| cat_cols = ['workclass', 'education', 'education.num', | |
| 'marital.status', 'occupation', 'relationship', 'race', | |
| 'sex', 'native.country', 'income'] | |
| for col in cat_cols: | |
| categories = df.groupby(col).size() | |
| print(categories) | |
| #workclass | |
| #Federal-gov 960 | |
| #Local-gov 2093 | |
| #Never-worked 7 | |
| # (...) | |
| #education | |
| #10th 933 | |
| #11th 1175 | |
| #12th 433 | |
| # (...) |