shuffle_split.py

def shuffle_split(documents, labels, split):
    """Shuffle data to ensure random class distribution in train/test split."""
    tuples = [[doc, label] for doc, label in zip(documents, labels)]
    random.shuffle(tuples)
    X, Y = zip(*tuples)

    split_point = int(split*len(X))

    Xtrain = X[:split_point]
    Ytrain = Y[:split_point]
    Xtest = X[split_point:]
    Ytest = Y[split_point:]

    return Xtrain, Xtest, Ytrain, Ytest