import pandas as pd
raw_data = {'first_name': ['Jason', 'Molly', 'Tina', 'Jake', 'Amy'],
'last_name': ['Miller', 'Jacobson', 'Ali', 'Milner', 'Cooze'],
'sex': ['male', 'female', 'male', 'female', 'female']}
df = pd.DataFrame(raw_data, columns = ['first_name', 'last_name', 'sex'])
df
first_name | last_name | sex | |
---|---|---|---|
0 | Jason | Miller | male |
1 | Molly | Jacobson | female |
2 | Tina | Ali | male |
3 | Jake | Milner | female |
4 | Amy | Cooze | female |
5 rows × 3 columns
df_sex = pd.get_dummies(df['sex'])
df_new = pd.concat([df, df_sex], axis=1)
df_new
first_name | last_name | sex | female | male | |
---|---|---|---|---|---|
0 | Jason | Miller | male | 0 | 1 |
1 | Molly | Jacobson | female | 1 | 0 |
2 | Tina | Ali | male | 0 | 1 |
3 | Jake | Milner | female | 1 | 0 |
4 | Amy | Cooze | female | 1 | 0 |
5 rows × 5 columns
df_new = df.join(df_sex)
df_new
first_name | last_name | sex | female | male | |
---|---|---|---|---|---|
0 | Jason | Miller | male | 0 | 1 |
1 | Molly | Jacobson | female | 1 | 0 |
2 | Tina | Ali | male | 0 | 1 |
3 | Jake | Milner | female | 1 | 0 |
4 | Amy | Cooze | female | 1 | 0 |
5 rows × 5 columns