from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Ridge
from sklearn.model_selection import cross_val_score
from sklearn.datasets import fetch_openml

X, y = fetch_openml("house_sales", as_frame=True, version=2,
                    return_X_y=True)
X = X.drop(['date'], axis=1)

prep = ColumnTransformer([
    ('encoder', OneHotEncoder(handle_unknown='ignore'), ['zipcode'])
], remainder=StandardScaler())

pipe = Pipeline([
    ('prep', prep),
    ('clf', Ridge())])

scores = cross_val_score(pipe, X, y)
scores.mean()

# 0.8037