Previous topic

fynance.models.rolling._RollingBasis.run

Next topic

fynance.models.rolling.RollMultiLayerPerceptron.run

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(self[, backtest_plot, backtest_kpi, …]) Run neural network model and backtest predictions.
set_roll_period(self, train_period, test_period) Callable method to set target features data, and model.
sub_predict(self, X) Predict.
save(self, path) Save the trained neural network model.
TODO:  
- fix train and predict methods  
- finish docstring  
- finish methods