예제 #1
0
    def test_groupByFixedLength(self):
        rdd = self.sc.parallelize([((0,), array([0, 1, 2, 3, 4, 5, 6, 7], dtype='float16'))])
        data = Series(rdd)

        test1 = data.groupByFixedLength(4)
        assert(test1.keys().collect() == [(0, 0), (0, 1)])
        assert(allclose(test1.index, array([0, 1, 2, 3])))
        assert(allclose(test1.values().collect(), [[0, 1, 2, 3], [4, 5, 6, 7]]))

        test2 = data.groupByFixedLength(2)
        assert(test2.keys().collect() == [(0, 0), (0, 1), (0, 2), (0, 3)])
        assert(allclose(test2.index, array([0, 1])))
        assert(allclose(test2.values().collect(), [[0, 1], [2, 3], [4, 5], [6, 7]]))