Open iris-j opened 5 years ago
It is not necessary for you to do so, the part 1 is only meant to see if you could fit the dataset perfectly or not as the dataset is linearly separatable, therefore I don't see the point why you need to split it into a training part and a test part.
Sorry for the late reply.
I've extended the deadline, so you will have one more week to do it, don't worry.
Are we supposed to split the given dataset into train set and test set when we implement the two models in part 1? And the accuracy and plot should be based on the performance of our model on test set?