https://github.com/mdbecker/word2vec_demo

word2vec demo for #hourofcode using gensim
https://github.com/mdbecker/word2vec_demo

Last synced: about 2 months ago
JSON representation

word2vec demo for #hourofcode using gensim

• Host: GitHub
• URL: https://github.com/mdbecker/word2vec_demo
• Owner: mdbecker
• License: mit
• Created: 2014-12-10T01:34:04.000Z (about 10 years ago)
• Default Branch: master
• Last Pushed: 2015-01-17T20:55:56.000Z (almost 10 years ago)
• Last Synced: 2023-08-01T05:28:06.592Z (over 1 year ago)
• Language: JavaScript
• Homepage:
• Size: 696 KB
• Stars: 22
• Watchers: 4
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Setup

1. Download GoogleNews-vectors-negative300.bin.gz from [https://code.google.com/p/word2vec/](https://code.google.com/p/word2vec/#Pre-trained_word_and_phrase_vectors)

2. ``conda create -n word2vec_demo python=2.7 ipython-notebook matplotlib pandas pip seaborn gensim; source ~/anaconda/bin/activate word2vec_demo; pip install flask-restful``

3. ``python word2vec_convert.py`` (takes 3+ minutes on my MacBook).

4. ``python word2vec_api.py`` (takes 30 seconds on my MacBook).

5. ``open -a Google\ Chrome --args --disable-web-security index.html`` (You might need to close Chrome if it's already open).

## Example

![https://raw.githubusercontent.com/mdbecker/word2vec_demo/master/example.png](https://raw.githubusercontent.com/mdbecker/word2vec_demo/master/example.png)