In [1]:

    

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


    

In [2]:

    

# Create dataframe
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'], 
        'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'], 
        'age': [42, 52, 36, 24, 73], 
        'preTestScore': [4, 24, 31, 2, 3],
        'postTestScore': [25, 94, 57, 62, 70]}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'preTestScore', 'postTestScore'])
df


    

    
Out[2]:






  

    

      

      
first_name
      
last_name
      
age
      
preTestScore
      
postTestScore
    
  
  

    

      
0
      
Jason
      
Miller
      
42
      
4
      
25
    
    

      
1
      
Molly
      
Jacobson
      
52
      
24
      
94
    
    

      
2
      
Tina
      
Ali
      
36
      
31
      
57
    
    

      
3
      
Jake
      
Milner
      
24
      
2
      
62
    
    

      
4
      
Amy
      
Cooze
      
73
      
3
      
70
    
  

In [3]:

    

# Index of the row with the highest value in the preTestScore column
df['preTestScore'].idxmax()


    

    
Out[3]:





2