python - 有没有办法理解零簇，然后将其从 numpy 数组中删除？

Question

我想从 numpy 数组中间删除零(但不应删除所有零)

stackoverflow 上的多个示例演示了删除零，但我仍然发现很难为我的问题编写逻辑。

import numpy as np

a = np.array([255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,207,0,0
,159,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,64,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
,0,0,0,0,0,0,0,0,0,88,239,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,231,88])

我有一个数组 a，其中有一些非零值和一大群零(以及非零值中间的一些零)。我想删除那个大的零簇或找到该大的簇开始的索引。然后将数组缩减为以下形式:

a1 = [255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,207,0,0
,159,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255
,255,64]

和

a2=[88,239,255,255,255,255,255,255,255
,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,231,88]

请注意，数组 a1 中仍然有一些零。仅当其中存在一定数量的连续零(例如 10 个零)时，该操作才应删除零。我可以通过循环遍历数组来完成此操作，但如果可以建议一种更简单、更快的方法，那就太好了。

Answer 1

没有任何导入，使用单个循环:

def remove_clusters(my_array, cluster_value, consecutive_max=10):
    my_result = [[]]
    cluster_list = []
    for e in my_array:
        if e == cluster_value:
            cluster_list.append(e)
        else:
            if len(cluster_list) <= consecutive_max:
                my_result[-1].extend(cluster_list)
            else:
                my_result.append([])
            cluster_list = []
            my_result[-1].append(e)
    return my_result

我使用itertools.groupby得到了这个，它简化了一些代码:

def remove_clusters(my_array, cluster_value=0, max_consecutive=10):
    from itertools import groupby
    my_result = [[]]
    for k,g in groupby(my_array):
        g = list(g)
        if k != cluster_value or len(g) <= max_consecutive:
            my_result[-1].extend(g)
        else:
            my_result.append([])
    return my_result

然后你可以这样做:

a1, a2 = remove_clusters(a)

最后，一个使用functools.reduce的非常丑陋的oneliner

from itertools import groupby
from functools import reduce
a1, a2 = reduce(lambda x,y: x + [[]] if not y[0] and len(y)>10 
                       else x[:-1] + [x[-1]+y], 
                map(lambda x: list(x[1]), groupby(a)), 
                [[]])

我很想解释一下这条直线，但我已经不明白了。