guenthermi/table-embeddings

Tools for training schema-aware Web table embedding for unsupervised and supervised machine learning on tabular data

26
/ 100
Experimental

This tool helps data professionals understand and compare tabular data, especially data found on the web. It takes text labels from table headers or data cells and converts them into numerical representations, which can then be used for various analytical tasks. Data analysts, researchers, or anyone working with large collections of tables would use this to find similar tables or classify table content.

No commits in the last 6 months.

Use this if you need to analyze, classify, or find relationships between many different tables, particularly those scraped from the web, and want to represent table elements numerically for machine learning.

Not ideal if your primary need is simply to extract data from a single web table, or if you are not comfortable with concepts like data embeddings or machine learning workflows.

data-analysis web-data-extraction tabular-data-matching data-classification data-integration
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

MIT

Last pushed

Apr 14, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/guenthermi/table-embeddings"

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