kumoai 2.13.0.dev202511191731__cp310-cp310-macosx_11_0_arm64.whl → 2.14.0rc2__cp310-cp310-macosx_11_0_arm64.whl

kumoai/experimental/rfm/{local_graph_store.py → backend/local/graph_store.py}

@@ -1,14 +1,12 @@
-import warnings
-from typing import Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING
 
 import numpy as np
 import pandas as pd
 from kumoapi.rfm.context import Subgraph
-from kumoapi.typing import Stype
 
-from kumoai.experimental.rfm import LocalGraph
-from kumoai.experimental.rfm.utils import normalize_text
-from kumoai.utils import InteractiveProgressLogger, ProgressLogger
+from kumoai.experimental.rfm.backend.local import LocalTable
+from kumoai.experimental.rfm.base import Table
+from kumoai.utils import ProgressLogger
 
 try:
     import torch
@@ -16,43 +14,40 @@ try:
 except ImportError:
     WITH_TORCH = False
 
+if TYPE_CHECKING:
+    from kumoai.experimental.rfm import Graph
+
 
 class LocalGraphStore:
     def __init__(
         self,
-        graph: LocalGraph,
-        preprocess: bool = False,
-        verbose: Union[bool, ProgressLogger] = True,
+        graph: 'Graph',
+        verbose: bool | ProgressLogger = True,
     ) -> None:
 
         if not isinstance(verbose, ProgressLogger):
-            verbose = InteractiveProgressLogger(
-                "Materializing graph",
+            verbose = ProgressLogger.default(
+                msg="Materializing graph",
                 verbose=verbose,
             )
 
         with verbose as logger:
-            self.df_dict, self.mask_dict = self.sanitize(graph, preprocess)
-            self.stype_dict = self.get_stype_dict(graph)
+            self.df_dict, self.mask_dict = self.sanitize(graph)
             logger.log("Sanitized input data")
 
-            self.pkey_name_dict, self.pkey_map_dict = self.get_pkey_data(graph)
+            self.pkey_map_dict = self.get_pkey_map_dict(graph)
             num_pkeys = sum(t.has_primary_key() for t in graph.tables.values())
             if num_pkeys > 1:
                 logger.log(f"Collected primary keys from {num_pkeys} tables")
             else:
                 logger.log(f"Collected primary key from {num_pkeys} table")
 
-            (
-                self.time_column_dict,
-                self.end_time_column_dict,
-                self.time_dict,
-                self.min_time,
-                self.max_time,
-            ) = self.get_time_data(graph)
-            if self.max_time != pd.Timestamp.min:
+            self.time_dict, self.min_max_time_dict = self.get_time_data(graph)
+            if len(self.min_max_time_dict) > 0:
+                min_time = min(t for t, _ in self.min_max_time_dict.values())
+                max_time = max(t for _, t in self.min_max_time_dict.values())
                 logger.log(f"Identified temporal graph from "
-                           f"{self.min_time.date()} to {self.max_time.date()}")
+                           f"{min_time.date()} to {max_time.date()}")
             else:
                 logger.log("Identified static graph without timestamps")
 
@@ -62,14 +57,6 @@ class LocalGraphStore:
             logger.log(f"Created graph with {num_nodes:,} nodes and "
                        f"{num_edges:,} edges")
 
-    @property
-    def node_types(self) -> List[str]:
-        return list(self.df_dict.keys())
-
-    @property
-    def edge_types(self) -> List[Tuple[str, str, str]]:
-        return list(self.row_dict.keys())
-
     def get_node_id(self, table_name: str, pkey: pd.Series) -> np.ndarray:
         r"""Returns the node ID given primary keys.
 
@@ -105,9 +92,8 @@ class LocalGraphStore:
 
     def sanitize(
         self,
-        graph: LocalGraph,
-        preprocess: bool = False,
-    ) -> Tuple[Dict[str, pd.DataFrame], Dict[str, np.ndarray]]:
+        graph: 'Graph',
+    ) -> tuple[dict[str, pd.DataFrame], dict[str, np.ndarray]]:
         r"""Sanitizes raw data according to table schema definition:
 
         In particular, it:
@@ -115,42 +101,25 @@ class LocalGraphStore:
         * drops timezone information from timestamps
         * drops duplicate primary keys
         * removes rows with missing primary keys or time values
-
-        If ``preprocess`` is set to ``True``, it will additionally pre-process
-        data for faster model processing. In particular, it:
-        * tokenizes any text column that is not a foreign key
         """
-        df_dict: Dict[str, pd.DataFrame] = {
-            table_name: table._data.copy(deep=False).reset_index(drop=True)
-            for table_name, table in graph.tables.items()
-        }
-
-        foreign_keys = {(edge.src_table, edge.fkey) for edge in graph.edges}
+        df_dict: dict[str, pd.DataFrame] = {}
+        for table_name, table in graph.tables.items():
+            assert isinstance(table, LocalTable)
+            df_dict[table_name] = Table._sanitize(
+                df=table._data.copy(deep=False).reset_index(drop=True),
+                dtype_dict={
+                    column.name: column.dtype
+                    for column in table.columns
+                },
+                stype_dict={
+                    column.name: column.stype
+                    for column in table.columns
+                },
+            )
 
-        mask_dict: Dict[str, np.ndarray] = {}
+        mask_dict: dict[str, np.ndarray] = {}
         for table in graph.tables.values():
-            for col in table.columns:
-                if col.stype == Stype.timestamp:
-                    ser = df_dict[table.name][col.name]
-                    if not pd.api.types.is_datetime64_any_dtype(ser):
-                        with warnings.catch_warnings():
-                            warnings.filterwarnings(
-                                'ignore',
-                                message='Could not infer format',
-                            )
-                            ser = pd.to_datetime(ser, errors='coerce')
-                        df_dict[table.name][col.name] = ser
-                    if isinstance(ser.dtype, pd.DatetimeTZDtype):
-                        ser = ser.dt.tz_localize(None)
-                        df_dict[table.name][col.name] = ser
-
-                # Normalize text in advance (but exclude foreign keys):
-                if (preprocess and col.stype == Stype.text
-                        and (table.name, col.name) not in foreign_keys):
-                    ser = df_dict[table.name][col.name]
-                    df_dict[table.name][col.name] = normalize_text(ser)
-
-            mask: Optional[np.ndarray] = None
+            mask: np.ndarray | None = None
             if table._time_column is not None:
                 ser = df_dict[table.name][table._time_column]
                 mask = ser.notna().to_numpy()
@@ -165,34 +134,16 @@ class LocalGraphStore:
 
         return df_dict, mask_dict
 
-    def get_stype_dict(self, graph: LocalGraph) -> Dict[str, Dict[str, Stype]]:
-        stype_dict: Dict[str, Dict[str, Stype]] = {}
-        foreign_keys = {(edge.src_table, edge.fkey) for edge in graph.edges}
-        for table in graph.tables.values():
-            stype_dict[table.name] = {}
-            for column in table.columns:
-                if column == table.primary_key:
-                    continue
-                if (table.name, column.name) in foreign_keys:
-                    continue
-                stype_dict[table.name][column.name] = column.stype
-        return stype_dict
-
-    def get_pkey_data(
+    def get_pkey_map_dict(
         self,
-        graph: LocalGraph,
-    ) -> Tuple[
-            Dict[str, str],
-            Dict[str, pd.DataFrame],
-    ]:
-        pkey_name_dict: Dict[str, str] = {}
-        pkey_map_dict: Dict[str, pd.DataFrame] = {}
+        graph: 'Graph',
+    ) -> dict[str, pd.DataFrame]:
+        pkey_map_dict: dict[str, pd.DataFrame] = {}
 
         for table in graph.tables.values():
             if table._primary_key is None:
                 continue
 
-            pkey_name_dict[table.name] = table._primary_key
             pkey = self.df_dict[table.name][table._primary_key]
             pkey_map = pd.DataFrame(
                 dict(arange=range(len(pkey))),
@@ -214,61 +165,48 @@ class LocalGraphStore:
 
             pkey_map_dict[table.name] = pkey_map
 
-        return pkey_name_dict, pkey_map_dict
+        return pkey_map_dict
 
     def get_time_data(
         self,
-        graph: LocalGraph,
-    ) -> Tuple[
-            Dict[str, str],
-            Dict[str, str],
-            Dict[str, np.ndarray],
-            pd.Timestamp,
-            pd.Timestamp,
+        graph: 'Graph',
+    ) -> tuple[
+            dict[str, np.ndarray],
+            dict[str, tuple[pd.Timestamp, pd.Timestamp]],
     ]:
-        time_column_dict: Dict[str, str] = {}
-        end_time_column_dict: Dict[str, str] = {}
-        time_dict: Dict[str, np.ndarray] = {}
-        min_time = pd.Timestamp.max
-        max_time = pd.Timestamp.min
+        time_dict: dict[str, np.ndarray] = {}
+        min_max_time_dict: dict[str, tuple[pd.Timestamp, pd.Timestamp]] = {}
         for table in graph.tables.values():
-            if table._end_time_column is not None:
-                end_time_column_dict[table.name] = table._end_time_column
-
             if table._time_column is None:
                 continue
 
             time = self.df_dict[table.name][table._time_column]
-            time_dict[table.name] = time.astype('datetime64[ns]').astype(
-                int).to_numpy() // 1000**3
-            time_column_dict[table.name] = table._time_column
+            time_dict[table.name] = time.astype(int).to_numpy() // 1000**3
 
             if table.name in self.mask_dict.keys():
                 time = time[self.mask_dict[table.name]]
             if len(time) > 0:
-                min_time = min(min_time, time.min())
-                max_time = max(max_time, time.max())
+                min_max_time_dict[table.name] = (time.min(), time.max())
+            else:
+                min_max_time_dict[table.name] = (
+                    pd.Timestamp.max,
+                    pd.Timestamp.min,
+                )
 
-        return (
-            time_column_dict,
-            end_time_column_dict,
-            time_dict,
-            min_time,
-            max_time,
-        )
+        return time_dict, min_max_time_dict
 
     def get_csc(
         self,
-        graph: LocalGraph,
-    ) -> Tuple[
-            Dict[Tuple[str, str, str], np.ndarray],
-            Dict[Tuple[str, str, str], np.ndarray],
+        graph: 'Graph',
+    ) -> tuple[
+            dict[tuple[str, str, str], np.ndarray],
+            dict[tuple[str, str, str], np.ndarray],
     ]:
         # A mapping from raw primary keys to node indices (0 to N-1):
-        map_dict: Dict[str, pd.CategoricalDtype] = {}
+        map_dict: dict[str, pd.CategoricalDtype] = {}
         # A dictionary to manage offsets of node indices for invalid rows:
-        offset_dict: Dict[str, np.ndarray] = {}
-        for table_name in set(edge.dst_table for edge in graph.edges):
+        offset_dict: dict[str, np.ndarray] = {}
+        for table_name in {edge.dst_table for edge in graph.edges}:
             ser = self.df_dict[table_name][graph[table_name]._primary_key]
             if table_name in self.mask_dict.keys():
                 mask = self.mask_dict[table_name]
@@ -277,8 +215,8 @@ class LocalGraphStore:
             map_dict[table_name] = pd.CategoricalDtype(ser, ordered=True)
 
         # Build CSC graph representation:
-        row_dict: Dict[Tuple[str, str, str], np.ndarray] = {}
-        colptr_dict: Dict[Tuple[str, str, str], np.ndarray] = {}
+        row_dict: dict[tuple[str, str, str], np.ndarray] = {}
+        colptr_dict: dict[tuple[str, str, str], np.ndarray] = {}
         for src_table, fkey, dst_table in graph.edges:
             src_df = self.df_dict[src_table]
             dst_df = self.df_dict[dst_table]
@@ -340,7 +278,7 @@ def _argsort(input: np.ndarray) -> np.ndarray:
     return torch.from_numpy(input).argsort().numpy()
 
 
-def _lexsort(inputs: List[np.ndarray]) -> np.ndarray:
+def _lexsort(inputs: list[np.ndarray]) -> np.ndarray:
     assert len(inputs) >= 1
 
     if not WITH_TORCH:

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

@@ -0,0 +1,312 @@
+from typing import TYPE_CHECKING, Literal
+
+import numpy as np
+import pandas as pd
+from kumoapi.pquery import ValidatedPredictiveQuery
+
+from kumoai.experimental.rfm.backend.local import LocalGraphStore
+from kumoai.experimental.rfm.base import Sampler, SamplerOutput
+from kumoai.experimental.rfm.pquery import PQueryPandasExecutor
+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, verbose=verbose)
+
+        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 _get_min_max_time_dict(
+        self,
+        table_names: list[str],
+    ) -> dict[str, tuple[pd.Timestamp, pd.Timestamp]]:
+        return {
+            key: value
+            for key, value in self._graph_store.min_max_time_dict.items()
+            if key in table_names
+        }
+
+    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:
+
+        index = self._graph_store.get_node_id(entity_table_name, entity_pkey)
+
+        if isinstance(anchor_time, pd.Series):
+            time = anchor_time.astype(int).to_numpy() // 1000**3  # to seconds
+        else:
+            assert anchor_time == 'entity'
+            time = self._graph_store.time_dict[entity_table_name][index]
+
+        (
+            row_dict,
+            col_dict,
+            node_dict,
+            batch_dict,
+            num_sampled_nodes_dict,
+            num_sampled_edges_dict,
+        ) = self._graph_sampler.sample(
+            {
+                '__'.join(edge_type): num_neighbors
+                for edge_type in self.edge_types
+            },
+            {},
+            entity_table_name,
+            index,
+            time,
+        )
+
+        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 = columns_dict[table_name]
+            if self.end_time_column_dict.get(table_name, None) in columns:
+                df = df.iloc[node]
+            elif len(columns) == 0:
+                df = df.iloc[node]
+            else:
+                # 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]
+            df = df.reset_index(drop=True)
+            df = df[list(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()
+        }
+
+        row_dict = {
+            edge_type: row_dict['__'.join(edge_type)]
+            for edge_type in self.edge_types
+        }
+        col_dict = {
+            edge_type: col_dict['__'.join(edge_type)]
+            for edge_type in self.edge_types
+        }
+        num_sampled_edges_dict = {
+            edge_type: num_sampled_edges_dict['__'.join(edge_type)].tolist()
+            for edge_type in self.edge_types
+        }
+
+        return SamplerOutput(
+            anchor_time=time * 1000**3,  # to nanoseconds
+            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,
+        )
+
+    def _sample_entity_table(
+        self,
+        table_name: str,
+        columns: set[str],
+        num_rows: int,
+        random_seed: int | None = None,
+    ) -> pd.DataFrame:
+        pkey_map = self._graph_store.pkey_map_dict[table_name]
+        if len(pkey_map) > num_rows:
+            pkey_map = pkey_map.sample(
+                n=num_rows,
+                random_state=random_seed,
+                ignore_index=True,
+            )
+        df = self._graph_store.df_dict[table_name]
+        df = df.iloc[pkey_map['arange']][list(columns)]
+        return df
+
+    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]:
+
+        train_y, train_mask = self._sample_target_set(
+            query=query,
+            pkey=entity_df[self.primary_key_dict[query.entity_table]],
+            index=train_index,
+            anchor_time=train_time,
+            num_examples=num_train_examples,
+            columns_dict=columns_dict,
+            time_offset_dict=time_offset_dict,
+        )
+
+        test_y, test_mask = self._sample_target_set(
+            query=query,
+            pkey=entity_df[self.primary_key_dict[query.entity_table]],
+            index=test_index,
+            anchor_time=test_time,
+            num_examples=num_test_examples,
+            columns_dict=columns_dict,
+            time_offset_dict=time_offset_dict,
+        )
+
+        return train_y, train_mask, test_y, test_mask
+
+    # Helper Methods ##########################################################
+
+    def _sample_target_set(
+        self,
+        query: ValidatedPredictiveQuery,
+        pkey: pd.Series,
+        index: np.ndarray,
+        anchor_time: pd.Series,
+        num_examples: int,
+        columns_dict: dict[str, set[str]],
+        time_offset_dict: dict[
+            tuple[str, str, str],
+            tuple[pd.DateOffset | None, pd.DateOffset],
+        ],
+        batch_size: int = 10_000,
+    ) -> tuple[pd.Series, np.ndarray]:
+
+        num_hops = 1 if len(time_offset_dict) > 0 else 0
+        num_neighbors_dict: dict[str, list[int]] = {}
+        unix_time_offset_dict: dict[str, list[list[int | None]]] = {}
+        for edge_type, (start, end) in time_offset_dict.items():
+            unix_time_offset_dict['__'.join(edge_type)] = [[
+                date_offset_to_seconds(start) if start is not None else None,
+                date_offset_to_seconds(end),
+            ]]
+        for edge_type in set(self.edge_types) - set(time_offset_dict.keys()):
+            num_neighbors_dict['__'.join(edge_type)] = [0] * num_hops
+
+        count = 0
+        ys: list[pd.Series] = []
+        mask = np.full(len(index), False, dtype=bool)
+        for start in range(0, len(index), batch_size):
+            subset = pkey.iloc[index[start:start + batch_size]]
+            time = anchor_time.iloc[start:start + batch_size]
+
+            _, _, node_dict, batch_dict, _, _ = self._graph_sampler.sample(
+                num_neighbors_dict,
+                unix_time_offset_dict,
+                query.entity_table,
+                self._graph_store.get_node_id(query.entity_table, subset),
+                time.astype(int).to_numpy() // 1000**3,  # to seconds
+            )
+
+            feat_dict: dict[str, pd.DataFrame] = {}
+            time_dict: dict[str, pd.Series] = {}
+            for table_name, columns in columns_dict.items():
+                df = self._graph_store.df_dict[table_name]
+                df = df.iloc[node_dict[table_name]].reset_index(drop=True)
+                df = df[list(columns)]
+                feat_dict[table_name] = df
+
+                time_column = self.time_column_dict.get(table_name)
+                if time_column in columns:
+                    time_dict[table_name] = df[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,
+            )
+            ys.append(y)
+            mask[start:start + batch_size] = _mask
+
+            count += len(y)
+            if count >= num_examples:
+                break
+
+        if len(ys) == 0:
+            y = pd.Series([], dtype=float)
+        elif len(ys) == 1:
+            y = ys[0]
+        else:
+            y = pd.concat(ys, axis=0, ignore_index=True)
+
+        return y, mask
+
+
+# Helper Functions ############################################################
+
+
+def date_offset_to_seconds(offset: pd.DateOffset) -> int:
+    r"""Convert a :class:`pandas.DateOffset` into a number of seconds.
+
+    .. note::
+        We are conservative and take months and years as their maximum value.
+        Additional values are then dropped in label computation where we know
+        the actual dates.
+    """
+    MAX_DAYS_IN_MONTH = 31
+    MAX_DAYS_IN_YEAR = 366
+
+    SECONDS_IN_MINUTE = 60
+    SECONDS_IN_HOUR = 60 * SECONDS_IN_MINUTE
+    SECONDS_IN_DAY = 24 * SECONDS_IN_HOUR
+
+    total_sec = 0
+    multiplier = getattr(offset, 'n', 1)  # The multiplier (if present).
+
+    for attr, value in offset.__dict__.items():
+        if value is None or value == 0:
+            continue
+        scaled_value = value * multiplier
+        if attr == 'years':
+            total_sec += scaled_value * MAX_DAYS_IN_YEAR * SECONDS_IN_DAY
+        elif attr == 'months':
+            total_sec += scaled_value * MAX_DAYS_IN_MONTH * SECONDS_IN_DAY
+        elif attr == 'days':
+            total_sec += scaled_value * SECONDS_IN_DAY
+        elif attr == 'hours':
+            total_sec += scaled_value * SECONDS_IN_HOUR
+        elif attr == 'minutes':
+            total_sec += scaled_value * SECONDS_IN_MINUTE
+        elif attr == 'seconds':
+            total_sec += scaled_value
+
+    return total_sec