refactor: update protocol names

cbrkit/case_sim/generic.py

@@ -1,10 +1,10 @@
 from typing import Any
 
 from cbrkit.case_sim.helpers import apply
-from cbrkit.typing import CasebaseSimFunc, SimilarityValue
+from cbrkit.typing import CaseSimBatchFunc, SimilarityValue
 
 
-def equality() -> CasebaseSimFunc[Any, Any]:
+def equality() -> CaseSimBatchFunc[Any, Any]:
     @apply
     def wrapped_func(case: Any, query: Any) -> SimilarityValue:
         return case == query

cbrkit/case_sim/helpers.py

@@ -5,8 +5,8 @@
 from cbrkit.typing import (
     AggregateFunc,
     Casebase,
-    CasebaseSimFunc,
     CaseName,
+    CaseSimBatchFunc,
     CaseSimFunc,
     CaseType,
     SimilarityMap,
@@ -17,7 +17,7 @@
 
 def apply(
     func: CaseSimFunc[CaseType],
-) -> CasebaseSimFunc[Any, CaseType]:
+) -> CaseSimBatchFunc[Any, CaseType]:
     def wrapped_func(
         casebase: Casebase[CaseName, CaseType],
         query: CaseType,

cbrkit/case_sim/tabular.py

@@ -8,9 +8,9 @@
 from cbrkit.typing import (
     AggregateFunc,
     Casebase,
-    CasebaseSimFunc,
+    CaseSimBatchFunc,
     CaseType,
-    DataSimFunc,
+    DataSimBatchFunc,
     SimilarityMap,
     SimilarityValue,
 )
@@ -37,17 +37,19 @@ def _value_getter(obj: TabularData, key: Any) -> Any:
 
 
 def factory(
-    attributes: Mapping[str, DataSimFunc[Any]] | None = None,
-    types: Mapping[type[Any], DataSimFunc[Any]] | None = None,
-    types_fallback: DataSimFunc[Any] | None = None,
+    attributes: Mapping[str, DataSimBatchFunc[Any]] | None = None,
+    types: Mapping[type[Any], DataSimBatchFunc[Any]] | None = None,
+    types_fallback: DataSimBatchFunc[Any] | None = None,
     aggregate: AggregateFunc = aggregate_default,
     value_getter: Callable[[Any, str], Any] = _value_getter,
     key_getter: Callable[[Any], Iterator[str]] = _key_getter,
-) -> CasebaseSimFunc[Any, TabularData]:
-    attributes_map: Mapping[str, DataSimFunc[Any]] = (
+) -> CaseSimBatchFunc[Any, TabularData]:
+    attributes_map: Mapping[str, DataSimBatchFunc[Any]] = (
         {} if attributes is None else attributes
     )
-    types_map: Mapping[type[Any], DataSimFunc[Any]] = {} if types is None else types
+    types_map: Mapping[type[Any], DataSimBatchFunc[Any]] = (
+        {} if types is None else types
+    )
 
     def wrapped_func(
         casebase: Casebase[Any, CaseType], query: CaseType

cbrkit/data_sim/collections.py

@@ -2,10 +2,10 @@
 from typing import Any
 
 from cbrkit.data_sim.helpers import apply, dist2sim
-from cbrkit.typing import DataSimFunc
+from cbrkit.typing import DataSimBatchFunc
 
 
-def jaccard() -> DataSimFunc[Collection[Any]]:
+def jaccard() -> DataSimBatchFunc[Collection[Any]]:
     from nltk.metrics import jaccard_distance
 
     @apply

cbrkit/data_sim/generic.py

@@ -3,7 +3,7 @@
 
 from cbrkit.data_sim.helpers import apply
 from cbrkit.typing import (
-    DataSimFunc,
+    DataSimBatchFunc,
     DataType,
     SimilaritySequence,
     SimilarityValue,
@@ -14,7 +14,7 @@ def table(
     *args: tuple[DataType, DataType, SimilarityValue],
     symmetric: bool = True,
     default: SimilarityValue = 0.0,
-) -> DataSimFunc[DataType]:
+) -> DataSimBatchFunc[DataType]:
     table: defaultdict[DataType, defaultdict[DataType, SimilarityValue]] = defaultdict(
         lambda: defaultdict(lambda: default)
     )
@@ -31,7 +31,7 @@ def wrapped_func(*args: tuple[DataType, DataType]) -> SimilaritySequence:
     return wrapped_func
 
 
-def equality() -> DataSimFunc[Any]:
+def equality() -> DataSimBatchFunc[Any]:
     @apply
     def wrapped_func(x: Any, y: Any) -> SimilarityValue:
         return x == y

cbrkit/data_sim/helpers.py

@@ -1,12 +1,12 @@
 from cbrkit.typing import (
-    DataPairSimFunc,
+    DataSimBatchFunc,
     DataSimFunc,
     DataType,
     SimilaritySequence,
 )
 
 
-def apply(func: DataPairSimFunc[DataType]) -> DataSimFunc[DataType]:
+def apply(func: DataSimFunc[DataType]) -> DataSimBatchFunc[DataType]:
     def wrapped_func(*args: tuple[DataType, DataType]) -> SimilaritySequence:
         return [func(data1, data2) for (data1, data2) in args]
 

cbrkit/data_sim/numeric.py

@@ -1,14 +1,14 @@
 import math
 
 from cbrkit.data_sim.helpers import apply
-from cbrkit.typing import DataSimFunc, SimilarityValue
+from cbrkit.typing import DataSimBatchFunc, SimilarityValue
 
 Number = float | int
 
 __all__ = ["linear", "threshold", "exponential", "sigmoid"]
 
 
-def linear(max: float, min: float = 0.0) -> DataSimFunc[Number]:
+def linear(max: float, min: float = 0.0) -> DataSimBatchFunc[Number]:
     """Linear similarity function.
 
     Args:
@@ -25,7 +25,7 @@ def wrapped_func(x: Number, y: Number) -> SimilarityValue:
     return wrapped_func
 
 
-def threshold(threshold: float) -> DataSimFunc[Number]:
+def threshold(threshold: float) -> DataSimBatchFunc[Number]:
     """Threshold similarity function.
 
     Args:
@@ -41,7 +41,7 @@ def wrapped_func(x: Number, y: Number) -> SimilarityValue:
     return wrapped_func
 
 
-def exponential(alpha: float = 1.0) -> DataSimFunc[Number]:
+def exponential(alpha: float = 1.0) -> DataSimBatchFunc[Number]:
     """Exponential similarity function.
 
     Args:
@@ -57,7 +57,7 @@ def wrapped_func(x: Number, y: Number) -> SimilarityValue:
     return wrapped_func
 
 
-def sigmoid(alpha: float = 1.0, theta: float = 1.0) -> DataSimFunc[Number]:
+def sigmoid(alpha: float = 1.0, theta: float = 1.0) -> DataSimBatchFunc[Number]:
     """Sigmoid similarity function.
 
     Args:

cbrkit/data_sim/strings.py

@@ -3,14 +3,14 @@
 from cbrkit.data_sim._taxonomy import Taxonomy, TaxonomyMeasure
 from cbrkit.data_sim.helpers import apply
 from cbrkit.typing import (
-    DataSimFunc,
+    DataSimBatchFunc,
     FilePath,
     SimilaritySequence,
     SimilarityValue,
 )
 
 
-def spacy(model_name: str = "en_core_web_lg") -> DataSimFunc[str]:
+def spacy(model_name: str = "en_core_web_lg") -> DataSimBatchFunc[str]:
     import spacy
 
     nlp = spacy.load(model_name)
@@ -28,7 +28,7 @@ def wrapped_func(*args: tuple[str, str]) -> SimilaritySequence:
 
 def taxonomy(
     path: FilePath, measure: TaxonomyMeasure = "wu_palmer"
-) -> DataSimFunc[str]:
+) -> DataSimBatchFunc[str]:
     taxonomy = Taxonomy(path)
 
     @apply
@@ -38,7 +38,7 @@ def wrapped_func(x: str, y: str) -> SimilarityValue:
     return wrapped_func
 
 
-def levenshtein(score_cutoff: float | None = None) -> DataSimFunc[str]:
+def levenshtein(score_cutoff: float | None = None) -> DataSimBatchFunc[str]:
     import Levenshtein
 
     @apply
@@ -48,7 +48,7 @@ def wrapped_func(x: str, y: str) -> SimilarityValue:
     return wrapped_func
 
 
-def jaro(score_cutoff: float | None = None) -> DataSimFunc[str]:
+def jaro(score_cutoff: float | None = None) -> DataSimBatchFunc[str]:
     import Levenshtein
 
     @apply
@@ -60,7 +60,7 @@ def wrapped_func(x: str, y: str) -> SimilarityValue:
 
 def jaro_winkler(
     score_cutoff: float | None = None, prefix_weight: float | None = None
-) -> DataSimFunc[str]:
+) -> DataSimBatchFunc[str]:
     import Levenshtein
 
     @apply

cbrkit/retrieve.py

@@ -5,8 +5,8 @@
 from cbrkit import load
 from cbrkit.typing import (
     Casebase,
-    CasebaseSimFunc,
     CaseName,
+    CaseSimBatchFunc,
     CaseType,
     RetrievalResultProtocol,
     RetrieveFunc,
@@ -74,7 +74,7 @@ def retrieve(
 
 
 def retriever(
-    similarity_func: CasebaseSimFunc[CaseName, CaseType],
+    similarity_func: CaseSimBatchFunc[CaseName, CaseType],
     casebase_limit: int | None = None,
 ) -> RetrieveFunc[CaseName, CaseType]:
     def wrapped_func(

cbrkit/typing.py

@@ -31,7 +31,7 @@
 )
 
 
-class CasebaseSimFunc(Protocol[CaseName, CaseType_contra]):
+class CaseSimBatchFunc(Protocol[CaseName, CaseType_contra]):
     def __call__(
         self, casebase: Casebase[CaseName, CaseType_contra], query: CaseType_contra
     ) -> SimilarityMap[CaseName]:
@@ -45,14 +45,14 @@ def __call__(
         ...
 
 
-class DataSimFunc(Protocol[DataType_contra]):
+class DataSimBatchFunc(Protocol[DataType_contra]):
     def __call__(
         self, *args: tuple[DataType_contra, DataType_contra]
     ) -> SimilaritySequence:
         ...
 
 
-class DataPairSimFunc(Protocol[DataType_contra]):
+class DataSimFunc(Protocol[DataType_contra]):
     def __call__(self, x: DataType_contra, y: DataType_contra) -> SimilarityValue:
         ...