SAP-samples/portal
Implementation of the deep learning models with training and evaluation pipelines described in the paper "PORTAL: Scalable Tabular Foundation Models via Content-Specific Tokenization"
This project helps data scientists and machine learning engineers analyze large, diverse datasets by offering a self-supervised learning framework. It takes raw tabular data from various sources without needing extensive cleaning, and outputs highly accurate models for complex classification and regression tasks. It's ideal for those working with business data, scientific observations, or financial records.
No commits in the last 6 months.
Use this if you need to build high-performing predictive models from messy, real-world tabular data without spending excessive time on manual data preparation.
Not ideal if your data is already perfectly clean, uniform, and small enough for traditional machine learning methods to suffice.
Stars
15
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
May 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SAP-samples/portal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PriorLabs/TabPFN
⚡ TabPFN: Foundation Model for Tabular Data ⚡
pyg-team/pytorch-frame
Tabular Deep Learning Library for PyTorch
NVIDIA-Merlin/NVTabular
NVTabular is a feature engineering and preprocessing library for tabular data designed to...
PriorLabs/tabpfn-extensions
Community extensions for TabPFN - the foundation model for tabular data. Built with TabPFN! 🤗
pytorch-tabular/pytorch_tabular
A unified framework for Deep Learning Models on tabular data