NLP Datasets from HuggingFace: How to Access and Train Them

The Datasets library from hugging Face provides a very efficient way to load and process NLP datasets from raw files or in-memory data. These NLP datasets have been shared by different research and practitioner communities across the world.

You can also load various evaluation metrics used to check the performance of NLP models on numerous tasks.

If you are working in Natural Language Processing and want an NLP dataset for your next project, I recommend you use this library from Hugging Face.

You can use this library with other popular frameworks in machine learning, such as Numpy, Pandas, Pytorch, and TensorFlow. You will learn more in the examples below.

The NLP datasets are available on different tasks such as

Text-classification
Question-Answering
Sequence-modelling
Machine translation,
Automatic speech-recognition
Sentiment Analysis
Speech Processing
Name entity Recognition
Part of Speech Tagging
others

You can find the NLP datasets in more than 186 languages. All these datasets can also be browsed on the HuggingFace Hub and can be viewed and explored online with the Datasets viewer.

In this article, you will learn how to download, load, configure and use NLP datasets from the hugging face datasets library.

Let's get started.

How to Install Datasets Library

Installation is easy and takes only a few minutes. You can use pip as follows:

pip install datasets

Another option for installation is using conda as follows.

conda install -c huggingface -c conda-forge datasets

List of Datasets

To view the list of different available datasets from the library, you can use the

list_datasets()

function from the library.

from datasets import list_datasets, load_dataset
from pprint import pprint

datasets_list = list_datasets() 
pprint(datasets_list,compact=True)

Currently, the datasets library has a total of 1182 datasets that can be used to create different NLP solutions.

List of Dataset with Details

You can also view a list of the datasets with details by adding an argument called

with_details

equal to

True

in the list_datases() function as follows.

datasets_list = list_datasets(with_details=True) 
pprint(datasets_list)

This will show a list of datasets with their id(name), descriptions, and files (if downloaded in your local machine).

Load Dataset

To load the dataset from the library, you need to pass the file name on the

load_dataset()

function.

The load_dataset function will do the following.

Download and import in the library the file processing script from the Hugging Face GitHub repo.
Run the file script to download the dataset
Return the dataset as asked by the user. By default, it returns the entire dataset

dataset = load_dataset('ethos','binary')

In the above example, I downloaded the ethos dataset from hugging face.

"ETHOS: onlinE haTe speecH detectiOn dataSet. This repository contains a dataset for hate speech detection on social media platforms, called Ethos. There are two variations of the dataset:"- HuggingFace's page

Note: Each dataset can have several configurations that define the sub-part of the dataset you can select. For example, the ethos dataset has two configurations.

binary version
multi-label version

Let’s load the binary version we have downloaded.

print(dataset)

Split the Train and Validation Sets

Sometimes you don't want to download the entire dataset, you can use the split parameter to specify if you want to download the train, validation, or test set from the dataset.

ethos_train = load_dataset('ethos','binary',split='train')

ethos_validation = load_dataset('ethos','binary',split='validation')

This will save the training set in the

ethos_train

variable and the validation set in

ethos_validation

variable.

Note: Not all datasets have the train, validation, and test set. Some of them can contain only the train set. So you need to read more about the dataset you want to download from the hugging face dataset page.

Load Dataset from Local File

You can use the library to load your local dataset from the local machine. You can load datasets that have the following format.

CSV files
JSON files
Text files (read as a line-by-line dataset),
Pandas pickled dataframe

To load the local file you need to define the format of your dataset (example "CSV") and the path to the local file.

dataset = load_dataset('csv', data_files='my_file.csv')

You can similarly instantiate a Dataset object from a pandas DataFrame as follows:

from datasets import Dataset
import pandas as pd 

df = pd.DataFrame({"a": [1, 2, 3]})
df_dataset = Dataset.from_pandas(df)

print(df_dataset)

Download Mode

When you load already downloaded data from the cache directory, you can control how the

load_datasets()

function handles it by setting its download_mode parameter.

The parameter options are as follows.

"reuse_dataset_if_exists" (default) - This will reuse both raw downloads and the prepared dataset if they exist in the cache directory.
"reuse_cache_if_exists"- This will use the cached dataset.
"force_redownload" - This will redownload the dataset.

dataset = load_dataset('ethos','binary', download_mode="force_redownload")

In the above example, we redownload the ethos dataset with binary configuration.

Setting The Format

You can set the format of the dataset instance by using the

set_format()

function that takes as arguments.

type: an optional string that defines the type of the objects that should be returned by

datasets.Dataset.getitem()

None/'python' (default): return python objects,
'torch'/'pytorch'/'pt': return PyTorch tensors,
'tensorflow'/'tf': return Tensorflow tensors,
'jax': return JAX arrays,
'numpy'/'np': return Numpy arrays,
'pandas'/'pd': return Pandas DataFrames

ethos_train.set_format(type='pandas', columns=['comment',  'label'])

In the above example, we set the format type as "pandas".

Final Thoughts on NLP Datasets from Huggingface

In this article, you have learned how to download datasets from hugging face datasets library, split into train and validation sets, change the format of the dataset, and more. We did not cover all the functions available from the datasets library. Check the following resources if you are looking to go deeper.

Datasets: https://huggingface.co/datasets
Datasets documentation: https://huggingface.co/docs/datasets/
NLP Metrics: https://huggingface.co/docs/datasets/loading_metrics.html

If you learned something new or enjoyed reading this article, please share it so that others can see it. Until then, see you in the next post!

You can also find me on Twitter @Davis_McDavid.

And you can read more articles like this here.

Want to keep up to date with all the latest in Data Science? Subscribe to our newsletter in the footer below.