AutoRegressive Moving Average with eXogenous input (ARMAX)
- class softsensor.armax.ARMAX(order: Tuple[int, int, int], delta1: float = 0.03, delta2: float = 0.01, num_iteration: int = 10)[source]
Represents an AutoRegressive Moving Average with eXogenous input model.
- Parameters:
order (Tuple[int, int, int]) – Parameter for the order of the outputs and inputs in den equation (na, nb, nc)
delta1 (float) – Threshold for parameters.
delta2 (float) – Threshold for prediction error.
num_iteration (int) – Number of iteration for the parameter estimation with the extended least squares algorithm.
- Return type:
None.
Example
>>> import pandas as pd >>> import numpy as np >>> import softsensor.armax as armax >>> d = {'in_col': np.random.rand(101), 'out_col': np.random.rand(101)}
>>> df = pd.DataFrame(d) >>> armax = armax.ARMAX(order=(4, 4, 4), num_iteration=1) >>> armax.fit(data_train=[df], input_sensors=['in_col'], output_sensors=['out_col']) >>> print(len(armax.parameters)) 12
- fit(data_train: List[DataFrame], input_sensors: List[str], output_sensors: List[str], windows: List[Tuple[int, int]] = None, verbose: bool = False) None[source]
Fit the ARMAX model