# Import modules
import pandas as pd
raw_data = {'first_name': ['Jason', 'Jason', 'Tina', 'Jake', 'Amy'],
'last_name': ['Miller', 'Miller', 'Ali', 'Milner', 'Cooze'],
'age': [42, 42, 36, 24, 73],
'preTestScore': [4, 4, 31, 2, 3],
'postTestScore': [25, 25, 57, 62, 70]}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'preTestScore', 'postTestScore'])
df
first_name | last_name | age | preTestScore | postTestScore | |
---|---|---|---|---|---|
0 | Jason | Miller | 42 | 4 | 25 |
1 | Jason | Miller | 42 | 4 | 25 |
2 | Tina | Ali | 36 | 31 | 57 |
3 | Jake | Milner | 24 | 2 | 62 |
4 | Amy | Cooze | 73 | 3 | 70 |
# View preTestscore where postTestscore is greater than 50
df['preTestScore'].where(df['postTestScore'] > 50)
0 NaN 1 NaN 2 31 3 2 4 3 Name: preTestScore, dtype: float64