https://github.com/karan/What-Would-I-Tweet

Automatically generates tweets for you! It trains a Markov bot based on bigram probabilities derived from your tweet history.
https://github.com/karan/What-Would-I-Tweet

Last synced: about 1 hour ago
JSON representation

Automatically generates tweets for you! It trains a Markov bot based on bigram probabilities derived from your tweet history.

• Host: GitHub
• URL: https://github.com/karan/What-Would-I-Tweet
• Owner: karan
• License: mit
• Created: 2013-11-14T21:08:06.000Z (almost 11 years ago)
• Default Branch: master
• Last Pushed: 2016-03-09T05:22:35.000Z (over 8 years ago)
• Last Synced: 2024-06-20T02:19:45.300Z (5 months ago)
• Language: CSS
• Homepage: http://tweeny.goel.io/
• Size: 1.62 MB
• Stars: 14
• Watchers: 3
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
What would I tweet

==================

**What would I tweet** automatically generates tweets for you! It trains a Markov bot based on bigram probabilities derived from your tweet history.

The app is built using:

- Python (Flask) in the backend. It provides a RESTful interface for generating tweets for a username. See the [end-point](https://github.com/karan/What-Would-I-Tweet/blob/master/gen.py#L69).

- AngularJS provides the client side manipulations and real-time interaction.

Usage

======

Get your `app_key` and `app_secret` from [Twitter Dev Center](https://dev.twitter.com/apps/new).

Create environment variables.

    $ export APP_KEY=xxxxxxxxxxxxxx

    $ export APP_SECRET=xxxxxxxxxxxxxxxxxxxxxxxxxxxx

Run the script:

    $ python gen.py

Or if you have heroku toolkit:

    

    $ foreman start

Open `localhost:5000` in your browser.