gistfile1.py

from random import sample

def split_data_random(data, ratio=0.8):
    '''
    Split data into two lists. With ratio=0.8, the first list
    will be 80% of the size of the original data, and the 
    second will be 20%. The items in each list will be
    randomly assigned. Ideally "data" is a list.
    '''
    n = len(data)
    train_indices = sample(xrange(n), int(n*ratio))
    test_indices  = list(set(xrange(n)) - set(train_indices))
    
    training_data = [data[i] for i in train_indices]
    testing_data  = [data[i] for i in test_indices]

    return (training_data, testing_data)

#Example usage: simply split some data in half randomly:
data1,data2 = split_data_random(data,ratio=0.5)