Why is cross_val_predict so much slower than fit for KNeighborsClassifier?

Question

Running locally on a Jupyter notebook and using the MNIST dataset (28k entries, 28x28 pixels per image, the following takes 27 seconds.

from sk         


        

Answer 1

cross_val_predict does a fit and a predict so it might take longer than just fitting, but I did not expect 64 times longer