cbrkit 0.2.0__tar.gz → 0.3.0__tar.gz

{cbrkit-0.2.0 → cbrkit-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cbrkit
-Version: 0.2.0
+Version: 0.3.0
 Summary: Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI.
 Home-page: https://wi2trier.github.io/cbrkit/
 License: MIT

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/global_sim/__init__.py

@@ -1,3 +1,4 @@
+from . import graph
 from ._aggregate import PoolingName, aggregator
 from ._attribute_value import AttributeValueData, AttributeValueSim, attribute_value
 
@@ -7,4 +8,5 @@ __all__ = [
     "AttributeValueSim",
     "aggregator",
     "PoolingName",
+    "graph",
 ]

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/global_sim/_attribute_value.py

@@ -8,9 +8,9 @@ import pandas as pd
 from cbrkit.sim import sim2map
 from cbrkit.typing import (
     AggregatorFunc,
-    AnnotatedFloat,
     AnySimFunc,
     Casebase,
+    FloatProtocol,
     KeyType,
     SimMap,
     SimMapFunc,
@@ -43,8 +43,8 @@ def _value_getter(obj: AttributeValueData, key: Any) -> Any:
         return getattr(obj, key)
 
 
-@dataclass(frozen=True)
-class AttributeValueSim(AnnotatedFloat, Generic[SimType]):
+@dataclass(slots=True, frozen=True)
+class AttributeValueSim(FloatProtocol, Generic[SimType]):
     value: float
     by_attribute: Mapping[str, SimType]
 

cbrkit-0.3.0/cbrkit/global_sim/graph/__init__.py

@@ -0,0 +1,25 @@
+from ._astar import GraphMapping, GraphSim, astar
+from ._model import (
+    EdgeData,
+    EdgeKey,
+    EdgeProtocol,
+    Graph,
+    GraphData,
+    NodeData,
+    NodeKey,
+    NodeProtocol,
+)
+
+__all__ = [
+    "NodeKey",
+    "NodeData",
+    "EdgeKey",
+    "EdgeData",
+    "GraphData",
+    "EdgeProtocol",
+    "NodeProtocol",
+    "Graph",
+    "GraphMapping",
+    "GraphSim",
+    "astar",
+]

cbrkit-0.2.0/cbrkit/global_sim/_graph/astar.py → cbrkit-0.3.0/cbrkit/global_sim/graph/_astar.py

@@ -8,7 +8,7 @@ from collections.abc import Iterable
 from dataclasses import dataclass, field
 from typing import Any, Generic, cast
 
-from cbrkit.global_sim._graph.model import (
+from cbrkit.global_sim.graph._model import (
     EdgeData,
     EdgeKey,
     Graph,
@@ -17,12 +17,12 @@ from cbrkit.global_sim._graph.model import (
     NodeKey,
 )
 from cbrkit.sim._helpers import unpack_sims
-from cbrkit.typing import Casebase, KeyType, SimPairFunc, SimType
+from cbrkit.typing import Casebase, FloatProtocol, KeyType, SimPairFunc, SimType
 
 logger = logging.getLogger(__name__)
 
 
-@dataclass
+@dataclass(slots=True)
 class GraphMapping(Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
     """Store all mappings and perform integrity checks on them"""
 
@@ -107,7 +107,7 @@ class GraphMapping(Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
         self.edge_mappings[x] = y
 
 
-@dataclass
+@dataclass(slots=True)
 class SearchNode(Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
     """Specific search node"""
 
@@ -136,17 +136,21 @@ class SearchNode(Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
             self.edges.remove(cast(EdgeKey, q))
 
 
-def run(
+@dataclass(slots=True, frozen=True)
+class GraphSim(FloatProtocol, Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
+    value: float
+    mapping: GraphMapping[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]
+
+
+def astar(
     x_map: Casebase[KeyType, Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]],
     y: Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
     node_sim_func: SimPairFunc[NodeData, SimType],
     edge_sim_func: SimPairFunc[EdgeData, SimType],
     queue_limit: int,
-) -> dict[KeyType, float]:
-    similarities: dict[KeyType, float] = {}
-
+) -> dict[KeyType, GraphSim[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]]:
     results = {
-        key: astar_search(
+        key: _astar_single(
             x,
             y,
             node_sim_func,
@@ -156,15 +160,17 @@ def run(
         for key, x in x_map.items()
     }
 
-    for key, result in results.items():
-        similarities[key] = g(result, node_sim_func, edge_sim_func)
-        # TODO: Add mapping to similarity
-
-    return similarities
+    return {
+        key: GraphSim(
+            g(result, node_sim_func, edge_sim_func),
+            result.mapping,
+        )
+        for key, result in results.items()
+    }
 
 
 # According to Bergmann and Gil, 2014
-def astar_search(
+def _astar_single(
     x: Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
     y: Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
     node_sim_func: SimPairFunc[NodeData, SimType],
@@ -172,17 +178,13 @@ def astar_search(
     queue_limit: int,
 ):
     """Perform an A* analysis of the x base and the y"""
-    q: list[SearchNode[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]] = []
     s0 = SearchNode(GraphMapping(x, y))
-
-    bisect.insort(q, s0, key=lambda x: x.f)
+    q = [s0]
 
     while q[-1].nodes or q[-1].edges:
         q = _expand(q, x, y, node_sim_func, edge_sim_func, queue_limit)
 
-    best_q = q[-1]
-
-    return best_q
+    return q[-1]
 
 
 def _expand(
@@ -197,7 +199,7 @@ def _expand(
 
     s = q[-1]
     mapped = False
-    query_obj, iterator = select1(s, x, y)
+    query_obj, iterator = select1(s, x)
 
     if query_obj and iterator:
         for case_obj in iterator:
@@ -221,11 +223,9 @@ def _expand(
     return q[len(q) - queue_limit :] if queue_limit > 0 else q
 
 
-# TODO: Check node types here
 def select1(
     s: SearchNode[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
     x: Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
-    y: Graph[GraphData, NodeKey, NodeData, EdgeKey, EdgeData],
 ) -> tuple[
     NodeKey | EdgeKey | None,
     Iterable[NodeKey | EdgeKey] | None,

cbrkit-0.2.0/cbrkit/global_sim/_graph/model.py → cbrkit-0.3.0/cbrkit/global_sim/graph/_model.py

@@ -19,7 +19,7 @@ class NodeProtocol(Hashable, Protocol[NodeData]):
     data: NodeData
 
 
-@dataclass
+@dataclass(slots=True)
 class Graph(Generic[GraphData, NodeKey, NodeData, EdgeKey, EdgeData]):
     nodes: dict[NodeKey, NodeProtocol[NodeData]]
     edges: dict[EdgeKey, EdgeProtocol[EdgeData, NodeKey]]

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/loaders.py

@@ -53,6 +53,8 @@ def python(import_name: str) -> Any:
 
 
 class DataFrameCasebase(abc.Mapping):
+    __slots__ = ("df",)
+
     df: DataFrame
 
     def __init__(self, df: DataFrame) -> None:
@@ -96,9 +98,16 @@ def _csv_pandas(path: FilePath) -> dict[int, pd.Series]:
     return cast(dict[int, pd.Series], dataframe(df))
 
 
-def json(path: FilePath) -> dict[str, Any]:
+def json(path: FilePath) -> dict[Any, Any]:
     with open(path, "rb") as fp:
-        return orjson.loads(fp.read())
+        data = orjson.loads(fp.read())
+
+        if isinstance(data, list):
+            return dict(enumerate(data))
+        elif isinstance(data, dict):
+            return data
+        else:
+            raise TypeError(f"Invalid data type: {type(data)}")
 
 
 def toml(path: FilePath) -> dict[str, Any]:
@@ -106,12 +115,18 @@ def toml(path: FilePath) -> dict[str, Any]:
         return tomllib.load(fp)
 
 
-def yaml(path: FilePath) -> dict[str, Any]:
-    data: dict[str, Any] = {}
+def yaml(path: FilePath) -> dict[Any, Any]:
+    data: dict[Any, Any] = {}
 
     with open(path, "rb") as fp:
-        for doc in yamllib.safe_load_all(fp):
-            data |= doc
+        for doc_idx, doc in enumerate(yamllib.safe_load_all(fp)):
+            if isinstance(doc, list):
+                for idx, item in enumerate(doc):
+                    data[doc_idx + idx] = item
+            elif isinstance(doc, dict):
+                data |= doc
+            else:
+                raise TypeError(f"Invalid document type: {type(doc)}")
 
     return data
 

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/retrieval.py

@@ -29,7 +29,7 @@ def _similarities2ranking(
     return sorted(sim_map, key=lambda key: unpack_sim(sim_map[key]), reverse=True)
 
 
-@dataclass
+@dataclass(slots=True)
 class _Result(Generic[KeyType, ValueType, SimType]):
     similarities: SimMap[KeyType, SimType]
     ranking: list[KeyType]
@@ -47,9 +47,9 @@ class _Result(Generic[KeyType, ValueType, SimType]):
         return cls(similarities=similarities, ranking=ranking, casebase=casebase)
 
 
-@dataclass
+@dataclass(slots=True)
 class Result(Generic[KeyType, ValueType, SimType]):
-    _final: _Result[KeyType, ValueType, SimType]
+    final: _Result[KeyType, ValueType, SimType]
     intermediate: list[_Result[KeyType, ValueType, SimType]]
 
     def __init__(

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/sim/taxonomy.py

@@ -11,7 +11,7 @@ class SerializedNode(TypedDict, total=False):
     children: list["SerializedNode | str"]
 
 
-@dataclass
+@dataclass(slots=True)
 class TaxonomyNode:
     key: str
     weight: float | None
@@ -21,6 +21,8 @@ class TaxonomyNode:
 
 
 class Taxonomy:
+    __slots__ = ("root", "nodes")
+
     root: TaxonomyNode
     nodes: dict[str, TaxonomyNode]
 

{cbrkit-0.2.0 → cbrkit-0.3.0}/cbrkit/typing.py

@@ -6,11 +6,11 @@ from typing import (
 )
 
 
-class AnnotatedFloat(Protocol):
+class FloatProtocol(Protocol):
     value: float
 
 
-AnyFloat = float | AnnotatedFloat
+AnyFloat = float | FloatProtocol
 
 FilePath = str | Path
 KeyType = TypeVar("KeyType")

{cbrkit-0.2.0 → cbrkit-0.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cbrkit"
-version = "0.2.0"
+version = "0.3.0"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI."
 authors = ["Mirko Lenz <mirko@mirkolenz.com>"]
 license = "MIT"