Skip to content

Twitter visualizaton experiment using various python-based technologies.

Notifications You must be signed in to change notification settings

jdwittenauer/twitter-viz-demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Twitter Visualization Demo

twitter-viz-demo

This project leverages a variety of technologies to visualize a real-time stream of twitter data using sentiment analysis and word vector space mapping via word2vec. It runs on a local Flask instance with a Redis/Celery back-end and uses Socket-IO to push events to the web client. Twitter integration is managed by the pattern library. NVD3 is used on the front-end to create the visualization.

Quick Setup Instructions

  • Clone this repository
  • Install dependencies (Flask, Flask-SocketIO, Redis, Celery, Pattern, Numpy, Pandas, Scikit-learn, Gensim)
  • Download twitter sentiment dataset here
  • Unzip the .csv file and save a copy in the 'scripts' folder
  • Run 'build_models.py' from the 'scripts' folder (can take a while on a slower machine)
  • Open a terminal window and start a local Redis server ('bash redis.sh')
  • Open another terminal window and start a Celery worker ('celery worker -A app.celery --loglevel=info')
  • Open a third terminal window and start the Flask application ('python app.py')
  • Browse to the app at 'http://127.0.0.1:5000/'

About

Twitter visualizaton experiment using various python-based technologies.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published