gistfile1.txt

def split_train_test(tweet_vectors, randomized_tweet_vectors) -> tuple:
    """
    Split into train and test sets

    :param tweet_vectors: tweets in vector form

    :return: train_set, test_set tuple of train set and test set
    """
    x_train_dim = math.floor(0.8 * tweet_vectors.shape[0])  # Use 80% of data for train set
    x_test_dim = math.ceil(0.2 * tweet_vectors.shape[0])  # Use 20% of data for test set
    y_dim = tweet_vectors.shape[1]

    train_set = np.zeros((x_train_dim, y_dim), dtype=int)
    test_set = np.zeros((x_test_dim, y_dim), dtype=int)

    for x in range(x_train_dim):
        for y in range(y_dim):
            train_set[x][y] = randomized_tweet_vectors[x][y]
    for x in range(x_test_dim):
        for y in range(y_dim):
            test_set[x][y] = randomized_tweet_vectors[x + x_train_dim][y]

    return train_set, test_set