Train test split and stratified cross validation done properly

                  from sklearn.model_selection import StratifiedKFold, train_test_split, cross_validate
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.2,
    stratify=y,
    random_state=42,
)

pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler()),
    ('model', LogisticRegression(max_iter=1000)),
])

cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
scores = cross_validate(pipeline, X_train, y_train, cv=cv, scoring=['roc_auc', 'f1', 'precision', 'recall'])
print(scores)