Testing out an recommender algorithm on real Foursquare data
foursquare.py
rest.csv
fstest.py
dictionary.txt
results.txt
analysis.py
regress.csv
script.sh
final.txt
rest.csv has the initial dataset, which is formated as follows:
Column 1 is a list of user ID's, and Column 2 is the retaurant ID of the restaurant that the user checked into.
foursquare.py takes this data and generates a table of recommendations based on an item-based collaborative filtering algorithm. The rest of the files are used to test the performance of this algorithm.