Specification
In this task, you should translate pykalman (https://github.com/pykalman/pykalman/blob/master/pykalman/standard.py#L920) to MQL5, features that must be translated:
initilization: KalmanFilter(transition_matrices=A,transition_covariance=Q)
function em: kf.em(z)
function smooth: x_mean,x_covar=kf.smooth(z)
function filter_update: kf.filter_update(filtered_state_mean=x_mean, filtered_state_covariance=x_covar) and variant with "observation"
A and Q is a CMatrixDouble(in test case it's (3,3)) matrix (from <Math/Alglib/matrix.mqh>)
z is a double[] array
x_mean and x_covar is a CMatrixDouble, it's the output of kf.smooth() step
I will provide a copy of test data to execute and validate this task, and a copy of python code too
I don't want to use python, just mql5