Training and predicting

This module aims to standardize the training and evaluation procedure.

ninolearn.learn.fit.cross_hindcast(model, pipeline, model_name)

Generate a hindcast from 1962 till today using the models which were trained by the .cross_training() method.

Parameters

• model – The considered model.

• pipeline – The data pipeline that already was used before in .cross_training().

ninolearn.learn.fit.cross_training(model, pipeline, n_iter, **kwargs)

Training the model on different training sets in which each time a period corresponing to a decade out of 1962-1971, 1972-1981, …, 2012-last ovserved date is spared.

Parameters

• model – A model that follows the guidelines how a model object should be set up.

• pipeline – a function that takes lead time as argument and returns the corresponding feature, label, time and persistance.

• save_dir – The prefix of the save directory.

• **kwargs –

  Arguments that shell be passed to the .set_parameter() method of the provided model.