- Basic Exploration of the data
- Extract reviewtext method: takes as input a DataFrame Column, and tokenizes(calls tokenize method) each reviewText. Returns a list of lists of tokens.
- Tokenize method: Takes as input a string(the reviewText for instance) and returns a list of tokens(tokenized according to the method's options).
- Extract sentiment column: takes a DataFrame column and returns a list of strings, each string is the sentiment.
- Split methods(K-Fold) or train_test_split
- Base Line Model
philipwins / secondyearproject2021 Goto Github PK
View Code? Open in Web Editor NEWThis project forked from johanlundberg12/secondyearproject2021