Encoding categorical variables without creating leakage

                  import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder, StandardScaler

numeric_features = ['age', 'income', 'tenure_months']
categorical_features = ['country', 'plan_tier', 'device_type']

numeric_pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='median')),
    ('scaler', StandardScaler()),
])

categorical_pipeline = Pipeline([
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('encoder', OneHotEncoder(handle_unknown='ignore', sparse_output=False)),
])

preprocessor = ColumnTransformer([
    ('num', numeric_pipeline, numeric_features),
    ('cat', categorical_pipeline, categorical_features),
])

print(preprocessor)