gistfile1.py

from random import sample

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

def format_data(reviews, label, feature_extraction_fn=None):
    if feature_extraction_fn is None: #If a feature extraction function is not provided, use simply the words of the review as features
        data = [(dict([(feature, True) for feature in review.words()]), label) for review in reviews]
    else:
        data = [(dict([(feature, True) for feature in feature_extraction_fn(review)]), label) for review in reviews]
    return data