Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Migrate evaluation functionalities to
pyss3.util
All the code related to evaluating models have been migrated to the ``pyss3.util`` module. There, a new class has been created, ``Evaluation``, which provides all the desired functionalities through its public methods (API). Before this change was made, the only way by which the user was able to use these functionalities was through the Command Line tool. That is, there was no way for the user to make use and, more importantly, take advantage of this functionalities through the source code. Now the user can import the ``Evaluation`` class to perform model evaluation and hyperparameter optimization. This class not only provide methods to evaluate models but also keeps all the advantages previously provided only through the Command Line tool, such as an evaluation cache that automatically keeps track of the evaluation history and the generation of the interactive 3D evaluation plot. For example, the following code performs a grid search (``s`` will take 6 different values between 0.2 and 0.8, ``l`` between 0.1 and 2, and ``p`` between 0.5 and 2), then open up the 3D plot in the web browser, and finally update the hyperparameters of the model with the best ones: ```python from pyss3.util import Evaluation, span from pyss3 import SS3 ... clf = SS3() clf.fit(x_train, y_train) s, l, p, a = Evaluation.grid_search( clf, x_test, y_test, s=span(.2, .8, 6), l=span(.1, 2, 6), p=span(.5, 2, 6) ) Evaluation.plot() clf.set_hyperparameters(s, l, p, a) ```
- Loading branch information