soda-inria/carte
Repository for CARTE: Context-Aware Representation of Table Entries
This project helps data scientists and machine learning engineers analyze complex tabular datasets more effectively. It takes your raw spreadsheet-like data, transforms each row into a graphical representation, and then uses a pre-trained model to find hidden patterns. The output is a highly accurate prediction for classification (e.g., categorizing items) or regression (e.g., predicting numerical values) tasks.
167 stars. No commits in the last 6 months.
Use this if you need to build highly accurate predictive models for tabular data and want to leverage advanced techniques for capturing relationships within your datasets.
Not ideal if you are a beginner looking for a simple, out-of-the-box solution without any programming or machine learning background.
Stars
167
Forks
16
Language
Python
License
BSD-3-Clause
Category
Last pushed
Aug 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/soda-inria/carte"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
VectorInstitute/odyssey
A toolkit for developing foundation models using Electronic Health Record (EHR) data.
ycq091044/BIOT
BIOT - A framework for pretraining biosignals at scale. Large EEG pre-trained models.
AntixK/PyTorch-Model-Compare
Compare neural networks by their feature similarity
woodRock/fishy-business
Machine Learning for Rapid Evaporative Ionization Mass Spectrometry for Marine Biomass Analysis...
harryjdavies/HeartGPT
Interpretable Pre-Trained Transformers for Heart Time-Series Data