KMNIST kNN 

Adding PCA dimension reduction produces better Test Accuracy 
`x_train = x_train.reshape(-1, 784)`
`x_test = x_test.reshape(-1, 784)`
After this code rows:
`pca = PCA(n_components= 60, random_state= 0 )`
`x_train = pca.fit_transform(x_train)`
`x_test = pca.transform(x_test)`
The resulting is `Test accuracy: 0.9398`