saffsd

langid.py. Stand-alone language identification system

wikidump. Tools to manipulate and extract data from wikipedia dumps

kaggle-stackoverflow2012. My entry to the Kaggle 2012 Stack Overflow competition. Ranked 10th on the final public leaderboard.

polyglot. Polyglot is a language identifier for detecting text documents containing text written in more than one language, and for identifying the languages therein.

langid.c. Pure C natural language identifier with support for 97 languages

geniatagger. - part-of-speech tagging, shallow parsing, and named entity recognition for biomedical text -

langid.js. An off-the-shelf client-side language identification module for JavaScript.

kaggle-stumbleupon2013. My entry to the Kaggle 2013 StumbleUpon competition. Ranked 4th on the final private leaderboard.

imgevolve. Evolve images from sets of triangles.

updatedir. Rsync-like directory updating over multiple protocols

daifugo. Simulation system for the japanese card game Daifugo.

linguini.py. linguini.py is a pure-Python implementation of linguini, a vector-space model language identifier with support for bilingual and trilingual documents.

forum_features. Data model for manipulating forum data.

assignmentprint. Pretty printer for student-submitted assignments. Helps with prettyprinting student code and generating reports.

language_data. Pythonic interface to natural language metadata