MaldiAMRKit 0.17.0__tar.gz → 0.18.0__tar.gz

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0/MaldiAMRKit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MaldiAMRKit
-Version: 0.17.0
+Version: 0.18.0
 Summary: A comprehensive toolkit for MALDI-TOF mass spectrometry data preprocessing for antimicrobial resistance (AMR) prediction purposes
 Author-email: Ettore Rocchi <ettore.rocchi3@unibo.it>
 License-Expression: MIT
@@ -41,14 +41,14 @@ Requires-Dist: sphinx>=7.0.0; extra == "docs"
 Requires-Dist: pydata-sphinx-theme>=0.15.0; extra == "docs"
 Requires-Dist: sphinx-autodoc-typehints>=2.0.0; extra == "docs"
 Requires-Dist: sphinx-design>=0.6.0; extra == "docs"
-Requires-Dist: sphinx-click>=5.0.0; extra == "docs"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "docs"
 Requires-Dist: nbsphinx>=0.9.0; extra == "docs"
 Requires-Dist: ipykernel>=6.0.0; extra == "docs"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: sphinx-click>=5.0.0; extra == "dev"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: batch
 Requires-Dist: umap-learn>=0.5; extra == "batch"

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/MaldiAMRKit.egg-info/SOURCES.txt

@@ -65,7 +65,6 @@ maldiamrkit/drift/peak_drift.py
 maldiamrkit/drift/plots.py
 maldiamrkit/drift/reference.py
 maldiamrkit/evaluation/__init__.py
-maldiamrkit/evaluation/label_encoder.py
 maldiamrkit/evaluation/metrics.py
 maldiamrkit/evaluation/mic_regression.py
 maldiamrkit/evaluation/splitting.py

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/MaldiAMRKit.egg-info/requires.txt

@@ -21,7 +21,7 @@ combatlearn>=1.3
 pytest>=7.0.0
 pytest-cov>=4.0.0
 ruff>=0.1.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 hypothesis>=6.0.0
 
 [docs]
@@ -29,6 +29,6 @@ sphinx>=7.0.0
 pydata-sphinx-theme>=0.15.0
 sphinx-autodoc-typehints>=2.0.0
 sphinx-design>=0.6.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 nbsphinx>=0.9.0
 ipykernel>=6.0.0

{maldiamrkit-0.17.0/MaldiAMRKit.egg-info → maldiamrkit-0.18.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: MaldiAMRKit
-Version: 0.17.0
+Version: 0.18.0
 Summary: A comprehensive toolkit for MALDI-TOF mass spectrometry data preprocessing for antimicrobial resistance (AMR) prediction purposes
 Author-email: Ettore Rocchi <ettore.rocchi3@unibo.it>
 License-Expression: MIT
@@ -41,14 +41,14 @@ Requires-Dist: sphinx>=7.0.0; extra == "docs"
 Requires-Dist: pydata-sphinx-theme>=0.15.0; extra == "docs"
 Requires-Dist: sphinx-autodoc-typehints>=2.0.0; extra == "docs"
 Requires-Dist: sphinx-design>=0.6.0; extra == "docs"
-Requires-Dist: sphinx-click>=5.0.0; extra == "docs"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "docs"
 Requires-Dist: nbsphinx>=0.9.0; extra == "docs"
 Requires-Dist: ipykernel>=6.0.0; extra == "docs"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
-Requires-Dist: sphinx-click>=5.0.0; extra == "dev"
+Requires-Dist: sphinxcontrib-typer>=0.5.0; extra == "dev"
 Requires-Dist: hypothesis>=6.0.0; extra == "dev"
 Provides-Extra: batch
 Requires-Dist: umap-learn>=0.5; extra == "batch"

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/__init__.py

@@ -27,7 +27,7 @@ Examples
 from .dataset import MaldiSet
 from .spectrum import MaldiSpectrum
 
-__version__ = "0.17.0"
+__version__ = "0.18.0"
 __author__ = "Ettore Rocchi"
 
 __all__ = [

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/peak_align.py

@@ -12,7 +12,7 @@ from __future__ import annotations
 import numpy as np
 
 from ..detection.peaklist import PeakSet
-from .strategies import ALIGNMENT_REGISTRY, AlignmentMethod, AlignmentStrategy
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod, AlignmentStrategy
 
 
 def _build_strategy(
@@ -24,7 +24,7 @@ def _build_strategy(
     lowess_it: int,
 ) -> AlignmentStrategy:
     """Instantiate the requested alignment strategy with its parameters."""
-    cls = ALIGNMENT_REGISTRY[method]
+    cls = _ALIGNMENT_REGISTRY[method]
     if method in (AlignmentMethod.shift, AlignmentMethod.linear):
         return cls(max_shift=max_shift_da)
     if method == AlignmentMethod.piecewise:

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/raw_warping.py

@@ -16,7 +16,7 @@ from ..io.readers import read_spectrum
 from ..preprocessing.binning import BinningMethod, bin_spectrum
 from ..preprocessing.pipeline import preprocess
 from ..preprocessing.preprocessing_pipeline import PreprocessingPipeline
-from .strategies import ALIGNMENT_REGISTRY, AlignmentMethod
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod
 
 
 def create_raw_input(
@@ -393,7 +393,7 @@ class RawWarping(BaseEstimator, TransformerMixin):
 
     def _get_strategy(self):
         """Build strategy instance from current parameters."""
-        cls = ALIGNMENT_REGISTRY[self.method]
+        cls = _ALIGNMENT_REGISTRY[self.method]
         if self.method == "shift":
             return cls(max_shift=self.max_shift_da)
         elif self.method == "linear":

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/strategies.py

@@ -689,7 +689,7 @@ class LOWESSStrategy(AlignmentStrategy):
         return new_mz, intensity
 
 
-ALIGNMENT_REGISTRY: dict[str, type[AlignmentStrategy]] = {
+_ALIGNMENT_REGISTRY: dict[str, type[AlignmentStrategy]] = {
     "shift": ShiftStrategy,
     "linear": LinearStrategy,
     "piecewise": PiecewiseStrategy,

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/alignment/warping.py

@@ -10,7 +10,7 @@ from joblib import Parallel, delayed
 from sklearn.base import BaseEstimator, TransformerMixin
 
 from ..detection.peak_detector import MaldiPeakDetector
-from .strategies import ALIGNMENT_REGISTRY, AlignmentMethod, DTWStrategy
+from .strategies import _ALIGNMENT_REGISTRY, AlignmentMethod, DTWStrategy
 
 
 class Warping(BaseEstimator, TransformerMixin):
@@ -177,7 +177,7 @@ class Warping(BaseEstimator, TransformerMixin):
 
     def _get_strategy(self):
         """Build strategy instance from current parameters."""
-        cls = ALIGNMENT_REGISTRY[self.method]
+        cls = _ALIGNMENT_REGISTRY[self.method]
         if self.method == "shift":
             return cls(max_shift=self.max_shift)
         elif self.method == "linear":

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/cli.py

@@ -420,7 +420,5 @@ def build(
         )
 
 
-typer_click_object = typer.main.get_command(app)
-
 if __name__ == "__main__":
     app()

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/data/__init__.py

@@ -22,8 +22,6 @@ from .duplicates import DuplicateStrategy
 from .input_layouts import BrukerTreeLayout, FlatLayout, InputLayout
 from .loader import DatasetLoader
 from .site_info import (
-    CURRENT_FORMAT_VERSION,
-    MANIFEST_FILENAME,
     BuildInfo,
     SiteInfo,
     read_site_info,
@@ -53,6 +51,4 @@ __all__ = [
     "BuildInfo",
     "read_site_info",
     "write_site_info",
-    "MANIFEST_FILENAME",
-    "CURRENT_FORMAT_VERSION",
 ]

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/data/dataset_layouts.py

@@ -30,7 +30,7 @@ logger = logging.getLogger(__name__)
 class _Sentinel:
     """Sentinel for ``DRIAMSLayout`` kwargs.
 
-    A kwarg defaulted to :data:`_AUTO` means: "fill from ``site_info.json``
+    A kwarg defaulted to ``_AUTO`` means: "fill from ``site_info.json``
     if present, otherwise use the library default".  Explicit kwargs
     always win.
     """
@@ -255,7 +255,7 @@ class DRIAMSLayout(DatasetLayout):
     ) -> None:
         """Initialise the layout.
 
-        Several kwargs accept the sentinel :data:`_AUTO` as their default.
+        Several kwargs accept the sentinel ``_AUTO`` as their default.
         When ``_AUTO``, the value is filled from ``site_info.json`` at the
         dataset root (if present) and otherwise falls back to the
         library-level default.  Explicit kwargs always win.  Fields with

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/data/site_info.py

@@ -45,10 +45,10 @@ from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any
 
-MANIFEST_FILENAME = "site_info.json"
+_MANIFEST_FILENAME = "site_info.json"
 """On-disk filename for the manifest, written at the dataset root."""
 
-CURRENT_FORMAT_VERSION = 1
+_CURRENT_FORMAT_VERSION = 1
 """Manifest schema version produced by *this* MaldiAMRKit release."""
 
 _REQUIRED_V1_KEYS: tuple[str, ...] = (
@@ -65,7 +65,7 @@ _REQUIRED_V1_KEYS: tuple[str, ...] = (
 
 @dataclass
 class BuildInfo:
-    """Optional provenance block nested under :attr:`SiteInfo.build_info`.
+    """Optional provenance block nested under :attr:`~maldiamrkit.data.SiteInfo.build_info`.
 
     Informational only; readers may inspect it but are not required to
     interpret any field.  All fields are optional.
@@ -102,8 +102,9 @@ class SiteInfo:
         Bin width in Daltons used at build time.
     build_info : BuildInfo, optional
         Optional provenance block.
-    format_version : int, default=:data:`CURRENT_FORMAT_VERSION`
-        Manifest schema version.
+    format_version : int, optional
+        Manifest schema version; defaults to the current release's schema
+        version.
     """
 
     id_column: str
@@ -114,7 +115,7 @@ class SiteInfo:
     mz_range: tuple[float, float]
     bin_width: float
     build_info: BuildInfo | None = None
-    format_version: int = CURRENT_FORMAT_VERSION
+    format_version: int = _CURRENT_FORMAT_VERSION
 
     def to_dict(self) -> dict[str, Any]:
         """Serialise as a plain dict, with ``format_version`` first."""
@@ -134,7 +135,7 @@ class SiteInfo:
 
 
 def write_site_info(dataset_dir: str | Path, site_info: SiteInfo) -> Path:
-    """Write a :class:`SiteInfo` to ``<dataset_dir>/site_info.json``.
+    """Write a :class:`~maldiamrkit.data.SiteInfo` to ``<dataset_dir>/site_info.json``.
 
     Parameters
     ----------
@@ -153,7 +154,7 @@ def write_site_info(dataset_dir: str | Path, site_info: SiteInfo) -> Path:
         raise FileNotFoundError(
             f"Cannot write manifest: dataset directory does not exist: {dataset_dir}"
         )
-    path = dataset_dir / MANIFEST_FILENAME
+    path = dataset_dir / _MANIFEST_FILENAME
     data = site_info.to_dict()
     path.write_text(json.dumps(data, indent=2, sort_keys=False) + "\n")
     return path
@@ -187,11 +188,11 @@ def read_site_info(
         If the manifest is malformed, missing a required field, or has
         a non-integer ``format_version``.
     """
-    path = Path(dataset_dir) / MANIFEST_FILENAME
+    path = Path(dataset_dir) / _MANIFEST_FILENAME
     if not path.exists():
         if missing_ok:
             return None
-        raise FileNotFoundError(f"{MANIFEST_FILENAME} not found in {dataset_dir}")
+        raise FileNotFoundError(f"{_MANIFEST_FILENAME} not found in {dataset_dir}")
 
     try:
         raw = json.loads(path.read_text())
@@ -218,10 +219,10 @@ def _site_info_from_dict(
     if not isinstance(fv, int):
         raise ValueError(f"site_info{where} has non-integer format_version={fv!r}.")
 
-    if fv > CURRENT_FORMAT_VERSION:
+    if fv > _CURRENT_FORMAT_VERSION:
         warnings.warn(
             f"site_info{where} was written by a newer MaldiAMRKit "
-            f"(format_version={fv}; this reader knows v{CURRENT_FORMAT_VERSION}). "
+            f"(format_version={fv}; this reader knows v{_CURRENT_FORMAT_VERSION}). "
             "Reading what I can; unknown fields will be ignored. "
             "Upgrade `maldiamrkit` if loading misbehaves.",
             UserWarning,
@@ -282,8 +283,6 @@ def _current_iso_utc() -> str:
 
 
 __all__ = [
-    "MANIFEST_FILENAME",
-    "CURRENT_FORMAT_VERSION",
     "SiteInfo",
     "BuildInfo",
     "read_site_info",

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/detection/peak_detector.py

@@ -14,7 +14,7 @@ from scipy.signal import find_peaks, peak_prominences
 from sklearn.base import BaseEstimator, TransformerMixin
 
 from .peaklist import (
-    RANK_BY,
+    _RANK_BY,
     PeakList,
     PeakSet,
     _array_hash,
@@ -365,7 +365,7 @@ class MaldiPeakDetector(BaseEstimator, TransformerMixin):
     def _detect_peaks_ph_scored(self, row: np.ndarray) -> tuple[np.ndarray, np.ndarray]:
         """Detect persistent-homology peaks and their persistence values.
 
-        Like :meth:`_detect_peaks_ph` but also returns the persistence
+        Like ``_detect_peaks_ph`` but also returns the persistence
         (death - birth) of each kept peak, index-ascending.
 
         Parameters
@@ -451,7 +451,9 @@ class MaldiPeakDetector(BaseEstimator, TransformerMixin):
                 raise ValueError("rank_by='persistence' requires method='ph'.")
             scores = persistences
         else:
-            raise ValueError(f"Unknown rank_by={rank_by!r}; expected one of {RANK_BY}.")
+            raise ValueError(
+                f"Unknown rank_by={rank_by!r}; expected one of {_RANK_BY}."
+            )
         return indices, np.asarray(scores, dtype=float)
 
     def detect_peakset(
@@ -560,8 +562,10 @@ class MaldiPeakDetector(BaseEstimator, TransformerMixin):
         PeakList
             One :class:`PeakSet` per spectrum.
         """
-        if rank_by not in RANK_BY:
-            raise ValueError(f"Unknown rank_by={rank_by!r}; expected one of {RANK_BY}.")
+        if rank_by not in _RANK_BY:
+            raise ValueError(
+                f"Unknown rank_by={rank_by!r}; expected one of {_RANK_BY}."
+            )
         if isinstance(X, pd.Series):
             X = X.to_frame().T
 

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/detection/peaklist.py

@@ -23,7 +23,7 @@ from typing import Any, Sequence
 import numpy as np
 import pandas as pd
 
-RANK_BY = ("intensity", "persistence", "prominence")
+_RANK_BY = ("intensity", "persistence", "prominence")
 
 
 def _config_hash(config: dict[str, Any]) -> str:
@@ -147,7 +147,7 @@ class PeakSet:
 
 
 class PeakList:
-    """A collection of per-spectrum :class:`PeakSet` objects.
+    """A collection of per-spectrum :class:`~maldiamrkit.detection.PeakSet` objects.
 
     Parameters
     ----------
@@ -364,7 +364,7 @@ def create_peakset_input(
     pipeline: Any | None = None,
     cache_dir: str | Path | None = None,
 ) -> PeakList:
-    """Build a :class:`PeakList` from a directory of raw spectrum files.
+    """Build a :class:`~maldiamrkit.detection.PeakList` from a directory of raw spectrum files.
 
     Analogue of :func:`maldiamrkit.alignment.create_raw_input`: discovers raw
     spectrum files, preprocesses each one per-spectrum, detects peaks at full
@@ -410,8 +410,8 @@ def create_peakset_input(
     from ..preprocessing.preprocessing_pipeline import PreprocessingPipeline
     from .peak_detector import MaldiPeakDetector
 
-    if rank_by not in RANK_BY:
-        raise ValueError(f"Unknown rank_by={rank_by!r}; expected one of {RANK_BY}.")
+    if rank_by not in _RANK_BY:
+        raise ValueError(f"Unknown rank_by={rank_by!r}; expected one of {_RANK_BY}.")
     if detector is None:
         detector = MaldiPeakDetector()
     pipe = pipeline or PreprocessingPipeline.default()

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/drift/reference.py

@@ -42,7 +42,7 @@ def _reference_similarity_timeseries(
     timestamps : pd.Series
         Parsed datetime Series aligned with ``X.index``.
     reference : ndarray
-        Reference spectrum from :func:`_compute_reference_spectrum`.
+        Reference spectrum from ``_compute_reference_spectrum``.
     window : str or pd.Timedelta
         Time window size forwarded to :class:`pandas.Grouper` (e.g.
         ``"30D"``).

maldiamrkit-0.18.0/maldiamrkit/evaluation/__init__.py

@@ -0,0 +1,44 @@
+"""Evaluation utilities for AMR prediction.
+
+Binary AMR metrics, MIC-regression reporting, and CV splitting helpers.
+"""
+
+from __future__ import annotations
+
+from .metrics import (
+    amr_classification_report,
+    amr_multilabel_report,
+    categorical_agreement,
+    major_error_rate,
+    me_scorer,
+    sensitivity_score,
+    specificity_score,
+    very_major_error_rate,
+    vme_me_curve,
+    vme_scorer,
+)
+from .mic_regression import mic_regression_report
+from .splitting import (
+    CaseGroupedKFold,
+    SpeciesDrugStratifiedKFold,
+    case_based_split,
+    stratified_species_drug_split,
+)
+
+__all__ = [
+    "very_major_error_rate",
+    "major_error_rate",
+    "sensitivity_score",
+    "specificity_score",
+    "categorical_agreement",
+    "vme_me_curve",
+    "amr_classification_report",
+    "amr_multilabel_report",
+    "mic_regression_report",
+    "vme_scorer",
+    "me_scorer",
+    "stratified_species_drug_split",
+    "case_based_split",
+    "SpeciesDrugStratifiedKFold",
+    "CaseGroupedKFold",
+]

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/preprocessing/__init__.py

@@ -1,6 +1,12 @@
 """Preprocessing functions for MALDI-TOF spectra."""
 
-from .binning import BinningMethod, bin_spectrum, get_bin_metadata
+from .binning import (
+    BinningMethod,
+    bin_spectrum,
+    get_bin_metadata,
+    register_binning_method,
+    unregister_binning_method,
+)
 from .merging import MergingMethod, detect_outlier_replicates, merge_replicates
 from .pipeline import preprocess
 from .preprocessing_pipeline import PreprocessingPipeline
@@ -30,6 +36,8 @@ __all__ = [
     "BinningMethod",
     "bin_spectrum",
     "get_bin_metadata",
+    "register_binning_method",
+    "unregister_binning_method",
     # Merging
     "MergingMethod",
     "merge_replicates",

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/preprocessing/binning.py

@@ -377,23 +377,95 @@ def _custom_edge_fn(*, mz_min, mz_max, custom_edges=None, **_kwargs) -> np.ndarr
     return _validate_custom_edges(custom_edges, mz_min, mz_max)
 
 
-BINNING_REGISTRY: dict[str, Callable[..., np.ndarray]] = {
+_BINNING_REGISTRY: dict[str, Callable[..., np.ndarray]] = {
     "uniform": _uniform_edge_fn,
     "proportional": _proportional_edge_fn,
     "adaptive": _adaptive_edge_fn,
     "custom": _custom_edge_fn,
 }
-"""Registry mapping binning method names to edge-generator functions.
+"""Internal registry mapping binning method names to edge-generator functions.
 
-To add a custom binning method::
+Register custom methods with :func:`register_binning_method` rather than
+mutating this mapping directly.
+"""
 
-    from maldiamrkit.preprocessing.binning import BINNING_REGISTRY
+_DEFAULT_BINNING_METHODS: frozenset[str] = frozenset(_BINNING_REGISTRY)
+"""Names of the built-in methods, which cannot be unregistered."""
 
-    def my_edges(*, mz_min, mz_max, **kwargs):
-        return np.array([mz_min, (mz_min + mz_max) / 2, mz_max])
 
-    BINNING_REGISTRY["my_method"] = my_edges
-"""
+def register_binning_method(name: str, edge_fn: Callable[..., np.ndarray]) -> None:
+    """Register a custom binning method for use with :func:`~maldiamrkit.preprocessing.bin_spectrum`.
+
+    After registration, pass ``method=name`` to :func:`bin_spectrum` to bin
+    with the custom edges.
+
+    Parameters
+    ----------
+    name : str
+        Method name to expose. Overwrites any existing method of the same
+        name, including the built-ins.
+    edge_fn : callable
+        Edge-generator returning a 1-D array of monotonically increasing bin
+        edges. It is called with keyword arguments ``df``, ``mz_min``,
+        ``mz_max``, ``bin_width``, ``custom_edges`` and the ``adaptive_*``
+        parameters forwarded from :func:`bin_spectrum`; accept ``**kwargs``
+        to ignore the ones it does not need.
+
+    Raises
+    ------
+    TypeError
+        If ``edge_fn`` is not callable.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from maldiamrkit.preprocessing import register_binning_method, bin_spectrum
+    >>> def my_edges(*, mz_min, mz_max, **kwargs):
+    ...     return np.array([mz_min, (mz_min + mz_max) / 2, mz_max])
+    >>> register_binning_method("my_method", my_edges)
+    >>> # binned, meta = bin_spectrum(df, method="my_method")
+    """
+    if not callable(edge_fn):
+        raise TypeError(f"edge_fn must be callable, got {type(edge_fn).__name__}.")
+    _BINNING_REGISTRY[name] = edge_fn
+
+
+def unregister_binning_method(name: str) -> None:
+    """Remove a custom binning method added with :func:`register_binning_method`.
+
+    Parameters
+    ----------
+    name : str
+        Method name to remove. Must have been registered with
+        :func:`register_binning_method`.
+
+    Raises
+    ------
+    ValueError
+        If ``name`` is one of the built-in methods ('uniform',
+        'proportional', 'adaptive', 'custom'), which cannot be removed.
+    KeyError
+        If no method named ``name`` is registered.
+
+    Examples
+    --------
+    >>> import numpy as np
+    >>> from maldiamrkit.preprocessing import (
+    ...     register_binning_method,
+    ...     unregister_binning_method,
+    ... )
+    >>> register_binning_method("my_method", lambda **kw: np.array([2000, 20000]))
+    >>> unregister_binning_method("my_method")
+    """
+    if name in _DEFAULT_BINNING_METHODS:
+        raise ValueError(
+            f"Cannot unregister built-in binning method {name!r}. "
+            f"Built-in methods are {sorted(_DEFAULT_BINNING_METHODS)}."
+        )
+    try:
+        del _BINNING_REGISTRY[name]
+    except KeyError:
+        raise KeyError(f"No binning method named {name!r} is registered.") from None
 
 
 def bin_spectrum(
@@ -428,8 +500,9 @@ def bin_spectrum(
         For 'proportional', this is the reference width at mz_min.
         Ignored for 'adaptive' and 'custom' methods.
     method : str, default='uniform'
-        Binning method. One of 'uniform', 'proportional', 'adaptive',
-        'custom'.
+        Binning method. One of the built-ins 'uniform', 'proportional',
+        'adaptive', 'custom', or a custom name registered with
+        :func:`register_binning_method`.
     custom_edges : array-like, optional
         User-provided bin edges. Required if method='custom'.
     adaptive_min_width : float, default=1.0
@@ -473,7 +546,16 @@ def bin_spectrum(
     >>> edges = [2000, 5000, 10000, 15000, 20000]
     >>> binned, metadata = bin_spectrum(df, method='custom', custom_edges=edges)
     """
-    method = BinningMethod(method)
+    try:
+        method = BinningMethod(method)
+    except ValueError:
+        # Allow custom methods registered via register_binning_method().
+        if method not in _BINNING_REGISTRY:
+            raise ValueError(
+                f"{method!r} is not a valid binning method. Use one of "
+                f"{sorted(_BINNING_REGISTRY)} or register a custom method "
+                "with register_binning_method()."
+            ) from None
 
     if mz_min >= mz_max:
         raise ValueError(f"mz_min ({mz_min}) must be less than mz_max ({mz_max}).")
@@ -482,7 +564,7 @@ def bin_spectrum(
         raise ValueError(f"mz_min must be > 0 for {method} binning, got {mz_min}")
 
     # Generate bin edges via registry
-    edge_fn = BINNING_REGISTRY[method]
+    edge_fn = _BINNING_REGISTRY[method]
     edges = edge_fn(
         df=df,
         mz_min=mz_min,

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/preprocessing/preprocessing_pipeline.py

@@ -33,7 +33,7 @@ from typing import Protocol, runtime_checkable
 import pandas as pd
 
 from .transformers import (
-    TRANSFORMER_REGISTRY,
+    _TRANSFORMER_REGISTRY,
     ClipNegatives,
     MzTrimmer,
     SavitzkyGolaySmooth,
@@ -190,7 +190,7 @@ class PreprocessingPipeline:
         for step_dict in d["steps"]:
             step_name = step_dict["step_name"]
             transformer_name = step_dict["name"]
-            transformer_cls = TRANSFORMER_REGISTRY[transformer_name]
+            transformer_cls = _TRANSFORMER_REGISTRY[transformer_name]
 
             # Extract constructor kwargs (everything except step_name and name)
             kwargs = {

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/preprocessing/transformers.py

@@ -603,7 +603,7 @@ class MzMultiTrimmer:
 
 
 # Registry mapping transformer names to classes (for deserialization)
-TRANSFORMER_REGISTRY: dict[str, type] = {
+_TRANSFORMER_REGISTRY: dict[str, type] = {
     "ClipNegatives": ClipNegatives,
     "SqrtTransform": SqrtTransform,
     "LogTransform": LogTransform,

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/similarity/__init__.py

@@ -10,14 +10,13 @@ from .clustering import (
     kmedoids_clustering,
     silhouette_scores,
 )
-from .metrics import METRIC_REGISTRY, SpectralMetric, spectral_distance
+from .metrics import SpectralMetric, spectral_distance
 from .pairwise import pairwise_distances
 from .plots import plot_dendrogram, plot_distance_heatmap
 
 __all__ = [
     "ClusteringMethod",
     "KMedoidsInit",
-    "METRIC_REGISTRY",
     "SpectralMetric",
     "cluster_metadata_concordance",
     "cluster_spectra",

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/similarity/metrics.py

@@ -175,13 +175,19 @@ class SpectralMetric(str, Enum):
     pearson = "pearson"
 
 
-METRIC_REGISTRY: dict[str, Callable] = {
+_METRIC_REGISTRY: dict[str, Callable] = {
     "wasserstein": _wasserstein_distance,
     "dtw": _dtw_distance,
     "cosine": _cosine_distance,
     "spectral_contrast_angle": _spectral_contrast_angle,
     "pearson": _pearson_correlation,
 }
+"""Mapping of metric name to its pairwise spectral-distance function.
+
+Keys are the values of :class:`~maldiamrkit.similarity.SpectralMetric`
+(``"wasserstein"``, ``"dtw"``, ``"cosine"``, ``"spectral_contrast_angle"``,
+``"pearson"``).
+"""
 
 
 def spectral_distance(
@@ -200,7 +206,7 @@ def spectral_distance(
         For binned metrics (``"cosine"``, ``"spectral_contrast_angle"``,
         ``"pearson"``): 1-D intensity arrays.
     metric : str or SpectralMetric, default="wasserstein"
-        Key in :data:`METRIC_REGISTRY`.
+        One of the values of :class:`~maldiamrkit.similarity.SpectralMetric`.
 
     Returns
     -------
@@ -210,7 +216,7 @@ def spectral_distance(
     Raises
     ------
     ValueError
-        If *metric* is not in :data:`METRIC_REGISTRY`.
+        If *metric* is not a recognised :class:`~maldiamrkit.similarity.SpectralMetric`.
     """
     metric = SpectralMetric(metric)
-    return METRIC_REGISTRY[metric](spec_a, spec_b)
+    return _METRIC_REGISTRY[metric](spec_a, spec_b)

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/similarity/pairwise.py

@@ -8,7 +8,7 @@ import numpy as np
 import pandas as pd
 from joblib import Parallel, delayed
 
-from .metrics import METRIC_REGISTRY, SpectralMetric, spectral_distance
+from .metrics import _METRIC_REGISTRY, SpectralMetric, spectral_distance
 
 if TYPE_CHECKING:
     from maldiamrkit.spectrum import MaldiSpectrum
@@ -31,7 +31,7 @@ def pairwise_distances(
         :class:`~maldiamrkit.spectrum.MaldiSpectrum`, raw/preprocessed data
         is used.
     metric : str or SpectralMetric, default="wasserstein"
-        Key in :data:`~maldiamrkit.similarity.METRIC_REGISTRY`.
+        One of the values of :class:`~maldiamrkit.similarity.SpectralMetric`.
     n_jobs : int, default=1
         Number of parallel jobs for pairwise computation.
 
@@ -61,7 +61,7 @@ def _pairwise_binned(X: pd.DataFrame, metric: str) -> np.ndarray:
     """Fast path using sklearn for binned feature matrices."""
     from sklearn.metrics import pairwise_distances as sklearn_pd
 
-    metric_fn = METRIC_REGISTRY[metric]
+    metric_fn = _METRIC_REGISTRY[metric]
     arr = X.values
 
     def _metric(a: np.ndarray, b: np.ndarray) -> float:

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/susceptibility/label_encoder.py

@@ -1,10 +1,6 @@
 """Label encoding utilities for AMR classification.
 
 Maps clinical resistance categories (R/I/S) to binary or numeric labels.
-Previously lived under ``maldiamrkit.evaluation``; moved here in v0.15 to
-group together with :class:`~maldiamrkit.susceptibility.MICEncoder` and
-:class:`~maldiamrkit.susceptibility.BreakpointTable`. The old import path
-still works for one release with a :class:`DeprecationWarning`.
 
 Examples
 --------

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/visualization/_common.py

@@ -13,7 +13,7 @@ from typing import Any
 
 _SUSCEPTIBILITY_ORDER: dict[str, int] = {"S": 0, "I": 1, "R": 2}
 
-DEFAULT_LABEL_MAP: dict = {
+_DEFAULT_LABEL_MAP: dict = {
     0: "Susceptible (S)",
     1: "Resistant (R)",
     "S": "Susceptible (S)",
@@ -64,4 +64,4 @@ def resolve_display_label(label: Any, label_map: dict | None = None) -> str:
     """
     if label_map and label in label_map:
         return str(label_map[label])
-    return str(DEFAULT_LABEL_MAP.get(label, label))
+    return str(_DEFAULT_LABEL_MAP.get(label, label))

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/maldiamrkit/visualization/spectrum_plots.py

@@ -8,7 +8,7 @@ from typing import TYPE_CHECKING, Any, Literal
 import numpy as np
 import pandas as pd
 
-from ._common import DEFAULT_LABEL_MAP, order_labels, show_with_warning
+from ._common import _DEFAULT_LABEL_MAP, order_labels, show_with_warning
 
 if TYPE_CHECKING:
     from matplotlib.axes import Axes
@@ -312,7 +312,7 @@ def plot_pseudogel(
     display_vmin = np.log1p(vmin) if (log_scale and vmin is not None) else vmin
     display_vmax = np.log1p(vmax) if (log_scale and vmax is not None) else vmax
 
-    merged_label_map: dict = dict(DEFAULT_LABEL_MAP)
+    merged_label_map: dict = dict(_DEFAULT_LABEL_MAP)
     if label_map:
         merged_label_map.update(label_map)
 

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/requirements-dev.txt

@@ -2,5 +2,5 @@
 pytest>=7.0.0
 pytest-cov>=4.0.0
 ruff>=0.1.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 hypothesis>=6.0.0

{maldiamrkit-0.17.0 → maldiamrkit-0.18.0}/requirements-docs.txt

@@ -5,7 +5,7 @@ sphinx>=7.0.0
 pydata-sphinx-theme>=0.15.0
 sphinx-autodoc-typehints>=2.0.0
 sphinx-design>=0.6.0
-sphinx-click>=5.0.0
+sphinxcontrib-typer>=0.5.0
 
 # Jupyter notebook support
 nbsphinx>=0.9.0

maldiamrkit-0.17.0/maldiamrkit/evaluation/__init__.py

@@ -1,81 +0,0 @@
-"""Evaluation utilities for AMR prediction.
-
-The label encoder previously lived here; in v0.15 it moved to
-:mod:`maldiamrkit.susceptibility` along with the new MIC encoder and
-breakpoint table. Access via ``from maldiamrkit.evaluation import LabelEncoder``
-still works for one release with a :class:`DeprecationWarning`.
-"""
-
-from __future__ import annotations
-
-import warnings
-
-from .metrics import (
-    amr_classification_report,
-    amr_multilabel_report,
-    categorical_agreement,
-    major_error_rate,
-    me_scorer,
-    sensitivity_score,
-    specificity_score,
-    very_major_error_rate,
-    vme_me_curve,
-    vme_scorer,
-)
-from .mic_regression import mic_regression_report
-from .splitting import (
-    CaseGroupedKFold,
-    SpeciesDrugStratifiedKFold,
-    case_based_split,
-    stratified_species_drug_split,
-)
-
-_LAZY_DEPRECATED = {
-    "LabelEncoder": "maldiamrkit.susceptibility.LabelEncoder",
-    "IntermediateHandling": "maldiamrkit.susceptibility.IntermediateHandling",
-}
-
-
-def __getattr__(name: str):
-    if name in _LAZY_DEPRECATED:
-        new_path = _LAZY_DEPRECATED[name]
-        warnings.warn(
-            f"{name} has moved to {new_path}; "
-            f"importing from maldiamrkit.evaluation is deprecated and "
-            f"will be removed in v0.17.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        from ..susceptibility.label_encoder import (
-            IntermediateHandling,
-            LabelEncoder,
-        )
-
-        return {
-            "LabelEncoder": LabelEncoder,
-            "IntermediateHandling": IntermediateHandling,
-        }[name]
-    raise AttributeError(f"module 'maldiamrkit.evaluation' has no attribute {name!r}")
-
-
-def __dir__() -> list[str]:
-    return sorted(list(__all__) + list(_LAZY_DEPRECATED.keys()))
-
-
-__all__ = [
-    "very_major_error_rate",
-    "major_error_rate",
-    "sensitivity_score",
-    "specificity_score",
-    "categorical_agreement",
-    "vme_me_curve",
-    "amr_classification_report",
-    "amr_multilabel_report",
-    "mic_regression_report",
-    "vme_scorer",
-    "me_scorer",
-    "stratified_species_drug_split",
-    "case_based_split",
-    "SpeciesDrugStratifiedKFold",
-    "CaseGroupedKFold",
-]

maldiamrkit-0.17.0/maldiamrkit/evaluation/label_encoder.py

@@ -1,42 +0,0 @@
-"""Deprecated location for :class:`LabelEncoder`.
-
-Moved to :mod:`maldiamrkit.susceptibility` in v0.15. Attribute access on
-this module emits a :class:`DeprecationWarning` and forwards to the new
-location; the shim will be removed in a future release.
-"""
-
-from __future__ import annotations
-
-import warnings
-
-_DEPRECATED = ("LabelEncoder", "IntermediateHandling")
-
-
-def __getattr__(name: str):
-    if name in _DEPRECATED:
-        warnings.warn(
-            "maldiamrkit.evaluation.label_encoder is deprecated; "
-            "import from maldiamrkit.susceptibility instead. "
-            "Will be removed in v0.17.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        from ..susceptibility.label_encoder import (
-            IntermediateHandling,
-            LabelEncoder,
-        )
-
-        return {
-            "LabelEncoder": LabelEncoder,
-            "IntermediateHandling": IntermediateHandling,
-        }[name]
-    raise AttributeError(
-        f"module 'maldiamrkit.evaluation.label_encoder' has no attribute {name!r}"
-    )
-
-
-def __dir__() -> list[str]:
-    return list(_DEPRECATED)
-
-
-__all__ = list(_DEPRECATED)