Given, a complex dataframe df: (expand for full code)

from skrub.datasets import fetch_employee_salaries
dataset = fetch_employee_salaries()
df = dataset.X
y = dataset.y
df
        

	gender	department	department_name	division	assignment_category	employee_position_title	date_first_hired	year_first_hired
1	M	FRS	Fire and Rescue Services	Third Battalion - Administration	Fulltime-Regular	Fire/Rescue Lieutenant	06/07/2004	2004
2	M	HHS	Department of Health and Human Services	Environmental Health and Regulatory Services	Fulltime-Regular	Environmental Health Specialist III	02/20/2007	2007
...	...	...	...	...	...	...	...	...
9226	M	DGS	Department of General Services	Facilities Maintenance	Fulltime-Regular	Master Plumber	03/26/2001	2001
9227	F	HHS	Department of Health and Human Services	Infants and Toddlers	Fulltime-Regular	Program Specialist II	03/25/2013	2013

from sklearn.model_selection import cross_val_score
from skrub import tabular_pipeline
cross_val_score(tabular_pipeline('regressor'), df, y)
        

array([0.89370447, 0.89279068, 0.92282557, 0.92319094, 0.92162666])