oliviaguest / gini Goto Github PK

    if np.amin(array) < 0:
        # Values cannot be negative:
        array -= np.amin(array)

from time import time

import numpy as np
from numba import jit

import matplotlib.pyplot as plt

def gini_normal(array):
    """Calculate the Gini coefficient of a numpy array."""
    # based on bottom eq: http://www.statsdirect.com/help/content/image/stat0206_wmf.gif
    # from: http://www.statsdirect.com/help/default.htm#nonparametric_methods/gini.htm
    array = array.flatten() #all values are treated equally, arrays must be 1d
    if np.amin(array) < 0:
        array -= np.amin(array) #values cannot be negative
    array += 0.0000001 #values cannot be 0
    array = np.sort(array) #values must be sorted
    index = np.arange(1,array.shape[0]+1) #index per array element
    n = array.shape[0]#number of array elements
    return ((np.sum((2 * index - n  - 1) * array)) / (n * np.sum(array)))

@jit(nopython=True)
def gini_numba(array):
    """Calculate the Gini coefficient of a numpy array."""
    # based on bottom eq: http://www.statsdirect.com/help/content/image/stat0206_wmf.gif
    # from: http://www.statsdirect.com/help/default.htm#nonparametric_methods/gini.htm
    array = array.flatten() #all values are treated equally, arrays must be 1d
    if np.amin(array) < 0:
        array -= np.amin(array) #values cannot be negative
    array += 0.0000001 #values cannot be 0
    array = np.sort(array) #values must be sorted
    index = np.arange(1,array.shape[0]+1) #index per array element
    n = array.shape[0]#number of array elements
    return ((np.sum((2 * index - n  - 1) * array)) / (n * np.sum(array)))

def profiler(func):
    """Quick and dirty utility func for timing perfromance"""
    timing = []
    for max_iter in (1e1, 1e2, 1e3, 1e4, 1e5, 1e6):
        
        start = time()
        for iteration in range(int(max_iter)):

            func(np.random.random(size=(10)))
        
        timing.append(time() - start)
    
    return timing

###################################################

time_normal = profiler(gini_normal)
time_numba = profiler(gini_numba)

plt.figure(figsize=(5, 5))
plt.plot(
    [1e1, 1e2, 1e3, 1e4, 1e5, 1e6],
    time_normal, 
    label='Raw Numpy'
)
plt.plot(
    [1e1, 1e2, 1e3, 1e4, 1e5, 1e6],
    time_numba, 
    label='Numba + Numpy'
)

plt.ylabel('Seconds')
plt.xlabel('Number of Iterations')

plt.legend()
plt.show()