gistfile1.py

from random import sample
from sussex_nltk.corpus_readers import AmazonReviewCorpusReader

 
def split_data(data, ratio=0.7):
    data = list(data)
 
    n = len(data)  #Found out number of samples present
    train_indices = sample(xrange(n), int(n * ratio))          #Randomly select training indices
    test_indices = list(set(xrange(n)) - set(train_indices))   #Randomly select testing indices
 
    training_data = [data[i] for i in train_indices]           #Use training indices to select data
    testing_data = [data[i] for i in test_indices]             #Use testing indices to select data
 
    return (training_data, testing_data)                       #Return split data
 
#Create an Amazon corpus reader pointing at only book reviews
book_reader = AmazonReviewCorpusReader().category("book")

#In order to get even random splits, where each data set is a list of Amazon Review objects.
pos_training_data, pos_testing_data = split_data(book_reader.positive().documents()) #See the note below this code snippet 
neg_training_data, neg_testing_data = split_data(book_reader.negative().documents())

#You can also combine the training data
training_data = pos_training_data + neg_training_data
testing_data = pos_testing_data + neg_testing_data