{% set name = "datasets" %}
{% set version = "2.12.0" %}

package:
  name: {{ name|lower }}
  version: {{ version }}

source:
  url: https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/{{ name }}-{{ version }}.tar.gz
  sha256: faf164c18a41bea51df3f369e872f8be5b84c12ea5f6393c3896f56038af1ea3

build:
  # s390x is missing pyarrow atm 
  skip: true  # [py<37 or s390x] 
  entry_points:
    - datasets-cli=datasets.commands.datasets_cli:main
  number: 0
  script: {{ PYTHON }} -m pip install . --no-deps --no-build-isolation --ignore-installed -vv

requirements:
  host:
    - python
    - pip
    - setuptools
    - wheel
  run:
    - python
    - numpy >=1.17
    - pyarrow >=8.0.0
    - dill >=0.3.0,<0.3.7
    - pandas
    - requests >=2.19.0
    - tqdm >=4.62.1
    - python-xxhash
    - multiprocess
    - importlib-metadata  # [py<38]
    - fsspec >=2021.11.1
    - aiohttp
    - huggingface_hub >=0.11.0,<1.0.0
    - packaging
    - responses <0.19
    - pyyaml >=5.1

test:
  imports:
    - datasets
    - datasets.commands
    - datasets.utils
  commands:
    - pip check
    - datasets-cli --help
  requires:
    - pip

about:
  home: https://github.com/huggingface/datasets
  summary: HuggingFace community-driven open-source library of datasets
  description: |
    Datasets is a lightweight library providing two main features:

    - one-line dataloaders for many public datasets: one-liners to download and pre-process any of the number of datasets major public datasets (text datasets in 467 languages and dialects, image datasets, audio datasets, etc.) provided on the HuggingFace Datasets Hub. With a simple command like squad_dataset = load_dataset("squad"), get any of these datasets ready to use in a dataloader for training/evaluating a ML model (Numpy/Pandas/PyTorch/TensorFlow/JAX),
    - efficient data pre-processing: simple, fast and reproducible data pre-processing for the above public datasets as well as your own local datasets in CSV/JSON/text/PNG/JPEG/etc. With simple commands like `processed_dataset = dataset.map(process_example)`, efficiently prepare the dataset for inspection and ML model evaluation and training.
  license: Apache-2.0
  license_family: Apache
  license_file: LICENSE  
  doc_url: https://huggingface.co/docs/datasets/index
  dev_url: https://github.com/huggingface/datasets

extra:
  recipe-maintainers:
    - oblute
    - Tata17
    - thewchan
    - mxr-conda
    - wietsedv