mm3.py

while 1:
    ...
    df = df.sample(frac=1)  # shuffle all rows
    ...
    i, j = 0, batch_size
    for _ in range(nbatches):
        sub = df.iloc[i:j]
        idx = sub.index.values
        X2 = bcolz.open(bcolz_dir)[idx]
        ...
        # Calculate X and Y appropriately
        ...
        yield [X, X2], Y
        i = j
        j += batch_size
        ...