Encode categorical and scale numerical variables
In this final step, you will perform one-hot encoding on the categorical variables and then scale the numerical columns. The pandas library has been loaded for you as pd, as well as the StandardScaler module from the sklearn.preprocessing module.
The raw telecom churn dataset telco_raw has been loaded for you as a pandas DataFrame, as well as the lists custid, target, categorical, and numerical with column names you have created in the previous exercise. You can familiarize yourself with the dataset by exploring it in the console.
Este exercício faz parte do curso
Machine Learning for Marketing in Python
Instruções do exercício
- Perform one-hot encoding on the categorical variables.
- Initialize a
StandardScalerinstance. - Fit and transform the
scaleron the numerical columns. - Build a DataFrame from
scaled_numerical.
Exercício interativo prático
Experimente este exercício completando este código de exemplo.
# Perform one-hot encoding to categorical variables
telco_raw = pd.get_dummies(data = ___, columns = categorical, drop_first=True)
# Initialize StandardScaler instance
scaler = ___()
# Fit and transform the scaler on numerical columns
scaled_numerical = ___.fit_transform(telco_raw[___])
# Build a DataFrame from scaled_numerical
scaled_numerical = pd.DataFrame(___, columns=numerical)