nlp-tt-balance.py

idx_positive = df[df['labels']=='positive'].index
nbr_to_drop = len(df) - len(idx_positive)

drop_indices = np.random.choice(idx_positive, nbr_to_drop, replace=False)
df = df.drop(drop_indices)

#transform all of it to lists
text_as_list = df['text'].tolist()
labels_as_list = df['labels'].tolist()