blob: 271dc355ae2080586f1c843708f89484c096069f (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
# Maintainer: trougnouf (Benoit Brummer) < trougnouf at gmail dot com >
# Maintainer: daskol (Daniel Bershatsky) < bepshatsky at yandex dot ru >
pkgname='python-datasets'
pkgver=2.19.0
pkgrel=1
pkgdesc='The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools'
arch=('x86_64')
url='https://github.com/huggingface/datasets'
license=('Apache')
depends=(
'python-aiohttp'
'python-dill'
'python-fsspec>=2023.9.0'
'python-huggingface-hub>=0.20.0'
'python-multiprocess'
'python-numpy'
'python-packaging'
'python-pandas'
'python-pyarrow>=14.0.1'
'python-yaml'
'python-requests'
'python-tqdm'
'python-xxhash'
)
makedepends=('python-build' 'python-hatchling' 'python-installer'
'python-setuptools' 'python-wheel')
optdepends=(
'python-librosa: Audio datasets'
'python-pillow: Vision datasets'
'python-tensorflow: TensorFlow support'
'python-pytorch: PyTorch support'
)
groups=('huggingface')
source=("datasets-${pkgver}.tar.gz::https://github.com/huggingface/datasets/archive/refs/tags/${pkgver}.tar.gz"
'python-datasets.diff')
sha256sums=('fb0b4196b94c8a744c1734a6119254fe2ebf82929957cb8c3afdd2df4d0ccf32'
'SKIP')
prepare() {
cd ${srcdir}/datasets-${pkgver}
patch -p1 -i ../python-datasets.diff
}
build() {
python -m build -nw ${srcdir}/datasets-${pkgver}
}
check() {
# Sanity check: import package.
cd ${srcdir}/datasets-${pkgver}/src
python -c "import datasets"
}
package() {
cd ${srcdir}/datasets-${pkgver}
install -Dm644 README.md -t "${pkgdir}/usr/share/doc/${pkgname}"
python -m installer --compile-bytecode 1 --destdir $pkgdir dist/*.whl
}
|