Data Spread¶

Mean
Stardard Deviation
Variance

---------------------------------------------¶

In [1]:

from __future__ import division

import numpy as np
import math
import pandas as pd

print np.__version__
print pd.__version__

1.14.2
0.20.3

Python Way¶

In [2]:

def mean(x):
    return sum(x) / len(x)

In [3]:

def variance(x):
    return (standard_deviation(x))**2

In [4]:

def standard_deviation(lst):
    m = mean(lst)
    return math.sqrt(float(reduce(lambda x, y: x + y, map(lambda x: (x - m) ** 2, lst))) / len(lst))

In [5]:

X = [1, 2, 3, 4, 5]
print 'Mean: {}'.format(mean(X))
print 'Variance: {}'.format(variance(X))
print 'Standard Deviation: {}'.format(standard_deviation(X))

Mean: 3.0
Variance: 2.0
Standard Deviation: 1.41421356237

Numpy Way¶

In [6]:

def mean(x):
    return np.mean(x)

In [7]:

def variance(x):
    return np.var(x)

In [8]:

def standard_deviation(x):
    return np.std(x)

In [9]:

X = [1, 2, 3, 4, 5]
print 'Mean: {}'.format(mean(X))
print 'Variance: {}'.format(variance(X))
print 'Standard Deviation: {}'.format(standard_deviation(X))

Mean: 3.0
Variance: 2.0
Standard Deviation: 1.41421356237