How to calculate mean values over columns in a given data structure?

Question

I have the following data structure ds:

{(\'AD\', \'TYPE_B\', \'TYPE_D\'): [array([84.0, 85.0, 115.0], dtype=object), array([31.0, 23.0, 599.0], dty         


        

Answer 1

use the built-in functions from numpy.

import numpy as np

ds = {('AD', 'TYPE_B', 'TYPE_D'): [np.array([84.0, 85.0, 115.0], dtype=object), 
                                   np.array([31.0, 23.0, 599.0], dtype=object), 
                                   np.array([75.0, 21.0, np.nan], dtype=object), 
                                   np.array([59.0, 52.0, 29.0], dtype=object)],
      ('AD', 'TYPE_A', 'TYPE_N'): [np.array([84.0, 85.0, 115.0], dtype=object), 
                                   np.array([31.0, 23.0, 599.0], dtype=object), 
                                   np.array([75.0, 21.0, 300.0], dtype=object), 
                                   np.array([59.0, 52.0, 29.0], dtype=object)]}

for key in ds.keys():
    #first cast to float and replace nan
    item    = np.nan_to_num(np.asarray(ds[key], dtype=np.float64));
    #calculate the mean
    mean    = np.mean(item, axis=0)
    #store it in the dictionary
    ds[key] = mean

print ds