In [18]:

    

import pandas as pd
df = pd.read_csv('./FGCU_salary_dataset.csv')
df_m = df
d = df_m['Annual Salary'].apply(lambda x: x.lstrip('$'))
d = d.astype('float64')
df.head()


    

    
Out[18]:






  

    

      

      
Last Name
      
First Name
      
Annual Salary
      
FGCU Hire Date
      
College/Dept
      
Class Title
      
Working Title
      
Employee Class
    
  
  

    

      
0
      
Gray-Vickrey
      
Margaret
      
$127972.27
      
07/01/1996
      
Academic Affairs Administration
      
Assoc. Vice President/Prof.
      
Assc. Provost/Assoc. VP C&I
      
Faculty Admin 10, 11, 12 mo
    
    

      
1
      
Rogers
      
Hudson
      
$134316.57
      
08/07/1997
      
Academic Affairs Administration
      
Assoc. Vice President/Prof.
      
Associate VP & Professor
      
Faculty Admin 10, 11, 12 mo
    
    

      
2
      
Hart
      
Erika
      
$26650.11
      
08/03/2001
      
Academic Affairs Administration
      
Program Asst
      
Program Assistant
      
Support Personnel NonExempt PT
    
    

      
3
      
Deschene
      
Catherine
      
$63960.27
      
01/05/2004
      
Academic Affairs Administration
      
Executive Asst
      
Exec Asst to Provost & VPAA
      
Administrative/Professional
    
    

      
4
      
Baker
      
Jennifer
      
$90000.00
      
05/26/2009
      
Academic Affairs Administration
      
Dir, Academic Support Services
      
Dir., Budgets & Management Svs
      
Administrative/Professional
    
  

In [32]:

    

%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
with plt.style.context('fivethirtyeight'):
    plt.hist(d.values, bins=50, alpha=0.4)
    plt.axvline(np.mean(d.values), ymin=0.0, ymax=600, linewidth=2, color='k', label='mean')
    plt.axvline(x=np.median(d.values), ymin=0.0, ymax=600, linewidth=2, color='b', linestyle='--', label='median')
    plt.legend(loc='upper right')
    plt.ylabel('Number of Employees')
    plt.xlabel('Annual Salary')
    plt.show()


    

In [34]:

    

data = np.random.normal(loc=0.0, scale=1.0, size=10000)


    

In [38]:

    

with plt.style.context('fivethirtyeight'):
    plt.hist(data, bins=50, alpha=0.4)
    plt.axvline(np.mean(data), ymin=0.0, ymax=600, linewidth=2, color='k', label='mean')
    plt.axvline(x=np.median(data), ymin=0.0, ymax=600, linewidth=2, color='b', linestyle='--', label='median')
    plt.legend(loc='upper right')
    plt.ylabel('Count')
    plt.xlabel('x')
    plt.show()


    

In [39]:

    

np.mean(data)


    

    
Out[39]:





0.0033737113299363549

In [40]:

    

np.median(data)


    

    
Out[40]:





0.016896725981360865

In [ ]: