cbrkit 0.26.0__tar.gz → 0.26.2__tar.gz

{cbrkit-0.26.0 → cbrkit-0.26.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: cbrkit
-Version: 0.26.0
+Version: 0.26.2
 Summary: Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI
 Keywords: cbr,case-based reasoning,api,similarity,nlp,retrieval,cli,tool,library
 Author: Mirko Lenz

{cbrkit-0.26.0 → cbrkit-0.26.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cbrkit"
-version = "0.26.0"
+version = "0.26.2"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI"
 authors = [{ name = "Mirko Lenz", email = "mirko@mirkolenz.com" }]
 readme = "README.md"

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/retrieval/build.py

@@ -2,7 +2,7 @@ import itertools
 from collections.abc import Sequence
 from dataclasses import dataclass
 from multiprocessing.pool import Pool
-from typing import Any, Literal, override
+from typing import Literal, override
 
 from ..helpers import (
     batchify_sim,
@@ -134,44 +134,59 @@ class combine[K, V, S: Float](RetrieverFunc[K, V, float]):
         A retriever function that combines the results from multiple retrievers.
     """
 
-    retriever_funcs: list[RetrieverFunc[K, V, S]]
-    aggregator: AggregatorFunc[Any, S] = default_aggregator
+    retriever_funcs: Sequence[RetrieverFunc[K, V, S]]
+    aggregator: AggregatorFunc[str, S] = default_aggregator
     strategy: Literal["intersection", "union"] = "union"
 
     @override
     def __call__(
         self, batches: Sequence[tuple[Casebase[K, V], V]]
     ) -> Sequence[SimMap[K, float]]:
-        results = [retriever_func(batches) for retriever_func in self.retriever_funcs]
-
-        return [
-            self.__call_batch__(
-                [
-                    results[retriever_idx][batch_idx]
-                    for retriever_idx in range(len(self.retriever_funcs))
-                ]
-            )
-            for batch_idx in range(len(batches))
-        ]
+        if isinstance(self.retriever_funcs, Sequence):
+            func_results = [
+                retriever_func(batches) for retriever_func in self.retriever_funcs
+            ]
+
+            return [
+                self.__call_batch__(
+                    [batch_results[batch_idx] for batch_results in func_results]
+                )
+                for batch_idx in range(len(batches))
+            ]
+
+        # elif isinstance(self.retriever_funcs, Mapping):
+        #     results = {
+        #         func_key: retriever_func(batches)
+        #         for func_key, retriever_func in self.retriever_funcs.items()
+        #     }
+
+        #     return [
+        #         self.__call_batch__(
+        #             {func_key: func_results[batch_idx] for func_key, func_results in results.items()}
+        #         )
+        #         for batch_idx in range(len(batches))
+        #     ]
+
+        raise ValueError(f"Invalid retriever_funcs type: {type(self.retriever_funcs)}")
 
-    def __call_batch__(self, results: list[SimMap[K, S]]) -> SimMap[K, float]:
+    def __call_batch__(self, results: Sequence[SimMap[K, S]]) -> SimMap[K, float]:
         if self.strategy == "intersection":
             return {
-                key: self.aggregator(
-                    [result[key] for result in results if key in result]
+                case_key: self.aggregator(
+                    [result[case_key] for result in results if case_key in result]
                 )
-                for key in set().intersection(
+                for case_key in set().intersection(
                     *[set(result.keys()) for result in results]
                 )
             }
 
         elif self.strategy == "union":
             return {
-                key: self.aggregator(
-                    [result[key] for result in results if key in result]
+                case_key: self.aggregator(
+                    [result[case_key] for result in results if case_key in result]
                 )
                 for result in results
-                for key in result.keys()
+                for case_key in result.keys()
             }
 
         raise ValueError(f"Unknown strategy: {self.strategy}")

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/__init__.py

@@ -15,6 +15,7 @@ from .attribute_value import AttributeValueSim, attribute_value
 from .wrappers import (
     attribute_table,
     cache,
+    combine,
     dynamic_table,
     table,
     transpose,
@@ -26,6 +27,7 @@ __all__ = [
     "transpose",
     "transpose_value",
     "cache",
+    "combine",
     "table",
     "dynamic_table",
     "type_table",

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/graphs/__init__.py

@@ -7,12 +7,15 @@ from .common import (
     GraphSim,
     SearchGraphSimFunc,
     SearchState,
+    SearchStateInit,
     SemanticEdgeSim,
+    init_empty,
+    init_unique_matches,
 )
 from .greedy import greedy
 from .lap import lap
 from .precompute import precompute
-from .vf2 import vf2
+from .vf2 import vf2, vf2_networkx, vf2_rustworkx
 
 with optional_dependencies():
     from .alignment import dtw
@@ -31,12 +34,17 @@ __all__ = [
     "lap",
     "precompute",
     "vf2",
+    "vf2_networkx",
+    "vf2_rustworkx",
     "dtw",
     "smith_waterman",
+    "init_empty",
+    "init_unique_matches",
     "GraphSim",
     "ElementMatcher",
     "SemanticEdgeSim",
     "BaseGraphSimFunc",
     "SearchGraphSimFunc",
     "SearchState",
+    "SearchStateInit",
 ]

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/graphs/astar.py

@@ -1,12 +1,8 @@
 import heapq
-import itertools
-from collections import defaultdict
 from collections.abc import Mapping
 from dataclasses import dataclass, field
 from typing import Protocol
 
-from frozendict import frozendict
-
 from ...helpers import (
     get_logger,
     unpack_float,
@@ -18,25 +14,20 @@ from ...model.graph import (
 )
 from ...typing import SimFunc
 from .common import (
-    ElementMatcher,
     GraphSim,
     SearchGraphSimFunc,
     SearchState,
-    _induced_edge_mapping,
 )
 
 __all__ = [
     "HeuristicFunc",
     "SelectionFunc",
-    "InitFunc",
     "h1",
     "h2",
     "h3",
     "select1",
     "select2",
     "select3",
-    "init1",
-    "init2",
     "build",
 ]
 
@@ -74,17 +65,6 @@ class SelectionFunc[K, N, E, G](Protocol):
     ) -> None | tuple[K, GraphElementType]: ...
 
 
-class InitFunc[K, N, E, G](Protocol):
-    def __call__(
-        self,
-        x: Graph[K, N, E, G],
-        y: Graph[K, N, E, G],
-        node_matcher: ElementMatcher[N],
-        edge_matcher: ElementMatcher[E],
-        /,
-    ) -> SearchState[K]: ...
-
-
 @dataclass(slots=True, frozen=True)
 class h1[K, N, E, G](HeuristicFunc[K, N, E, G]):
     def __call__(
@@ -274,61 +254,6 @@ class select3[K, N, E, G](SelectionFunc[K, N, E, G]):
         return selection_key, selection_type
 
 
-@dataclass(slots=True, frozen=True)
-class init1[K, N, E, G](InitFunc[K, N, E, G]):
-    def __call__(
-        self,
-        x: Graph[K, N, E, G],
-        y: Graph[K, N, E, G],
-        node_matcher: ElementMatcher[N],
-        edge_matcher: ElementMatcher[E],
-    ) -> SearchState[K]:
-        return SearchState(
-            frozendict(),
-            frozendict(),
-            frozenset(y.nodes.keys()),
-            frozenset(y.edges.keys()),
-            frozenset(x.nodes.keys()),
-            frozenset(x.edges.keys()),
-        )
-
-
-@dataclass(slots=True, init=False)
-class init2[K, N, E, G](InitFunc[K, N, E, G]):
-    def __call__(
-        self,
-        x: Graph[K, N, E, G],
-        y: Graph[K, N, E, G],
-        node_matcher: ElementMatcher[N],
-        edge_matcher: ElementMatcher[E],
-    ) -> SearchState[K]:
-        # pre-populate the mapping with nodes/edges that only have one possible legal mapping
-        possible_node_mappings: defaultdict[K, set[K]] = defaultdict(set)
-
-        for y_key, x_key in itertools.product(y.nodes.keys(), x.nodes.keys()):
-            if node_matcher(x.nodes[x_key].value, y.nodes[y_key].value):
-                possible_node_mappings[y_key].add(x_key)
-
-        node_mapping: frozendict[K, K] = frozendict(
-            (y_key, next(iter(x_keys)))
-            for y_key, x_keys in possible_node_mappings.items()
-            if len(x_keys) == 1
-        )
-
-        edge_mapping: frozendict[K, K] = _induced_edge_mapping(
-            x, y, node_mapping, edge_matcher
-        )
-
-        return SearchState(
-            node_mapping,
-            edge_mapping,
-            frozenset(y.nodes.keys() - node_mapping.keys()),
-            frozenset(y.edges.keys() - edge_mapping.keys()),
-            frozenset(x.nodes.keys() - node_mapping.values()),
-            frozenset(x.edges.keys() - edge_mapping.values()),
-        )
-
-
 @dataclass(slots=True)
 class build[K, N, E, G](
     SearchGraphSimFunc[K, N, E, G], SimFunc[Graph[K, N, E, G], GraphSim[K]]
@@ -355,7 +280,6 @@ class build[K, N, E, G](
 
     heuristic_func: HeuristicFunc[K, N, E, G] = field(default_factory=h3)
     selection_func: SelectionFunc[K, N, E, G] = field(default_factory=select3)
-    init_func: InitFunc[K, N, E, G] = field(default_factory=init1)
     beam_width: int = 0
     pathlength_weight: int = 0
 
@@ -439,14 +363,10 @@ class build[K, N, E, G](
         x: Graph[K, N, E, G],
         y: Graph[K, N, E, G],
     ) -> GraphSim[K]:
-        # if len(y.nodes) + len(y.edges) > len(x.nodes) + len(x.edges):
-        #     self_inv = dataclasses.replace(self, _invert=True)
-        #     return self.invert_similarity(x, y, self_inv(x=y, y=x))
-
         node_pair_sims, edge_pair_sims = self.pair_similarities(x, y)
 
         open_set: list[PriorityState[K]] = []
-        best_state = self.init_func(x, y, self.node_matcher, self.edge_matcher)
+        best_state = self.init_search_state(x, y)
         heapq.heappush(open_set, PriorityState(0, best_state))
 
         while open_set:

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/graphs/common.py

@@ -1,18 +1,19 @@
 import itertools
+from collections import defaultdict
 from collections.abc import Mapping, Sequence
 from dataclasses import dataclass, field
-from typing import Any, Protocol
+from typing import Any, Protocol, cast
 
 from frozendict import frozendict
 
 from ...helpers import (
     batchify_sim,
-    reverse_batch_positional,
-    reverse_positional,
+    total_params,
     unpack_float,
+    unpack_floats,
 )
-from ...model.graph import Edge, Graph, Node
-from ...typing import AnySimFunc, BatchSimFunc, Float, StructuredValue
+from ...model.graph import Graph, Node
+from ...typing import AnySimFunc, BatchSimFunc, Float, SimFunc, StructuredValue
 from ..wrappers import transpose_value
 
 type PairSim[K] = Mapping[tuple[K, K], float]
@@ -36,26 +37,38 @@ def default_element_matcher(x: Any, y: Any) -> bool:
 
 @dataclass(slots=True, frozen=True)
 class SemanticEdgeSim[K, N, E]:
-    source_weight: float = 0.5
-    target_weight: float = 0.5
+    source_weight: float = 1.0
+    target_weight: float = 1.0
+    edge_sim_func: AnySimFunc[E, Float] | None = None
 
     def __call__(
         self,
-        batches: Sequence[tuple[Edge[K, N, E], Edge[K, N, E], PairSim[K]]],
+        batches: Sequence[tuple[E, E, float, float]],
     ) -> list[float]:
-        source_sims = (
-            node_pair_sims.get((y.source.key, x.source.key), 0.0)
-            for x, y, node_pair_sims in batches
-        )
-        target_sims = (
-            node_pair_sims.get((y.target.key, x.target.key), 0.0)
-            for x, y, node_pair_sims in batches
-        )
+        source_sims = (source_sim for _, _, source_sim, _ in batches)
+        target_sims = (target_sim for _, _, _, target_sim in batches)
+
+        if self.edge_sim_func is not None:
+            edge_sim_func = batchify_sim(self.edge_sim_func)
+            edge_sims = unpack_floats(
+                edge_sim_func(
+                    [(x, y) for x, y, _, _ in batches],
+                )
+            )
+        else:
+            edge_sims = [1.0] * len(batches)
+
+        scaling_factor = self.source_weight + self.target_weight
+
+        if scaling_factor == 0:
+            return edge_sims
 
         return [
-            (self.source_weight * source + self.target_weight * target)
-            / (self.source_weight + self.target_weight)
-            for source, target in zip(source_sims, target_sims, strict=True)
+            (edge * source * self.source_weight / scaling_factor)
+            + (edge * target * self.target_weight / scaling_factor)
+            for source, target, edge in zip(
+                source_sims, target_sims, edge_sims, strict=True
+            )
         ]
 
 
@@ -80,37 +93,14 @@ def _induced_edge_mapping[K, N, E, G](
 @dataclass(slots=True)
 class BaseGraphSimFunc[K, N, E, G]:
     node_sim_func: AnySimFunc[N, Float]
-    edge_sim_func: AnySimFunc[Edge[K, N, E], Float] | SemanticEdgeSim[K, N, E] = (
-        default_edge_sim
-    )
+    edge_sim_func: SemanticEdgeSim[K, N, E] = default_edge_sim
     node_matcher: ElementMatcher[N] = default_element_matcher
     edge_matcher: ElementMatcher[E] = default_element_matcher
     batch_node_sim_func: BatchSimFunc[Node[K, N], Float] = field(init=False)
-    batch_edge_sim_func: (
-        BatchSimFunc[Edge[K, N, E], Float] | SemanticEdgeSim[K, N, E]
-    ) = field(init=False)
-    _invert: bool = False
 
     def __post_init__(self) -> None:
         self.batch_node_sim_func = batchify_sim(transpose_value(self.node_sim_func))
 
-        if isinstance(self.edge_sim_func, SemanticEdgeSim):
-            self.batch_edge_sim_func = self.edge_sim_func
-        else:
-            self.batch_edge_sim_func = batchify_sim(self.edge_sim_func)
-
-        if self._invert:
-            self.node_matcher = reverse_positional(self.node_matcher)
-            self.edge_matcher = reverse_positional(self.edge_matcher)
-            self.batch_node_sim_func = reverse_batch_positional(
-                self.batch_node_sim_func
-            )
-            if not isinstance(self.batch_edge_sim_func, SemanticEdgeSim):
-                # semantic edge sim is agnostic to order
-                self.batch_edge_sim_func = reverse_batch_positional(
-                    self.batch_edge_sim_func
-                )
-
     def induced_edge_mapping(
         self,
         x: Graph[K, N, E, G],
@@ -161,16 +151,17 @@ class BaseGraphSimFunc[K, N, E, G]:
             ]
 
         edge_pair_values = [(x.edges[x_key], y.edges[y_key]) for y_key, x_key in pairs]
-
-        if isinstance(self.batch_edge_sim_func, SemanticEdgeSim):
-            edge_pair_sims = self.batch_edge_sim_func(
-                [
-                    (x_edge, y_edge, node_pair_sims)
-                    for x_edge, y_edge in edge_pair_values
-                ]
-            )
-        else:
-            edge_pair_sims = self.batch_edge_sim_func(edge_pair_values)
+        edge_pair_sims = self.edge_sim_func(
+            [
+                (
+                    x_edge.value,
+                    y_edge.value,
+                    node_pair_sims[(y_edge.source.key, x_edge.source.key)],
+                    node_pair_sims[(y_edge.target.key, x_edge.target.key)],
+                )
+                for x_edge, y_edge in edge_pair_values
+            ]
+        )
 
         return {
             (y_edge.key, x_edge.key): unpack_float(sim)
@@ -256,7 +247,113 @@ class SearchState[K]:
     open_x_edges: frozenset[K]
 
 
+class SearchStateInit[K, N, E, G](Protocol):
+    def __call__(
+        self,
+        x: Graph[K, N, E, G],
+        y: Graph[K, N, E, G],
+        node_matcher: ElementMatcher[N],
+        edge_matcher: ElementMatcher[E],
+        /,
+    ) -> SearchState[K]: ...
+
+
+@dataclass(slots=True, frozen=True)
+class init_empty[K, N, E, G](SearchStateInit[K, N, E, G]):
+    def __call__(
+        self,
+        x: Graph[K, N, E, G],
+        y: Graph[K, N, E, G],
+        node_matcher: ElementMatcher[N],
+        edge_matcher: ElementMatcher[E],
+    ) -> SearchState[K]:
+        return SearchState(
+            frozendict(),
+            frozendict(),
+            frozenset(y.nodes.keys()),
+            frozenset(y.edges.keys()),
+            frozenset(x.nodes.keys()),
+            frozenset(x.edges.keys()),
+        )
+
+
+@dataclass(slots=True, init=False)
+class init_unique_matches[K, N, E, G](SearchStateInit[K, N, E, G]):
+    def __call__(
+        self,
+        x: Graph[K, N, E, G],
+        y: Graph[K, N, E, G],
+        node_matcher: ElementMatcher[N],
+        edge_matcher: ElementMatcher[E],
+    ) -> SearchState[K]:
+        # pre-populate the mapping with nodes/edges that only have one possible legal mapping
+        possible_node_mappings: defaultdict[K, set[K]] = defaultdict(set)
+
+        for y_key, x_key in itertools.product(y.nodes.keys(), x.nodes.keys()):
+            if node_matcher(x.nodes[x_key].value, y.nodes[y_key].value):
+                possible_node_mappings[y_key].add(x_key)
+
+        node_mapping: frozendict[K, K] = frozendict(
+            (y_key, next(iter(x_keys)))
+            for y_key, x_keys in possible_node_mappings.items()
+            if len(x_keys) == 1
+        )
+
+        edge_mapping: frozendict[K, K] = _induced_edge_mapping(
+            x, y, node_mapping, edge_matcher
+        )
+
+        return SearchState(
+            node_mapping,
+            edge_mapping,
+            frozenset(y.nodes.keys() - node_mapping.keys()),
+            frozenset(y.edges.keys() - edge_mapping.keys()),
+            frozenset(x.nodes.keys() - node_mapping.values()),
+            frozenset(x.edges.keys() - edge_mapping.values()),
+        )
+
+
+@dataclass(slots=True)
 class SearchGraphSimFunc[K, N, E, G](BaseGraphSimFunc[K, N, E, G]):
+    init_func: (
+        SearchStateInit[K, N, E, G] | AnySimFunc[Graph[K, N, E, G], GraphSim[K]]
+    ) = field(default_factory=init_unique_matches)
+
+    def init_search_state(
+        self, x: Graph[K, N, E, G], y: Graph[K, N, E, G]
+    ) -> SearchState[K]:
+        init_func_params = total_params(self.init_func)
+        sim: GraphSim[K]
+
+        if init_func_params == 4:
+            init_func = cast(SearchStateInit[K, N, E, G], self.init_func)
+
+            return init_func(x, y, self.node_matcher, self.edge_matcher)
+
+        elif init_func_params == 2:
+            init_func = cast(SimFunc[Graph[K, N, E, G], GraphSim[K]], self.init_func)
+            sim = init_func(x, y)
+
+        elif init_func_params == 1:
+            init_func = cast(
+                BatchSimFunc[Graph[K, N, E, G], GraphSim[K]], self.init_func
+            )
+            sim = init_func([(x, y)])[0]
+
+        else:
+            raise ValueError(
+                f"Invalid number of parameters for init_func: {init_func_params}"
+            )
+
+        return SearchState(
+            node_mapping=sim.node_mapping,
+            edge_mapping=sim.edge_mapping,
+            open_y_nodes=frozenset(y.nodes.keys() - sim.node_mapping.keys()),
+            open_y_edges=frozenset(y.edges.keys() - sim.edge_mapping.keys()),
+            open_x_nodes=frozenset(x.nodes.keys() - sim.node_mapping.values()),
+            open_x_edges=frozenset(x.edges.keys() - sim.edge_mapping.values()),
+        )
+
     def finished(self, state: SearchState[K]) -> bool:
         # the following condition could save a few iterations, but needs to be tested
         # return (not state.open_y_nodes and not state.open_y_edges) or (

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/graphs/dfs.py

@@ -11,8 +11,6 @@ from .common import BaseGraphSimFunc, GraphSim
 
 logger = get_logger(__name__)
 
-__all__ = ["dfs"]
-
 
 class RootsFunc[K, N, E, G](Protocol):
     """Support for matching rooted graphs
@@ -37,10 +35,10 @@ with optional_dependencies():
     class dfs[K, N, E, G](
         BaseGraphSimFunc[K, N, E, G], SimFunc[Graph[K, N, E, G], GraphSim[K]]
     ):
-        node_del_cost: float = 2.0
-        node_ins_cost: float = 0.0
-        edge_del_cost: float = 2.0
-        edge_ins_cost: float = 0.0
+        node_del_cost: float = 1.0
+        node_ins_cost: float = 1.0
+        edge_del_cost: float = 1.0
+        edge_ins_cost: float = 1.0
         max_iterations: int = 0
         upper_bound: float | None = None
         strictly_decreasing: bool = True

{cbrkit-0.26.0 → cbrkit-0.26.2}/src/cbrkit/sim/graphs/greedy.py

@@ -1,7 +1,5 @@
 from dataclasses import dataclass
 
-from frozendict import frozendict
-
 from ...helpers import (
     get_logger,
 )
@@ -13,8 +11,6 @@ from .common import GraphSim, SearchGraphSimFunc, SearchState
 
 logger = get_logger(__name__)
 
-__all__ = ["greedy"]
-
 
 @dataclass(slots=True)
 class greedy[K, N, E, G](
@@ -37,23 +33,17 @@ class greedy[K, N, E, G](
         x: Graph[K, N, E, G],
         y: Graph[K, N, E, G],
     ) -> GraphSim[K]:
-        # if len(y.nodes) + len(y.edges) > len(x.nodes) + len(x.edges):
-        #     self_inv = dataclasses.replace(self, _invert=True)
-        #     return self.invert_similarity(x, y, self_inv(x=y, y=x))
+        node_pair_sims, edge_pair_sims = self.pair_similarities(x, y)
 
-        current_state = SearchState(
-            frozendict(),
-            frozendict(),
-            frozenset(y.nodes.keys()),
-            frozenset(y.edges.keys()),
-            frozenset(x.nodes.keys()),
-            frozenset(x.edges.keys()),
+        current_state = self.init_search_state(x, y)
+        current_sim = self.similarity(
+            x,
+            y,
+            current_state.node_mapping,
+            current_state.edge_mapping,
+            node_pair_sims,
+            edge_pair_sims,
         )
-        current_sim = GraphSim(
-            0.0, frozendict(), frozendict(), frozendict(), frozendict()
-        )
-
-        node_pair_sims, edge_pair_sims = self.pair_similarities(x, y)
 
         while not self.finished(current_state):
             # Iterate over all open pairs and find the best pair