kumoai 2.13.0.dev202512031731__cp312-cp312-macosx_11_0_arm64.whl → 2.14.0.dev202512301731__cp312-cp312-macosx_11_0_arm64.whl

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

@@ -1,11 +1,22 @@
 import re
-from typing import List, Optional, Sequence
+from collections import Counter
+from collections.abc import Sequence
+from typing import cast
 
 import pandas as pd
+from kumoapi.model_plan import MissingType
 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.backend.snow import Connection
+from kumoai.experimental.rfm.base import (
+    ColumnSpec,
+    ColumnSpecType,
+    DataBackend,
+    SourceColumn,
+    SourceForeignKey,
+    Table,
+)
+from kumoai.utils import quote_ident
 
 
 class SnowTable(Table):
@@ -14,6 +25,10 @@ class SnowTable(Table):
     Args:
         connection: The connection to a :class:`snowflake` database.
         name: The name of this table.
+        source_name: The source name of this table. If set to ``None``,
+            ``name`` is being used.
+        database: The database.
+        schema: The schema.
         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.
@@ -24,72 +39,204 @@ class SnowTable(Table):
         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,
+        source_name: str | None = None,
+        database: str | None = None,
+        schema: str | 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,
     ) -> None:
 
+        if database is None or schema is None:
+            with connection.cursor() as cursor:
+                cursor.execute("SELECT CURRENT_DATABASE(), CURRENT_SCHEMA()")
+                result = cursor.fetchone()
+                database = database or result[0]
+                assert database is not None
+                schema = schema or result[1]
+
+        if schema is None:
+            raise ValueError(f"Unspecified 'schema' for table "
+                             f"'{source_name or name}' in database "
+                             f"'{database}'")
+
         self._connection = connection
+        self._database = database
+        self._schema = schema
 
         super().__init__(
             name=name,
+            source_name=source_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] = []
+    @property
+    def source_name(self) -> str:
+        names: list[str] = []
+        if self._database is not None:
+            names.append(self._database)
+        if self._schema is not None:
+            names.append(self._schema)
+        return '.'.join(names + [self._source_name])
+
+    @property
+    def _quoted_source_name(self) -> str:
+        names: list[str] = []
+        if self._database is not None:
+            names.append(quote_ident(self._database))
+        if self._schema is not None:
+            names.append(quote_ident(self._schema))
+        return '.'.join(names + [quote_ident(self._source_name)])
+
+    @property
+    def backend(self) -> DataBackend:
+        return cast(DataBackend, DataBackend.SNOWFLAKE)
+
+    def _get_source_columns(self) -> list[SourceColumn]:
+        source_columns: list[SourceColumn] = []
         with self._connection.cursor() as cursor:
             try:
-                cursor.execute(f"DESCRIBE TABLE {self.name}")
+                sql = f"DESCRIBE TABLE {self._quoted_source_name}"
+                cursor.execute(sql)
             except Exception as e:
-                raise ValueError(f"Table '{self.name}' does not exist") from e
+                raise ValueError(f"Table '{self.source_name}' does not exist "
+                                 f"in the remote data backend") from e
 
             for row in cursor.fetchall():
-                column, type, _, _, _, is_pkey, is_unique = row[:7]
-
-                type = type.strip().upper()
-                if type.startswith('NUMBER'):
-                    dtype = Dtype.int
-                elif type.startswith('VARCHAR'):
-                    dtype = Dtype.string
-                elif type == 'FLOAT':
-                    dtype = Dtype.float
-                elif type == 'BOOLEAN':
-                    dtype = Dtype.bool
-                elif re.search('DATE|TIMESTAMP', type):
-                    dtype = Dtype.date
-                else:
-                    continue
+                column, dtype, _, null, _, is_pkey, is_unique, *_ = row
 
                 source_column = SourceColumn(
                     name=column,
-                    dtype=dtype,
+                    dtype=self._to_dtype(dtype),
                     is_primary_key=is_pkey.strip().upper() == 'Y',
                     is_unique_key=is_unique.strip().upper() == 'Y',
+                    is_nullable=null.strip().upper() == 'Y',
                 )
                 source_columns.append(source_column)
 
         return source_columns
 
-    def _get_source_foreign_keys(self) -> List[SourceForeignKey]:
-        source_fkeys: List[SourceForeignKey] = []
+    def _get_source_foreign_keys(self) -> list[SourceForeignKey]:
+        source_foreign_keys: list[SourceForeignKey] = []
         with self._connection.cursor() as cursor:
-            cursor.execute(f"SHOW IMPORTED KEYS IN TABLE {self.name}")
-            for row in cursor.fetchall():
-                _, _, _, dst_table, pkey, _, _, _, fkey = row[:9]
-                source_fkeys.append(SourceForeignKey(fkey, dst_table, pkey))
-        return source_fkeys
+            sql = f"SHOW IMPORTED KEYS IN TABLE {self._quoted_source_name}"
+            cursor.execute(sql)
+            rows = cursor.fetchall()
+            counts = Counter(row[13] for row in rows)
+            for row in rows:
+                if counts[row[13]] == 1:
+                    source_foreign_key = SourceForeignKey(
+                        name=row[8],
+                        dst_table=f'{row[1]}.{row[2]}.{row[3]}',
+                        primary_key=row[4],
+                    )
+                    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:
+            columns = [quote_ident(col) for col in self._source_column_dict]
+            sql = (f"SELECT {', '.join(columns)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
+            cursor.execute(sql)
+            table = cursor.fetch_arrow_all()
 
-    def _get_sample_df(self) -> pd.DataFrame:
+        if table is None:
+            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_expr_sample_df(
+        self,
+        columns: Sequence[ColumnSpec],
+    ) -> pd.DataFrame:
         with self._connection.cursor() as cursor:
-            columns = ', '.join(self._source_column_dict.keys())
-            cursor.execute(f"SELECT {columns} FROM {self.name} LIMIT 1000")
+            projections = [
+                f"{column.expr} AS {quote_ident(column.name)}"
+                for column in columns
+            ]
+            sql = (f"SELECT {', '.join(projections)} "
+                   f"FROM {self._quoted_source_name} "
+                   f"LIMIT {self._NUM_SAMPLE_ROWS}")
+            cursor.execute(sql)
             table = cursor.fetch_arrow_all()
-            return table.to_pandas()
 
-    def _get_num_rows(self) -> Optional[int]:
+        if table is None:
+            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 dtype.startswith('NUMBER'):
+            try:  # Parse `scale` from 'NUMBER(precision, scale)':
+                scale = int(dtype.split(',')[-1].split(')')[0])
+                return Dtype.int if scale == 0 else Dtype.float
+            except Exception:
+                return Dtype.float
+        if dtype == 'FLOAT':
+            return Dtype.float
+        if dtype.startswith('VARCHAR'):
+            return Dtype.string
+        if dtype.startswith('BINARY'):
+            return Dtype.binary
+        if dtype == 'BOOLEAN':
+            return Dtype.bool
+        if dtype.startswith('DATE') or dtype.startswith('TIMESTAMP'):
+            return Dtype.date
+        if dtype.startswith('TIME'):
+            return Dtype.time
+        if dtype.startswith('VECTOR'):
+            try:  # Parse element data type from 'VECTOR(dtype, dimension)':
+                dtype = dtype.split(',')[0].split('(')[1].strip()
+                if dtype == 'INT':
+                    return Dtype.intlist
+                elif dtype == 'FLOAT':
+                    return Dtype.floatlist
+            except Exception:
+                pass
+            return Dtype.unsupported
+        if dtype.startswith('ARRAY'):
+            try:  # Parse element data type from 'ARRAY(dtype)':
+                dtype = dtype.split('(', maxsplit=1)[1]
+                dtype = dtype.rsplit(')', maxsplit=1)[0]
+                _dtype = SnowTable._to_dtype(dtype)
+                if _dtype is not None and _dtype.is_int():
+                    return Dtype.intlist
+                elif _dtype is not None and _dtype.is_float():
+                    return Dtype.floatlist
+                elif _dtype is not None and _dtype.is_string():
+                    return Dtype.stringlist
+            except Exception:
+                pass
+            return Dtype.unsupported
+        # Unsupported data types:
+        if re.search(
+                'DECFLOAT|VARIANT|OBJECT|MAP|FILE|GEOGRAPHY|GEOMETRY',
+                dtype,
+        ):
+            return Dtype.unsupported
         return None

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

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Any, TypeAlias, Union
+from typing import Any, TypeAlias
 
 try:
     import adbc_driver_sqlite.dbapi as adbc
@@ -11,7 +11,7 @@ except ImportError:
 Connection: TypeAlias = adbc.AdbcSqliteConnection
 
 
-def connect(uri: Union[str, Path, None] = None, **kwargs: Any) -> Connection:
+def connect(uri: str | Path | None = None, **kwargs: Any) -> Connection:
     r"""Opens a connection to a :class:`sqlite` database.
 
     uri: The path to the database file to be opened.
@@ -22,9 +22,11 @@ def connect(uri: Union[str, Path, None] = None, **kwargs: Any) -> Connection:
 
 
 from .table import SQLiteTable  # noqa: E402
+from .sampler import SQLiteSampler  # noqa: E402
 
 __all__ = [
     'connect',
     'Connection',
     'SQLiteTable',
+    'SQLiteSampler',
 ]