In [157]:

    

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import statistics
%matplotlib inline


    

In [158]:

    

df=pd.DataFrame()


    

In [159]:

    

df['age']=[28, 42, 27, 24, 35, 54, 35, 37]


    

In [160]:

    

sum(df['age'])/len(df['age'])


    

    
Out[160]:





35.25

In [161]:

    

np.mean(df['age'])


    

    
Out[161]:





35.25

In [162]:

    

statistics.median(df['age'])


    

    
Out[162]:





35.0

In [163]:

    

np.median(df['age'])


    

    
Out[163]:





35.0

In [164]:

    

statistics.mode(df['age'])


    

    
Out[164]:





35

In [165]:

    

(values, counts) = np.unique(df['age'], return_counts=True)


    

In [166]:

    

ind = np.argmax(counts)
print(ind)
values[ind]


    

    




3






    
Out[166]:





35

In [167]:

    

a=np.var(df['age'])


    

In [168]:

    

np.std(df['age'])


    

    
Out[168]:





8.9965271077232902

In [169]:

    

np.std(df['age'],ddof=1)


    

    
Out[169]:





9.6176920308356717

In [170]:

    

v = a**0.5
print(v)


    

    




8.99652710772

In [171]:

    

np.std(df['age'])/np.sqrt(len(df['age']))


    

    
Out[171]:





3.1807526624998679

In [172]:

    

pop=pd.DataFrame()
pop['low_var']=np.random.normal(60,10,1000)
pop['high_var']=np.random.normal(60,100,1000)


    

In [173]:

    

pop.hist(layout=(2, 1), sharex=True)
plt.show()


    

In [174]:

    

print(pop.max())
print(pop.min())


    

    




low_var      86.598866
high_var    369.461379
dtype: float64
low_var      23.371762
high_var   -247.338647
dtype: float64

In [175]:

    

sample=pd.DataFrame()
sample['low_var'] = np.random.choice(pop['low_var'], 1000)
sample['high_var']=np.random.choice(pop['high_var'], 1000)


    

In [176]:

    

sample.hist()
plt.show()


    

In [177]:

    

sample.mean()
sample.std(ddof=1)


    

    
Out[177]:





low_var       9.698314
high_var    103.008697
dtype: float64

In [ ]:

    




    

In [ ]:

    




    

In [ ]: