from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
import pandas as pd
# Create some sample data
data = {'age': [20, 30, 40], 'income': [50000, 60000, 70000],
'gender': ['male', 'female', 'male'],
'education': ['high_school', 'university', 'high_school']}
df = pd.DataFrame(data)
# ColumnTransformer for numerical and categorical features
ct = ColumnTransformer(transformers=[ ('num', StandardScaler(),
['age', 'income']),('cat', OneHotEncoder(), ['gender', 'education'])])
# Fit and transform the ColumnTransformer on the sample data
ct.fit(df)
transformed = ct.transform(df)
# Get the feature names output by the ColumnTransformer
feature_names = ct.get_feature_names_out()
# Print the feature names and the transformed data
print(feature_names)
print(transformed)