summaryrefslogtreecommitdiff
path: root/sci-ml
diff options
context:
space:
mode:
Diffstat (limited to 'sci-ml')
-rw-r--r--sci-ml/Manifest.gzbin5237 -> 5239 bytes
-rw-r--r--sci-ml/datasets/Manifest4
-rw-r--r--sci-ml/datasets/datasets-3.0.2-r1.ebuild1
-rw-r--r--sci-ml/datasets/datasets-3.1.0.ebuild112
4 files changed, 116 insertions, 1 deletions
diff --git a/sci-ml/Manifest.gz b/sci-ml/Manifest.gz
index 5100930771ed..632bbd237a40 100644
--- a/sci-ml/Manifest.gz
+++ b/sci-ml/Manifest.gz
Binary files differ
diff --git a/sci-ml/datasets/Manifest b/sci-ml/datasets/Manifest
index 44490cc68f28..0f7f7dbc7341 100644
--- a/sci-ml/datasets/Manifest
+++ b/sci-ml/datasets/Manifest
@@ -1,5 +1,7 @@
AUX datasets-2.21.0-tests.patch 721 BLAKE2B cf85b02a4eb5da27e52bf819f00e333d6e3fb3fb0b9f7279afff24e3fddf76fcd46cb5e06d29b4780d0ce6b48c9378df301c70f6339e2f2898560219ebab4210 SHA512 43cdc5af6ba3fff3e7641006be6d8e10a5ad00136c1cf137628456019cccbd3d05b888b7eeec1cb8cd42d5ce52091b2a66d32a5b41ff2193658c4257900ea45c
AUX datasets-3.0.2-tests.patch 335 BLAKE2B b7499d85cc8cf09a2cb9b58aa0c7ab16c1bc700812c767465979cc59b11d63d05f52422ae731317f373314164715079f6fa81b30d47e3058ce88d6539d049789 SHA512 3f533ab765362ea6a1bc7a1766d332f5bc53e342cbb684061eaed58ef415f715c003f210b73a8b0ca20245d8e1f60517191829fb64feb53101211a9f81542e5a
DIST datasets-3.0.2.gh.tar.gz 1867037 BLAKE2B 92475ac566bd825c542dbd3e138c83e1733e6d1137f30a2cfd8f82f7dd54ed78c0566aa766182625e8787413be18f5a0c0c0a289b5823fa9112dcb2876074b7e SHA512 aa55dd2f53df7217c30999f759c76a13d78851233bce4df9b1ad85081e101a7280e905822160874d24d15ea1e1a5ecee1bae9cc66785e89af45ad16dd0339595
-EBUILD datasets-3.0.2-r1.ebuild 3795 BLAKE2B 5a9872b29860c319740bbd17f1b269d35e9d37704f17c3f0f06198f6e8351e57c35ab4e290349b793e4ab424c24780f8535ab32aed9d52369fa8e785d8f29480 SHA512 685a9e3129cec344b01b336fee90f59d68ecd431faf48ffb5b7d84278ecafebb8869ff27d5c16236cf85f616c1d5760744179a51d9c07ed6c2f8bffe7c64d411
+DIST datasets-3.1.0.gh.tar.gz 1877057 BLAKE2B 818cbf10282f775cda5956ae37607bb5357a753229fa91788b19437eb28df609a99c9000f283a8b9b27a920efb3b32f991d729db94a0acf08aaca8cdcd6c4f4b SHA512 7e2a22b6ca423f4358153137f50d963075d37ad01e834c78176dc432f1b3adc3b80df44ac35b22d727db4e1aa8331c938efca1ab2d678e58401e8e7ce571abfc
+EBUILD datasets-3.0.2-r1.ebuild 3862 BLAKE2B 757bd443b59c6636a4a993d1ed8010a0e331bf98d93e0228d2df15f1b31056c1555f9f9bc5790c682d23866ba3f9b5dec154356f6cfacf1e7b6e9a450759e181 SHA512 9c7e9572592716ddc2ad4a84e5df69fc46cba872f17f92de36ba803ae0e1db0bc65568e9bc9327c42b0053ff1f28dc58533eab57a1753f696510e042c713f916
+EBUILD datasets-3.1.0.ebuild 3869 BLAKE2B 4646f5dd6fd885f98321956d3875b656fc49b88d69e3235dfb741e95127aa925a2e64316a43acb47fd2f01c4d2391b65980b28cf206843c785f7aba73bfdfecd SHA512 29269df33350b63b0a7e6ccd847a73eb9647a4c292fb8fe22b9960fdc7152dcc002f54b279249155c194c5db1f665ff4bead14a45bd3c8f83278128dc4d602f3
MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1
diff --git a/sci-ml/datasets/datasets-3.0.2-r1.ebuild b/sci-ml/datasets/datasets-3.0.2-r1.ebuild
index 4b438c0f0888..3a4fb6545732 100644
--- a/sci-ml/datasets/datasets-3.0.2-r1.ebuild
+++ b/sci-ml/datasets/datasets-3.0.2-r1.ebuild
@@ -106,6 +106,7 @@ src_test() {
tests/test_file_utils.py::test_xopen_remote
tests/test_hub.py::test_delete_from_hub
tests/test_offline_util.py::test_offline_with_timeout
+ tests/test_search.py::ElasticSearchIndexTest::test_elasticsearch
)
distutils-r1_src_test
}
diff --git a/sci-ml/datasets/datasets-3.1.0.ebuild b/sci-ml/datasets/datasets-3.1.0.ebuild
new file mode 100644
index 000000000000..206da6ebe884
--- /dev/null
+++ b/sci-ml/datasets/datasets-3.1.0.ebuild
@@ -0,0 +1,112 @@
+# Copyright 2023-2025 Gentoo Authors
+# Distributed under the terms of the GNU General Public License v2
+
+EAPI=8
+
+DISTUTILS_USE_PEP517=setuptools
+PYTHON_COMPAT=( python3_{10..13} )
+DISTUTILS_SINGLE_IMPL=1
+inherit distutils-r1
+
+DESCRIPTION="Access and share datasets for Audio, Computer Vision, and NLP tasks"
+HOMEPAGE="https://pypi.org/project/datasets/"
+SRC_URI="https://github.com/huggingface/${PN}/archive/refs/tags/${PV}.tar.gz
+ -> ${P}.gh.tar.gz"
+
+LICENSE="Apache-2.0"
+SLOT="0"
+KEYWORDS="~amd64"
+
+RDEPEND="
+ ${PYTHON_DEPS}
+ sci-ml/caffe2[${PYTHON_SINGLE_USEDEP},numpy]
+ sci-ml/huggingface_hub[${PYTHON_SINGLE_USEDEP}]
+ sci-ml/pytorch[${PYTHON_SINGLE_USEDEP}]
+ $(python_gen_cond_dep '
+ dev-python/aiohttp[${PYTHON_USEDEP}]
+ dev-python/dill[${PYTHON_USEDEP}]
+ dev-python/filelock[${PYTHON_USEDEP}]
+ dev-python/fsspec[${PYTHON_USEDEP}]
+ dev-python/multiprocess[${PYTHON_USEDEP}]
+ dev-python/numpy[${PYTHON_USEDEP}]
+ dev-python/packaging[${PYTHON_USEDEP}]
+ dev-python/pandas[${PYTHON_USEDEP}]
+ dev-python/pyarrow[${PYTHON_USEDEP},parquet,snappy]
+ dev-python/pyyaml[${PYTHON_USEDEP}]
+ dev-python/requests[${PYTHON_USEDEP}]
+ dev-python/tqdm[${PYTHON_USEDEP}]
+ dev-python/xxhash[${PYTHON_USEDEP}]
+ ')
+"
+DEPEND="${RDEPEND}"
+BDEPEND="test? (
+ sci-ml/torchvision[${PYTHON_SINGLE_USEDEP}]
+ $(python_gen_cond_dep '
+ dev-python/absl-py[${PYTHON_USEDEP}]
+ dev-python/decorator[${PYTHON_USEDEP}]
+ dev-python/lz4[${PYTHON_USEDEP}]
+ dev-python/pytest-datadir[${PYTHON_USEDEP}]
+ dev-python/scikit-learn[${PYTHON_USEDEP}]
+ dev-python/soundfile[${PYTHON_USEDEP}]
+ dev-python/sqlalchemy[${PYTHON_USEDEP}]
+ dev-python/zstandard[${PYTHON_USEDEP}]
+ sci-ml/jiwer[${PYTHON_USEDEP}]
+ sci-ml/seqeval[${PYTHON_USEDEP}]
+ ')
+)"
+
+PATCHES=(
+ "${FILESDIR}"/${PN}-3.0.2-tests.patch
+)
+
+distutils_enable_tests pytest
+
+src_prepare() {
+ distutils-r1_src_prepare
+ sed -i -e \
+ "/pyarrow_hotfix/d" \
+ src/datasets/features/features.py || die
+}
+
+src_test() {
+ local EPYTEST_IGNORE=(
+ tests/features/test_audio.py
+ tests/packaged_modules/test_audiofolder.py
+ tests/packaged_modules/test_spark.py
+ tests/test_fingerprint.py
+ tests/test_iterable_dataset.py
+ tests/test_inspect.py
+ tests/test_load.py
+ tests/test_upstream_hub.py
+ )
+
+ local EPYTEST_DESELECT=(
+ tests/commands/test_test.py::test_test_command
+ tests/io/test_parquet.py::test_parquet_read_geoparquet
+ tests/packaged_modules/test_cache.py::test_cache_multi_configs
+ tests/packaged_modules/test_cache.py::test_cache_single_config
+ tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_caching_on_disk
+ tests/test_arrow_dataset.py::BaseDatasetTest::test_map_caching_on_disk
+ tests/test_distributed.py::test_torch_distributed_run
+ tests/test_file_utils.py::TestxPath::test_xpath_rglob
+ tests/test_file_utils.py::TestxPath::test_xpath_glob
+ tests/test_file_utils.py::test_xexists_private
+ tests/test_file_utils.py::test_xlistdir_private
+ tests/test_file_utils.py::test_xisdir_private
+ tests/test_file_utils.py::test_xisfile_private
+ tests/test_file_utils.py::test_xgetsize_private
+ tests/test_file_utils.py::test_xglob_private
+ tests/test_file_utils.py::test_xwalk_private
+ tests/test_hub.py::test_convert_to_parquet
+ tests/packaged_modules/test_cache.py::test_cache_capital_letters
+ tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_different_levels_no_metadata
+ tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_one_label_no_metadata
+ tests/test_data_files.py::test_DataFilesList_from_patterns_locally_with_extra_files
+ tests/test_data_files.py::test_DataFilesDict_from_patterns_locally_or_remote_hashing
+ tests/test_file_utils.py::test_xopen_remote
+ tests/test_hub.py::test_delete_from_hub
+ tests/test_offline_util.py::test_offline_with_timeout
+ tests/test_search.py::ElasticSearchIndexTest::test_elasticsearch
+ )
+ distutils-r1_src_test
+}