# Import required modules
import pandas as pd
import numpy as np
data = {'name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'age': [42, 52, 36, 24, 73],
'preTestScore': [4, 24, 31, 2, 3],
'postTestScore': [25, 94, 57, 62, 70]}
df = pd.DataFrame(data, columns = ['name', 'age', 'preTestScore', 'postTestScore'])
df
name | age | preTestScore | postTestScore | |
---|---|---|---|---|
0 | Jason | 42 | 4 | 25 |
1 | Molly | 52 | 24 | 94 |
2 | Tina | 36 | 31 | 57 |
3 | Jake | 24 | 2 | 62 |
4 | Amy | 73 | 3 | 70 |
5 rows × 4 columns
# Create a new column called df.elderly where the value is yes
# if df.age is greater than 50 and no if not
df['elderly'] = np.where(df['age']>=50, 'yes', 'no')
# View the dataframe
df
name | age | preTestScore | postTestScore | elderly | |
---|---|---|---|---|---|
0 | Jason | 42 | 4 | 25 | no |
1 | Molly | 52 | 24 | 94 | yes |
2 | Tina | 36 | 31 | 57 | no |
3 | Jake | 24 | 2 | 62 | no |
4 | Amy | 73 | 3 | 70 | yes |
5 rows × 5 columns