dataeval 0.86.9__py3-none-any.whl → 0.88.0__py3-none-any.whl

dataeval/utils/torch/trainer.py

@@ -16,7 +16,7 @@ from dataeval.config import DeviceLike, get_device
 
 def get_images_from_batch(batch: Any) -> Any:
     """Extracts images from a batch of collated data by DataLoader"""
-    return batch[0] if isinstance(batch, (list, tuple)) else batch
+    return batch[0] if isinstance(batch, list | tuple) else batch
 
 
 class AETrainer:

dataeval/workflows/sufficiency.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 
 __all__ = []
 
-from typing import Any, Callable, Generic, Iterable, Mapping, Sequence, Sized, TypeVar
+from collections.abc import Callable, Iterable, Mapping, Sequence, Sized
+from typing import Any, Generic, TypeVar
 
 import numpy as np
 import torch
@@ -207,7 +208,9 @@ class Sufficiency(Generic[T]):
         ...     substeps=5,
         ... )
         >>> suff.evaluate()
-        SufficiencyOutput(steps=array([  1,   3,  10,  31, 100], dtype=uint32), measures={'test': array([1., 1., 1., 1., 1.])}, n_iter=1000)
+        SufficiencyOutput(steps=array([  1,   3,  10,  31, 100], dtype=uint32), measures={'test': array([[1., 1., 1., 1., 1.],
+               [1., 1., 1., 1., 1.],
+               [1., 1., 1., 1., 1.]])}, averaged_measures={'test': array([1., 1., 1., 1., 1.])}, n_iter=1000)
 
         Evaluate at a single value
 
@@ -219,7 +222,7 @@ class Sufficiency(Generic[T]):
         ...     eval_fn=eval_fn,
         ... )
         >>> suff.evaluate(eval_at=50)
-        SufficiencyOutput(steps=array([50]), measures={'test': array([1.])}, n_iter=1000)
+        SufficiencyOutput(steps=array([50]), measures={'test': array([[1.]])}, averaged_measures={'test': array([1.])}, n_iter=1000)
 
         Evaluating at linear steps from 0-100 inclusive
 
@@ -231,7 +234,7 @@ class Sufficiency(Generic[T]):
         ...     eval_fn=eval_fn,
         ... )
         >>> suff.evaluate(eval_at=np.arange(0, 101, 20))
-        SufficiencyOutput(steps=array([  0,  20,  40,  60,  80, 100]), measures={'test': array([1., 1., 1., 1., 1., 1.])}, n_iter=1000)
+        SufficiencyOutput(steps=array([  0,  20,  40,  60,  80, 100]), measures={'test': array([[1., 1., 1., 1., 1., 1.]])}, averaged_measures={'test': array([1., 1., 1., 1., 1., 1.])}, n_iter=1000)
 
         """  # noqa: E501
         if eval_at is not None:
@@ -249,7 +252,7 @@ class Sufficiency(Generic[T]):
         measures = {}
 
         # Run each model over all indices
-        for _ in range(self.runs):
+        for run in range(self.runs):
             # Create a randomized set of indices to use
             indices = np.random.randint(0, self._length, size=self._length)
             # Reset the network weights to "create" an untrained model
@@ -272,9 +275,10 @@ class Sufficiency(Generic[T]):
                     # Sum result into current substep iteration to be averaged later
                     value = np.array(value).ravel()
                     if name not in measures:
-                        measures[name] = np.zeros(substeps if len(value) == 1 else (substeps, len(value)))
-                    measures[name][iteration] += value
+                        measures[name] = np.zeros(
+                            (self.runs, substeps) if len(value) == 1 else (self.runs, substeps, len(value))
+                        )
 
+                    measures[name][run, iteration] = value
         # The mean for each measure must be calculated before being returned
-        measures = {k: (v / self.runs).T for k, v in measures.items()}
-        return SufficiencyOutput(ranges, measures)
+        return SufficiencyOutput(ranges, measures=measures)

{dataeval-0.86.9.dist-info → dataeval-0.88.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataeval
-Version: 0.86.9
+Version: 0.88.0
 Summary: DataEval provides a simple interface to characterize image data and its impact on model performance across classification and object-detection tasks
 Project-URL: Homepage, https://dataeval.ai/
 Project-URL: Repository, https://github.com/aria-ml/dataeval/
@@ -8,33 +8,29 @@ Project-URL: Documentation, https://dataeval.readthedocs.io/
 Author-email: Andrew Weng <andrew.weng@ariacoustics.com>, Bill Peria <bill.peria@ariacoustics.com>, Jon Botts <jonathan.botts@ariacoustics.com>, Jonathan Christian <jonathan.christian@ariacoustics.com>, Justin McMillan <justin.mcmillan@ariacoustics.com>, Ryan Wood <ryan.wood@ariacoustics.com>, Scott Swan <scott.swan@ariacoustics.com>, Shaun Jullens <shaun.jullens@ariacoustics.com>
 Maintainer-email: ARiA <dataeval@ariacoustics.com>
 License-Expression: MIT
-License-File: LICENSE.txt
+License-File: LICENSE
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
-Requires-Python: <3.13,>=3.9
-Requires-Dist: defusedxml>=0.7.1
+Requires-Python: <3.13,>=3.10
 Requires-Dist: fast-hdbscan==0.2.0
 Requires-Dist: lightgbm>=4
 Requires-Dist: numba>=0.59.1
 Requires-Dist: numpy>=1.24.2
 Requires-Dist: pandas>=2.0
-Requires-Dist: pillow>=10.3.0
 Requires-Dist: polars>=1.0.0
-Requires-Dist: requests>=2.32.3
 Requires-Dist: scikit-learn>=1.5.0
 Requires-Dist: scipy>=1.10
 Requires-Dist: torch>=2.2.0
 Requires-Dist: torchvision>=0.17.0
 Requires-Dist: tqdm>=4.66
-Requires-Dist: typing-extensions>=4.12; python_version ~= '3.9'
+Requires-Dist: typing-extensions>=4.12
 Requires-Dist: xxhash>=3.3
 Provides-Extra: all
 Requires-Dist: matplotlib>=3.7.1; extra == 'all'
@@ -91,7 +87,7 @@ using MAITE-compliant datasets and models.
 
 ## Getting Started
 
-**Python versions:** 3.9 - 3.12
+**Python versions:** 3.10 - 3.12
 
 **Supported packages**: _NumPy_, _Pandas_, _Sci-kit learn_, _MAITE_, _NRTK_
 
@@ -123,14 +119,8 @@ micromamba create -f environment\environment.yaml -c pytorch
 
 ### **Installing from GitHub**
 
-To install DataEval from source locally on Ubuntu, you will need `git-lfs` to
-download larger, binary source files.
-
-```bash
-sudo apt-get install git-lfs
-```
-
-Pull the source down and change to the DataEval project directory.
+To install DataEval from source locally on Ubuntu, pull the source down and
+change to the DataEval project directory.
 
 ```bash
 git clone https://github.com/aria-ml/dataeval.git
@@ -167,10 +157,7 @@ source .venv/bin/activate
 
 ## Contact Us
 
-If you have any questions, feel free to reach out to the people below:
-
-- **POC**: Scott Swan @scott.swan
-- **DPOC**: Andrew Weng @aweng
+If you have any questions, feel free to reach out to [us](mailto:dataeval@ariacoustics.com)!
 
 ## Acknowledgement
 

dataeval-0.88.0.dist-info/RECORD

@@ -0,0 +1,105 @@
+dataeval/__init__.py,sha256=aFzX3SLx8wgc763RY772P41ZLqeHcUHRKW9XAN0KfHQ,1793
+dataeval/_log.py,sha256=Q2d6oqYKXyn1wkgMdNX9iswod4Jq0jPADShrCFVgJI0,374
+dataeval/_version.py,sha256=p36W3DcVLrkAWnGoljUjU-PF8_IvHjfGbC98bXZ2g_c,513
+dataeval/config.py,sha256=lL73s_xa9pBxHHCnBKi59D_tl4vS7ig1rfWbIYkM_ac,3839
+dataeval/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dataeval/typing.py,sha256=cKpK8rY7iVf-KL9kuye6qi_6LS6hKbMxHpurdWlYY44,7445
+dataeval/data/__init__.py,sha256=wzQ6uUFLNB3VJR0a2QnRBYwEmwXT93q0WpHu7FmFW1E,486
+dataeval/data/_embeddings.py,sha256=BHoiSdt46TblVSglg9Cyrm8iAJJq1Z2jR4wesL0WOf4,14731
+dataeval/data/_images.py,sha256=9q0O5Zurf-5727rMC7DB_i3TtXcL67D9a5GGx5qlov8,3875
+dataeval/data/_metadata.py,sha256=-dhmyX6vvv97S9YHr6roNcbzXequkxMw48PwNDdzZ9I,24163
+dataeval/data/_selection.py,sha256=4qI-GwSdEGiRCyr3kqxr6uOiyRRKsPBRzYHmpgdWLY0,5301
+dataeval/data/_split.py,sha256=aCkXFvkCw8VkWICdCmY9tHiEvkQI5j9jUa7QLjm-gZE,16759
+dataeval/data/selections/__init__.py,sha256=2m8ZB53wXzqLcqmc6p5atO6graB6ZyiRSNJFxf11X_g,613
+dataeval/data/selections/_classbalance.py,sha256=AqExg-QnYBcfBNzS1Ygsz3Cgb2cqcgGXE0-cseD8_vA,1580
+dataeval/data/selections/_classfilter.py,sha256=sn7Lbhb5KJyiqDH7ZdugX5WnRlglwCckWzK6K5uXbwg,4447
+dataeval/data/selections/_indices.py,sha256=PcM4qQwFVUXO9xY2brO6OUDFMeVgiSlTRKFDhTA_W-0,655
+dataeval/data/selections/_limit.py,sha256=JG4GmEiNKt3sk4PbOUbBnGGzNlyz72H-kQrt8COMm4Y,512
+dataeval/data/selections/_prioritize.py,sha256=ss_GZ5MB2ohdNuB55C69TYNwV3PUSmk715gDJI6qfYA,20140
+dataeval/data/selections/_reverse.py,sha256=FqYlpPg-0Vz75kbEhGFrJlzIGELSmDZxPlBMY18a57I,365
+dataeval/data/selections/_shuffle.py,sha256=uW_Zss773ob2swqwTdL6G-CzMElCq8TO2TScvABQR1U,1268
+dataeval/detectors/__init__.py,sha256=3Sg-XWlwr75zEEH3hZKA4nWMtGvaRlnfzTWvZG_Ak6U,189
+dataeval/detectors/drift/__init__.py,sha256=Jqv98oOVeC2tvHlNGxQ8RJ6De2q4SyS5lTpaYlb4ocM,756
+dataeval/detectors/drift/_base.py,sha256=__mlqkiPW0GcVSVE4u9t6M2mp3rAU5leSk_XPQn_Mp8,7619
+dataeval/detectors/drift/_cvm.py,sha256=cS33zWJmFY1fft1XcANcP2jSD5ou7TxvIU2AldhTynM,3004
+dataeval/detectors/drift/_ks.py,sha256=uMc5-NA-lSV1IODrY8uJe87ll3uRJT_oXLJFXy95M1w,3186
+dataeval/detectors/drift/_mmd.py,sha256=EkfbeK5L6xGGQrcA1v_0YlpIOingF73jn2H6s3tRKbo,11550
+dataeval/detectors/drift/_mvdc.py,sha256=WMN6aDOWCh1q1MtdRXFIZlFcfnVi4XgBHsS0A6L5UuY,2942
+dataeval/detectors/drift/_uncertainty.py,sha256=-4aiwNosJ1_4kY-d2n4YbZV_jvnf5xdTMDELXSoW6OM,5874
+dataeval/detectors/drift/updates.py,sha256=L1PnrPlIE1x6ujCc5mCwjcAZwadVTn-Zjb6MnTDvzJQ,2251
+dataeval/detectors/drift/_nml/__init__.py,sha256=MNyKyZlfTjr5uQql2uBBfRkUdsuduie_WJdn09GYmqg,137
+dataeval/detectors/drift/_nml/_base.py,sha256=wMqegfa92Tldqix1RL6dLMdiKgX0GqHmTiFxO38ja_c,2672
+dataeval/detectors/drift/_nml/_chunk.py,sha256=5WhpcIHJ3EVBGZjDJLri54fWikYAT_7sC0DxQkSs0tI,13591
+dataeval/detectors/drift/_nml/_domainclassifier.py,sha256=n7Ttq5Ej7sAY9Jn2iagaGj4IIWiG8gmA3wwFizlBqes,7292
+dataeval/detectors/drift/_nml/_result.py,sha256=mH_tYrYVaIXhsU9gcSFqEdaI38BArlpKuW0-8SPS8aY,3295
+dataeval/detectors/drift/_nml/_thresholds.py,sha256=jAbRdAPP4O4hJqTLpvfVAbWNdw3zL6UrTl2KNWphQPc,12083
+dataeval/detectors/linters/__init__.py,sha256=xn2zPwUcmsuf-Jd9uw6AVI11C9z1b1Y9fYtuFnXenZ0,404
+dataeval/detectors/linters/duplicates.py,sha256=k5cQz_1i9vchugSfC267mugWzgy6sVDa36BdQAy_PXs,4990
+dataeval/detectors/linters/outliers.py,sha256=a980lDV9g_tZYHV9k6wSh2d11nNYEqTy56IduC-H5GA,10159
+dataeval/detectors/ood/__init__.py,sha256=qDoDdQetJY1xZB43dNzcOIO_8NiEuEU0z1QNU4QkEXs,341
+dataeval/detectors/ood/ae.py,sha256=jo6aHcKT1N13ew0tV6FZa3vQI5DQivZo5-uAm4uLaAs,2950
+dataeval/detectors/ood/base.py,sha256=eWzODq2i1Tah7Mqm1guASTf9p2tF4Tr6mZoDT3pDvsk,4401
+dataeval/detectors/ood/knn.py,sha256=Fu77geQFHPYNOn81VIXUJ3yC3t5Ylv0ZgvwMeA2JX6I,3782
+dataeval/detectors/ood/mixin.py,sha256=cNmRrR9cv9phwAGSuQMC7EhmrFtf68C63wdTggy1UaU,5458
+dataeval/metadata/__init__.py,sha256=XDDmJbOZBNM6pL0r6Nbu6oMRoyAh22IDkPYGndNlkZU,316
+dataeval/metadata/_distance.py,sha256=MbXM9idsooNWnGLaTKg8j4ZqavUeJUjuW7EPW3-UQyg,4234
+dataeval/metadata/_ood.py,sha256=lNPHouj_9WfM_uTtsaiRaPn46RcVy3YebD1c32vDj-c,8981
+dataeval/metadata/_utils.py,sha256=4fX-1eA3fK4uwNh_DfOGiXxl4PHZ1AghOejJ03rV3RI,1219
+dataeval/metrics/__init__.py,sha256=8VC8q3HuJN3o_WN51Ae2_wXznl3RMXIvA5GYVcy7vr8,225
+dataeval/metrics/bias/__init__.py,sha256=329S1_3WnWqeU4-qVcbe0fMy4lDrj9uKslWHIQf93yg,839
+dataeval/metrics/bias/_balance.py,sha256=aDAII2lXeAz9dZk0TdgZHtyab1tObQlya8jdNNdn8eI,5718
+dataeval/metrics/bias/_completeness.py,sha256=2cvOXe7fhtxZGH_4QBuiCafIeamxFBarMiUBuEP7QGI,4596
+dataeval/metrics/bias/_coverage.py,sha256=v2x2hbOf2za9jFcSVSJUAoJ2BJfzzlCzt0mFIGtBL0A,3639
+dataeval/metrics/bias/_diversity.py,sha256=Z7UQzKp9bsmB-hC3_sY6HIJUJRkLHb5cVEoU79cNDzc,5800
+dataeval/metrics/bias/_parity.py,sha256=ZIKc5OK6wQ4moleBJzGDfOPvyNzj03-KoHAGBZnO4pk,11433
+dataeval/metrics/estimators/__init__.py,sha256=Pnds8uIyAovt2fKqZjiHCIP_kVoBWlVllekYuK5UmmU,568
+dataeval/metrics/estimators/_ber.py,sha256=7noeRyOJJYqrJ_jt90nRHtR2t2u5MIvTCmWt0_rd4EU,5370
+dataeval/metrics/estimators/_clusterer.py,sha256=1HrpihGTJ63IkNSOy4Ibw633Gllkm1RxKmoKT5MOgt0,1434
+dataeval/metrics/estimators/_divergence.py,sha256=t-Z_7Bq4V4FunxKlq7G4ThtgLany8n4iEU0n0afr7F8,3991
+dataeval/metrics/estimators/_uap.py,sha256=BULEBbJ9BQ1IcTeZf0x7iI60QHAWCccBOM97FIu9VXA,1928
+dataeval/metrics/stats/__init__.py,sha256=6tA_9nbbM5ObJ6cds8Y1VBtTQiTOxrpGQSFLu_lWGGA,1098
+dataeval/metrics/stats/_base.py,sha256=vE8dvrNqjAKGyCzqlgQa-3ArP6PJ-P8Y4rdNPUZ0ml8,11703
+dataeval/metrics/stats/_boxratiostats.py,sha256=CFn-BqnPmAXagaLlhJGusdGLQewWxRweb9Xxv_JAOaw,6477
+dataeval/metrics/stats/_dimensionstats.py,sha256=GlzshH7nZurVWANmZmpuXy_v5ZfMrdAfO_FbtHTL38Q,2903
+dataeval/metrics/stats/_hashstats.py,sha256=wsy8F8-UMUbtjeCnaqAR9Yxv_jp4kFerHH2L0UMIAgY,5415
+dataeval/metrics/stats/_imagestats.py,sha256=gUPNgN5Zwzdr7WnSwbve1NXNsyxd5dy3cSnlR_7guCg,3007
+dataeval/metrics/stats/_labelstats.py,sha256=_dXt3p8_-SHEtHvJWbL0rnQvO2g30zxX42mG2LGJepU,3195
+dataeval/metrics/stats/_pixelstats.py,sha256=XEFByxMUbNaCvEsnVhH5ewJ8UH253ySdpFe5u1jr38w,3339
+dataeval/metrics/stats/_visualstats.py,sha256=SbXvNWxfKrw-2wCu5FXMsnpsMUVaQzdJkj6RB4qEsBM,3740
+dataeval/outputs/__init__.py,sha256=geHB5M3QOiFFaQGV4ZwDTTKpqZPvPePbqG7lzaPhaXQ,1741
+dataeval/outputs/_base.py,sha256=lVC7xmBgv3JYY2wVLaGBMPlkRE_KV9UloaeQn0nQydA,5875
+dataeval/outputs/_bias.py,sha256=gj2AgSKOdq6bj59RMiHpha4Skld6ZMB8cW5KesOZ6T4,10483
+dataeval/outputs/_drift.py,sha256=hXILED_soY8ppIQZgftQvmumtwDrTnABbYl-flIGEU4,4588
+dataeval/outputs/_estimators.py,sha256=SUjur5jI6OU9C7GpsAuA_qqO1PRnS-8eZN-otsaV5q0,3120
+dataeval/outputs/_linters.py,sha256=N4nP5HMoeN2zLndWzhoIT5QB1Ujxbs8Gx5pWPKhl3yc,6683
+dataeval/outputs/_metadata.py,sha256=ffZgpX8KWURPHXpOWjbvJ2KRqWQkS2nWuIjKUzoHhMI,1710
+dataeval/outputs/_ood.py,sha256=suLKVXULGtXH0rq9eXHI1d3d2jhGmItJtz4QiQd47A4,1718
+dataeval/outputs/_stats.py,sha256=PsDV0uw41aTy-X9tjz-PqOj78TTnH4JQVpOrU3OThAE,17423
+dataeval/outputs/_utils.py,sha256=KJ1P8tcMFIkGi2A6VfqbZwLcT1cD0c2YssTbWbHALjE,938
+dataeval/outputs/_workflows.py,sha256=sw13FNx1vANX7DBsKeOLfP2bkp5r6SexBorfb9dxYxU,12160
+dataeval/utils/__init__.py,sha256=sjelzMPaTImF6isiRcp8UGDE3tppEpWS5GoR8WKPZ1k,242
+dataeval/utils/_array.py,sha256=P4_gyH3kkksUJm9Vqx-oPtLWxFmqMacUJzhj0vmrUd8,6361
+dataeval/utils/_bin.py,sha256=QjlRCB5mOauETdxSbvRxRG17riO6gScsMd_lNnnvqxs,7391
+dataeval/utils/_clusterer.py,sha256=rUvEdyMwp95lffmt6xKMEwsjRXNoBS0n5mAS_HNOnck,5656
+dataeval/utils/_fast_mst.py,sha256=pv42flr1Uf5RBa9qDG0YLDXWH7Mr7a9zpauO1HqZXaY,8061
+dataeval/utils/_image.py,sha256=4uxTIOYZZlRJOfNmdA3ek3no3FrLWCK5un48kStMDt8,3578
+dataeval/utils/_method.py,sha256=53Q3xfQvpyGa-z9_rn6GhjfCcUR5Q9nuWQtCNav4Ftc,391
+dataeval/utils/_mst.py,sha256=bLmJmu_1Dtj3hC5gQp3oAiJ_7TKtEjahTqusVRRU4eI,2168
+dataeval/utils/_multiprocessing.py,sha256=n6qCVybheWry42NCdxzcsgkJ9xLGkz8m12SWgviTJQM,1060
+dataeval/utils/_plot.py,sha256=kwYZbSdHCV02wRrZDTxR3xd0XfQ-6TlLmfvubwiEQcw,7252
+dataeval/utils/data/__init__.py,sha256=_XoNxADxBdR96Ca-0RgkDlQa6C2FHld1nwts-Xdif3g,294
+dataeval/utils/data/_merge.py,sha256=9JKtlpBarMX_9jlhnQg1AmBwTe9I2w6xQkFGss3IkkU,14729
+dataeval/utils/data/_validate.py,sha256=YH5Q6uzcTRdf_AMKMRyYW37RUlXm-S8ddhw6cegdNkc,6950
+dataeval/utils/data/collate.py,sha256=AWoQ2k9FXyTeq6ExTsGa6sBML_lZm9p38-DN9hnpm8E,3963
+dataeval/utils/torch/__init__.py,sha256=dn5mjCrFp0b1aL_UEURhONU0Ag0cmXoTOBSGagpkTiA,325
+dataeval/utils/torch/_blocks.py,sha256=HVhBTMMD5NA4qheMUgyol1KWiKZDIuc8k5j4RcMKmhk,1466
+dataeval/utils/torch/_gmm.py,sha256=XM68GNEP97EjaB1U49-ZXRb81d0CEFnPS910alrcB3g,3740
+dataeval/utils/torch/_internal.py,sha256=LiuqZGIzKewp_29_Lskj0mnNqdMffMheMdgGeXLDI5g,4173
+dataeval/utils/torch/models.py,sha256=1idpXyjrYcCBSsbxxRUOto8xr4MJNjDEqQHiIXVU5Zc,9700
+dataeval/utils/torch/trainer.py,sha256=kBdgxd9TL1Pvz-dyZbS__POAKeFrDiQ4vKFh8ltJApc,5543
+dataeval/workflows/__init__.py,sha256=ou8y0KO-d6W5lgmcyLjKlf-J_ckP3vilW7wHkgiDlZ4,255
+dataeval/workflows/sufficiency.py,sha256=4DTDaYyEuAfO0LTFpQGXXXayV5aCIbziSL2Rddd1vQ0,10360
+dataeval-0.88.0.dist-info/METADATA,sha256=Y5NRZgrhfpyGQKHUnqnO6rAItVR3oWUqIp646_0xluQ,5601
+dataeval-0.88.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dataeval-0.88.0.dist-info/licenses/LICENSE,sha256=uAooygKWvX6NbU9Ran9oG2msttoG8aeTeHSTe5JeCnY,1061
+dataeval-0.88.0.dist-info/RECORD,,

dataeval/utils/data/_dataset.py

@@ -1,246 +0,0 @@
-from __future__ import annotations
-
-__all__ = []
-
-from typing import Any, Generic, Iterable, Literal, Sequence, SupportsFloat, SupportsInt, TypeVar, cast
-
-from dataeval.typing import (
-    Array,
-    ArrayLike,
-    DatasetMetadata,
-    ImageClassificationDataset,
-    ObjectDetectionDataset,
-)
-from dataeval.utils._array import as_numpy
-
-
-def _validate_data(
-    datum_type: Literal["ic", "od"],
-    images: Array | Sequence[Array],
-    labels: Array | Sequence[int] | Sequence[Array] | Sequence[Sequence[int]],
-    bboxes: Array | Sequence[Array] | Sequence[Sequence[Array]] | Sequence[Sequence[Sequence[float]]] | None,
-    metadata: Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None,
-) -> None:
-    # Validate inputs
-    dataset_len = len(images)
-
-    if not isinstance(images, (Sequence, Array)) or len(images[0].shape) != 3:
-        raise ValueError("Images must be a sequence or array of 3 dimensional arrays (H, W, C).")
-    if len(labels) != dataset_len:
-        raise ValueError(f"Number of labels ({len(labels)}) does not match number of images ({dataset_len}).")
-    if bboxes is not None and len(bboxes) != dataset_len:
-        raise ValueError(f"Number of bboxes ({len(bboxes)}) does not match number of images ({dataset_len}).")
-    if metadata is not None and (
-        len(metadata) != dataset_len
-        if isinstance(metadata, Sequence)
-        else any(
-            not isinstance(metadatum, Sequence) or len(metadatum) != dataset_len for metadatum in metadata.values()
-        )
-    ):
-        raise ValueError(f"Number of metadata ({len(metadata)}) does not match number of images ({dataset_len}).")
-
-    if datum_type == "ic":
-        if not isinstance(labels, (Sequence, Array)) or not isinstance(labels[0], (int, SupportsInt)):
-            raise TypeError("Labels must be a sequence of integers for image classification.")
-    elif datum_type == "od":
-        if (
-            not isinstance(labels, (Sequence, Array))
-            or not isinstance(labels[0], (Sequence, Array))
-            or not isinstance(cast(Sequence[Any], labels[0])[0], (int, SupportsInt))
-        ):
-            raise TypeError("Labels must be a sequence of sequences of integers for object detection.")
-        if (
-            bboxes is None
-            or not isinstance(bboxes, (Sequence, Array))
-            or not isinstance(bboxes[0], (Sequence, Array))
-            or not isinstance(bboxes[0][0], (Sequence, Array))
-            or not isinstance(bboxes[0][0][0], (float, SupportsFloat))
-            or not len(bboxes[0][0]) == 4
-        ):
-            raise TypeError("Boxes must be a sequence of sequences of (x0, y0, x1, y1) for object detection.")
-    else:
-        raise ValueError(f"Unknown datum type '{datum_type}'. Must be 'ic' or 'od'.")
-
-
-def _listify_metadata(
-    metadata: Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None,
-) -> Sequence[dict[str, Any]] | None:
-    if isinstance(metadata, dict):
-        return [{k: v[i] for k, v in metadata.items()} for i in range(len(next(iter(metadata.values()))))]
-    return metadata
-
-
-def _find_max(arr: ArrayLike) -> Any:
-    if not isinstance(arr, (bytes, str)) and isinstance(arr, (Iterable, Sequence, Array)):
-        nested = [x for x in [_find_max(x) for x in arr] if x is not None]
-        return max(nested) if len(nested) > 0 else None
-    return arr
-
-
-_TLabels = TypeVar("_TLabels", Sequence[int], Sequence[Sequence[int]])
-
-
-class BaseAnnotatedDataset(Generic[_TLabels]):
-    def __init__(
-        self,
-        datum_type: Literal["ic", "od"],
-        images: Array | Sequence[Array],
-        labels: _TLabels,
-        metadata: Sequence[dict[str, Any]] | None,
-        classes: Sequence[str] | None,
-        name: str | None = None,
-    ) -> None:
-        self._classes = classes if classes is not None else [str(i) for i in range(_find_max(labels) + 1)]
-        self._index2label = dict(enumerate(self._classes))
-        self._images = images
-        self._labels = labels
-        self._metadata = metadata
-        self._id = name or f"{len(self._images)}_image_{len(self._index2label)}_class_{datum_type}_dataset"
-
-    @property
-    def metadata(self) -> DatasetMetadata:
-        return DatasetMetadata(id=self._id, index2label=self._index2label)
-
-    def __len__(self) -> int:
-        return len(self._images)
-
-
-class CustomImageClassificationDataset(BaseAnnotatedDataset[Sequence[int]], ImageClassificationDataset):
-    def __init__(
-        self,
-        images: Array | Sequence[Array],
-        labels: Array | Sequence[int],
-        metadata: Sequence[dict[str, Any]] | None,
-        classes: Sequence[str] | None,
-        name: str | None = None,
-    ) -> None:
-        super().__init__(
-            "ic", images, as_numpy(labels).tolist() if isinstance(labels, Array) else labels, metadata, classes
-        )
-        if name is not None:
-            self.__name__ = name
-            self.__class__.__name__ = name
-            self.__class__.__qualname__ = name
-
-    def __getitem__(self, idx: int, /) -> tuple[Array, Array, dict[str, Any]]:
-        one_hot = [0.0] * len(self._index2label)
-        one_hot[self._labels[idx]] = 1.0
-        return (
-            self._images[idx],
-            as_numpy(one_hot),
-            self._metadata[idx] if self._metadata is not None else {},
-        )
-
-
-class CustomObjectDetectionDataset(BaseAnnotatedDataset[Sequence[Sequence[int]]], ObjectDetectionDataset):
-    class ObjectDetectionTarget:
-        def __init__(self, labels: Sequence[int], bboxes: Sequence[Sequence[float]]) -> None:
-            self._labels = labels
-            self._bboxes = bboxes
-            self._scores = [1.0] * len(labels)
-
-        @property
-        def labels(self) -> Sequence[int]:
-            return self._labels
-
-        @property
-        def boxes(self) -> Sequence[Sequence[float]]:
-            return self._bboxes
-
-        @property
-        def scores(self) -> Sequence[float]:
-            return self._scores
-
-    def __init__(
-        self,
-        images: Array | Sequence[Array],
-        labels: Array | Sequence[Array] | Sequence[Sequence[int]],
-        bboxes: Array | Sequence[Array] | Sequence[Sequence[Array]] | Sequence[Sequence[Sequence[float]]],
-        metadata: Sequence[dict[str, Any]] | None,
-        classes: Sequence[str] | None,
-        name: str | None = None,
-    ) -> None:
-        super().__init__(
-            "od",
-            images,
-            [as_numpy(label).tolist() if isinstance(label, Array) else label for label in labels],
-            metadata,
-            classes,
-        )
-        if name is not None:
-            self.__name__ = name
-            self.__class__.__name__ = name
-            self.__class__.__qualname__ = name
-        self._bboxes = [[as_numpy(box).tolist() if isinstance(box, Array) else box for box in bbox] for bbox in bboxes]
-
-    @property
-    def metadata(self) -> DatasetMetadata:
-        return DatasetMetadata(id=self._id, index2label=self._index2label)
-
-    def __getitem__(self, idx: int, /) -> tuple[Array, ObjectDetectionTarget, dict[str, Any]]:
-        return (
-            self._images[idx],
-            self.ObjectDetectionTarget(self._labels[idx], self._bboxes[idx]),
-            self._metadata[idx] if self._metadata is not None else {},
-        )
-
-
-def to_image_classification_dataset(
-    images: Array | Sequence[Array],
-    labels: Array | Sequence[int],
-    metadata: Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None,
-    classes: Sequence[str] | None,
-    name: str | None = None,
-) -> ImageClassificationDataset:
-    """
-    Helper function to create custom ImageClassificationDataset classes.
-
-    Parameters
-    ----------
-    images : Array | Sequence[Array]
-        The images to use in the dataset.
-    labels : Array | Sequence[int]
-        The labels to use in the dataset.
-    metadata : Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None
-        The metadata to use in the dataset.
-    classes : Sequence[str] | None
-        The classes to use in the dataset.
-
-    Returns
-    -------
-    ImageClassificationDataset
-    """
-    _validate_data("ic", images, labels, None, metadata)
-    return CustomImageClassificationDataset(images, labels, _listify_metadata(metadata), classes, name)
-
-
-def to_object_detection_dataset(
-    images: Array | Sequence[Array],
-    labels: Array | Sequence[Array] | Sequence[Sequence[int]],
-    bboxes: Array | Sequence[Array] | Sequence[Sequence[Array]] | Sequence[Sequence[Sequence[float]]],
-    metadata: Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None,
-    classes: Sequence[str] | None,
-    name: str | None = None,
-) -> ObjectDetectionDataset:
-    """
-    Helper function to create custom ObjectDetectionDataset classes.
-
-    Parameters
-    ----------
-    images : Array | Sequence[Array]
-        The images to use in the dataset.
-    labels : Array | Sequence[Array] | Sequence[Sequence[int]]
-        The labels to use in the dataset.
-    bboxes : Array | Sequence[Array] | Sequence[Sequence[Array]] | Sequence[Sequence[Sequence[float]]]
-        The bounding boxes (x0,y0,x1,y0) to use in the dataset.
-    metadata : Sequence[dict[str, Any]] | dict[str, Sequence[Any]] | None
-        The metadata to use in the dataset.
-    classes : Sequence[str] | None
-        The classes to use in the dataset.
-
-    Returns
-    -------
-    ObjectDetectionDataset
-    """
-    _validate_data("od", images, labels, bboxes, metadata)
-    return CustomObjectDetectionDataset(images, labels, bboxes, _listify_metadata(metadata), classes, name)

dataeval/utils/datasets/__init__.py

@@ -1,21 +0,0 @@
-"""Provides access to common Computer Vision datasets."""
-
-from dataeval.utils.datasets._antiuav import AntiUAVDetection
-from dataeval.utils.datasets._cifar10 import CIFAR10
-from dataeval.utils.datasets._milco import MILCO
-from dataeval.utils.datasets._mnist import MNIST
-from dataeval.utils.datasets._seadrone import SeaDrone
-from dataeval.utils.datasets._ships import Ships
-from dataeval.utils.datasets._voc import VOCDetection, VOCDetectionTorch, VOCSegmentation
-
-__all__ = [
-    "MNIST",
-    "Ships",
-    "CIFAR10",
-    "AntiUAVDetection",
-    "MILCO",
-    "SeaDrone",
-    "VOCDetection",
-    "VOCDetectionTorch",
-    "VOCSegmentation",
-]