This is a pre-production deployment of Warehouse, however changes made here WILL affect the production instance of PyPI.
Latest Version Dependencies status unknown Test status unknown Test coverage unknown
Project Description

Research project on twitter sentiment analysis using the Naïve Bayes


Install from PyPI (soon) or github with::

pip install -e git+


First, start the twentiment server that loads the data from a JSON file. A
sample is available `in the repository <https:"" passy="" twentiment="" blob="" 623f4064469850b40b50db4707f12a07047f022b="" samples="" few_tweets.json="">`_.


twentiment_server samples/few_tweets.json

After that, you can use ``twentiment_client`` to query the server using the
syntax ``GUESS my tweet to be scored``.



twentiment> GUESS hello world
OK 0.0
twentiment> GUESS This car is amazing.
OK 0.5
twentiment> GUESS My best friend is great.
OK 0.9285714285714286
twentiment> GUESS Whatever.
OK 0.0
twentiment> GUESS This car is horrible.
OK -0.5
twentiment> GUESS I am not looking forward to my appointment tomorrow.
OK -0.9852941176470597


(Ranked by importance)

* Have a web-frontend that searches for tweets and rates their sentiment.
* Give the server an option to fork the server process into the background
and launch a shell like twentiment_client right away.
* Restructure the Classifier to allow adaptive retraining, i.e. provide a
TRAIN command that adds new samples at runtime.
* At the moment, most of the calculations are done at start-up time, so
querying is rather cheap. Could be difficult to find a good balance.

* Persistence of the server state. Maybe through redis? Only important with
TRAIN functionality.
* Add some sort of parallelism to the server, so querying doesn't block.
* Add a way of importing live training data from twitter (like from
analysing emoticons)


This is a project report for the Business Intelligence course. To increase the
learning potential, I tried to reuse as little as possible from the excellent
`NLTK <http:""/>`_ project and reimplemented the relevant parts myself.
Release History

Release History


This version

History Node

TODO: Figure out how to actually get changelog content.

Changelog content for this version goes here.

Donec et mollis dolor. Praesent et diam eget libero egestas mattis sit amet vitae augue. Nam tincidunt congue enim, ut porta lorem lacinia consectetur. Donec ut libero sed arcu vehicula ultricies a non tortor. Lorem ipsum dolor sit amet, consectetur adipiscing elit.

Show More

Download Files

Download Files

TODO: Brief introduction on what you do with files - including link to relevant help section.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
twentiment-0.1.0.tar.gz (28.2 kB) Copy SHA256 Checksum SHA256 Source Oct 9, 2012

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS HPE HPE Development Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting