Tuning multiple hyperparameters
In this exercise, you will practice tuning multiple hyperparameters simultaneously. This is a valuable topic to learn, as hyperparameters of an algorithm usually affect each other's values. Therefore, tuning them individually is not usually the recommended course of action.
You will tune the max_features and max_samples parameters of IForest using a sample of the Big Mart sales data.
IForest and airbnb_df are already loaded for you. The product function from itertools is also available.
Cet exercice fait partie du cours
Anomaly Detection in Python
Exercice interactif pratique
Essayez cet exercice en complétant cet exemple de code.
# Create two lists for max_features and max_samples
max_features = ____
max_samples = ____
scores = dict()