The repo contains:
- the .py script of the single solution
- the .pdf report
- two .csv files (developmentImproved.csv and evaluationImproved.csv) (The improved dataset after a semi-manual preprocessing as described in the report)
Remark: the program uses a .txt file that is not present in this .zip , but can be generated calling the printStopwordsFile() and passing its relative path to the getStopwordslist() method