Interactively explore your Huggingface dataset with one line of code

The Hugging Face datasets library not only provides access to more than 70k publicly available datasets, but also offers very convenient data preparation pipelines for custom datasets.

Renumics Spotlight allows you to create interactive visualizations to identify critical clusters in your data. Because Spotlight understands the data semantics within Hugging Face datasets, you can get started with just one line of code:

import datasets
from renumics import spotlight

ds = datasets.load_dataset('speech_commands', 'v0.01', split='validation')

spotlight.show(ds)

Spotlight allows to leverage model results such as predictions and embeddings to gain a deeper understanding in data segments and model failure modes:

ds_results = datasets.load_dataset('renumics/speech_commands-ast-finetuned-results', 'v0.01', split='validation')
ds = datasets.concatenate_datasets([ds, ds_results], axis=1)

spotlight.show(ds, dtype={'embedding': spotlight.Embedding}, layout=spotlight.layouts.debug_classification(embedding='embedding', inspect={'audio': spotlight.dtypes.audio_dtype}))

Data inspection is a very important task in almost all ML development stages, but it can also be very time consuming.

“Manual inspection of data has probably the highest value-to-prestige ratio of any activity in machine learning.” — Greg Brockman

Spotlight helps you to make data inspection more scalable along two dimensions: Setting up and maintaining custom data inspection workflows and finding relevant data samples and clusters to inspect. In the following sections we show some examples based on Hugging Face datasets.

Spotlight 🤝 Hugging Face datasets

The datasets library has several features that makes it an ideal tool for working with ML datasets: It stores tabular data (e.g. metadata, labels) along with unstructured data (e.g. images, audio) in a common Arrows table. Datasets also describes important data semantics through features (e.g. images, audio) and additional task-specific metadata.