kumoai 2.10.0.dev202509231831__cp313-cp313-macosx_11_0_arm64.whl → 2.14.0.dev202512161731__cp313-cp313-macosx_11_0_arm64.whl

kumoai/experimental/rfm/base/source.py

@@ -0,0 +1,19 @@
+from dataclasses import dataclass
+
+from kumoapi.typing import Dtype
+
+
+@dataclass
+class SourceColumn:
+    name: str
+    dtype: Dtype
+    is_primary_key: bool
+    is_unique_key: bool
+    is_nullable: bool
+
+
+@dataclass
+class SourceForeignKey:
+    name: str
+    dst_table: str
+    primary_key: str

kumoai/experimental/rfm/base/sql_sampler.py

@@ -0,0 +1,60 @@
+from abc import abstractmethod
+from typing import Literal
+
+import numpy as np
+import pandas as pd
+
+from kumoai.experimental.rfm.base import Sampler, SamplerOutput
+
+
+class SQLSampler(Sampler):
+    def _sample_subgraph(
+        self,
+        entity_table_name: str,
+        entity_pkey: pd.Series,
+        anchor_time: pd.Series | Literal['entity'],
+        columns_dict: dict[str, set[str]],
+        num_neighbors: list[int],
+    ) -> SamplerOutput:
+
+        df, batch = self._by_pkey(
+            table_name=entity_table_name,
+            pkey=entity_pkey,
+            columns=columns_dict[entity_table_name],
+        )
+        if len(batch) != len(entity_pkey):
+            mask = np.ones(len(entity_pkey), dtype=bool)
+            mask[batch] = False
+            raise KeyError(f"The primary keys "
+                           f"{entity_pkey.iloc[mask].tolist()} do not exist "
+                           f"in the '{entity_table_name}' table")
+
+        perm = batch.argsort()
+        batch = batch[perm]
+        df = df.iloc[perm].reset_index(drop=True)
+
+        if not isinstance(anchor_time, pd.Series):
+            time_column = self.time_column_dict[entity_table_name]
+            anchor_time = df[time_column]
+
+        return SamplerOutput(
+            anchor_time=anchor_time.astype(int).to_numpy(),
+            df_dict={entity_table_name: df},
+            inverse_dict={},
+            batch_dict={entity_table_name: batch},
+            num_sampled_nodes_dict={entity_table_name: [len(batch)]},
+            row_dict={},
+            col_dict={},
+            num_sampled_edges_dict={},
+        )
+
+    # Abstract Methods ########################################################
+
+    @abstractmethod
+    def _by_pkey(
+        self,
+        table_name: str,
+        pkey: pd.Series,
+        columns: set[str],
+    ) -> tuple[pd.DataFrame, np.ndarray]:
+        pass

kumoai/experimental/rfm/{local_table.py → base/table.py}

@@ -1,149 +1,103 @@
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional
+from abc import ABC, abstractmethod
+from collections import defaultdict
+from functools import cached_property
+from typing import Dict, List, Optional, Sequence, Set
 
 import pandas as pd
 from kumoapi.source_table import UnavailableSourceTable
 from kumoapi.table import Column as ColumnDefinition
 from kumoapi.table import TableDefinition
-from kumoapi.typing import Dtype, Stype
+from kumoapi.typing import Stype
 from typing_extensions import Self
 
-from kumoai import in_notebook
-from kumoai.experimental.rfm import utils
-
-
-@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,
-    ) -> None:
-        self._name = name
-        self._dtype = Dtype(dtype)
-        self._is_primary_key = is_primary_key
-        self._is_time_column = is_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.name == self._is_time_column and val != Stype.timestamp:
-                raise ValueError(f"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})')
-
-
-class LocalTable:
-    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:`LocalGraph`.
-
-    .. 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",
-        )
-
-        # Verify metadata:
-        table.print_metadata()
-
-        # Change the semantic type of a column:
-        table[column].stype = "text"
+from kumoai import in_notebook, in_snowflake_notebook
+from kumoai.experimental.rfm.base import (
+    Column,
+    DataBackend,
+    SourceColumn,
+    SourceForeignKey,
+)
+from kumoai.experimental.rfm.infer import (
+    contains_categorical,
+    contains_id,
+    contains_multicategorical,
+    contains_timestamp,
+    infer_primary_key,
+    infer_time_column,
+)
+
+
+class Table(ABC):
+    r"""A :class:`Table` fully specifies the relevant metadata of a single
+    table, *i.e.* its selected columns, data types, semantic types, primary
+    keys and time columns.
 
     Args:
-        df: The data frame to create the table from.
-        name: The name of the table.
+        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,
-        df: pd.DataFrame,
         name: str,
+        columns: Optional[Sequence[str]] = None,
         primary_key: Optional[str] = None,
         time_column: Optional[str] = None,
+        end_time_column: Optional[str] = None,
     ) -> None:
 
-        if df.empty:
-            raise ValueError("Data frame must have at least one row")
-        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")
-
-        df = df.copy(deep=False)
-
-        self._data = df
         self._name = name
         self._primary_key: Optional[str] = None
         self._time_column: Optional[str] = None
+        self._end_time_column: Optional[str] = None
+
+        if len(self._source_column_dict) == 0:
+            raise ValueError(f"Table '{name}' does not hold any column with "
+                             f"a supported data type")
+
+        primary_keys = [
+            column.name for column in self._source_column_dict.values()
+            if column.is_primary_key
+        ]
+        if len(primary_keys) == 1:  # NOTE No composite keys yet.
+            if primary_key is not None and primary_key != primary_keys[0]:
+                raise ValueError(f"Found duplicate primary key "
+                                 f"definition '{primary_key}' and "
+                                 f"'{primary_keys[0]}' in table '{name}'")
+            primary_key = primary_keys[0]
+
+        unique_keys = [
+            column.name for column in self._source_column_dict.values()
+            if column.is_unique_key
+        ]
+        if primary_key is None and len(unique_keys) == 1:
+            primary_key = unique_keys[0]
 
         self._columns: Dict[str, Column] = {}
-        for column_name in df.columns:
+        for column_name in columns or list(self._source_column_dict.keys()):
             self.add_column(column_name)
 
         if primary_key is not None:
+            if primary_key not in self:
+                self.add_column(primary_key)
             self.primary_key = primary_key
 
         if time_column is not None:
+            if time_column not in self:
+                self.add_column(time_column)
             self.time_column = time_column
 
+        if end_time_column is not None:
+            if end_time_column not in self:
+                self.add_column(end_time_column)
+            self.end_time_column = end_time_column
+
     @property
     def name(self) -> str:
-        r"""The name of the table."""
+        r"""The name of this table."""
         return self._name
 
     # Data column #############################################################
@@ -187,24 +141,35 @@ class LocalTable:
             raise KeyError(f"Column '{name}' already exists in table "
                            f"'{self.name}'")
 
-        if name not in self._data.columns:
-            raise KeyError(f"Column '{name}' does not exist in the underyling "
-                           f"data frame")
+        if name not in self._source_column_dict:
+            raise KeyError(f"Column '{name}' does not exist in the underlying "
+                           f"source table")
 
         try:
-            dtype = utils.to_dtype(self._data[name])
+            dtype = self._source_column_dict[name].dtype
         except Exception as e:
-            raise RuntimeError(f"Data type inference for column '{name}' in "
-                               f"table '{self.name}' failed. Consider "
-                               f"changing the data type of the column or "
-                               f"removing it from the table.") from e
+            raise RuntimeError(f"Could not obtain data type for column "
+                               f"'{name}' in table '{self.name}'. Change "
+                               f"the data type of the column in the source "
+                               f"table or remove it from the table.") from e
+
         try:
-            stype = utils.infer_stype(self._data[name], name, dtype)
+            ser = self._sample_df[name]
+            if contains_id(ser, name, dtype):
+                stype = Stype.ID
+            elif contains_timestamp(ser, name, dtype):
+                stype = Stype.timestamp
+            elif contains_multicategorical(ser, name, dtype):
+                stype = Stype.multicategorical
+            elif contains_categorical(ser, name, dtype):
+                stype = Stype.categorical
+            else:
+                stype = dtype.default_stype
         except Exception as e:
-            raise RuntimeError(f"Semantic type inference for column '{name}' "
-                               f"in table '{self.name}' failed. Consider "
-                               f"changing the data type of the column or "
-                               f"removing it from the table.") from e
+            raise RuntimeError(f"Could not obtain semantic type for column "
+                               f"'{name}' in table '{self.name}'. Change "
+                               f"the data type of the column in the source "
+                               f"table or remove it from the table.") from e
 
         self._columns[name] = Column(
             name=name,
@@ -230,6 +195,8 @@ class LocalTable:
             self.primary_key = None
         if self._time_column == name:
             self.time_column = None
+        if self._end_time_column == name:
+            self.end_time_column = None
         del self._columns[name]
 
         return self
@@ -253,9 +220,8 @@ class LocalTable:
         :class:`ValueError` if the primary key has a non-ID semantic type or
         if the column name does not match a column in the data frame.
         """
-        if not self.has_primary_key():
+        if self._primary_key is None:
             return None
-        assert self._primary_key is not None
         return self[self._primary_key]
 
     @primary_key.setter
@@ -264,6 +230,10 @@ class LocalTable:
             raise ValueError(f"Cannot specify column '{name}' as a primary "
                              f"key since it is already defined to be a time "
                              f"column")
+        if name is not None and name == self._end_time_column:
+            raise ValueError(f"Cannot specify column '{name}' as a primary "
+                             f"key since it is already defined to be an end "
+                             f"time column")
 
         if self.primary_key is not None:
             self.primary_key._is_primary_key = False
@@ -295,9 +265,8 @@ class LocalTable:
         :class:`ValueError` if the time column has a non-timestamp semantic
         type or if the column name does not match a column in the data frame.
         """
-        if not self.has_time_column():
+        if self._time_column is None:
             return None
-        assert self._time_column is not None
         return self[self._time_column]
 
     @time_column.setter
@@ -306,6 +275,10 @@ class LocalTable:
             raise ValueError(f"Cannot specify column '{name}' as a time "
                              f"column since it is already defined to be a "
                              f"primary key")
+        if name is not None and name == self._end_time_column:
+            raise ValueError(f"Cannot specify column '{name}' as a time "
+                             f"column since it is already defined to be an "
+                             f"end time column")
 
         if self.time_column is not None:
             self.time_column._is_time_column = False
@@ -318,6 +291,52 @@ class LocalTable:
         self[name]._is_time_column = True
         self._time_column = name
 
+    # End Time column #########################################################
+
+    def has_end_time_column(self) -> bool:
+        r"""Returns ``True`` if this table has an end time column; ``False``
+        otherwise.
+        """
+        return self._end_time_column is not None
+
+    @property
+    def end_time_column(self) -> Optional[Column]:
+        r"""The end time column of this table.
+
+        The getter returns the end time column of this table, or ``None`` if no
+        such end time column is present.
+
+        The setter sets a column as an end time column on this table, and
+        raises a :class:`ValueError` if the end time column has a non-timestamp
+        semantic type or if the column name does not match a column in the data
+        frame.
+        """
+        if self._end_time_column is None:
+            return None
+        return self[self._end_time_column]
+
+    @end_time_column.setter
+    def end_time_column(self, name: Optional[str]) -> None:
+        if name is not None and name == self._primary_key:
+            raise ValueError(f"Cannot specify column '{name}' as an end time "
+                             f"column since it is already defined to be a "
+                             f"primary key")
+        if name is not None and name == self._time_column:
+            raise ValueError(f"Cannot specify column '{name}' as an end time "
+                             f"column since it is already defined to be a "
+                             f"time column")
+
+        if self.end_time_column is not None:
+            self.end_time_column._is_end_time_column = False
+
+        if name is None:
+            self._end_time_column = None
+            return
+
+        self[name].stype = Stype.timestamp
+        self[name]._is_end_time_column = True
+        self._end_time_column = name
+
     # Metadata ################################################################
 
     @property
@@ -326,16 +345,18 @@ class LocalTable:
         information about the columns in this table.
 
         The returned dataframe has columns ``name``, ``dtype``, ``stype``,
-        ``is_primary_key``, and ``is_time_column``, which provide an aggregate
-        view of the properties of the columns of this table.
+        ``is_primary_key``, ``is_time_column`` and ``is_end_time_column``,
+        which provide an aggregate view of the properties of the columns of
+        this table.
 
         Example:
+            >>> # doctest: +SKIP
             >>> import kumoai.experimental.rfm as rfm
             >>> table = rfm.LocalTable(df=..., name=...).infer_metadata()
             >>> table.metadata
-                name        dtype       stype    is_primary_key is_time_column
-            0   CustomerID  float64     ID       True            False
-        """
+                name        dtype    stype  is_primary_key  is_time_column  is_end_time_column
+            0   CustomerID  float64  ID     True            False           False
+        """  # noqa: E501
         cols = self.columns
 
         return pd.DataFrame({
@@ -355,15 +376,28 @@ class LocalTable:
                 dtype=bool,
                 data=[self._time_column == c.name for c in cols],
             ),
+            'is_end_time_column':
+            pd.Series(
+                dtype=bool,
+                data=[self._end_time_column == c.name for c in cols],
+            ),
         })
 
     def print_metadata(self) -> None:
-        r"""Prints the :meth:`~LocalTable.metadata` of the table."""
-        if in_notebook():
+        r"""Prints the :meth:`~metadata` of this table."""
+        num_rows_repr = ''
+        if self._num_rows is not None:
+            num_rows_repr = ' ({self._num_rows:,} rows)'
+
+        if in_snowflake_notebook():
+            import streamlit as st
+            md_repr = f"### 🏷️ Metadata of Table `{self.name}`{num_rows_repr}"
+            st.markdown(md_repr)
+            st.dataframe(self.metadata, hide_index=True)
+        elif in_notebook():
             from IPython.display import Markdown, display
-            display(
-                Markdown(f"### 🏷️ Metadata of Table `{self.name}` "
-                         f"({len(self._data):,} rows)"))
+            md_repr = f"### 🏷️ Metadata of Table `{self.name}`{num_rows_repr}"
+            display(Markdown(md_repr))
             df = self.metadata
             try:
                 if hasattr(df.style, 'hide'):
@@ -373,8 +407,7 @@ class LocalTable:
             except ImportError:
                 print(df.to_string(index=False))  # missing jinja2
         else:
-            print(f"🏷️ Metadata of Table '{self.name}' "
-                  f"({len(self._data):,} rows):")
+            print(f"🏷️ Metadata of Table '{self.name}'{num_rows_repr}")
             print(self.metadata.to_string(index=False))
 
     def infer_metadata(self, verbose: bool = True) -> Self:
@@ -404,9 +437,9 @@ class LocalTable:
                 column.name for column in self.columns if is_candidate(column)
             ]
 
-            if primary_key := utils.detect_primary_key(
+            if primary_key := infer_primary_key(
                     table_name=self.name,
-                    df=self._data,
+                    df=self._sample_df,
                     candidates=candidates,
             ):
                 self.primary_key = primary_key
@@ -417,8 +450,12 @@ class LocalTable:
             candidates = [
                 column.name for column in self.columns
                 if column.stype == Stype.timestamp
+                and column.name != self._end_time_column
             ]
-            if time_column := utils.detect_time_column(self._data, candidates):
+            if time_column := infer_time_column(
+                    df=self._sample_df,
+                    candidates=candidates,
+            ):
                 self.time_column = time_column
                 logs.append(f"time column '{time_column}'")
 
@@ -430,24 +467,26 @@ class LocalTable:
     # Helpers #################################################################
 
     def _to_api_table_definition(self) -> TableDefinition:
-        cols: List[ColumnDefinition] = []
-        for col in self.columns:
-            cols.append(ColumnDefinition(col.name, col.stype, col.dtype))
-        pkey = self._primary_key
-        time_col = self._time_column
-        source_table = UnavailableSourceTable(table=self.name)
-
         return TableDefinition(
-            cols=cols,
-            source_table=source_table,
-            pkey=pkey,
-            time_col=time_col,
+            cols=[
+                ColumnDefinition(col.name, col.stype, col.dtype)
+                for col in self.columns
+            ],
+            source_table=UnavailableSourceTable(table=self.name),
+            pkey=self._primary_key,
+            time_col=self._time_column,
+            end_time_col=self._end_time_column,
         )
 
     # Python builtins #########################################################
 
     def __hash__(self) -> int:
-        return hash(tuple(self.columns + [self.primary_key, self.time_column]))
+        special_columns = [
+            self.primary_key,
+            self.time_column,
+            self.end_time_column,
+        ]
+        return hash(tuple(self.columns + special_columns))
 
     def __contains__(self, name: str) -> bool:
         return self.has_column(name)
@@ -464,4 +503,54 @@ class LocalTable:
                 f'  num_columns={len(self.columns)},\n'
                 f'  primary_key={self._primary_key},\n'
                 f'  time_column={self._time_column},\n'
+                f'  end_time_column={self._end_time_column},\n'
                 f')')
+
+    # Abstract Methods ########################################################
+
+    @property
+    @abstractmethod
+    def backend(self) -> DataBackend:
+        r"""The data backend of this table."""
+        pass
+
+    @cached_property
+    def _source_column_dict(self) -> Dict[str, SourceColumn]:
+        return {col.name: col for col in self._get_source_columns()}
+
+    @abstractmethod
+    def _get_source_columns(self) -> List[SourceColumn]:
+        pass
+
+    @cached_property
+    def _source_foreign_key_dict(self) -> Dict[str, SourceForeignKey]:
+        fkeys = self._get_source_foreign_keys()
+        # NOTE Drop all keys that link to different primary keys in the same
+        # table since we don't support composite keys yet:
+        table_pkeys: Dict[str, Set[str]] = defaultdict(set)
+        for fkey in fkeys:
+            table_pkeys[fkey.dst_table].add(fkey.primary_key)
+        return {
+            fkey.name: fkey
+            for fkey in fkeys if len(table_pkeys[fkey.dst_table]) == 1
+        }
+
+    @abstractmethod
+    def _get_source_foreign_keys(self) -> List[SourceForeignKey]:
+        pass
+
+    @cached_property
+    def _sample_df(self) -> pd.DataFrame:
+        return self._get_sample_df()
+
+    @abstractmethod
+    def _get_sample_df(self) -> pd.DataFrame:
+        pass
+
+    @cached_property
+    def _num_rows(self) -> Optional[int]:
+        return self._get_num_rows()
+
+    @abstractmethod
+    def _get_num_rows(self) -> Optional[int]:
+        pass