# pytorch-tabular/pytorch_tabular

A unified framework for Deep Learning Models on tabular data

Repository: https://github.com/pytorch-tabular/pytorch_tabular
Canonical: https://ross.abutalabs.com/products/pytorch_tabular
Homepage: https://pytorch-tabular.readthedocs.io/
Language: Python
License: MIT
License Family: permissive
Topics: tabular-data, deep-learning, pytorch, pytorch-lightning, hacktoberfest, machine-learning
Last push: 2026-04-17T11:32:50+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 77, release rhythm 36, longevity 100
- inputs: {"age_days": 2087, "days_push": 138, "days_rel": 219, "gap_med": 423, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1677, forks 177 (observed 2026-08-28T04:05:20.936452+00:00)

## What it is
PyTorch Tabular is a Python library providing a unified, high-level interface for deep learning models on tabular data, built on PyTorch and PyTorch Lightning. It bundles standard tabular architectures with automatic GPU/CPU scaling and logging.

## Use cases
- train deep learning models on tabular data
- apply neural networks to structured CSV datasets
- use TabNet or FT-Transformer style architectures
- scale tabular model training on GPU with PyTorch Lightning
- replace gradient boosting with deep learning for classification or regression

## When to choose
- you want a high-level API for deep learning on tabular data without writing boilerplate
- you want built-in access to multiple tabular architectures under one interface
- you already use PyTorch Lightning and want automatic logging and GPU scaling

## When to avoid
- you need a quick baseline on small tabular data, where gradient boosting (XGBoost/LightGBM) is often stronger
- you need custom architectures outside the supported set
- you work with images, text, or audio rather than structured tables

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, data-science
- platform: python
- tags: tabular-data, pytorch-lightning, neural-networks, high-level-api

## Member repositories
- pytorch-tabular/pytorch_tabular (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:20.936452+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:41:37.892465+00:00, confidence not recorded.
  - readme: https://github.com/pytorch-tabular/pytorch_tabular (fetched 2026-08-28T04:05:20.936452+00:00, sha 3fdfbfd7892c)
  - registry_pypi: https://pypi.org/pypi/pytorch_tabular/json (fetched 2026-08-29T11:15:33.527160+00:00, sha a896939bdf43)
- Data as of 2026-08-30T08:39:29.467469+00:00.