cbrkit 0.7.0__tar.gz → 0.9.0__tar.gz

{cbrkit-0.7.0 → cbrkit-0.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cbrkit
-Version: 0.7.0
+Version: 0.9.0
 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
@@ -28,17 +28,22 @@ Provides-Extra: all
 Provides-Extra: api
 Provides-Extra: cli
 Provides-Extra: nlp
+Provides-Extra: timeseries
 Provides-Extra: transformers
+Requires-Dist: dtaidistance (>=2.3,<3.0) ; 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,<4.0) ; 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)
 Requires-Dist: pandas (>=2.1,<3.0)
 Requires-Dist: pyarrow (>=13.0)
+Requires-Dist: pydantic (>=2.0,<3.0)
 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: setuptools (>=69,<70)
+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-0.7.0 → cbrkit-0.9.0}/cbrkit/__init__.py

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

{cbrkit-0.7.0 → cbrkit-0.9.0}/cbrkit/cli.py

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

{cbrkit-0.7.0 → cbrkit-0.9.0}/cbrkit/loaders.py

@@ -1,7 +1,11 @@
+"""
+This module provides several loaders to read data from different file formats and convert it into a Casebase. To validate the data against a Pydantic model, a `validate` function is also provided.
+"""
+
 import csv as csvlib
 import tomllib
 from collections import abc
-from collections.abc import Callable, Iterator
+from collections.abc import Callable, Iterator, Mapping
 from importlib import import_module
 from pathlib import Path
 from typing import Any, cast
@@ -11,6 +15,7 @@ import pandas as pd
 import xmltodict
 import yaml as yamllib
 from pandas import DataFrame, Series
+from pydantic import BaseModel
 
 from cbrkit.typing import Casebase, FilePath
 
@@ -26,6 +31,7 @@ __all__ = [
     "python",
     "txt",
     "xml",
+    "validate",
 ]
 
 
@@ -325,6 +331,7 @@ def file(path: Path) -> Casebase[Any, Any] | None:
         >>> from pathlib import Path
         >>> file_path = Path("./data/cars-1k.csv")
         >>> result = file(file_path)
+
     """
     if path.suffix not in _batch_loaders:
         return None
@@ -348,16 +355,47 @@ def folder(path: Path, pattern: str) -> Casebase[Any, Any] | None:
     Examples:
         >>> from pathlib import Path
         >>> folder_path = Path("./data")
-        >>> result = folder(folder_path, ".csv")
+        >>> result = folder(folder_path, "*.csv")
+        >>> assert result is not None
     """
     cb: Casebase[Any, Any] = {}
 
     for file in path.glob(pattern):
         if file.is_file() and file.suffix in _single_loaders:
-            loader = _single_loaders[path.suffix]
+            loader = _single_loaders[file.suffix]
             cb[file.name] = loader(file)
 
     if len(cb) == 0:
         return None
 
     return cb
+
+
+def validate(data: Casebase[Any, Any] | Any, validation_model: BaseModel):
+    """Validates the data against a Pydantic model. Throws a ValueError if data is None or a Pydantic ValidationError if the data does not match the model.
+
+    Args:
+        data: Data to validate. Can be an entire case base or a single case.
+        validation_model: Pydantic model to validate the data.
+
+    Examples:
+        >>> from pydantic import BaseModel, PositiveInt, NonNegativeInt
+        >>> from data.cars_validation_model import Car
+        >>> from pathlib import Path
+        >>> data = path(Path("data/cars-1k.csv"))
+        >>> validate(data, Car)
+        >>> import pandas as pd
+        >>> df = pd.read_csv("data/cars-1k.csv")
+        >>> data = dataframe(df)
+        >>> validate(data, Car)
+    """
+    assert data is not None
+
+    if isinstance(data, DataFrameCasebase):
+        data = data.df.to_dict("index")
+
+    if isinstance(data, Mapping):
+        for item in data.values():
+            validation_model.model_validate(item)
+    else:
+        validation_model.model_validate(data)

cbrkit-0.9.0/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-0.7.0 → cbrkit-0.9.0}/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-0.7.0 → cbrkit-0.9.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cbrkit"
-version = "0.7.0"
+version = "0.9.0"
 description = "Customizable Case-Based Reasoning (CBR) toolkit for Python with a built-in API and CLI."
 authors = ["Mirko Lenz <mirko@mirkolenz.com>"]
 license = "MIT"
@@ -40,8 +40,10 @@ cbrkit = "cbrkit.cli:app"
 
 [tool.poetry.dependencies]
 python = ">=3.11, <3.13"
+dtaidistance = { version = "^2.3", optional = true }
 fastapi = { version = ">=0.100, <1.0", optional = true, extras = ["all"] }
 levenshtein = { version = ">=0.23, <1.0", optional = true }
+minineedle = { version = "^3.1", optional = true }
 nltk = { version = "^3.8", optional = true }
 openai = { version = "^1.5", optional = true }
 orjson = "^3.9"
@@ -49,16 +51,19 @@ pandas = "^2.1"
 pyarrow = ">=13.0"
 pyyaml = "^6.0"
 sentence-transformers = { version = "^2.2", optional = true }
+setuptools = "^69"
 spacy = { version = "^3.7", optional = true }
 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"] }
 xmltodict = ">=0.13, <1.0"
+pydantic = "^2.0"
 
 [tool.poetry.group.dev.dependencies]
-pytest = "^8.0.0"
-pytest-cov = "^5.0.0"
+pytest = "^8.0"
+pytest-cov = "^5.0"
+ruff = "^0.3"
 
 [tool.poetry.group.docs.dependencies]
 pdoc = "^14.4"
@@ -71,16 +76,18 @@ 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"
@@ -89,7 +96,7 @@ doctest_optionflags = "NORMALIZE_WHITESPACE IGNORE_EXCEPTION_DETAIL ELLIPSIS"
 [tool.ruff]
 target-version = "py311"
 
-[tool.ruff.pydocstyle]
+[tool.ruff.lint.pydocstyle]
 convention = "google"
 
 [build-system]

cbrkit-0.7.0/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