cbrkit 0.6.2__tar.gz → 0.8.0__tar.gz

{cbrkit-0.6.2 → cbrkit-0.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cbrkit
-Version: 0.6.2
+Version: 0.8.0
 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
@@ -28,9 +28,12 @@ Provides-Extra: all
 Provides-Extra: api
 Provides-Extra: cli
 Provides-Extra: nlp
+Provides-Extra: timeseries
 Provides-Extra: transformers
+Requires-Dist: dtaidistance (>=2.3.11,<3.0.0) ; extra == "all" or extra == "timeseries"
 Requires-Dist: fastapi[all] (>=0.100,<1.0) ; extra == "all" or extra == "api"
 Requires-Dist: levenshtein (>=0.23,<1.0) ; extra == "all" or extra == "nlp"
+Requires-Dist: minineedle (>=3.1.5,<4.0.0) ; extra == "all" or extra == "timeseries"
 Requires-Dist: nltk (>=3.8,<4.0) ; extra == "all" or extra == "nlp"
 Requires-Dist: openai (>=1.5,<2.0) ; extra == "all" or extra == "nlp"
 Requires-Dist: orjson (>=3.9,<4.0)
@@ -38,7 +41,7 @@ Requires-Dist: pandas (>=2.1,<3.0)
 Requires-Dist: pyarrow (>=13.0)
 Requires-Dist: pyyaml (>=6.0,<7.0)
 Requires-Dist: sentence-transformers (>=2.2,<3.0) ; extra == "all" or extra == "transformers"
-Requires-Dist: spacy (>=3.7,<4.0) ; extra == "all" or extra == "all" or extra == "nlp"
+Requires-Dist: spacy (>=3.7,<4.0) ; extra == "all" or extra == "nlp"
 Requires-Dist: torch (>=2.1.1,<3.0.0) ; extra == "all" or extra == "transformers"
 Requires-Dist: transformers (>=4.35,<5.0) ; extra == "all" or extra == "transformers"
 Requires-Dist: typer[all] (>=0.9,<1.0) ; extra == "all" or extra == "cli"

{cbrkit-0.6.2 → cbrkit-0.8.0}/cbrkit/__init__.py

@@ -5,7 +5,6 @@
 
 """
 
-
 from . import helpers, loaders, retrieval, sim, typing
 
 __all__ = [

{cbrkit-0.6.2 → cbrkit-0.8.0}/cbrkit/cli.py

@@ -2,7 +2,6 @@
 .. include:: ../cli.md
 """
 
-
 from pathlib import Path
 
 try:

cbrkit-0.8.0/cbrkit/sim/collections.py

@@ -0,0 +1,91 @@
+from collections.abc import Collection, Sequence, Set
+from typing import Any
+
+from cbrkit.helpers import dist2sim
+from cbrkit.typing import SimPairFunc
+
+Number = float | int
+
+__all__ = ["jaccard", "smith_waterman", "dtw"]
+
+
+def jaccard() -> SimPairFunc[Collection[Any], float]:
+    """Jaccard similarity function.
+
+    Examples:
+        >>> sim = jaccard()
+        >>> sim(["a", "b", "c", "d"], ["a", "b", "c"])
+        0.8
+    """
+    from nltk.metrics import jaccard_distance
+
+    def wrapped_func(x: Collection[Any], y: Collection[Any]) -> float:
+        if not isinstance(x, Set):
+            x = set(x)
+        if not isinstance(y, Set):
+            y = set(y)
+
+        return dist2sim(jaccard_distance(x, y))
+
+    return wrapped_func
+
+
+def smith_waterman(
+    match_score: int = 2, mismatch_penalty: int = -1, gap_penalty: int = -1
+) -> SimPairFunc[Sequence[Any], float]:
+    """
+    Performs the Smith-Waterman alignment with configurable scoring parameters. If no element matches it returns 0.0.
+
+    Args:
+        match_score: Score for matching characters. Defaults to 2.
+        mismatch_penalty: Penalty for mismatching characters. Defaults to -1.
+        gap_penalty: Penalty for gaps. Defaults to -1.
+
+    Example:
+        >>> sim = smith_waterman()
+        >>> sim("abcde", "fghe")
+        2
+    """
+    from minineedle import core, smith
+
+    def wrapped_func(x: Sequence[Any], y: Sequence[Any]) -> float:
+        try:
+            alignment = smith.SmithWaterman(x, y)
+            alignment.change_matrix(
+                core.ScoreMatrix(
+                    match=match_score, miss=mismatch_penalty, gap=gap_penalty
+                )
+            )
+            alignment.align()
+
+            return alignment.get_score()
+        except ZeroDivisionError:
+            return 0.0
+
+    return wrapped_func
+
+
+def dtw() -> SimPairFunc[Collection[int], float]:
+    """Dynamic Time Warping similarity function.
+
+    Examples:
+        >>> sim = dtw()
+        >>> sim([1, 2, 3], [1, 2, 3, 4])
+        0.5
+    """
+    import numpy as np
+    from dtaidistance import dtw
+
+    def wrapped_func(
+        x: Collection[Number] | np.ndarray, y: Collection[Number] | np.ndarray
+    ) -> float:
+        if not isinstance(x, np.ndarray):
+            x = np.array(x)
+        if not isinstance(y, np.ndarray):
+            y = np.array(y)
+
+        distance = dtw.distance(x, y)
+
+        return dist2sim(distance)
+
+    return wrapped_func

{cbrkit-0.6.2 → cbrkit-0.8.0}/cbrkit/sim/strings/__init__.py

@@ -3,8 +3,10 @@
 """
 
 import csv
+import fnmatch
 import itertools
-from collections.abc import Sequence
+import re
+from collections.abc import Callable, Sequence
 from pathlib import Path
 from typing import cast
 
@@ -187,6 +189,80 @@ def jaro_winkler(
     return wrapped_func
 
 
+def ngram(
+    n: int,
+    case_sensitive: bool = False,
+    tokenizer: Callable[[str], Sequence[str]] | None = None,
+) -> SimPairFunc[str, float]:
+    """N-gram similarity function to compute [similarity](https://procake.pages.gitlab.rlp.net/procake-wiki/sim/strings/#n-gram) between two strings.
+
+    Args:
+        n: Length of the n-gram
+        case_sensitive: If True, the comparison is case-sensitive
+        tokenizer: Tokenizer function to split the input strings into tokens. If None, the input strings are split into characters.
+    Examples:
+        >>> sim = ngram(3, case_sensitive=False)
+        >>> sim("kitten", "sitting")
+        0.125
+
+    """
+    from nltk.util import ngrams
+
+    def wrapped_func(x: str, y: str) -> float:
+        if not case_sensitive:
+            x = x.lower()
+            y = y.lower()
+
+        x_items = tokenizer(x) if tokenizer is not None else list(x)
+        y_items = tokenizer(y) if tokenizer is not None else list(y)
+
+        x_ngrams = set(ngrams(x_items, n))
+        y_ngrams = set(ngrams(y_items, n))
+
+        return len(x_ngrams.intersection(y_ngrams)) / len(x_ngrams.union(y_ngrams))
+
+    return wrapped_func
+
+
+def regex() -> SimPairFunc[str, float]:
+    """Compares a case x to a query y, written as a regular expression. If the case matches the query, the similarity is 1.0, otherwise 0.0.
+
+    Examples:
+        >>> sim = regex()
+        >>> sim("Test1", "T.st[0-9]")
+        1.0
+        >>> sim("Test2", "T.st[3-6]")
+        0.0
+    """
+
+    def wrapped_func(x: str, y: str) -> float:
+        regex = re.compile(y)
+        return 1.0 if regex.match(x) else 0.0
+
+    return wrapped_func
+
+
+def glob(case_sensitive: bool = False) -> SimPairFunc[str, float]:
+    """Compares a case x to a query y, written as a glob pattern, which can contain wildcards. If the case matches the query, the similarity is 1.0, otherwise 0.0.
+
+    Args:
+        case_sensitive: If True, the comparison is case-sensitive
+    Examples:
+        >>> sim = glob()
+        >>> sim("Test1", "Test?")
+        1.0
+        >>> sim("Test2", "Test[3-9]")
+        0.0
+    """
+
+    comparison_func = fnmatch.fnmatchcase if case_sensitive else fnmatch.fnmatch
+
+    def wrapped_func(x: str, y: str) -> float:
+        return 1.0 if comparison_func(x, y) else 0.0
+
+    return wrapped_func
+
+
 def table(
     entries: Sequence[tuple[str, str, float]] | FilePath,
     symmetric: bool = True,

{cbrkit-0.6.2 → cbrkit-0.8.0}/cbrkit/typing.py

@@ -32,20 +32,17 @@ SimSeqOrMap = SimMap[KeyType, SimType] | SimSeq[SimType]
 class SimMapFunc(Protocol[KeyType, ValueType_contra, SimType_cov]):
     def __call__(
         self, x_map: Mapping[KeyType, ValueType_contra], y: ValueType_contra
-    ) -> SimMap[KeyType, SimType_cov]:
-        ...
+    ) -> SimMap[KeyType, SimType_cov]: ...
 
 
 class SimSeqFunc(Protocol[ValueType_contra, SimType_cov]):
     def __call__(
         self, pairs: Sequence[tuple[ValueType_contra, ValueType_contra]], /
-    ) -> SimSeq[SimType_cov]:
-        ...
+    ) -> SimSeq[SimType_cov]: ...
 
 
 class SimPairFunc(Protocol[ValueType_contra, SimType_cov]):
-    def __call__(self, x: ValueType_contra, y: ValueType_contra, /) -> SimType_cov:
-        ...
+    def __call__(self, x: ValueType_contra, y: ValueType_contra, /) -> SimType_cov: ...
 
 
 AnySimFunc = (
@@ -60,8 +57,7 @@ class AggregatorFunc(Protocol[KeyType, SimType_contra]):
         self,
         similarities: SimSeqOrMap[KeyType, SimType_contra],
         /,
-    ) -> float:
-        ...
+    ) -> float: ...
 
 
 class PoolingFunc(Protocol):
@@ -69,5 +65,4 @@ class PoolingFunc(Protocol):
         self,
         similarities: SimSeq[float],
         /,
-    ) -> float:
-        ...
+    ) -> float: ...

{cbrkit-0.6.2 → cbrkit-0.8.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cbrkit"
-version = "0.6.2"
+version = "0.8.0"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI."
 authors = ["Mirko Lenz <mirko@mirkolenz.com>"]
 license = "MIT"
@@ -54,11 +54,14 @@ torch = { version = "^2.1.1", optional = true }
 transformers = { version = "^4.35", optional = true }
 typer = { version = ">=0.9, <1.0", extras = ["all"], optional = true }
 uvicorn = { version = ">=0.24, <1.0", optional = true, extras = ["standard"] }
+dtaidistance = { version = "^2.3.11", optional = true }
+minineedle ={ version = "^3.1.5", optional = true }
 xmltodict = ">=0.13, <1.0"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"
 pytest-cov = "^5.0.0"
+ruff = "^0.3.4"
 
 [tool.poetry.group.docs.dependencies]
 pdoc = "^14.4"
@@ -71,16 +74,18 @@ all = [
     "openai",
     "sentence-transformers",
     "spacy",
-    "spacy",
     "torch",
     "transformers",
     "typer",
     "uvicorn",
+    "minineedle",
+    "dtaidistance",
 ]
 cli = ["typer"]
 api = ["fastapi", "uvicorn"]
 nlp = ["levenshtein", "nltk", "openai", "spacy"]
 transformers = ["sentence-transformers", "torch", "transformers"]
+timeseries = ["minineedle", "dtaidistance"]
 
 [tool.pytest.ini_options]
 addopts = "--cov cbrkit --cov-report term-missing --doctest-modules --ignore cbrkit/cli.py --ignore cbrkit/api.py --ignore result"

cbrkit-0.6.2/cbrkit/sim/collections.py

@@ -1,28 +0,0 @@
-from collections.abc import Collection, Set
-from typing import Any
-
-from cbrkit.helpers import dist2sim
-from cbrkit.typing import SimPairFunc
-
-__all__ = ["jaccard"]
-
-
-def jaccard() -> SimPairFunc[Collection[Any], float]:
-    """Jaccard similarity function.
-
-    Examples:
-        >>> sim = jaccard()
-        >>> sim(["a", "b", "c", "d"], ["a", "b", "c"])
-        0.8
-    """
-    from nltk.metrics import jaccard_distance
-
-    def wrapped_func(x: Collection[Any], y: Collection[Any]) -> float:
-        if not isinstance(x, Set):
-            x = set(x)
-        if not isinstance(y, Set):
-            y = set(y)
-
-        return dist2sim(jaccard_distance(x, y))
-
-    return wrapped_func