MATLAB: Classification Learner Dataset Preparation

Question

In regards to the Classification Learner, does it matter how the responses are organized? For example, for 2 response classes, if I have 100,000 observations, is it ok to have the first 50,000 be all of the 0s and the last 50,000 be all of the 1s?

Answer 1

You can perform supervised machine learning by supplying a known set of input data and the corresponding responses to that data (labels or classes). You use this data to train a model that generates predictions for the response to new data and it doesn’t matter how the data is organized.