import pandas as pd
import numpy as np
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'],
'age': [42, 52, 36, 24, 73],
'preTestScore': [-999, -999, -999, 2, 1],
'postTestScore': [2, 2, -999, 2, -999]}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'age', 'preTestScore', 'postTestScore'])
df
df.replace(-999, np.nan)
first_name | last_name | age | preTestScore | postTestScore | |
---|---|---|---|---|---|
0 | Jason | Miller | 42 | 1 | 2 |
1 | Molly | Jacobson | 52 | 1 | 2 |
2 | Tina | Ali | 36 | 1 | 1 |
3 | Jake | Milner | 24 | 2 | 2 |
4 | Amy | Cooze | 73 | 1 | 1 |
5 rows × 5 columns