summaryrefslogtreecommitdiff
path: root/sci-ml/datasets
diff options
context:
space:
mode:
Diffstat (limited to 'sci-ml/datasets')
-rw-r--r--sci-ml/datasets/Manifest2
-rw-r--r--sci-ml/datasets/datasets-3.4.1.ebuild119
2 files changed, 121 insertions, 0 deletions
diff --git a/sci-ml/datasets/Manifest b/sci-ml/datasets/Manifest
index 6aa909177994..fad5caa1423d 100644
--- a/sci-ml/datasets/Manifest
+++ b/sci-ml/datasets/Manifest
@@ -4,8 +4,10 @@ DIST datasets-3.0.2.gh.tar.gz 1867037 BLAKE2B 92475ac566bd825c542dbd3e138c83e173
DIST datasets-3.1.0.gh.tar.gz 1877057 BLAKE2B 818cbf10282f775cda5956ae37607bb5357a753229fa91788b19437eb28df609a99c9000f283a8b9b27a920efb3b32f991d729db94a0acf08aaca8cdcd6c4f4b SHA512 7e2a22b6ca423f4358153137f50d963075d37ad01e834c78176dc432f1b3adc3b80df44ac35b22d727db4e1aa8331c938efca1ab2d678e58401e8e7ce571abfc
DIST datasets-3.2.0.gh.tar.gz 1877261 BLAKE2B 0169ee27e1128f8b64fda0e3a4dd63d5d603874cdbf703cd73f100ad1ea69294c300b93cddaa4f2dd8c795570b76adb34e40475d38730f4733679008fb593d84 SHA512 2e381d6919ea7f2e934e832d6bff30a4b23cfe929c0b4345703ce39c7882daf8a234fe71ca89d1d9bcd75000e35845156f7036f9604504ac584feb1b8d3239b1
DIST datasets-3.3.2.gh.tar.gz 1886396 BLAKE2B bb51d8e929fbadd9d04f7ca6c8894dc06b88940643f02743b10cea3c2dd5b91b720358d2229a2263e236a6b4911d9dc60e8698da4369393a63f2603274a4f599 SHA512 4c6c4a4e748b5018574c0968929d1dac2aee96bc6f964dedf54c63e872808ca4a4958ed59e0240c958f352ca7a8d333de7ac44095e7c9525e2d9e703afbaeabf
+DIST datasets-3.4.1.gh.tar.gz 1888651 BLAKE2B 836f0e0bb55cefd5a0616785c87c867292cc46ec609934b4f7688462aa7ec95b248f06018cd99e68a88b4e179e0aa48dd601a2fc74bc1b809c336bd70ae0bd6a SHA512 c3654fec241b5da1fb2c9349ff2d0f309e184e5158a0bd19ca0477f1bfb7570d9268e93d1828e1648132563c04ba62ec4eabead2f29d8ef1a29b593aec1c62b1
EBUILD datasets-3.0.2-r1.ebuild 3862 BLAKE2B 757bd443b59c6636a4a993d1ed8010a0e331bf98d93e0228d2df15f1b31056c1555f9f9bc5790c682d23866ba3f9b5dec154356f6cfacf1e7b6e9a450759e181 SHA512 9c7e9572592716ddc2ad4a84e5df69fc46cba872f17f92de36ba803ae0e1db0bc65568e9bc9327c42b0053ff1f28dc58533eab57a1753f696510e042c713f916
EBUILD datasets-3.1.0.ebuild 3869 BLAKE2B 4646f5dd6fd885f98321956d3875b656fc49b88d69e3235dfb741e95127aa925a2e64316a43acb47fd2f01c4d2391b65980b28cf206843c785f7aba73bfdfecd SHA512 29269df33350b63b0a7e6ccd847a73eb9647a4c292fb8fe22b9960fdc7152dcc002f54b279249155c194c5db1f665ff4bead14a45bd3c8f83278128dc4d602f3
EBUILD datasets-3.2.0.ebuild 3869 BLAKE2B 4646f5dd6fd885f98321956d3875b656fc49b88d69e3235dfb741e95127aa925a2e64316a43acb47fd2f01c4d2391b65980b28cf206843c785f7aba73bfdfecd SHA512 29269df33350b63b0a7e6ccd847a73eb9647a4c292fb8fe22b9960fdc7152dcc002f54b279249155c194c5db1f665ff4bead14a45bd3c8f83278128dc4d602f3
EBUILD datasets-3.3.2.ebuild 3817 BLAKE2B 8a06e33e8dfcb01f16008bfe3ff80be0751c18b39ce14031b1218c926169d7a790f6d990f9470df91e7b1068a5a92eee114e0af68781366de3ab7ea7d10b4546 SHA512 82948eb49d0730998c039795116e8493ce9b2236b74e2df953b39dcd6b79c94fb7d686f13e80d0d46b1d48d0c78a6725b380000f4cd84baedd190351c8d6584f
+EBUILD datasets-3.4.1.ebuild 4109 BLAKE2B afa5500f83907c5a657b2f350e960cf2c21866424efb3c3d7cc3f6266836f23d3557549333a83831d7a5115fd72f159fabcfde8c40f0e9bbf9eec1b28cb86e9f SHA512 1dbee5af66807c2590017b5f6fc5d6065f4e74933e70b882de6e63c21bb922a1d3ed4414f02cfad8f27a5a9515add951a518bdcedc2dc73e8fcad98dec66d255
MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1
diff --git a/sci-ml/datasets/datasets-3.4.1.ebuild b/sci-ml/datasets/datasets-3.4.1.ebuild
new file mode 100644
index 000000000000..7941f2f45941
--- /dev/null
+++ b/sci-ml/datasets/datasets-3.4.1.ebuild
@@ -0,0 +1,119 @@
+# 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_{11..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
+ -> ${P}.gh.tar.gz"
+
+LICENSE="Apache-2.0"
+SLOT="0"
+KEYWORDS="~amd64"
+
+RDEPEND="
+ sci-ml/huggingface_hub[${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="${RDEPEND}"
+# Missing x test:
+# joblib
+# joblibspark
+# faiss-cpu
+# jax
+# jaxlib
+# polars
+# pyav
+# pyspark
+# py7zr
+# s3fs
+# tensorflow
+# tiktoken
+# torchdata
+# transformers
+BDEPEND="test? (
+ sci-ml/caffe2[${PYTHON_SINGLE_USEDEP},numpy]
+ sci-ml/pytorch[${PYTHON_SINGLE_USEDEP}]
+ sci-ml/torchvision[${PYTHON_SINGLE_USEDEP}]
+ $(python_gen_cond_dep '
+ dev-python/absl-py[${PYTHON_USEDEP}]
+ dev-python/decorator[${PYTHON_USEDEP}]
+ dev-python/elasticsearch[${PYTHON_USEDEP}]
+ dev-python/lz4[${PYTHON_USEDEP}]
+ dev-python/moto[${PYTHON_USEDEP}]
+ dev-python/protobuf:=[${PYTHON_USEDEP}]
+ dev-python/pytest-datadir[${PYTHON_USEDEP}]
+ dev-python/pytest-xdist[${PYTHON_USEDEP}]
+ dev-python/soundfile[${PYTHON_USEDEP}]
+ dev-python/sqlalchemy[${PYTHON_USEDEP}]
+ dev-python/zstandard[${PYTHON_USEDEP}]
+ ')
+)"
+
+distutils_enable_tests pytest
+
+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/features/test_video.py::test_video_feature_encode_example
+ tests/features/test_video.py::test_dataset_with_video_feature
+ tests/features/test_video.py::test_dataset_with_video_map_and_formatted
+ 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
+}