In [1]:

    

import pandas as pd


    

In [2]:

    

%pylab inline


    

    




Populating the interactive namespace from numpy and matplotlib

In [3]:

    

plt.style.use('ggplot')
#Some default stuff for my plotting
aspect_mult = 0.9
figsize(aspect_mult*16,aspect_mult*9)
linewidth = 3


    

In [4]:

    

df = pd.read_csv("data/universities_2015.csv")


    

In [5]:

    

df.head()


    

    
Out[5]:






  

    

      

      
University
    
  
  

    

      
0
      
CUT
    
    

      
1
      
NMMU
    
    

      
2
      
UCT
    
    

      
3
      
UCT
    
    

      
4
      
UCT
    
  

In [6]:

    

result = df.groupby('University').size()


    

In [7]:

    

result.sort_index()


    

    
Out[7]:





University
CUT      1
NMMU     1
UCT      8
UJ       1
UKZN     3
UL       2
UP       1
US       1
UV       1
WSU      1
Wits    14
dtype: int64

In [8]:

    

result


    

    
Out[8]:





University
CUT      1
NMMU     1
UCT      8
UJ       1
UKZN     3
UL       2
UP       1
US       1
UV       1
WSU      1
Wits    14
dtype: int64

In [9]:

    

result.keys()


    

    
Out[9]:





Index([u'CUT', u'NMMU', u'UCT', u'UJ', u'UKZN', u'UL', u'UP', u'US', u'UV',
       u'WSU', u'Wits'],
      dtype='object', name=u'University')

In [10]:

    

plt.barh(range(result.shape[0]),result.values)
plt.yticks(np.arange(result.shape[0])+0.4,result.keys(), rotation=0,fontsize=14)
plt.xlim(0,max(result)+1)
plt.title("DSIDE 2016/2017 University Representation",fontsize=18, color = 'k')
plt.ylabel("Universities",fontsize=16, color = 'k')
plt.xlabel("Number of Students",fontsize=16, color = 'k')
pyplot.savefig('../images/2015-universities.png',bbox_inches='tight')


    

In [ ]: