Training-validation-test split and cross-validation done right
One crucial step in machine learning is the choice of model. A suitable model with suitable hyperparameter is the key to a good prediction result. When we are faced with a choice between models, how should the decision be made? This is why we have cross validation. In scikit-learn, there is a family of functions that help us do this. But quite often, we see cross validation used improperly, or the result of cross validation not being interpreted correctly. In […]
Read more