[self.primary_key_dict[query.entity_table]],
                     anchor_time=time,
                     min_offset=_min,
                     max_offset=_max,
@@ -337,13 +452,3 @@ class SQLiteSampler(SQLSampler):
             y = pd.concat(ys, axis=0, ignore_index=True)
 
         return y, mask
-
-    def _sanitize(self, table_name: str, table: pa.table) -> pd.DataFrame:
-        df = table.to_pandas(types_mapper=pd.ArrowDtype)
-
-        stype_dict = self.table_stype_dict[table_name]
-        for column_name in df.columns:
-            if stype_dict.get(column_name) == Stype.timestamp:
-                df[column_name] = pd.to_datetime(df[column_name])
-
-        return df

kumoai/experimental/rfm/backend/sqlite/table.py

@@ -1,5 +1,5 @@
 import re
-import warnings
+from collections import Counter
 from collections.abc import Sequence
 from typing import cast
 
@@ -9,27 +9,25 @@ from kumoapi.typing import Dtype
 
 from kumoai.experimental.rfm.backend.sqlite import Connection
 from kumoai.experimental.rfm.base import (
-    ColumnExpressionSpec,
-    ColumnExpressionType,
+    ColumnSpec,
+    ColumnSpecType,
     DataBackend,
     SourceColumn,
     SourceForeignKey,
-    SQLTable,
+    Table,
 )
-from kumoai.experimental.rfm.infer import infer_dtype
 from kumoai.utils import quote_ident
 
 
-class SQLiteTable(SQLTable):
+class SQLiteTable(Table):
     r"""A table backed by a :class:`sqlite` database.
 
     Args:
         connection: The connection to a :class:`sqlite` database.
-        name: The logical name of this table.
-        source_name: The physical name of this table in the database. If set to
-            ``None``, ``name`` is being used.
-        columns: The selected physical columns of this table.
-        column_expressions: The logical columns of this table.
+        name: The name of this table.
+        source_name: The source name of this table. If set to ``None``,
+            ``name`` is being used.
+        columns: The selected columns of this table.
         primary_key: The name of the primary key of this table, if it exists.
         time_column: The name of the time column of this table, if it exists.
         end_time_column: The name of the end time column of this table, if it
@@ -40,8 +38,7 @@ class SQLiteTable(SQLTable):
         connection: Connection,
         name: str,
         source_name: str | None = None,
-        columns: Sequence[str] | None = None,
-        column_expressions: Sequence[ColumnExpressionType] | None = None,
+        columns: Sequence[ColumnSpecType] | None = None,
         primary_key: MissingType | str | None = MissingType.VALUE,
         time_column: str | None = None,
         end_time_column: str | None = None,
@@ -53,7 +50,6 @@ class SQLiteTable(SQLTable):
             name=name,
             source_name=source_name,
             columns=columns,
-            column_expressions=column_expressions,
             primary_key=primary_key,
             time_column=time_column,
             end_time_column=end_time_column,
@@ -66,16 +62,16 @@ class SQLiteTable(SQLTable):
     def _get_source_columns(self) -> list[SourceColumn]:
         source_columns: list[SourceColumn] = []
         with self._connection.cursor() as cursor:
-            sql = f"PRAGMA table_info({self.fqn})"
+            sql = f"PRAGMA table_info({self._quoted_source_name})"
             cursor.execute(sql)
             columns = cursor.fetchall()
 
             if len(columns) == 0:
-                raise ValueError(f"Table '{self._source_name}' does not exist "
+                raise ValueError(f"Table '{self.source_name}' does not exist "
                                  f"in the SQLite database")
 
             unique_keys: set[str] = set()
-            sql = f"PRAGMA index_list({self.fqn})"
+            sql = f"PRAGMA index_list({self._quoted_source_name})"
             cursor.execute(sql)
             for _, index_name, is_unique, *_ in cursor.fetchall():
                 if bool(is_unique):
@@ -85,32 +81,19 @@ class SQLiteTable(SQLTable):
                     if len(index) == 1:
                         unique_keys.add(index[0][2])
 
-            for _, column, type, notnull, _, is_pkey in columns:
-                # Determine column affinity:
-                type = type.strip().upper()
-                if re.search('INT', type):
-                    dtype = Dtype.int
-                elif re.search('TEXT|CHAR|CLOB', type):
-                    dtype = Dtype.string
-                elif re.search('REAL|FLOA|DOUB', type):
-                    dtype = Dtype.float
-                else:  # NUMERIC affinity.
-                    ser = self._source_sample_df[column]
-                    try:
-                        dtype = infer_dtype(ser)
-                    except Exception:
-                        warnings.warn(f"Encountered unsupported data type "
-                                      f"'{ser.dtype}' with source data type "
-                                      f"'{type}' for column '{column}' in "
-                                      f"table '{self.name}'. If possible, "
-                                      f"change the data type of the column in "
-                                      f"your SQLite database to use it within "
-                                      f"this table.")
-                        continue
+            # Special SQLite case that creates a rowid alias for
+            # `INTEGER PRIMARY KEY` annotated columns:
+            rowid_candidates = [
+                column for _, column, dtype, _, _, is_pkey in columns
+                if bool(is_pkey) and dtype.strip().upper() == 'INTEGER'
+            ]
+            if len(rowid_candidates) == 1:
+                unique_keys.add(rowid_candidates[0])
 
+            for _, column, dtype, notnull, _, is_pkey in columns:
                 source_column = SourceColumn(
                     name=column,
-                    dtype=dtype,
+                    dtype=self._to_dtype(dtype),
                     is_primary_key=bool(is_pkey),
                     is_unique_key=column in unique_keys,
                     is_nullable=not bool(is_pkey) and not bool(notnull),
@@ -120,35 +103,82 @@ class SQLiteTable(SQLTable):
         return source_columns
 
     def _get_source_foreign_keys(self) -> list[SourceForeignKey]:
-        source_fkeys: list[SourceForeignKey] = []
+        source_foreign_keys: list[SourceForeignKey] = []
         with self._connection.cursor() as cursor:
-            sql = f"PRAGMA foreign_key_list({self.fqn})"
+            sql = f"PRAGMA foreign_key_list({self._quoted_source_name})"
             cursor.execute(sql)
-            for _, _, dst_table, fkey, pkey, *_ in cursor.fetchall():
-                source_fkeys.append(SourceForeignKey(fkey, dst_table, pkey))
-        return source_fkeys
+            rows = cursor.fetchall()
+            counts = Counter(row[0] for row in rows)
+            for idx, _, dst_table, foreign_key, primary_key, *_ in rows:
+                if counts[idx] == 1:
+                    source_foreign_key = SourceForeignKey(
+                        name=foreign_key,
+                        dst_table=dst_table,
+                        primary_key=primary_key,
+                    )
+                    source_foreign_keys.append(source_foreign_key)
+        return source_foreign_keys
 
     def _get_source_sample_df(self) -> pd.DataFrame:
         with self._connection.cursor() as cursor:
-            sql = (f"SELECT * FROM {self.fqn} "
-                   f"ORDER BY rowid LIMIT 1000")
+            columns = [quote_ident(col) for col in self._source_column_dict]
+            sql = (f"SELECT {', '.join(columns)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"ORDER BY rowid "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
             cursor.execute(sql)
             table = cursor.fetch_arrow_table()
-            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+        if len(table) == 0:
+            raise RuntimeError(f"Table '{self.source_name}' is empty")
+
+        return self._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict={
+                column.name: column.dtype
+                for column in self._source_column_dict.values()
+            },
+            stype_dict=None,
+        )
 
     def _get_num_rows(self) -> int | None:
         return None
 
-    def _get_expression_sample_df(
+    def _get_expr_sample_df(
         self,
-        specs: Sequence[ColumnExpressionSpec],
+        columns: Sequence[ColumnSpec],
     ) -> pd.DataFrame:
         with self._connection.cursor() as cursor:
-            columns = [
-                f"{spec.expr} AS {quote_ident(spec.name)}" for spec in specs
+            projections = [
+                f"{column.expr} AS {quote_ident(column.name)}"
+                for column in columns
             ]
-            sql = (f"SELECT {', '.join(columns)} FROM {self.fqn} "
-                   f"ORDER BY rowid LIMIT 1000")
+            sql = (f"SELECT {', '.join(projections)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"ORDER BY rowid "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
             cursor.execute(sql)
             table = cursor.fetch_arrow_table()
-            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+        if len(table) == 0:
+            raise RuntimeError(f"Table '{self.source_name}' is empty")
+
+        return self._sanitize(
+            df=table.to_pandas(types_mapper=pd.ArrowDtype),
+            dtype_dict={column.name: column.dtype
+                        for column in columns},
+            stype_dict=None,
+        )
+
+    @staticmethod
+    def _to_dtype(dtype: str | None) -> Dtype | None:
+        if dtype is None:
+            return None
+        dtype = dtype.strip().upper()
+        if re.search('INT', dtype):
+            return Dtype.int
+        if re.search('TEXT|CHAR|CLOB', dtype):
+            return Dtype.string
+        if re.search('REAL|FLOA|DOUB', dtype):
+            return Dtype.float
+        return None  # NUMERIC affinity.

kumoai/experimental/rfm/base/__init__.py

@@ -8,12 +8,9 @@ class DataBackend(StrEnum):
 
 
 from .source import SourceColumn, SourceForeignKey  # noqa: E402
-from .column import Column  # noqa: E402
-from .column_expression import ColumnExpressionSpec  # noqa: E402
-from .column_expression import ColumnExpressionType  # noqa: E402
-from .column_expression import ColumnExpression  # noqa: E402
+from .expression import Expression, LocalExpression  # noqa: E402
+from .column import ColumnSpec, ColumnSpecType, Column  # noqa: E402
 from .table import Table  # noqa: E402
-from .sql_table import SQLTable  # noqa: E402
 from .sampler import SamplerOutput, Sampler  # noqa: E402
 from .sql_sampler import SQLSampler  # noqa: E402
 
@@ -21,12 +18,12 @@ __all__ = [
     'DataBackend',
     'SourceColumn',
     'SourceForeignKey',
+    'Expression',
+    'LocalExpression',
+    'ColumnSpec',
+    'ColumnSpecType',
     'Column',
-    'ColumnExpressionSpec',
-    'ColumnExpressionType',
-    'ColumnExpression',
     'Table',
-    'SQLTable',
     'SamplerOutput',
     'Sampler',
     'SQLSampler',