kumoai 2.13.0.dev202511271731__cp312-cp312-win_amd64.whl → 2.14.0.dev202512111731__cp312-cp312-win_amd64.whl

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

@@ -0,0 +1,101 @@
+import re
+import warnings
+from typing import List, Optional, Sequence
+
+import pandas as pd
+from kumoapi.typing import Dtype
+
+from kumoai.experimental.rfm.backend.sqlite import Connection
+from kumoai.experimental.rfm.base import SourceColumn, SourceForeignKey, Table
+from kumoai.experimental.rfm.infer import infer_dtype
+
+
+class SQLiteTable(Table):
+    r"""A table backed by a :class:`sqlite` database.
+
+    Args:
+        connection: The connection to a :class:`sqlite` database.
+        name: The name of this table.
+        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
+            exists.
+    """
+    def __init__(
+        self,
+        connection: Connection,
+        name: str,
+        columns: Optional[Sequence[str]] = None,
+        primary_key: Optional[str] = None,
+        time_column: Optional[str] = None,
+        end_time_column: Optional[str] = None,
+    ) -> None:
+
+        self._connection = connection
+
+        super().__init__(
+            name=name,
+            columns=columns,
+            primary_key=primary_key,
+            time_column=time_column,
+            end_time_column=end_time_column,
+        )
+
+    def _get_source_columns(self) -> List[SourceColumn]:
+        source_columns: List[SourceColumn] = []
+        with self._connection.cursor() as cursor:
+            cursor.execute(f"PRAGMA table_info({self.name})")
+            rows = cursor.fetchall()
+
+            if len(rows) == 0:
+                raise ValueError(f"Table '{self.name}' does not exist")
+
+            for _, column, type, _, _, is_pkey in rows:
+                # 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._sample_df[column]
+                    try:
+                        dtype = infer_dtype(ser)
+                    except Exception:
+                        warnings.warn(
+                            f"Data type inference for column '{column}' in "
+                            f"table '{self.name}' failed. Consider changing "
+                            f"the data type of the column to use it within "
+                            f"this table.")
+                        continue
+
+                source_column = SourceColumn(
+                    name=column,
+                    dtype=dtype,
+                    is_primary_key=bool(is_pkey),
+                    is_unique_key=False,
+                )
+                source_columns.append(source_column)
+
+        return source_columns
+
+    def _get_source_foreign_keys(self) -> List[SourceForeignKey]:
+        source_fkeys: List[SourceForeignKey] = []
+        with self._connection.cursor() as cursor:
+            cursor.execute(f"PRAGMA foreign_key_list({self.name})")
+            for _, _, dst_table, fkey, pkey, _, _, _ in cursor.fetchall():
+                source_fkeys.append(SourceForeignKey(fkey, dst_table, pkey))
+        return source_fkeys
+
+    def _get_sample_df(self) -> pd.DataFrame:
+        with self._connection.cursor() as cursor:
+            cursor.execute(f"SELECT * FROM {self.name} "
+                           f"ORDER BY rowid LIMIT 1000")
+            table = cursor.fetch_arrow_table()
+            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+    def _get_num_rows(self) -> Optional[int]:
+        return None

kumoai/experimental/rfm/base/__init__.py

@@ -0,0 +1,13 @@
+from .source import SourceColumn, SourceForeignKey
+from .column import Column
+from .table import Table
+from .sampler import SamplerOutput, Sampler
+
+__all__ = [
+    'SourceColumn',
+    'SourceForeignKey',
+    'Column',
+    'Table',
+    'SamplerOutput',
+    'Sampler',
+]

kumoai/experimental/rfm/base/column.py

@@ -0,0 +1,66 @@
+from dataclasses import dataclass
+from typing import Any
+
+from kumoapi.typing import Dtype, Stype
+
+
+@dataclass(init=False, repr=False, eq=False)
+class Column:
+    stype: Stype
+
+    def __init__(
+        self,
+        name: str,
+        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._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.stype = Stype(stype)
+
+    @property
+    def name(self) -> str:
+        return self._name
+
+    @property
+    def dtype(self) -> Dtype:
+        return self._dtype
+
+    def __setattr__(self, key: str, val: Any) -> None:
+        if key == 'stype':
+            if isinstance(val, str):
+                val = Stype(val)
+            assert isinstance(val, Stype)
+            if not val.supports_dtype(self.dtype):
+                raise ValueError(f"Column '{self.name}' received an "
+                                 f"incompatible semantic type (got "
+                                 f"dtype='{self.dtype}' and stype='{val}')")
+            if self._is_primary_key and val != Stype.ID:
+                raise ValueError(f"Primary key '{self.name}' must have 'ID' "
+                                 f"semantic type (got '{val}')")
+            if self._is_time_column and val != Stype.timestamp:
+                raise ValueError(f"Time column '{self.name}' must have "
+                                 f"'timestamp' semantic type (got '{val}')")
+            if self._is_end_time_column and val != Stype.timestamp:
+                raise ValueError(f"End time column '{self.name}' must have "
+                                 f"'timestamp' semantic type (got '{val}')")
+
+        super().__setattr__(key, val)
+
+    def __hash__(self) -> int:
+        return hash((self.name, self.stype, self.dtype))
+
+    def __eq__(self, other: Any) -> bool:
+        if not isinstance(other, Column):
+            return False
+        return hash(self) == hash(other)
+
+    def __repr__(self) -> str:
+        return (f'{self.__class__.__name__}(name={self.name}, '
+                f'stype={self.stype}, dtype={self.dtype})')