Project: Enhancing Apriori algorithm to identify frequent itemsets in transaction databases. We explore augmenting it with new strategies. Idea 1: When encountering frequent k-itemsets, we derive (k+1)-item candidates, reducing database scans for improved efficiency.
Authors: Chase Mossing Daniil Pleskach O'Brien Little Robbert Hendricks
Reference Apriori package used: https://pypi.org/project/apriori-python/
Uncomment lines in idea1.py once the package has been installed to view testing behaviours of our implementation vs. a standard package.
How to use:
"To compile cpp files: make" "To generate databases: ./GenDatabase" "To run apriori standard: ./apriori {Database w/o extension} {min_supp}" "To run idea1: ./idea1.py {Database w/o extension} {minn_supp}"
Project: Enhancing Apriori algorithm to identify frequent itemsets in transaction databases. We explore augmenting it with new strategies. Idea 1: When encountering frequent k-itemsets, we derive (k+1)-item candidates, reducing database scans for improved efficiency.