import numpy as np

from sklearn.datasets import load$\_$breast$\_$cancer

#from sklearn.model$\_$selection import train$\_$test$\_$split

from sklearn.model$\_$selection import cross$\_$val$\_$score

# Load the breast cancer dataset

data $=$ load$\_$breast$\_$cancer$()$

X $=$ data.data

y $=$ data.target

# Create training and testing sets

X$\_$train, X$\_$test, y$\_$train, y$\_$test $=$ load$\_$breast$\_$cancer$($X$,$ y$,$ test$\_$size$=0\mathrm{.}1,$ random$\_$state$=500)$

# Compute the base rate of malignant cancer in the training set

# Malignant cancer is labeled as $0$

malignant$\_$count $=$ np$.$sum$($y$\_$train $==0)$

total$\_$count $=$ len$($y$\_$train$)$

base$\_$rate $=$ malignant$\_$count $/$ total$\_$count

print$($f$"$Base rate of malignant cancer in the training set: $\{$base$\_$rate:$\mathrm{.}2$f$\}")$