nlp-tt-read-prepare-df.py

#import
df = pd.read_csv('data/reviews.csv')

#drop useless data
df = df.drop(['Id', 'ProductId', 'UserId', 'ProfileName', 'HelpfulnessNumerator',
       'HelpfulnessDenominator', 'Time', 'Summary',], axis=1)

#remove ambiguous 3 and 4 stars for balancing
df = df[df['Score'] != 3]

#create labels and preprocess
df['Score'] = df['Score'].apply(lambda i: 'positive' if i > 4 else 'negative')
df['Text'] = df['Text'].apply(lambda x:x.lower())

#set names for beautiful df
df.columns = ['labels', 'text']