IgnitionHacks2020

This code uses the data in the contestant_judgment.csv file, cleans it (removing all punctuation, URLs, and making everything lowercase), then uses the nltk sentiment library to figure out how positive, negative, and neutral a sentence is (in percents) and compares these values to figure out if the phrase is overall more positive or negative. It then stores it in the results.csv file.
IMPORTANT: We were unable to figure out how to add the training_data.csv and contestant_judgment.csv to this repository as the files were too large, even when compressed. If you have those downloaded separately, this should still work.
Members: Selena Zhang, Michelle Saltoun

Built With

• python