aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRicardo Wurmus <rekado@elephly.net>2022-12-06 15:14:46 +0100
committerRicardo Wurmus <rekado@elephly.net>2022-12-12 14:37:03 +0100
commiteb2337982888a1445d1b6067ff6090f08dd0b8ae (patch)
tree781e589340b5a987b2e41e9424a17fb2ddad9326
parent2c8a53cb6b3d2224a12d99c28fcea13c7aa1e3f1 (diff)
downloadguix-eb2337982888a1445d1b6067ff6090f08dd0b8ae.tar
guix-eb2337982888a1445d1b6067ff6090f08dd0b8ae.tar.gz
gnu: Add python-cleanlab.
* gnu/packages/machine-learning.scm (python-cleanlab): New variable.
-rw-r--r--gnu/packages/machine-learning.scm46
1 files changed, 46 insertions, 0 deletions
diff --git a/gnu/packages/machine-learning.scm b/gnu/packages/machine-learning.scm
index fbc06f96b6..6546a17f5c 100644
--- a/gnu/packages/machine-learning.scm
+++ b/gnu/packages/machine-learning.scm
@@ -43,6 +43,7 @@
#:use-module (guix build-system cmake)
#:use-module (guix build-system gnu)
#:use-module (guix build-system ocaml)
+ #:use-module (guix build-system pyproject)
#:use-module (guix build-system python)
#:use-module (guix build-system r)
#:use-module (guix build-system trivial)
@@ -1283,6 +1284,51 @@ good at identifying feature interactions that are normally overlooked by
standard feature selection algorithms.")
(license license:expat)))
+(define-public python-cleanlab
+ (package
+ (name "python-cleanlab")
+ (version "2.2.0")
+ ;; The version on pypi does not come with tests.
+ (source (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/cleanlab/cleanlab")
+ (commit (string-append "v" version))))
+ (file-name (git-file-name name version))
+ (sha256
+ (base32
+ "00dqhxpwg781skknw943ynll2s44g4j125dx8aapk1d5d71sbzqy"))))
+ (build-system pyproject-build-system)
+ (arguments
+ (list
+ #:phases
+ '(modify-phases %standard-phases
+ (add-after 'unpack 'disable-bad-tests
+ (lambda _
+ ;; XXX This requires pytest lazy_fixture
+ (delete-file "tests/test_multilabel_classification.py")
+ ;; Requires tensorflow
+ (delete-file "tests/test_frameworks.py")
+ ;; Tries to download datasets from the internet at runtime.
+ (delete-file "tests/test_dataset.py"))))))
+ (propagated-inputs
+ (list python-numpy
+ python-pandas
+ python-scikit-learn
+ python-termcolor
+ python-tqdm))
+ (native-inputs
+ (list python-pytest
+ python-pytorch
+ python-torchvision))
+ (home-page "https://cleanlab.ai")
+ (synopsis "Automatically find and fix dataset issues")
+ (description
+ "cleanlab automatically finds and fixes errors in any ML dataset. This
+data-centric AI package facilitates machine learning with messy, real-world
+data by providing clean labels during training.")
+ (license license:agpl3+)))
+
(define-public python-cmaes
(package
(name "python-cmaes")