kumoai 2.12.0.dev202511031731__cp313-cp313-macosx_11_0_arm64.whl → 2.13.0.dev202512061731__cp313-cp313-macosx_11_0_arm64.whl

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

@@ -0,0 +1,131 @@
+from typing import TYPE_CHECKING
+
+import numpy as np
+import pandas as pd
+
+from kumoai.experimental.rfm.backend.local import LocalGraphStore
+from kumoai.experimental.rfm.base import EdgeSpec, Sampler, SamplerOutput
+from kumoai.utils import ProgressLogger
+
+if TYPE_CHECKING:
+    from kumoai.experimental.rfm import Graph
+
+
+class LocalSampler(Sampler):
+    def __init__(
+        self,
+        graph: 'Graph',
+        verbose: bool | ProgressLogger = True,
+    ) -> None:
+        super().__init__(graph=graph)
+
+        import kumoai.kumolib as kumolib
+
+        self._graph_store = LocalGraphStore(graph, verbose)
+        self._graph_sampler = kumolib.NeighborSampler(
+            list(self.table_stype_dict.keys()),
+            self.edge_types,
+            {
+                '__'.join(edge_type): colptr
+                for edge_type, colptr in self._graph_store.colptr_dict.items()
+            },
+            {
+                '__'.join(edge_type): row
+                for edge_type, row in self._graph_store.row_dict.items()
+            },
+            self._graph_store.time_dict,
+        )
+
+    def sample(
+        self,
+        entity_table_name: str,
+        entity_pkey: pd.Series,
+        anchor_time: pd.Series,
+        column_spec_dict: dict[str, list[str]],
+        edge_spec_dict: dict[tuple[str, str, str], list[EdgeSpec]],
+        drop_duplicates: bool = False,
+        return_edges: bool = False,
+    ) -> SamplerOutput:
+
+        if anchor_time.dtype != 'datetime64[ns]':
+            anchor_time = anchor_time.astype('datetime64[ns]')
+
+        num_hops = max([len(specs) for specs in edge_spec_dict.values()] + [0])
+        num_neighbors_dict: dict[str, list[int]] = {}
+
+        for edge_type, specs in edge_spec_dict.items():
+            edge_type_str = '__'.join(edge_type)
+            num_neighbors_dict[edge_type_str] = [0] * num_hops
+            for hop, spec in enumerate(specs):
+                # TODO Add support for time-based sampling.
+                assert spec.num_neighbors is not None
+                num_neighbors_dict[edge_type_str][hop] = spec.num_neighbors
+
+        (
+            row_dict,
+            col_dict,
+            node_dict,
+            batch_dict,
+            num_sampled_nodes_dict,
+            num_sampled_edges_dict,
+        ) = self._graph_sampler.sample(
+            num_neighbors_dict,
+            {},
+            entity_table_name,
+            self._graph_store.get_node_id(entity_table_name, entity_pkey),
+            anchor_time.astype(int).to_numpy() // 1000**3,  # to seconds
+        )
+
+        df_dict: dict[str, pd.DataFrame] = {}
+        inverse_dict: dict[str, np.ndarray] = {}
+        for table_name, node in node_dict.items():
+            df = self._graph_store.df_dict[table_name]
+            columns = column_spec_dict[table_name]
+            if self.end_time_column_dict.get(table_name, None) in columns:
+                df = df.iloc[node]
+            elif len(columns) > 0 and drop_duplicates:
+                # Only store unique rows in `df` above a certain threshold:
+                unique_node, inverse = np.unique(node, return_inverse=True)
+                if len(node) > 1.05 * len(unique_node):
+                    df = df.iloc[unique_node]
+                    inverse_dict[table_name] = inverse
+                else:
+                    df = df.iloc[node]
+            else:
+                df = df.iloc[node]
+            df = df.reset_index(drop=True)
+            df = df[columns]
+            df_dict[table_name] = df
+
+        num_sampled_nodes_dict = {
+            table_name: num_sampled_nodes.tolist()
+            for table_name, num_sampled_nodes in
+            num_sampled_nodes_dict.items()
+        }
+
+        if return_edges:
+            row_dict = {
+                edge_type: row_dict['__'.join(edge_type)]
+                for edge_type in edge_spec_dict.keys()
+            }
+            col_dict = {
+                edge_type: col_dict['__'.join(edge_type)]
+                for edge_type in edge_spec_dict.keys()
+            }
+            num_sampled_edges_dict = {
+                edge_type:
+                num_sampled_edges_dict['__'.join(edge_type)].tolist()
+                for edge_type in edge_spec_dict.keys()
+            }
+        else:
+            row_dict = col_dict = num_sampled_edges_dict = None
+
+        return SamplerOutput(
+            df_dict=df_dict,
+            inverse_dict=inverse_dict,
+            batch_dict=batch_dict,
+            num_sampled_nodes_dict=num_sampled_nodes_dict,
+            row_dict=row_dict,
+            col_dict=col_dict,
+            num_sampled_edges_dict=num_sampled_edges_dict,
+        )

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

@@ -0,0 +1,109 @@
+import warnings
+from typing import List, Optional
+
+import pandas as pd
+
+from kumoai.experimental.rfm.base import SourceColumn, SourceForeignKey, Table
+from kumoai.experimental.rfm.infer import infer_dtype
+
+
+class LocalTable(Table):
+    r"""A table backed by a :class:`pandas.DataFrame`.
+
+    A :class:`LocalTable` fully specifies the relevant metadata, *i.e.*
+    selected columns, column semantic types, primary keys and time columns.
+    :class:`LocalTable` is used to create a :class:`Graph`.
+
+    .. code-block:: python
+
+        import pandas as pd
+        import kumoai.experimental.rfm as rfm
+
+        # Load data from a CSV file:
+        df = pd.read_csv("data.csv")
+
+        # Create a table from a `pandas.DataFrame` and infer its metadata ...
+        table = rfm.LocalTable(df, name="my_table").infer_metadata()
+
+        # ... or create a table explicitly:
+        table = rfm.LocalTable(
+            df=df,
+            name="my_table",
+            primary_key="id",
+            time_column="time",
+            end_time_column=None,
+        )
+
+        # Verify metadata:
+        table.print_metadata()
+
+        # Change the semantic type of a column:
+        table[column].stype = "text"
+
+    Args:
+        df: The data frame to create this table from.
+        name: The name 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,
+        df: pd.DataFrame,
+        name: str,
+        primary_key: Optional[str] = None,
+        time_column: Optional[str] = None,
+        end_time_column: Optional[str] = None,
+    ) -> None:
+
+        if df.empty:
+            raise ValueError("Data frame is empty")
+        if isinstance(df.columns, pd.MultiIndex):
+            raise ValueError("Data frame must not have a multi-index")
+        if not df.columns.is_unique:
+            raise ValueError("Data frame must have unique column names")
+        if any(col == '' for col in df.columns):
+            raise ValueError("Data frame must have non-empty column names")
+
+        self._data = df.copy(deep=False)
+
+        super().__init__(
+            name=name,
+            columns=list(df.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] = []
+        for column in self._data.columns:
+            ser = self._data[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=False,
+                is_unique_key=False,
+            )
+            source_columns.append(source_column)
+
+        return source_columns
+
+    def _get_source_foreign_keys(self) -> List[SourceForeignKey]:
+        return []
+
+    def _get_sample_df(self) -> pd.DataFrame:
+        return self._data
+
+    def _get_num_rows(self) -> Optional[int]:
+        return len(self._data)

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

@@ -0,0 +1,35 @@
+from typing import Any, TypeAlias
+
+try:
+    import snowflake.connector
+except ImportError:
+    raise ImportError("No module named 'snowflake'. Please install Kumo SDK "
+                      "with the 'snowflake' extension via "
+                      "`pip install kumoai[snowflake]`.")
+
+Connection: TypeAlias = snowflake.connector.SnowflakeConnection
+
+
+def connect(**kwargs: Any) -> Connection:
+    r"""Opens a connection to a :class:`snowflake` database.
+
+    If available, will return a connection to the active session.
+
+    kwargs: Connection arguments, following the :class:`snowflake` protocol.
+    """
+    try:
+        from snowflake.snowpark.context import get_active_session
+        return get_active_session().connection
+    except Exception:
+        pass
+
+    return snowflake.connector.connect(**kwargs)
+
+
+from .table import SnowTable  # noqa: E402
+
+__all__ = [
+    'connect',
+    'Connection',
+    'SnowTable',
+]

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

@@ -0,0 +1,117 @@
+import re
+from typing import List, Optional, Sequence
+
+import pandas as pd
+from kumoapi.typing import Dtype
+
+from kumoai.experimental.rfm.backend.snow import Connection
+from kumoai.experimental.rfm.base import SourceColumn, SourceForeignKey, Table
+
+
+class SnowTable(Table):
+    r"""A table backed by a :class:`sqlite` database.
+
+    Args:
+        connection: The connection to a :class:`snowflake` database.
+        name: The name of this table.
+        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.
+        end_time_column: The name of the end time column of this table, if it
+            exists.
+    """
+    def __init__(
+        self,
+        connection: Connection,
+        name: str,
+        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,
+    ) -> None:
+
+        if database is not None and schema is None:
+            raise ValueError(f"Missing 'schema' for table '{name}' in "
+                             f"database '{database}'")
+
+        self._connection = connection
+        self._database = database
+        self._schema = schema
+
+        super().__init__(
+            name=name,
+            columns=columns,
+            primary_key=primary_key,
+            time_column=time_column,
+            end_time_column=end_time_column,
+        )
+
+    @property
+    def fqn_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._schema)
+        names.append(self._name)
+        return '.'.join(names)
+
+    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}")
+            except Exception as e:
+                raise ValueError(
+                    f"Table '{self.fqn_name}' does not exist") 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
+
+                source_column = SourceColumn(
+                    name=column,
+                    dtype=dtype,
+                    is_primary_key=is_pkey.strip().upper() == 'Y',
+                    is_unique_key=is_unique.strip().upper() == 'Y',
+                )
+                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"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
+
+    def _get_sample_df(self) -> 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")
+            table = cursor.fetch_arrow_all()
+            return table.to_pandas(types_mapper=pd.ArrowDtype)
+
+    def _get_num_rows(self) -> Optional[int]:
+        return None

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

@@ -0,0 +1,30 @@
+from pathlib import Path
+from typing import Any, TypeAlias, Union
+
+try:
+    import adbc_driver_sqlite.dbapi as adbc
+except ImportError:
+    raise ImportError("No module named 'adbc_driver_sqlite'. Please install "
+                      "Kumo SDK with the 'sqlite' extension via "
+                      "`pip install kumoai[sqlite]`.")
+
+Connection: TypeAlias = adbc.AdbcSqliteConnection
+
+
+def connect(uri: Union[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.
+    kwargs: Additional connection arguments, following the
+        :class:`adbc_driver_sqlite` protocol.
+    """
+    return adbc.connect(uri, **kwargs)
+
+
+from .table import SQLiteTable  # noqa: E402
+
+__all__ = [
+    'connect',
+    'Connection',
+    'SQLiteTable',
+]

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 +1,14 @@
+from .source import SourceColumn, SourceForeignKey
+from .column import Column
+from .table import Table
+from .sampler import EdgeSpec, SamplerOutput, Sampler
+
+__all__ = [
+    'SourceColumn',
+    'SourceForeignKey',
+    'Column',
+    'Table',
+    'EdgeSpec',
+    '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})')