GitHub - PhilippeMarcotte/languageDetector: Machine learning software that learn to distinguish languages.

PhilippeMarcotte / languageDetector Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

Machine learning software that learn to distinguish languages.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
data		data
.gitignore		.gitignore
README.txt		README.txt
machine.py		machine.py
machine.pyc		machine.pyc
wikipediaScraper.py		wikipediaScraper.py

Repository files navigation

Machine learning software that learns to distinguish written languages.

wikipediaScraper.py:
args : -h, -l --languages, -n --numberOfArticles
The purpose of this script is to collect a certain numer of random articles of each languages from Wikipedia. It requires the library Wikipedia to be installed.

https://github.com/goldsmith/Wikipedia

machine.py:
This is the main script. Simply execute it to see the results of the learning process.
The script requires numpy, scipy, sklearn and matplotlib.