rdd + map快速解决方案

def split(r):
    A, B = [], []
    a, b = [], []

    for x, y in zip(*r):
        if x != 7:
            a.append(x)
            b.append(y)
        else:
            A.append([*a, x])
            B.append([*b, y])

            a, b = [], [] # reset
    return [*r, A, B]

result = df.rdd.map(split).toDF(['ids', 'names', 'ids_splited', 'names_splited'])

结果

+---------------------------------------+---------------------------------------+-------------------------------------------+-------------------------------------------+
|ids                                    |names                                  |ids_splited                                |names_splited                              |
+---------------------------------------+---------------------------------------+-------------------------------------------+-------------------------------------------+
|[1, 1, 2, 3, 1, 2, 3, 7, 5]            |[a, b, c, l, s, o, c, d, e]            |[[1, 1, 2, 3, 1, 2, 3, 7]]                 |[[a, b, c, l, s, o, c, d]]                 |
|[3, 8, 9, 3, 9, 0, 0, 6, 7, 8]         |[s, l, h, p, q, g, c, d, p, s]         |[[3, 8, 9, 3, 9, 0, 0, 6, 7]]              |[[s, l, h, p, q, g, c, d, p]]              |
|[9, 6, 5, 4, 7, 6, 5, 9, 2, 5, 5, 4, 7]|[q, a, z, w, s, e, r, t, y, o, p, a, x]|[[9, 6, 5, 4, 7], [6, 5, 9, 2, 5, 5, 4, 7]]|[[q, a, z, w, s], [e, r, t, y, o, p, a, x]]|
+---------------------------------------+---------------------------------------+-------------------------------------------+-------------------------------------------+