def perf_comp_data(func_list, data_list, rep=3, number=1): 
  '''Function to compare the performance of different functions. 
  Parameters 
  func_list : list 
  list with function names as strings

  data_list : list 
  list with data set names as strings 

  rep : int 
  number of repetitions of the whole comparison 
  number : int 
  number ofexecutions for every function 
  '''
  from timeit import repeat 
  res_list = {} 
  for name in enumerate(func_list): 
    stmt = name[1] + '(' + data_list[name[0]] + ')' 
    setup = "from __main__ import " + name[1] + ','+ data_list[name[0]] 
    results = repeat(stmt=stmt, setup=setup, repeat=rep, number=number) 
    res_list[name[1]] = sum(results) / rep
  res_sort = sorted(res_list.items(), key = lambda item : item[1])
  for item in res_sort: 
    rel = item[1] / res_sort[0][1]
    print ('function: ' + item[0] + ', av. time sec: %9.5f,  ' % item[1] + 'relative: %6.1f' % rel)

from math import * 
def f(x): 
  return abs(cos(x)) ** 0.5 + sin(2 + 3 * x)

i=500000
a_py = range(i)

def f1(a): 
  res = [] 
  for x in a: 
    res.append(f(x)) 
  return res

def f2(a): 
  return [f(x) for x in a]

def f3(a): 
  ex = 'abs(cos(x)) **0.5+ sin(2 + 3 * x)' 
  return [eval(ex) for x in a] 

def f7(a): 
  return (f(x) for x in a)

def f8(a): 
  return map(f, a)

import numpy as np 
a_np = np.arange(i) 

def f4(a): 
  return (np.abs(np.cos(a)) ** 0.5 + np.sin(2 + 3 * a))

import numexpr as ne

def f5(a): 
  ex = 'abs(cos(a)) ** 0.5 + sin( 2 + 3 * a)' 
  ne.set_num_threads(1) 
  return ne.evaluate(ex)

def f6(a): 
  ex = 'abs(cos(a)) ** 0.5 + sin(2 + 3 * a)' 
  ne.set_num_threads(2) 
  return ne.evaluate(ex)

func_list = ['f1', 'f2', 'f3', 'f4', 'f5', 'f6', 'f7', 'f8'] 
data_list = ['a_py', 'a_py', 'a_py', 'a_np', 'a_np', 'a_np', 'a_py', 'a_py']
perf_comp_data(func_list, data_list)

function: f8, av. time sec:  0.00000,  relative:  1.0
function: f7, av. time sec:  0.00001,  relative:  1.7
function: f6, av. time sec:  0.03787,  relative: 11982.7
function: f5, av. time sec:  0.05838,  relative: 18472.4
function: f4, av. time sec:  0.09711,  relative: 30726.8
function: f2, av. time sec:  0.82343,  relative: 260537.0
function: f1, av. time sec:  0.92557,  relative: 292855.2
function: f3, av. time sec: 32.80889,  relative: 10380938.6

function: f8, av. time sec: 0.000002483,  relative:  1.0
function: f7, av. time sec: 0.000004741,  relative:  1.9
function: f5, av. time sec: 0.028068110,  relative: 11303.0
function: f6, av. time sec: 0.031389788,  relative: 12640.6
function: f4, av. time sec: 0.053619114,  relative: 21592.4
function: f1, av. time sec: 0.852619225,  relative: 343348.7
function: f2, av. time sec: 1.009691877,  relative: 406601.7
function: f3, av. time sec: 26.035869787,  relative: 10484613.6

x = np.random.standard_normal(( 3, 1500000))
c = np.array(x, order='C') 
f = np.array(x, order='F') 

%timeit c.sum(axis=0)
%timeit c.std(axis=0)
%timeit f.sum(axis=0)
%timeit f.std(axis=0)
%timeit c.sum(axis=1)
%timeit c.std(axis=1)
%timeit f.sum(axis=1)
%timeit f.std(axis=1)

loops, best of 3: 12.1 ms per loop
loops, best of 3: 83.3 ms per loop
loops, best of 3: 70.2 ms per loop
loop, best of 3: 235 ms per loop
loops, best of 3: 7.11 ms per loop
loops, best of 3: 37.2 ms per loop
loops, best of 3: 54.7 ms per loop
loops, best of 3: 193 ms per loop