Big Data with HierarchicalRegression

Questions
4

I managed to get around it by using Minibatch.update_shared_f:

def choice_iterator(size, nrows, seed):
    state = np.random.RandomState()
    state.seed(seed)

    while True:
        yield sorted(np.random.randint(0, nrows+1, size=size))

def update_shared_f_in_memory(obj, size, seed):

    nrows     = len(obj) if isinstance(obj, np.ndarray) else len(obj.index)
    generator = choice_iterator(size=size, nrows=nrows, seed=seed)

    def f():
        where = next(generator)
        return obj[where] if isinstance(obj, np.ndarray) else obj.iloc[where]

    return f
2 Likes