dataeval 0.81.0__py3-none-any.whl → 0.82.1__py3-none-any.whl

{dataeval-0.81.0.dist-info → dataeval-0.82.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dataeval
-Version: 0.81.0
+Version: 0.82.1
 Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
 Home-page: https://dataeval.ai/
 License: MIT
@@ -74,7 +74,7 @@ DataEval is easy to install, supports a wide range of Python versions, and is
 compatible with many of the most popular packages in the scientific and T&E
 communities.
 
-DataEval also has native interopability between JATIC's suite of tools when
+DataEval also has native interoperability between JATIC's suite of tools when
 using MAITE-compliant datasets and models.
 <!-- end JATIC interop -->
 

dataeval-0.82.1.dist-info/RECORD

@@ -0,0 +1,105 @@
+dataeval/__init__.py,sha256=5VDv2s5EVQIekwUGMu3Bj2p38NdJToNibRA5do5sjwQ,1510
+dataeval/_log.py,sha256=Mn5bRWO0cgtAYd5VGYSFiPgu57ta3zoktrtHAZ1m3dU,357
+dataeval/config.py,sha256=lAOPOPwXHsMXTmZPpCXvWJ1xBg9HY8e0dRsa5MsIKws,3459
+dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
+dataeval/detectors/drift/__init__.py,sha256=6is_XBtG1d-vUbhHvqXGOdnAwxJ7NA5yRfURn7pCeIw,651
+dataeval/detectors/drift/_base.py,sha256=mJdKvyROgWvz-p1VlAIJqUI6BAj9ss8riUvR5An5wIw,13459
+dataeval/detectors/drift/_cvm.py,sha256=H2w-I0eMD7yP-CSmpdodeJ0-TYznJT7w_H7JuobESow,3859
+dataeval/detectors/drift/_ks.py,sha256=-5k3RBPA3kadX7oD14Wc52rAqQf1udwFeW7Qf3Sv4Tw,4058
+dataeval/detectors/drift/_mmd.py,sha256=NEXowx9UHIvmEKS8sqssw6PMLJMh0BZPhRNX1hYlkz4,7239
+dataeval/detectors/drift/_torch.py,sha256=VrFCyTaRrUslFPy_mYZ4UL70LZ8faH4eHwLurZ9qqNE,7628
+dataeval/detectors/drift/_uncertainty.py,sha256=O5h6_bJbeQEE660SLLP8k-EHqImmKegIcxzcnUKI7X4,5714
+dataeval/detectors/drift/updates.py,sha256=Btu2iaZW7fbO59G1w5v3ykFot0YPzy2U6VjF0d440VE,2195
+dataeval/detectors/linters/__init__.py,sha256=xn2zPwUcmsuf-Jd9uw6AVI11C9z1b1Y9fYtuFnXenZ0,404
+dataeval/detectors/linters/duplicates.py,sha256=tcxniL8rRZkDdQqfuS502UmfKxS3a7iRA22Dtt_vQIk,4935
+dataeval/detectors/linters/outliers.py,sha256=Hln2dPQZjF_uV2QYptA_o6ZF3ugyCImVT-XLDB2-q3A,9042
+dataeval/detectors/ood/__init__.py,sha256=juCYBDs7CQEAtMhnEpPqF6uTrOIH9kTBSuQ_GRw6a8o,283
+dataeval/detectors/ood/ae.py,sha256=YQfhB1ShQLjM1V4uCz9Oo2tCZpOfAZ_-SBCAl4Ac67Y,2921
+dataeval/detectors/ood/base.py,sha256=9b-Ljznf0lB1SXF4F_Aj3eJ4Y3ijGEDPMjucUsWOGJM,3051
+dataeval/detectors/ood/metadata_ood_mi.py,sha256=aMSP3zh5EwIWqM7w135ZAuTVnpqYI4dN3tEOrx41lsk,3837
+dataeval/detectors/ood/mixin.py,sha256=0_o-1HPvgf3-Lf1MSOIfjj5UB8LTLEBGYtJJfyCCzwc,5431
+dataeval/detectors/ood/vae.py,sha256=Fcq0-WbLhzYCgYOAJPBklHm7yuXmFJuEpBkhgwM5kiA,2291
+dataeval/metadata/__init__.py,sha256=B5Ix4T75UPEqY0rofaJlbRf8zCqx8yWLdE3Jo9cALHc,262
+dataeval/metadata/_distance.py,sha256=xsXMMg1pJkHcEZ-KIlqv9YOGYVID3ELjt3-fr1QVnOs,4082
+dataeval/metadata/_ood.py,sha256=DsFnxWgaa6-1FJDg_Q2ZDCeTzhfXpX8YyLvlRGwtJpw,8236
+dataeval/metadata/_utils.py,sha256=r8qBJT83RblobD5W5zyTVi6vYi51Dwkqswizdbzss-M,1169
+dataeval/metrics/__init__.py,sha256=8VC8q3HuJN3o_WN51Ae2_wXznl3RMXIvA5GYVcy7vr8,225
+dataeval/metrics/bias/__init__.py,sha256=1yTLmgiu1kwT_7ZWcjOUbj8R0NJ0DjGoCuWdA0_T7kc,683
+dataeval/metrics/bias/_balance.py,sha256=yADHFrdxW6-WieXIeINqO9cy5vhSIq4tx3Q9Aa1vnTo,6143
+dataeval/metrics/bias/_coverage.py,sha256=PeUoOiaghUEdn6Ov8z2-am7-fnBVIPcFbJK7Ty5JObA,3647
+dataeval/metrics/bias/_diversity.py,sha256=U_l4oYjH39rON2Io0BdCIwJxxob0cKTW8bZNufG0CWs,5820
+dataeval/metrics/bias/_parity.py,sha256=8JRZv4wLpxN9zTvMDlcpKgz-2nO-9eVjqccODcf2nbw,11535
+dataeval/metrics/estimators/__init__.py,sha256=Pnds8uIyAovt2fKqZjiHCIP_kVoBWlVllekYuK5UmmU,568
+dataeval/metrics/estimators/_ber.py,sha256=TrZNO1frRldUDICLzaQGt9wuMiqmvsUFdkZ3cIVv9W4,5344
+dataeval/metrics/estimators/_clusterer.py,sha256=1HrpihGTJ63IkNSOy4Ibw633Gllkm1RxKmoKT5MOgt0,1434
+dataeval/metrics/estimators/_divergence.py,sha256=QDWl1lyAYoO9D3Ho7qOHSk6ud8Gi2MGuXEsYwO1HxvA,4043
+dataeval/metrics/estimators/_uap.py,sha256=BULEBbJ9BQ1IcTeZf0x7iI60QHAWCccBOM97FIu9VXA,1928
+dataeval/metrics/stats/__init__.py,sha256=6tA_9nbbM5ObJ6cds8Y1VBtTQiTOxrpGQSFLu_lWGGA,1098
+dataeval/metrics/stats/_base.py,sha256=5x27-zZMIJR3HcMe_COIx1YOjlVnYK5GaTED6fifRP0,10838
+dataeval/metrics/stats/_boxratiostats.py,sha256=8Kd2FTZ5PLNYZfdAjU_R385gb0Z16JY0L9H_d5ZhgQs,6341
+dataeval/metrics/stats/_dimensionstats.py,sha256=73mFP-Myxne0peFliwvTntc0kk4cpq0krzMvSLDSIMM,2702
+dataeval/metrics/stats/_hashstats.py,sha256=gp9X_pnTT3mPH9YNrWLdn2LQPK_epJ3dQRoyOCwmKlg,4758
+dataeval/metrics/stats/_imagestats.py,sha256=gUPNgN5Zwzdr7WnSwbve1NXNsyxd5dy3cSnlR_7guCg,3007
+dataeval/metrics/stats/_labelstats.py,sha256=PtGyqj4RHw0cyLAWAR9FzZGqgA81AtxLGHZiuMAL2h0,4100
+dataeval/metrics/stats/_pixelstats.py,sha256=SfergRbjNJE4h0xqe-0c8RnKtZmEkZ9MwExdipLSGvg,3247
+dataeval/metrics/stats/_visualstats.py,sha256=cq4AbF2B50Ihbzb86FphcnKQ1TSwNnP3PsnbpiPQZWw,3698
+dataeval/outputs/__init__.py,sha256=FLtrqwjRAT6qeU-BnosWVqvIpOn6dOys18D-fJiYxKw,1609
+dataeval/outputs/_base.py,sha256=aZFbgybnZSQ3ws7QYRLTbDFqUfBFRVtIwX2LZfeGFUA,5703
+dataeval/outputs/_bias.py,sha256=O5RHbTUJDwkwJfz2-YoOfRb4eDl5Tg1UFVtvs025wfA,12173
+dataeval/outputs/_drift.py,sha256=gOiu2C-ERTWiRqlP0auMYxPBGdm9HecWPqWfg7I4tZg,2015
+dataeval/outputs/_estimators.py,sha256=a2oAIxxEDZ9WLGfMWH8KD-BVUS_SnULRPR-iI9hFPoQ,3047
+dataeval/outputs/_linters.py,sha256=YOdjrfm8ypdRrqYOaPM9nc6wVJI3-ita3Haj7LHDNaw,6416
+dataeval/outputs/_metadata.py,sha256=VVcGbtx9DtHQdqgab-fzuVqAhnctZr8WX93RxVNEg5Y,1502
+dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
+dataeval/outputs/_stats.py,sha256=PhRdyWWZxewzenFx0MxK9y9ZLE2MnMA-a4-JeSJ_Bs8,13180
+dataeval/outputs/_utils.py,sha256=HHlGC7sk416m_3Bgn075Qdblz_aPup_UOafJpB0RuXY,893
+dataeval/outputs/_workflows.py,sha256=MkRD6ubI4NCBXb9v3kjXy64cUGs3G-JKkBdOpRD9XVE,10750
+dataeval/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dataeval/typing.py,sha256=YNSCZ6V39JaPoXwOEexIOIejTjoCQTE9UA_DbHyW34o,5824
+dataeval/utils/__init__.py,sha256=T8F8zJh4ZAeu0wDzfpld92I2zJg9mWBmkGCHrDPU7gk,264
+dataeval/utils/_array.py,sha256=fc04sYShIdsRS4qtG1UCnlGGk-yVRxlOHTNAmW7NpDY,4990
+dataeval/utils/_bin.py,sha256=nylthmsC3vzLHLhlUMACvZs--h7xvAh9Pt75InaQJW8,7322
+dataeval/utils/_clusterer.py,sha256=fw5x-2QN0TIbiodDKHZxRgxKHINedpPcOklzce0Rbjg,5436
+dataeval/utils/_fast_mst.py,sha256=4_7ykVihCL5jWtxcGnrecIsDQo65kUml9SZ1JxgBZYY,7172
+dataeval/utils/_image.py,sha256=capzF_X5H0jy0PmTP3Hf52GFgLqrnfU6gS4tiwck9jo,1939
+dataeval/utils/_method.py,sha256=9B9JQbgqWJBRhQJb7glajUtWaQzUTIUuvrZ9_bisxsM,394
+dataeval/utils/_mst.py,sha256=gXjUUhz9G4wkcCUTqQ-61Ti9sZUFx08hEjlZXWiEmPc,2163
+dataeval/utils/_plot.py,sha256=mTRQNbJsA42QMiOwZbJaH8sNYgP996QFDEGVVE9HSgY,7076
+dataeval/utils/data/__init__.py,sha256=vldQ2ZXl8gnI3s4vAGqUUVi6dc_R58F3JMSpbCOyFRI,820
+dataeval/utils/data/_dataset.py,sha256=tjZUJnxj9IY71GKqdKltrwufkn0EC0S3a6ylrW5Bc2s,7756
+dataeval/utils/data/_embeddings.py,sha256=K33F-swjOOxrII2Oq1tUZHx_BGJtQjoSH23deKy_kqI,3528
+dataeval/utils/data/_images.py,sha256=pv_vvpH8hWxPgLvjeVC2mZiyZivZFNLARNIOXam5ceY,1984
+dataeval/utils/data/_metadata.py,sha256=VqeePp7NtoFFWzmIhH4fn-cjrnATpgzgzs-d73cnBXM,14370
+dataeval/utils/data/_selection.py,sha256=etnEn1QsBlcmtAltjbrCXh6YwHRHKzFPp84fj6MJeGs,4058
+dataeval/utils/data/_split.py,sha256=YdsqTRjKbdSfg8w0f4XgX7j0uOSdtfzvvyObAzyqgI0,18433
+dataeval/utils/data/_targets.py,sha256=ws5d9wRiDkIuOV7GSAKNxzgSm6AWTgb0BFroQK5nAmM,3057
+dataeval/utils/data/collate.py,sha256=Z5nmBnWV_IoJzMp_tj8RCKjMJA9sSCY_zZITqISGixc,3865
+dataeval/utils/data/datasets/__init__.py,sha256=jBrswiERrvBx4pJQJZIq_B5UE-Wy8a2_SBfM2crG8R8,511
+dataeval/utils/data/datasets/_base.py,sha256=lvC13xCy6DDlDBSu5PSdU73ySyeBde2Q91NxrMtos_s,8732
+dataeval/utils/data/datasets/_cifar10.py,sha256=tDALqZKKcUbG6dHZm4MXQMhUCS1W_U-aC9aOu4fjxcM,5160
+dataeval/utils/data/datasets/_fileio.py,sha256=SixIk5nIlIwJdX9zjNXS10vHA3hL8aaYbqHsDg1xSpY,6447
+dataeval/utils/data/datasets/_milco.py,sha256=8FLMNn1qI92zGlsB3sAqDTATdK807wqQNCCiSL5lBOM,6068
+dataeval/utils/data/datasets/_mixin.py,sha256=FJgZP_cpJkgAHA3j3ai_j3Wt7aFSEjIMVmt9NpvVXzg,1757
+dataeval/utils/data/datasets/_mnist.py,sha256=PmEEyhJ50Wo4utCYYDJUSgY69FCvXgAhndSCTjfrWN0,7223
+dataeval/utils/data/datasets/_ships.py,sha256=b521rr8OYuBBTHerBtIdYRTGnEs-E8AOZ2hsa2BvkN4,4361
+dataeval/utils/data/datasets/_types.py,sha256=OOxgMjX3QnB-M2O_NqBOB9xsU26vmJO1CVZLksgiuSY,1203
+dataeval/utils/data/datasets/_voc.py,sha256=_fqcwi7AQXmCkYomLe-4_u6wRAWCkBKYNd3HJGnINsY,13837
+dataeval/utils/data/selections/__init__.py,sha256=RLjkIh2IAvPktLbUmyLv3p-rvDEaBAdWzjiNnnhVtn8,481
+dataeval/utils/data/selections/_classfilter.py,sha256=hg6QTpUO4XqjQCwSkbFHzg9PWnaZAKcrd-HjQZqTUU0,2420
+dataeval/utils/data/selections/_indices.py,sha256=QdLgXN7GABCvGPYe28PV1RAc_RSP_nZOyCvEpKRBdWg,636
+dataeval/utils/data/selections/_limit.py,sha256=ECvHRsp7OF4LZw2tE4sGqqJ085kjC-hd2c7QDMfvXr8,518
+dataeval/utils/data/selections/_reverse.py,sha256=6SWpELC9Wgx-kPqzhDrPNn4NKU6FqDJveLrxV4D2Ypk,374
+dataeval/utils/data/selections/_shuffle.py,sha256=U2dQPlX5JQhLjpqlk_uztks8G0H_GAl2DOl6ADNJaDY,581
+dataeval/utils/metadata.py,sha256=X8Hu4LdCzAaE9uk1hI4BflmFve_VOQCqK9lXq0sk9ow,14196
+dataeval/utils/torch/__init__.py,sha256=dn5mjCrFp0b1aL_UEURhONU0Ag0cmXoTOBSGagpkTiA,325
+dataeval/utils/torch/_blocks.py,sha256=HVhBTMMD5NA4qheMUgyol1KWiKZDIuc8k5j4RcMKmhk,1466
+dataeval/utils/torch/_gmm.py,sha256=XBHNLPTtLGRrzq0B4GI48Sha7YHL-0PpXil3s3exLGE,3714
+dataeval/utils/torch/_internal.py,sha256=23DCnF7C7N3tZgZUpT2nyH7mMb8Pi4GcnQyjK0BKHpg,5735
+dataeval/utils/torch/models.py,sha256=hmroEs6C6jQ5tAoZa71RFeIvXLxfXrTJSFH_jG2LGQU,9749
+dataeval/utils/torch/trainer.py,sha256=iUotX4OdirH8-ZtjdpU8gbJavkYW9YY9qpA2mAlFy1Y,5520
+dataeval/workflows/__init__.py,sha256=ou8y0KO-d6W5lgmcyLjKlf-J_ckP3vilW7wHkgiDlZ4,255
+dataeval/workflows/sufficiency.py,sha256=mjKmfRrAjShLUFIARv5o8yT5fnFvDsS5Qu6ujIPUgQg,8497
+dataeval-0.82.1.dist-info/LICENSE.txt,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.82.1.dist-info/METADATA,sha256=3HhWy9SOUtb9cCENZfd_DOpBEsVp8BZvf5zuK7r0kEM,5304
+dataeval-0.82.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+dataeval-0.82.1.dist-info/RECORD,,

dataeval/_output.py

@@ -1,137 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-import inspect
-import logging
-import sys
-from collections.abc import Mapping
-from datetime import datetime, timezone
-from functools import partial, wraps
-from typing import Any, Callable, Iterator, TypeVar
-
-import numpy as np
-
-if sys.version_info >= (3, 10):
-    from typing import ParamSpec
-else:
-    from typing_extensions import ParamSpec
-
-from dataeval import __version__
-
-
-class Output:
-    _name: str
-    _execution_time: datetime
-    _execution_duration: float
-    _arguments: dict[str, str]
-    _state: dict[str, str]
-    _version: str
-
-    def __str__(self) -> str:
-        return f"{self.__class__.__name__}: {str(self.dict())}"
-
-    def dict(self) -> dict[str, Any]:
-        """
-        Output attributes as a dictionary.
-
-        Returns
-        -------
-        dict[str, Any]
-        """
-        return {k: v for k, v in self.__dict__.items() if not k.startswith("_")}
-
-    def meta(self) -> dict[str, Any]:
-        """
-        Execution metadata as a dictionary.
-
-        Returns
-        -------
-        dict[str, Any]
-        """
-        return {k.removeprefix("_"): v for k, v in self.__dict__.items() if k.startswith("_")}
-
-
-TKey = TypeVar("TKey", str, int, float, set)
-TValue = TypeVar("TValue")
-
-
-class MappingOutput(Mapping[TKey, TValue], Output):
-    __slots__ = ["_data"]
-
-    def __init__(self, data: Mapping[TKey, TValue]):
-        self._data = data
-
-    def __getitem__(self, key: TKey) -> TValue:
-        return self._data.__getitem__(key)
-
-    def __iter__(self) -> Iterator[TKey]:
-        return self._data.__iter__()
-
-    def __len__(self) -> int:
-        return self._data.__len__()
-
-    def dict(self) -> dict[str, TValue]:
-        return {str(k): v for k, v in self._data.items()}
-
-
-P = ParamSpec("P")
-R = TypeVar("R", bound=Output)
-
-
-def set_metadata(fn: Callable[P, R] | None = None, *, state: list[str] | None = None) -> Callable[P, R]:
-    """Decorator to stamp Output classes with runtime metadata"""
-
-    if fn is None:
-        return partial(set_metadata, state=state)  # type: ignore
-
-    @wraps(fn)
-    def wrapper(*args: P.args, **kwargs: P.kwargs) -> R:
-        def fmt(v):
-            if np.isscalar(v):
-                return v
-            if hasattr(v, "shape"):
-                return f"{v.__class__.__name__}: shape={getattr(v, 'shape')}"
-            if hasattr(v, "__len__"):
-                return f"{v.__class__.__name__}: len={len(v)}"
-            return f"{v.__class__.__name__}"
-
-        # Collect function metadata
-        # set all params with defaults then update params with mapped arguments and explicit keyword args
-        fn_params = inspect.signature(fn).parameters
-        arguments = {k: None if v.default is inspect.Parameter.empty else v.default for k, v in fn_params.items()}
-        arguments.update(zip(fn_params, args))
-        arguments.update(kwargs)
-        arguments = {k: fmt(v) for k, v in arguments.items()}
-        is_method = "self" in arguments
-        state_attrs = {k: fmt(getattr(args[0], k)) for k in state or []} if is_method else {}
-        module = args[0].__class__.__module__ if is_method else fn.__module__.removeprefix("src.")
-        class_prefix = f".{args[0].__class__.__name__}." if is_method else "."
-        name = f"{module}{class_prefix}{fn.__name__}"
-        arguments = {k: v for k, v in arguments.items() if k != "self"}
-
-        _logger = logging.getLogger(module)
-        time = datetime.now(timezone.utc)
-        _logger.log(logging.INFO, f">>> Executing '{name}': args={arguments} state={state} <<<")
-
-        ##### EXECUTE FUNCTION #####
-        result = fn(*args, **kwargs)
-        ############################
-
-        duration = (datetime.now(timezone.utc) - time).total_seconds()
-        _logger.log(logging.INFO, f">>> Completed '{name}': args={arguments} state={state} duration={duration} <<<")
-
-        # Update output with recorded metadata
-        metadata = {
-            "_name": name,
-            "_execution_time": time,
-            "_execution_duration": duration,
-            "_arguments": arguments,
-            "_state": state_attrs,
-            "_version": __version__,
-        }
-        for k, v in metadata.items():
-            object.__setattr__(result, k, v)
-        return result
-
-    return wrapper

dataeval/detectors/ood/metadata_ks_compare.py

@@ -1,129 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-import numbers
-import warnings
-from typing import Any, Mapping, NamedTuple
-
-import numpy as np
-from numpy.typing import NDArray
-from scipy.stats import iqr, ks_2samp
-from scipy.stats import wasserstein_distance as emd
-
-from dataeval._output import MappingOutput, set_metadata
-
-
-class MetadataKSResult(NamedTuple):
-    statistic: float
-    statistic_location: float
-    shift_magnitude: float
-    pvalue: float
-
-
-class KSOutput(MappingOutput[str, MetadataKSResult]):
-    """
-    Output dictionary class for results of ks_2samp featurewise comparisons of new metadata to reference metadata.
-
-    Attributes
-    ----------
-    key: str
-        Metadata feature names
-    value: NamedTuple[float, float, float, float]
-        Each value contains four floats, which are:
-        - statistic: the KS statistic itself
-        - statistic_location: its location within the range of the reference metadata
-        - shift_magnitude: the shift of new metadata relative to reference
-        - pvalue: the p-value from the KS two-sample test
-    """
-
-
-@set_metadata
-def meta_distribution_compare(
-    md0: Mapping[str, list[Any] | NDArray[Any]], md1: Mapping[str, list[Any] | NDArray[Any]]
-) -> KSOutput:
-    """
-    Measures the featurewise distance between two metadata distributions, and computes a p-value to evaluate its
-    significance.
-
-    Uses the Earth Mover's Distance and the Kolmogorov-Smirnov two-sample test, featurewise.
-
-    Parameters
-    ----------
-    md0 : Mapping[str, list[Any] | NDArray[Any]]
-        A set of arrays of values, indexed by metadata feature names, with one value per data example per feature.
-    md1 : Mapping[str, list[Any] | NDArray[Any]]
-        Another set of arrays of values, indexed by metadata feature names, with one value per data example per
-        feature.
-
-    Returns
-    -------
-    dict[str, KstestResult]
-        A dictionary with keys corresponding to metadata feature names, and values that are KstestResult objects, as
-        defined by scipy.stats.ks_2samp. These values also have two additional attributes: shift_magnitude and
-        statistic_location. The first is the Earth Mover's Distance normalized by the interquartile range (IQR) of
-        the reference, while the second is the value at which the KS statistic has its maximum, measured in
-        IQR-normalized units relative to the median of the reference distribution.
-
-    Examples
-    --------
-    Imagine we have 3 data examples, and that the corresponding metadata contains 2 features called time and
-    altitude.
-
-    >>> md0 = {"time": [1.2, 3.4, 5.6], "altitude": [235, 6789, 101112]}
-    >>> md1 = {"time": [7.8, 9.10, 11.12], "altitude": [532, 9876, 211101]}
-    >>> md_out = meta_distribution_compare(md0, md1)
-    >>> for k, v in md_out.items():
-    ...     print(f"{k}: { {kv: round(vv, 3) for kv, vv in v._asdict().items()} }")
-    time: {'statistic': 1.0, 'statistic_location': 0.444, 'shift_magnitude': 2.7, 'pvalue': 0.0}
-    altitude: {'statistic': 0.333, 'statistic_location': 0.478, 'shift_magnitude': 0.749, 'pvalue': 0.944}
-    """
-
-    if (metadata_keys := md0.keys()) != md1.keys():
-        raise ValueError(f"Both sets of metadata keys must be identical: {list(md0)}, {list(md1)}")
-
-    mdc = {}  # output dict
-    for k in metadata_keys:
-        mdc.update({k: {}})
-
-        x0, x1 = list(md0[k]), list(md1[k])
-
-        allx = x0 + x1  # "+" sign concatenates lists.
-
-        if not all(isinstance(allxi, numbers.Number) for allxi in allx):  # NB: np.nan *is* a number in this context.
-            continue  # non-numeric features will return an empty dict for feature k
-
-        # from Numerical Recipes in C, 3rd ed. p. 737. If too few points, warn and keep going.
-        if np.sqrt(((N := len(x0)) * (M := len(x1))) / (N + M)) < 4:
-            warnings.warn(
-                f"Sample sizes of {N}, {M} for feature {k} will yield unreliable p-values from the KS test.",
-                UserWarning,
-            )
-
-        xmin, xmax = min(allx), max(allx)
-        if xmin == xmax:  # only one value in this feature, so fill in the obvious results for feature k
-            mdc[k] = MetadataKSResult(
-                **{"statistic": 0.0, "statistic_location": 0.0, "shift_magnitude": 0.0, "pvalue": 1.0}
-            )
-            continue
-
-        ks_result = ks_2samp(x0, x1, method="asymp")
-        dev = ks_result.statistic_location - xmin  #  pyright: ignore  (KSresult type)
-        loc = dev / (xmax - xmin) if xmax > xmin else dev
-
-        dX = iqr(x0)  # preferred value of dX, which is the scale of the the md0 values for feature k
-        dX = (max(x0) - min(x0)) / 2.0 if dX == 0 else dX  # reasonable alternative value of dX, when iqr is zero.
-        dX = 1.0 if dX == 0 else dX  # if dX is *still* zero, just avoid division by zero this way
-
-        drift = emd(x0, x1) / dX
-
-        mdc[k] = MetadataKSResult(
-            **{
-                "statistic": ks_result.statistic,  #  pyright: ignore
-                "statistic_location": loc,
-                "shift_magnitude": drift,
-                "pvalue": ks_result.pvalue,  #  pyright: ignore
-            }
-        )
-
-    return KSOutput(mdc)

dataeval/metrics/stats/_datasetstats.py

@@ -1,198 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-from dataclasses import dataclass
-from typing import Any, Iterable
-
-from dataeval._output import Output, set_metadata
-from dataeval.metrics.stats._base import BaseStatsOutput, HistogramPlotMixin, _is_plottable, run_stats
-from dataeval.metrics.stats._dimensionstats import DimensionStatsOutput, DimensionStatsProcessor
-from dataeval.metrics.stats._labelstats import LabelStatsOutput, labelstats
-from dataeval.metrics.stats._pixelstats import PixelStatsOutput, PixelStatsProcessor
-from dataeval.metrics.stats._visualstats import VisualStatsOutput, VisualStatsProcessor
-from dataeval.typing import ArrayLike
-from dataeval.utils._plot import channel_histogram_plot
-
-
-@dataclass(frozen=True)
-class DatasetStatsOutput(Output, HistogramPlotMixin):
-    """
-    Output class for :func:`.datasetstats` stats metric.
-
-    This class represents the outputs of various stats functions against a single
-    dataset, such that each index across all stat outputs are representative of
-    the same source image. Modifying or mixing outputs will result in inaccurate
-    outlier calculations if not created correctly.
-
-    Attributes
-    ----------
-    dimensionstats : DimensionStatsOutput
-    pixelstats: PixelStatsOutput
-    visualstats: VisualStatsOutput
-    labelstats: LabelStatsOutput or None
-    """
-
-    dimensionstats: DimensionStatsOutput
-    pixelstats: PixelStatsOutput
-    visualstats: VisualStatsOutput
-    labelstats: LabelStatsOutput | None = None
-
-    _excluded_keys = ["histogram", "percentiles"]
-
-    def _outputs(self) -> list[Output]:
-        return [s for s in (self.dimensionstats, self.pixelstats, self.visualstats, self.labelstats) if s is not None]
-
-    def dict(self) -> dict[str, Any]:
-        return {k: v for o in self._outputs() for k, v in o.dict().items()}
-
-    def __post_init__(self) -> None:
-        lengths = [len(s) for s in self._outputs() if isinstance(s, BaseStatsOutput)]
-        if not all(length == lengths[0] for length in lengths):
-            raise ValueError("All StatsOutput classes must contain the same number of image sources.")
-
-
-def _get_channels(cls, channel_limit: int | None = None, channel_index: int | Iterable[int] | None = None):
-    raw_channels = max([si.channel for si in cls.dict()["source_index"]]) + 1
-    if isinstance(channel_index, int):
-        max_channels = 1 if channel_index < raw_channels else raw_channels
-        ch_mask = cls.pixelstats.get_channel_mask(channel_index)
-    elif isinstance(channel_index, Iterable) and all(isinstance(val, int) for val in list(channel_index)):
-        max_channels = len(list(channel_index))
-        ch_mask = cls.pixelstats.get_channel_mask(channel_index)
-    elif isinstance(channel_limit, int):
-        max_channels = channel_limit
-        ch_mask = cls.pixelstats.get_channel_mask(None, channel_limit)
-    else:
-        max_channels = raw_channels
-        ch_mask = None
-
-    if max_channels > raw_channels:
-        max_channels = raw_channels
-    if ch_mask is not None and not any(ch_mask):
-        ch_mask = None
-
-    return max_channels, ch_mask
-
-
-@dataclass(frozen=True)
-class ChannelStatsOutput(Output):
-    """
-    Output class for :func:`.channelstats` stats metric.
-
-    This class represents the outputs of various per-channel stats functions against
-    a single dataset, such that each index across all stat outputs are representative
-    of the same source image. Modifying or mixing outputs will result in inaccurate
-    outlier calculations if not created correctly.
-
-    Attributes
-    ----------
-    pixelstats: PixelStatsOutput
-    visualstats: VisualStatsOutput
-    """
-
-    pixelstats: PixelStatsOutput
-    visualstats: VisualStatsOutput
-
-    def _outputs(self) -> tuple[PixelStatsOutput, VisualStatsOutput]:
-        return (self.pixelstats, self.visualstats)
-
-    def dict(self) -> dict[str, Any]:
-        return {**self.pixelstats.dict(), **self.visualstats.dict()}
-
-    def __post_init__(self) -> None:
-        lengths = [len(s) for s in self._outputs()]
-        if not all(length == lengths[0] for length in lengths):
-            raise ValueError("All StatsOutput classes must contain the same number of image sources.")
-
-    def plot(
-        self, log: bool, channel_limit: int | None = None, channel_index: int | Iterable[int] | None = None
-    ) -> None:
-        max_channels, ch_mask = _get_channels(self, channel_limit, channel_index)
-        data_dict = {k: v for k, v in self.dict().items() if _is_plottable(k, v, ("histogram", "percentiles"))}
-        channel_histogram_plot(data_dict, log, max_channels, ch_mask)
-
-
-@set_metadata
-def datasetstats(
-    images: Iterable[ArrayLike],
-    bboxes: Iterable[ArrayLike] | None = None,
-    labels: Iterable[ArrayLike] | None = None,
-) -> DatasetStatsOutput:
-    """
-    Calculates various :term:`statistics<Statistics>` for each image.
-
-    This function computes dimension, pixel and visual metrics
-    on the images or individual bounding boxes for each image as
-    well as label statistics if provided.
-
-    Parameters
-    ----------
-    images : Iterable[ArrayLike]
-        Images to perform calculations on
-    bboxes : Iterable[ArrayLike] or None
-        Bounding boxes in `xyxy` format for each image to perform calculations on
-    labels : Iterable[ArrayLike] or None
-        Labels of images or boxes to perform calculations on
-
-    Returns
-    -------
-    DatasetStatsOutput
-        Output class containing the outputs of various stats functions
-
-    See Also
-    --------
-    dimensionstats, labelstats, pixelstats, visualstats, Outliers
-
-    Examples
-    --------
-    Calculating the dimension, pixel and visual stats for a dataset with bounding boxes
-
-    >>> stats = datasetstats(stats_images, bboxes)
-    >>> print(stats.dimensionstats.aspect_ratio)
-    [ 0.864   0.5884 16.      1.143   1.692   0.5835  0.6665  2.555   1.3   ]
-    >>> print(stats.visualstats.sharpness)
-    [4.04   4.434  0.2778 4.957  5.145  5.22   4.957  3.076  2.855 ]
-    """
-    outputs = run_stats(images, bboxes, False, [DimensionStatsProcessor, PixelStatsProcessor, VisualStatsProcessor])
-    return DatasetStatsOutput(*outputs, labelstats=labelstats(labels) if labels else None)  # type: ignore
-
-
-@set_metadata
-def channelstats(
-    images: Iterable[ArrayLike],
-    bboxes: Iterable[ArrayLike] | None = None,
-) -> ChannelStatsOutput:
-    """
-    Calculates various per-channel :term:`statistics` for each image.
-
-    This function computes pixel and visual metrics on the images
-    or individual bounding boxes for each image.
-
-    Parameters
-    ----------
-    images : Iterable[ArrayLike]
-        Images to perform calculations on
-    bboxes : Iterable[ArrayLike] or None
-        Bounding boxes in `xyxy` format for each image to perform calculations on
-
-    Returns
-    -------
-    ChannelStatsOutput
-        Output class containing the per-channel outputs of various stats functions
-
-    See Also
-    --------
-    pixelstats, visualstats
-
-    Examples
-    --------
-    Calculating the per-channel pixel and visual stats for a dataset
-
-    >>> stats = channelstats(stats_images)
-    >>> print(stats.visualstats.darkness)
-    [0.1499 0.3499 0.55   0.2094 0.2219 0.2344 0.4194 0.6094 0.622  0.6343
-     0.8154]
-    """
-    outputs = run_stats(images, bboxes, True, [PixelStatsProcessor, VisualStatsProcessor])
-    return ChannelStatsOutput(*outputs)  # type: ignore