In [1]:

    

import matplotlib
import matplotlib.pyplot as plt
import pandas as pd
%matplotlib inline
matplotlib.style.use("ggplot")


    

In [4]:

    

file_path = "/Users/szabolcs/dev/git/DAT210x/Module3/Datasets/"
file_name = "students.data"
df = pd.read_csv(file_path + file_name)
print(df.columns)
df.head()


    

    




Index(['id', 'sex', 'age', 'address', 'famsize', 'Pstatus', 'Medu', 'Fedu',
       'traveltime', 'studytime', 'failures', 'schoolsup', 'famsup', 'paid',
       'activities', 'nursery', 'higher', 'internet', 'romantic', 'famrel',
       'freetime', 'goout', 'Dalc', 'Walc', 'health', 'absences', 'G1', 'G2',
       'G3'],
      dtype='object')






    
Out[4]:






  

    

      

      
id
      
sex
      
age
      
address
      
famsize
      
Pstatus
      
Medu
      
Fedu
      
traveltime
      
studytime
      
...
      
famrel
      
freetime
      
goout
      
Dalc
      
Walc
      
health
      
absences
      
G1
      
G2
      
G3
    
  
  

    

      
0
      
0
      
1
      
18
      
0
      
1
      
0
      
4
      
4
      
2
      
2
      
...
      
4
      
3
      
4
      
1
      
1
      
3
      
4
      
0
      
11
      
11
    
    

      
1
      
1
      
1
      
17
      
0
      
1
      
1
      
1
      
1
      
1
      
2
      
...
      
5
      
3
      
3
      
1
      
1
      
3
      
2
      
9
      
11
      
11
    
    

      
2
      
2
      
1
      
15
      
0
      
0
      
1
      
1
      
1
      
1
      
2
      
...
      
4
      
3
      
2
      
2
      
3
      
3
      
6
      
12
      
13
      
12
    
    

      
3
      
3
      
1
      
15
      
0
      
1
      
1
      
4
      
2
      
1
      
3
      
...
      
3
      
2
      
2
      
1
      
1
      
5
      
0
      
14
      
14
      
14
    
    

      
4
      
4
      
1
      
16
      
0
      
1
      
1
      
3
      
3
      
1
      
2
      
...
      
4
      
3
      
2
      
1
      
2
      
5
      
0
      
11
      
13
      
13
    
  

5 rows × 29 columns

In [11]:

    

df.plot.scatter(x="G1", y="G3")
df.plot.scatter(x="G1", y="G2")
df.plot.scatter(x="failures", y="age")
df.plot.scatter(x="failures", y="absences")


    

    













    






<matplotlib.figure.Figure at 0x1121b63c8>






    













    






<matplotlib.figure.Figure at 0x11208fb00>






    













    






<matplotlib.figure.Figure at 0x112ca9390>






    

In [ ]: