This post is a continuation of recent post where we implemented gradient descent method for solving logistic regression problem. Today we will try to evaluate our algorithm to find out how it works in the wild.

Last time the logistic regression problem was stated strictly as optimization problem which suggests our evaluation should consider the goal function itself – which is to some extend correct, indeed it makes sense to check how J changes while algorithm runs. But it is not the best idea one can have. Please recall our goal. We aimed for parametrized labelling machine producing labels for new upcoming obveravations/objects based on pre-defined features they are characterized by. The word **new** is crucial here. We want our model to fit to new data – to predict labels correctly for unseen data.