huggingface/datasets

pip install datasets

pip install "datasets @ git+https://github.com/huggingface/datasets.git"

conda install -c huggingface -c conda-forge datasets

# For audio (torchcodec)
pip install datasets[audio]

# For image/video (Pillow, torchcodec)
pip install datasets[vision]

# For PDFs/NIfTI (pdfplumber, nibabel)
pip install datasets[pdfs,nibabel]

# For PyTorch/TensorFlow/JAX integration
pip install datasets[torch,tensorflow,jax]

from datasets import load_dataset

# Load a dataset and print the first example in the training set
squad_dataset = load_dataset('rajpurkar/squad')
print(squad_dataset['train'][0])

# Process the dataset - add a column with the length of the context texts
dataset_with_length = squad_dataset.map(lambda x: {"length": len(x["context"])})

# Tokenize the context texts (using a tokenizer from the 🤗 Transformers library)
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')

tokenized_dataset = squad_dataset.map(lambda x: tokenizer(x['context']), batched=True)

# Tokenize chat conversations with a chat template (using a model that supports chat templates)
# This is useful for fine-tuning instruction/chat models

# Load a popular chat dataset (ultrachat_200k contains ~200k AI assistant conversations)
chat_dataset = load_dataset('HuggingFaceH4/ultrachat_200k', split='train_sft')

chat_tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-7B-Instruct')

def tokenize_chat(examples):
    # Apply the chat template and tokenize in one step
    return chat_tokenizer.apply_chat_template(examples["messages"])

tokenized_chat_dataset = chat_dataset.map(tokenize_chat, batched=True)

# Stream the dataset without downloading anything
image_dataset = load_dataset('timm/imagenet-1k-wds', streaming=True)
for example in image_dataset["train"]:
    print(example["image"])
    break

# Audio dataset
dataset = load_dataset("openslr/librispeech_asr", "clean")

# Image dataset
dataset = load_dataset("ILSVRC/imagenet-1k")

# Video dataset
dataset = load_dataset("Shofo/shofo-tiktok-general-small")

# PDF documents
dataset = load_dataset("pixparse/pdfa-eng-wds")

# NIfTI (3D medical imaging)
dataset = load_dataset("dartbrains/localizer", "betas")

# Load from local CSV
dataset = load_dataset('csv', data_files='my_data.csv')

# Load from local Parquet
dataset = load_dataset('parquet', data_files='data/*.parquet')

# Load from a local directory (auto-detect format)
dataset = load_dataset('./path/to/data')

from datasets import Dataset

# From a dictionary
dataset = Dataset.from_dict({"text": ["Hello world", "How are you?"]})

# From a list
dataset = Dataset.from_list([{"text": "Hello world"}, {"text": "How are you?"}])

# From Pandas
import pandas as pd
df = pd.DataFrame({"col1": [1, 2, 3], "col2": ["a", "b", "c"]})
dataset = Dataset.from_pandas(df)

# From a generator
def gen():
    for i in range(10):
        yield {"value": i}
dataset = Dataset.from_generator(gen)

@inproceedings{lhoest-etal-2021-datasets,
    title = "Datasets: A Community Library for Natural Language Processing",
    author = "Lhoest, Quentin  and
      Villanova del Moral, Albert  and
      Jernite, Yacine  and
      Thakur, Abhishek  and
      von Platen, Patrick  and
      Patil, Suraj  and
      Chaumond, Julien  and
      Drame, Mariama  and
      Plu, Julien  and
      Tunstall, Lewis  and
      Davison, Joe  and
      {\v{S}}a{\v{s}}ko, Mario  and
      Chhablani, Gunjan  and
      Malik, Bhavitvya  and
      Brandeis, Simon  and
      Le Scao, Teven  and
      Sanh, Victor  and
      Xu, Canwen  and
      Patry, Nicolas  and
      McMillan-Major, Angelina  and
      Schmid, Philipp  and
      Gugger, Sylvain  and
      Delangue, Cl{\'e}ment  and
      Matussi{\`e}re, Th{\'e}o  and
      Debut, Lysandre  and
      Bekman, Stas  and
      Cistac, Pierric  and
      Goehringer, Thibault  and
      Mustar, Victor  and
      Lagunas, Fran{\c{c}}ois  and
      Rush, Alexander  and
      Wolf, Thomas",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.emnlp-demo.21",
    pages = "175--184",
    abstract = "The scale, variety, and quantity of publicly-available NLP datasets has grown rapidly as researchers propose new tasks, larger models, and novel benchmarks. Datasets is a community library for contemporary NLP designed to support this ecosystem. Datasets aims to standardize end-user interfaces, versioning, and documentation, while providing a lightweight front-end that behaves similarly for small datasets as for internet-scale corpora. The design of the library incorporates a distributed, community-driven approach to adding datasets and documenting usage. After a year of development, the library now includes more than 650 unique datasets, has more than 250 contributors, and has helped support a variety of novel cross-dataset research projects and shared tasks. The library is available at https://github.com/huggingface/datasets.",
    eprint={2109.02846},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
}