$2$ Data Partitioning

Rarely will you receive $$training$$ data and $$validation$$ data; usually you will have to partition

available labeled data yourself. In this question, you will shuffle and partition each of the datasets

in the assignment. Shuffling prior to splitting crucially ensures that all classes are represented in

your partitions. For this question, please do not use any functions available in sklearn.

$($a$)$ For the MNIST dataset, write code that sets aside $10,000$ training images as a validation set.

$($b$)$ For the spam dataset, write code that sets aside $20\%$ of the training data as a validation set.

$($c$)$ For the CIFAR$-10$ dataset, write code that sets aside $5,000$ training images as a validation set.