Hawkes process model exponential kernels with fixed and given decays. It is modeled with least square loss:
where \(\lambda_i\) is the intensity:
where
\(D\) is the number of nodes
\(\mu_i\) are the baseline intensities
\(\phi_{ij}\) are the kernels
\(t_k^j\) are the timestamps of all events of node \(j\)
and with an exponential parametrisation of the kernels
In our implementation we denote:
Integer \(D\) by the attribute n_nodes
Matrix \(B = (\beta_{ij})_{ij} \in \mathbb{R}^{D \times D}\) by the
parameter decays. This parameter is given to the model
decays : float or numpy.ndarray, shape=(n_nodes, n_nodes)
Either a
floatgiving the decay of all exponential kernels or a (n_nodes, n_nodes)numpy.ndarraygiving the decays of the exponential kernels for all pairs of nodes.
approx : int, default=0 (read-only)
Level of approximation used for computing exponential functions
if 0: no approximation
if 1: a fast approximated exponential function is used
n_threads : int, default=1
Number of threads used for parallel computation.
if
int <= 0: the number of threads available on the CPUotherwise the desired number of threads
n_nodes : int (read-only)
Number of components, or dimension of the Hawkes model
data : list of numpy.array (read-only)
The events given to the model through
fitmethod. Note that data given throughincremental_fitis not stored