cbrkit 0.26.1__tar.gz → 0.26.3__tar.gz

{cbrkit-0.26.1 → cbrkit-0.26.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: cbrkit
-Version: 0.26.1
+Version: 0.26.3
 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-0.26.1 → cbrkit-0.26.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "cbrkit"
-version = "0.26.1"
+version = "0.26.3"
 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-0.26.1 → cbrkit-0.26.3}/src/cbrkit/retrieval/build.py

@@ -1,5 +1,5 @@
 import itertools
-from collections.abc import Sequence
+from collections.abc import Mapping, Sequence
 from dataclasses import dataclass
 from multiprocessing.pool import Pool
 from typing import Literal, override
@@ -129,14 +129,18 @@ class combine[K, V, S: Float](RetrieverFunc[K, V, float]):
         retriever_funcs: A list of retriever functions to be combined.
         aggregator: A function to aggregate the results from the retriever functions.
         strategy: The strategy to combine the results. Either "intersection" or "union".
+        default_sim: The default similarity value to use for strategy "union" when a case is not found in one of the retriever results.
 
     Returns:
         A retriever function that combines the results from multiple retrievers.
     """
 
-    retriever_funcs: Sequence[RetrieverFunc[K, V, S]]
-    aggregator: AggregatorFunc[str, S] = default_aggregator
+    retriever_funcs: (
+        Sequence[RetrieverFunc[K, V, S]] | Mapping[str, RetrieverFunc[K, V, S]]
+    )
+    aggregator: AggregatorFunc[str, S | float] = default_aggregator
     strategy: Literal["intersection", "union"] = "union"
+    default_sim: float = 0.0
 
     @override
     def __call__(
@@ -154,42 +158,65 @@ class combine[K, V, S: Float](RetrieverFunc[K, V, float]):
                 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()
-        #     }
+        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))
-        #     ]
+            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: Sequence[SimMap[K, S]]) -> SimMap[K, float]:
-        if self.strategy == "intersection":
+    def __call_batch__(
+        self, results: Sequence[SimMap[K, S]] | Mapping[str, SimMap[K, S]]
+    ) -> SimMap[K, float]:
+        case_keys: set[K]
+
+        if isinstance(results, Sequence):
+            if self.strategy == "intersection":
+                case_keys = set().intersection(*(result.keys() for result in results))
+            elif self.strategy == "union":
+                case_keys = set().union(*(result.keys() for result in results))
+            else:
+                raise ValueError(f"Unknown strategy: {self.strategy}")
+
             return {
                 case_key: self.aggregator(
-                    [result[case_key] for result in results if case_key in result]
-                )
-                for case_key in set().intersection(
-                    *[set(result.keys()) for result in results]
+                    [result.get(case_key, self.default_sim) for result in results]
                 )
+                for case_key in case_keys
             }
 
-        elif self.strategy == "union":
+        elif isinstance(results, Mapping):
+            if self.strategy == "intersection":
+                case_keys = set().intersection(
+                    *(result.keys() for result in results.values())
+                )
+            elif self.strategy == "union":
+                case_keys = set().union(*(result.keys() for result in results.values()))
+            else:
+                raise ValueError(f"Unknown strategy: {self.strategy}")
+
             return {
                 case_key: self.aggregator(
-                    [result[case_key] for result in results if case_key in result]
+                    {
+                        func_key: result.get(case_key, self.default_sim)
+                        for func_key, result in results.items()
+                    }
                 )
-                for result in results
-                for case_key in result.keys()
+                for case_key in case_keys
             }
 
-        raise ValueError(f"Unknown strategy: {self.strategy}")
+        raise ValueError(f"Invalid results type: {type(results)}")
 
 
 @dataclass(slots=True, frozen=True)

{cbrkit-0.26.1 → cbrkit-0.26.3}/src/cbrkit/retrieval/rerank.py

@@ -311,12 +311,15 @@ with optional_dependencies():
                 k=len(casebase),
             )
             max_score = np.max(scores)
+            min_score = np.min(scores)
 
             key_index = {idx: key for idx, key in enumerate(casebase)}
 
             return [
                 {
-                    key_index[case_id]: float(score / max_score)
+                    key_index[case_id]: float(
+                        (score - min_score) / (max_score - min_score)
+                    )
                     for case_id, score in zip(
                         results[query_id], scores[query_id], strict=True
                     )

{cbrkit-0.26.1 → cbrkit-0.26.3}/src/cbrkit/sim/graphs/__init__.py

@@ -15,7 +15,7 @@ from .common import (
 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
@@ -34,6 +34,8 @@ __all__ = [
     "lap",
     "precompute",
     "vf2",
+    "vf2_networkx",
+    "vf2_rustworkx",
     "dtw",
     "smith_waterman",
     "init_empty",

{cbrkit-0.26.1 → cbrkit-0.26.3}/src/cbrkit/sim/graphs/astar.py

@@ -60,7 +60,6 @@ class SelectionFunc[K, N, E, G](Protocol):
         s: SearchState[K],
         node_pair_sims: Mapping[tuple[K, K], float],
         edge_pair_sims: Mapping[tuple[K, K], float],
-        heuristic_func: HeuristicFunc[K, N, E, G],
         /,
     ) -> None | tuple[K, GraphElementType]: ...
 
@@ -127,7 +126,7 @@ class h3[K, N, E, G](HeuristicFunc[K, N, E, G]):
                 default=0.0,
             )
 
-        def mapping_possible(x_node: Node[K, N], y_node: Node[K, N]) -> bool:
+        def can_map(x_node: Node[K, N], y_node: Node[K, N]) -> bool:
             return x_node.key == s.node_mapping.get(y_node.key) or (
                 y_node.key in s.open_y_nodes and x_node.key in s.open_x_nodes
             )
@@ -137,8 +136,8 @@ class h3[K, N, E, G](HeuristicFunc[K, N, E, G]):
                 (
                     edge_pair_sims.get((y_key, x_key), 0.0)
                     for x_key in s.open_x_edges
-                    if mapping_possible(x.edges[x_key].source, y.edges[y_key].source)
-                    and mapping_possible(x.edges[x_key].target, y.edges[y_key].target)
+                    if can_map(x.edges[x_key].source, y.edges[y_key].source)
+                    and can_map(x.edges[x_key].target, y.edges[y_key].target)
                 ),
                 default=0.0,
             )
@@ -155,7 +154,6 @@ class select1[K, N, E, G](SelectionFunc[K, N, E, G]):
         s: SearchState[K],
         node_pair_sims: Mapping[tuple[K, K], float],
         edge_pair_sims: Mapping[tuple[K, K], float],
-        heuristic_func: HeuristicFunc[K, N, E, G],
     ) -> None | tuple[K, GraphElementType]:
         """Select the next node or edge to be mapped"""
 
@@ -181,7 +179,6 @@ class select2[K, N, E, G](SelectionFunc[K, N, E, G]):
         s: SearchState[K],
         node_pair_sims: Mapping[tuple[K, K], float],
         edge_pair_sims: Mapping[tuple[K, K], float],
-        heuristic_func: HeuristicFunc[K, N, E, G],
     ) -> None | tuple[K, GraphElementType]:
         """Select the next node or edge to be mapped"""
 
@@ -212,36 +209,58 @@ class select3[K, N, E, G](SelectionFunc[K, N, E, G]):
         s: SearchState[K],
         node_pair_sims: Mapping[tuple[K, K], float],
         edge_pair_sims: Mapping[tuple[K, K], float],
-        heuristic_func: HeuristicFunc[K, N, E, G],
     ) -> None | tuple[K, GraphElementType]:
         """Select the next node or edge to be mapped"""
 
-        heuristic_scores: list[tuple[K, GraphElementType, float]] = []
+        mapping_options: dict[tuple[K, GraphElementType], int] = {}
+        heuristic_scores: dict[tuple[K, GraphElementType], float] = {}
 
         for y_key in s.open_y_nodes:
-            heuristic_scores.append(
-                (
-                    y_key,
-                    "node",
-                    heuristic_func(x, y, s, node_pair_sims, edge_pair_sims),
-                )
+            h_vals = [
+                node_pair_sims[(y_key, x_key)]
+                for x_key in s.open_x_nodes
+                if (y_key, x_key) in node_pair_sims
+            ]
+
+            if h_vals:
+                mapping_options[(y_key, "node")] = len(h_vals)
+                heuristic_scores[(y_key, "node")] = max(h_vals)
+
+        def can_map(x_node: Node[K, N], y_node: Node[K, N]) -> bool:
+            return x_node.key == s.node_mapping.get(y_node.key) or (
+                y_node.key in s.open_y_nodes and x_node.key in s.open_x_nodes
             )
 
         for y_key in s.open_y_edges:
-            heuristic_scores.append(
-                (
-                    y_key,
-                    "edge",
-                    heuristic_func(x, y, s, node_pair_sims, edge_pair_sims),
-                )
-            )
+            h_vals = [
+                edge_pair_sims[(y_key, x_key)]
+                for x_key in s.open_x_edges
+                if (y_key, x_key) in edge_pair_sims
+                and can_map(x.edges[x_key].source, y.edges[y_key].source)
+                and can_map(x.edges[x_key].target, y.edges[y_key].target)
+            ]
+
+            if h_vals:
+                mapping_options[(y_key, "edge")] = len(h_vals)
+                heuristic_scores[(y_key, "edge")] = max(h_vals)
 
         if not heuristic_scores:
+            # Fallback: select any remaining node or edge for null mapping
+            if s.open_y_nodes:
+                return next(iter(s.open_y_nodes)), "node"
+            elif s.open_y_edges:
+                return next(iter(s.open_y_edges)), "edge"
             return None
 
-        best_selection = max(heuristic_scores, key=lambda x: x[2])
+        max_score = max(heuristic_scores.values())
+        best_selections = [
+            key for key, value in heuristic_scores.items() if value == max_score
+        ]
 
-        selection_key, selection_type, _ = best_selection
+        # if multiple selections have the same score, select the one with the lowest number of possible mappings
+        best_selection = min(best_selections, key=lambda key: mapping_options[key])
+
+        selection_key, selection_type = best_selection
 
         if selection_type == "edge":
             edge = y.edges[selection_key]
@@ -300,7 +319,6 @@ class build[K, N, E, G](
             state,
             node_pair_sims,
             edge_pair_sims,
-            self.heuristic_func,
         )
 
         if selection is None:
@@ -363,19 +381,37 @@ 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_search_state(x, y)
+        # best_similarity = self.similarity(
+        #     x,
+        #     y,
+        #     best_state.node_mapping,
+        #     best_state.edge_mapping,
+        #     node_pair_sims,
+        #     edge_pair_sims,
+        # )
         heapq.heappush(open_set, PriorityState(0, best_state))
 
         while open_set:
             first_elem = heapq.heappop(open_set)
             current_state = first_elem.state
+            # current_similarity = self.similarity(
+            #     x,
+            #     y,
+            #     current_state.node_mapping,
+            #     current_state.edge_mapping,
+            #     node_pair_sims,
+            #     edge_pair_sims,
+            # )
+
+            # not needed because we add null mappings and
+            # the first item of the queue is always the best one
+            # if current_similarity.value > best_similarity.value:
+            #     best_state = current_state
+            #     best_similarity = current_similarity
 
             if self.finished(current_state):
                 best_state = current_state

{cbrkit-0.26.1 → cbrkit-0.26.3}/src/cbrkit/sim/graphs/brute_force.py

@@ -74,8 +74,16 @@ class brute_force[K, N, E, G](
 
                     if next_sim and (
                         next_sim.value > best_sim.value
-                        or len(next_sim.node_mapping) > len(best_sim.node_mapping)
-                        or len(next_sim.edge_mapping) > len(best_sim.edge_mapping)
+                        or (
+                            next_sim.value >= best_sim.value
+                            and (
+                                len(next_sim.node_mapping) > len(best_sim.node_mapping)
+                                or (
+                                    len(next_sim.edge_mapping)
+                                    > len(best_sim.edge_mapping)
+                                )
+                            )
+                        )
                     ):
                         best_sim = next_sim
 

{cbrkit-0.26.1 → cbrkit-0.26.3}/src/cbrkit/sim/graphs/common.py

@@ -8,12 +8,11 @@ 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 ...model.graph import Graph, Node
 from ...typing import AnySimFunc, BatchSimFunc, Float, SimFunc, StructuredValue
 from ..wrappers import transpose_value
 
@@ -38,26 +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
+            )
         ]
 
 
@@ -82,37 +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],
@@ -163,16 +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)
@@ -298,16 +287,18 @@ class init_unique_matches[K, N, E, G](SearchStateInit[K, N, E, G]):
         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)
+        y2x_map: defaultdict[K, set[K]] = defaultdict(set)
+        x2y_map: 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)
+                y2x_map[y_key].add(x_key)
+                x2y_map[x_key].add(y_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
+            for y_key, x_keys in y2x_map.items()
+            if len(x_keys) == 1 and len(x2y_map[next(iter(x_keys))]) == 1
         )
 
         edge_mapping: frozendict[K, K] = _induced_edge_mapping(

{cbrkit-0.26.1 → cbrkit-0.26.3}/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-0.26.1 → cbrkit-0.26.3}/src/cbrkit/sim/graphs/greedy.py

@@ -11,8 +11,6 @@ from .common import GraphSim, SearchGraphSimFunc, SearchState
 
 logger = get_logger(__name__)
 
-__all__ = ["greedy"]
-
 
 @dataclass(slots=True)
 class greedy[K, N, E, G](
@@ -35,10 +33,6 @@ 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 = self.init_search_state(x, y)