In [1]:

    

csvfile = "GENdata.csv"


    

In [3]:

    

gendata = open(csvfile, 'r')


    

In [4]:

    

gendata


    

    
Out[4]:





<_io.TextIOWrapper name='GENdata.csv' mode='r' encoding='cp1252'>

In [5]:

    

memdata = gendata.read()


    

In [6]:

    

memdata


    

    
Out[6]:





'PatientID,GeneticMarker,TestGroup\n1234,sep13,A\n2345,oct14,B\n98754,nov12,A\n323424,mar02,B\n'

In [7]:

    

print(memdata)


    

    




PatientID,GeneticMarker,TestGroup
1234,sep13,A
2345,oct14,B
98754,nov12,A
323424,mar02,B

In [8]:

    

import pandas as pd


    

In [12]:

    

csvdf = pd.read_csv(csvfile)


    

In [13]:

    

csvdf


    

    
Out[13]:






  

    

      

      
PatientID
      
GeneticMarker
      
TestGroup
    
  
  

    

      
0
      
1234
      
sep13
      
A
    
    

      
1
      
2345
      
oct14
      
B
    
    

      
2
      
98754
      
nov12
      
A
    
    

      
3
      
323424
      
mar02
      
B
    
  

In [16]:

    

csvdf.TestGroup.astype('category')


    

    
Out[16]:





0    A
1    B
2    A
3    B
Name: TestGroup, dtype: category
Categories (2, object): [A, B]

In [17]:

    

csvhist = csvdf.hist(by=csvdf.TestGroup)


    

In [18]:

    

csvdf.describe


    

    
Out[18]:





<bound method NDFrame.describe of    PatientID GeneticMarker TestGroup
0       1234         sep13         A
1       2345         oct14         B
2      98754         nov12         A
3     323424         mar02         B>

In [ ]: