kumoai 2.13.0.dev202512091732__cp311-cp311-macosx_11_0_arm64.whl → 2.14.0.dev202601051732__cp311-cp311-macosx_11_0_arm64.whl

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

@@ -0,0 +1,297 @@
+import json
+from collections.abc import Iterator
+from contextlib import contextmanager
+from typing import TYPE_CHECKING
+
+import numpy as np
+import pandas as pd
+import pyarrow as pa
+from kumoapi.pquery import ValidatedPredictiveQuery
+
+from kumoai.experimental.rfm.backend.snow import Connection, SnowTable
+from kumoai.experimental.rfm.base import SQLSampler, Table
+from kumoai.experimental.rfm.pquery import PQueryPandasExecutor
+from kumoai.utils import ProgressLogger
+
+if TYPE_CHECKING:
+    from kumoai.experimental.rfm import Graph
+
+
+@contextmanager
+def paramstyle(connection: Connection, style: str = 'qmark') -> Iterator[None]:
+    _style = connection._paramstyle
+    connection._paramstyle = style
+    yield
+    connection._paramstyle = _style
+
+
+class SnowSampler(SQLSampler):
+    def __init__(
+        self,
+        graph: 'Graph',
+        verbose: bool | ProgressLogger = True,
+    ) -> None:
+        super().__init__(graph=graph, verbose=verbose)
+
+        for table in graph.tables.values():
+            assert isinstance(table, SnowTable)
+            self._connection = table._connection
+
+    def _get_min_max_time_dict(
+        self,
+        table_names: list[str],
+    ) -> dict[str, tuple[pd.Timestamp, pd.Timestamp]]:
+        selects: list[str] = []
+        for table_name in table_names:
+            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({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)
+
+        out_dict: dict[str, tuple[pd.Timestamp, pd.Timestamp]] = {}
+        with paramstyle(self._connection), self._connection.cursor() as cursor:
+            cursor.execute(sql, table_names)
+            rows = cursor.fetchall()
+        for table_name, _min, _max in rows:
+            out_dict[table_name] = (
+                pd.Timestamp.max if _min is None else pd.Timestamp(_min),
+                pd.Timestamp.min if _max is None else pd.Timestamp(_max),
+            )
+
+        return out_dict
+
+    def _sample_entity_table(
+        self,
+        table_name: str,
+        columns: set[str],
+        num_rows: int,
+        random_seed: int | None = None,
+    ) -> pd.DataFrame:
+        # NOTE Snowflake does support `SEED` only as part of `SYSTEM` sampling.
+        num_rows = min(num_rows, 1_000_000)  # Snowflake's upper limit.
+
+        source_table = self.source_table_dict[table_name]
+        filters: list[str] = []
+
+        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")
+
+        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]}\n"
+               f"SAMPLE ROW ({num_rows} ROWS)")
+        if len(filters) > 0:
+            sql += f"\nWHERE{' AND'.join(filters)}"
+
+        with self._connection.cursor() as cursor:
+            # NOTE This may return duplicate primary keys. This is okay.
+            cursor.execute(sql)
+            table = cursor.fetch_arrow_all()
+
+        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,
+        query: ValidatedPredictiveQuery,
+        entity_df: pd.DataFrame,
+        train_index: np.ndarray,
+        train_time: pd.Series,
+        num_train_examples: int,
+        test_index: np.ndarray,
+        test_time: pd.Series,
+        num_test_examples: int,
+        columns_dict: dict[str, set[str]],
+        time_offset_dict: dict[
+            tuple[str, str, str],
+            tuple[pd.DateOffset | None, pd.DateOffset],
+        ],
+    ) -> tuple[pd.Series, np.ndarray, pd.Series, np.ndarray]:
+
+        # NOTE For Snowflake, we execute everything at once to pay minimal
+        # query initialization costs.
+        index = np.concatenate([train_index, test_index])
+        time = pd.concat([train_time, test_time], axis=0, ignore_index=True)
+
+        entity_df = entity_df.iloc[index].reset_index(drop=True)
+
+        feat_dict: dict[str, pd.DataFrame] = {query.entity_table: entity_df}
+        time_dict: dict[str, pd.Series] = {}
+        time_column = self.time_column_dict.get(query.entity_table)
+        if time_column in columns_dict[query.entity_table]:
+            time_dict[query.entity_table] = entity_df[time_column]
+        batch_dict: dict[str, np.ndarray] = {
+            query.entity_table: np.arange(len(entity_df)),
+        }
+        for edge_type, (min_offset, max_offset) in time_offset_dict.items():
+            table_name, fkey, _ = edge_type
+            feat_dict[table_name], batch_dict[table_name] = self._by_time(
+                table_name=table_name,
+                fkey=fkey,
+                pkey=entity_df[self.primary_key_dict[query.entity_table]],
+                anchor_time=time,
+                min_offset=min_offset,
+                max_offset=max_offset,
+                columns=columns_dict[table_name],
+            )
+            time_column = self.time_column_dict.get(table_name)
+            if time_column in columns_dict[table_name]:
+                time_dict[table_name] = feat_dict[table_name][time_column]
+
+        y, mask = PQueryPandasExecutor().execute(
+            query=query,
+            feat_dict=feat_dict,
+            time_dict=time_dict,
+            batch_dict=batch_dict,
+            anchor_time=time,
+            num_forecasts=query.num_forecasts,
+        )
+
+        train_mask = mask[:len(train_index)]
+        test_mask = mask[len(train_index):]
+
+        boundary = int(train_mask.sum())
+        train_y = y.iloc[:boundary]
+        test_y = y.iloc[boundary:].reset_index(drop=True)
+
+        return train_y, train_mask, test_y, test_mask
+
+    def _by_pkey(
+        self,
+        table_name: str,
+        pkey: pd.Series,
+        columns: set[str],
+    ) -> tuple[pd.DataFrame, np.ndarray]:
+        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
+        ]
+
+        payload = json.dumps(list(pkey))
+
+        sql = ("WITH TMP as (\n"
+               "  SELECT\n"
+               "    f.index as __KUMO_BATCH__,\n")
+        if self.table_dtype_dict[table_name][key].is_int():
+            sql += "    f.value::NUMBER as __KUMO_ID__\n"
+        elif self.table_dtype_dict[table_name][key].is_float():
+            sql += "    f.value::FLOAT as __KUMO_ID__\n"
+        else:
+            sql += "    f.value::VARCHAR as __KUMO_ID__\n"
+        sql += (f"  FROM TABLE(FLATTEN(INPUT => PARSE_JSON(?))) f\n"
+                f")\n"
+                f"SELECT "
+                f"TMP.__KUMO_BATCH__ as __KUMO_BATCH__, "
+                f"{', '.join(projections)}\n"
+                f"FROM TMP\n"
+                f"JOIN {self.source_name_dict[table_name]} ENT\n"
+                f"  ON {key_ref} = TMP.__KUMO_ID__")
+
+        with paramstyle(self._connection), self._connection.cursor() as cursor:
+            cursor.execute(sql, (payload, ))
+            table = cursor.fetch_arrow_all()
+
+        # Remove any duplicated primary keys in post-processing:
+        tmp = table.append_column('__KUMO_ID__', pa.array(range(len(table))))
+        gb = tmp.group_by('__KUMO_BATCH__').aggregate([('__KUMO_ID__', 'min')])
+        table = table.take(gb['__KUMO_ID___min'])
+
+        batch = table['__KUMO_BATCH__'].cast(pa.int64()).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
+
+    # Helper Methods ##########################################################
+
+    def _by_time(
+        self,
+        table_name: str,
+        fkey: str,
+        pkey: 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]
+
+        end_time = anchor_time + max_offset
+        end_time = end_time.dt.strftime("%Y-%m-%d %H:%M:%S")
+        if min_offset is not None:
+            start_time = anchor_time + min_offset
+            start_time = start_time.dt.strftime("%Y-%m-%d %H:%M:%S")
+            payload = json.dumps(list(zip(pkey, end_time, start_time)))
+        else:
+            payload = json.dumps(list(zip(pkey, end_time)))
+
+        key_ref = self.table_column_ref_dict[table_name][fkey]
+        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 = ("WITH TMP as (\n"
+               "  SELECT\n"
+               "    f.index as __KUMO_BATCH__,\n")
+        if self.table_dtype_dict[table_name][fkey].is_int():
+            sql += "    f.value[0]::NUMBER as __KUMO_ID__,\n"
+        elif self.table_dtype_dict[table_name][fkey].is_float():
+            sql += "    f.value[0]::FLOAT as __KUMO_ID__,\n"
+        else:
+            sql += "    f.value[0]::VARCHAR as __KUMO_ID__,\n"
+        sql += "    f.value[1]::TIMESTAMP_NTZ as __KUMO_END_TIME__"
+        if min_offset is not None:
+            sql += ",\n    f.value[2]::TIMESTAMP_NTZ as __KUMO_START_TIME__"
+        sql += (f"\n"
+                f"  FROM TABLE(FLATTEN(INPUT => PARSE_JSON(?))) f\n"
+                f")\n"
+                f"SELECT "
+                f"TMP.__KUMO_BATCH__ as __KUMO_BATCH__, "
+                f"{', '.join(projections)}\n"
+                f"FROM TMP\n"
+                f"JOIN {self.source_name_dict[table_name]} FACT\n"
+                f"  ON {key_ref} = TMP.__KUMO_ID__\n"
+                f" AND {time_ref} <= TMP.__KUMO_END_TIME__")
+        if min_offset is not None:
+            sql += f"\n AND {time_ref} > TMP.__KUMO_START_TIME__"
+
+        with paramstyle(self._connection), self._connection.cursor() as cursor:
+            cursor.execute(sql, (payload, ))
+            table = cursor.fetch_arrow_all()
+
+        batch = table['__KUMO_BATCH__'].cast(pa.int64()).to_numpy()
+        batch_index = table.schema.get_field_index('__KUMO_BATCH__')
+        table = table.remove_column(batch_index)
+
+        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

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.snow import Connection
-from kumoai.experimental.rfm.base import SourceColumn, SourceForeignKey, Table
+from kumoai.experimental.rfm.base import (
+    ColumnSpec,
+    ColumnSpecType,
+    DataBackend,
+    SourceColumn,
+    SourceForeignKey,
+    Table,
+)
+from kumoai.utils import quote_ident
 
 
 class SnowTable(Table):
@@ -14,6 +25,8 @@ 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.
@@ -26,17 +39,27 @@ class SnowTable(Table):
         self,
         connection: Connection,
         name: str,
+        source_name: str | None = None,
         database: str | None = None,
         schema: str | None = None,
-        columns: Optional[Sequence[str]] = None,
-        primary_key: Optional[str] = None,
-        time_column: Optional[str] = None,
-        end_time_column: Optional[str] = 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 not None and schema is None:
-            raise ValueError(f"Missing 'schema' for table '{name}' in "
-                             f"database '{database}'")
+        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
@@ -44,6 +67,7 @@ class SnowTable(Table):
 
         super().__init__(
             name=name,
+            source_name=source_name,
             columns=columns,
             primary_key=primary_key,
             time_column=time_column,
@@ -51,67 +75,168 @@ class SnowTable(Table):
         )
 
     @property
-    def fqn_name(self) -> str:
-        names: List[str] = []
+    def source_name(self) -> str:
+        names: list[str] = []
         if self._database is not None:
-            assert self._schema is not None
-            names.extend([self._database, self._schema])
-        elif self._schema is not None:
+            names.append(self._database)
+        if self._schema is not None:
             names.append(self._schema)
-        names.append(self._name)
-        return '.'.join(names)
+        return '.'.join(names + [self._source_name])
 
-    def _get_source_columns(self) -> List[SourceColumn]:
-        source_columns: List[SourceColumn] = []
+    @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.fqn_name}")
+                sql = f"DESCRIBE TABLE {self._quoted_source_name}"
+                cursor.execute(sql)
             except Exception as e:
-                raise ValueError(
-                    f"Table '{self.fqn_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.fqn_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.fqn_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(types_mapper=pd.ArrowDtype)
 
-    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',
 ]