I suggest adding some explanation in this notebook about CV in GridSearchCV, which indicates that this class uses the cross_validate function to do the search.
It was somehow unclear and confusing, especially later in the “Evaluation and hyperparameter tuning” notebook.
In reality, it does not use cross_validate
but rather does cross-validation internally.
It is true that we don’t explicitly state that cross-validation happens. We can make the following paragraph more explicit:
In the previous exercise we used one
for
loop for each hyperparameter to find the best combination over a fixed grid of values.GridSearchCV
is a scikit-learn class that implements a very similar logic with less repetitive code.
And then, just add a note about the split#_test_score
reported in cv_results
to make it obvious that we did such evaluation internally.
1 Like
Thank you for the explanation. That seems very helpful.