arashdn/dtt

DTT: A Deep Learning Framework to Transform Tabular Data for Joinability by Leveraging Large Language Models

13
/ 100
Experimental

This project helps data professionals clean and standardize messy tabular data so it can be accurately combined, or 'joined,' with other datasets. It takes a source table and a target table, applies a deep learning model to transform the source data's format, and outputs a revised source table ready for joining. It's designed for data analysts, data scientists, or database administrators who deal with inconsistent data formats.

No commits in the last 6 months.

Use this if you frequently encounter situations where you need to join multiple tables but their text-based columns (like names, addresses, or product descriptions) don't match perfectly due to variations in spelling, formatting, or abbreviations.

Not ideal if your data cleaning needs are limited to numerical data transformations or simple string operations that can be handled with standard scripting or spreadsheet functions.

data-preparation data-integration data-wrangling database-management data-standardization
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Python

License

Last pushed

Jun 13, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/arashdn/dtt"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.