https://github.com/sandinmyjoints/visularity
Realtime semantic similarity visualization with gensim, d3.js, and hookbox
https://github.com/sandinmyjoints/visularity
Last synced: 3 months ago
JSON representation
Realtime semantic similarity visualization with gensim, d3.js, and hookbox
- Host: GitHub
- URL: https://github.com/sandinmyjoints/visularity
- Owner: sandinmyjoints
- Created: 2012-04-24T01:45:56.000Z (about 13 years ago)
- Default Branch: master
- Last Pushed: 2014-03-05T02:43:27.000Z (over 11 years ago)
- Last Synced: 2024-10-07T09:08:13.513Z (8 months ago)
- Language: JavaScript
- Homepage:
- Size: 359 KB
- Stars: 40
- Watchers: 7
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
Visularity
==========
This was created as a proof of concept for a talk I gave, called [An Introduction to Gensim: Topic Modelling for Humans](http://williamjohnbert.com/2012/05/an-introduction-to-gensim-topic-modelling-for-humans/).
It is fairly experimental and rough. Feel free to fork and improve.
Similarity cluster visualization
--------------------------------
Visularity does not come with any of the data needed to do similarity comparison (e.g., transformation models and
dictionaries). This data is generally application-specific and also large (think hundreds of megabytes).
Visit http://radimrehurek.com/gensim to learn how to generate data. It's not that hard.
Requires:
* gensim>=0.8
* scipy>=0.10.1
* hookbox>=0.3.4dev (not on Pypi, try https://github.com/hookbox/hookbox)
* Flask>=0.8
* scikit-learn>=0.10
* requests>=0.11.1
* gensim models and a dictionary -- see http://radimrehurek.com/gensim for how to generate these.