PYTHON

sklearn columntransformer

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

# Preprocessing for numerical data
numerical_transformer = SimpleImputer(strategy='mean')

# Preprocessing for categorical data
categorical_transformer = Pipeline(steps=[
    ('Categorical_Imputer', SimpleImputer(strategy='most_frequent')),
    ('One_Hot_Encoder', OneHotEncoder(handle_unknown='ignore'))
])

# Bundle preprocessing for numerical and categorical data
preprocessor = ColumnTransformer(
    transformers=[
        ('Numerical_Transformer', numerical_transformer, numerical_cols),
        ('Categorical_Transformer', categorical_transformer, categorical_cols)
    ])