fynance.models.rolling.RollMultiLayerPerceptron¶
-
class
fynance.models.rolling.
RollMultiLayerPerceptron
(X, y, layers=[], activation=None, drop=None, bias=True, x_type=None, y_type=None, activation_kwargs={}, **kwargs)¶ Rolling version of the vanilla neural network model.
Attributes: - lr_scheduler
- optimizer
- seed_numpy
- seed_torch
Methods
run
([backtest_plot, backtest_kpi, figsize, func])Run neural network model and backtest predictions. set_roll_period
(train_period, test_period[, …])Callable method to set target features data, and model. sub_predict
(X)Predict. save
(path)Save the trained neural network model. TODO: - fix train and predict methods - finish docstring - finish methods