Implements the second step of the experiment pipeline. Trains a series of classifiers based on different configurations in a nested cross validation scheme.
Implements the third step of the experiment pipeline. Given a classifier, this step is responsible to find the best performing classifier configuration.
Implements the fourth step of the experiment pipeline. This step reads the best performing configuration from the previous steps and trains the corresponding model on all available train dataset.
Implements the fifth step of the experiment pipeline. This step loads a pickled trained model from the previous step and deploys it in order to make predictions on a test dataset.
