0
$\begingroup$

I'm trying to get to a tool for Fuzzy Grouping as I do not have a reference column for matching the string. Is there any package on Python or R? I looked at a package called textpack but the results aren't good.

found here: https://pypi.org/project/textpack/

I'd really appreciate if someone could suggest a tool or a package so I can go ahead and research.

$\endgroup$
  • $\begingroup$ See stackoverflow.com/q/13636848/745868 $\endgroup$ – Guillermo Mosse Jun 5 '20 at 9:43
  • $\begingroup$ Isn't that fuzzy matching? I'm trying to get fuzzy grouping done since I don't have a reference column $\endgroup$ – minion_1 Jun 5 '20 at 12:26
  • $\begingroup$ I expanded my comment into an answer $\endgroup$ – Guillermo Mosse Jun 5 '20 at 14:27
1
$\begingroup$

Probably there are more direct solutions, but you can try using some sort of fuzzy matching to get the most similar words to each word. That returns you an unweighted graph where the nodes are words and the edge indicates whether the world is similar. then, you can try clustering the resulting graph, for example with the Louvain's algorithm. Than would return non overlapping groups of related words.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.