def test_standardization_axis1(self): rdd = self.sc.parallelize([(0, array([1, 2], dtype='float16')), (0, array([3, 4], dtype='float16'))]) data = Series(rdd, dtype='float16') centered = data.center(1) standardized = data.standardize(1) zscored = data.zscore(1) assert(allclose(centered.first()[1], array([-1, -1]), atol=1e-3)) assert(allclose(standardized.first()[1], array([1, 2]), atol=1e-3)) assert(allclose(zscored.first()[1], array([-1, -1]), atol=1e-3))
def test_standardization_axis0(self): rdd = self.sc.parallelize([(0, array([1, 2, 3, 4, 5], dtype='float16'))]) data = Series(rdd, dtype='float16') centered = data.center(0) standardized = data.standardize(0) zscored = data.zscore(0) assert(allclose(centered.first()[1], array([-2, -1, 0, 1, 2]), atol=1e-3)) assert(allclose(standardized.first()[1], array([0.70710, 1.41421, 2.12132, 2.82842, 3.53553]), atol=1e-3)) assert(allclose(zscored.first()[1], array([-1.41421, -0.70710, 0, 0.70710, 1.41421]), atol=1e-3))