ehtsham / DeliciousRecommendationEngine

In Python and MySQL, A User-based Collaborative filtering algorithm for recommending links from Delicious

Home Page:http://ehtshamml.blogspot.com/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

A User-based Collaborative Filtering Algorithm for Delicious Link Recommendation Engine

Technology: pydelicious, Python, MySQL
distance metric: Pearson Correlation Coefficient

Step-1: Using the pydelicious.py API, I build a MySQL database of users and their posts
and a rating, 1 or 0, based on whether they have posted the url or not

Step-2: Just for the fun of it, I implemented a user-based Collaborative filtering method
details (from sarwat et. al) 

The output of the algorithm is a list of recommended links for an input user of choice
A sample output is: the link and the relative ranking indicating the user preference
http://tele-task.de/archive/video/flash/14029/ 0.910118709912
http://gent.ilcore.com/2011/08/finding-memory-leaks.html 0.549350785728
http://ssssnakes.com/smoke/ 0.519390355699
https://github.com/lojjic/PIE 0.48942992567
https://github.com/laughinghan/choreographer 0.48942992567
https://github.com/coolaj86/futures 0.48942992567
https://github.com/cool-shark/redimon 0.48942992567
https://github.com/aikar/wormhole 0.48942992567
http://www.ipdusa.com/prodtype.asp?numRecordPosition=403 0.48942992567
http://sound.westhost.com/project100.htm 0.48942992567

About

In Python and MySQL, A User-based Collaborative filtering algorithm for recommending links from Delicious

http://ehtshamml.blogspot.com/