def LPs(jj=None):
return [
(11, 1, LP.spatial1d(jj)),
(12, 1, LP.correlations),
(15, 0, LP.spectral_errors),
(13, 0, LP.phase_particles(True, jj)),
(14, 0, LP.sliding_marginals(jj)),
]
def LPs(jj=None, params=params):
return [
(14, 1, LP.sliding_marginals(obs_inds=jj, zoomy=0.8, **params)),
(13, 1,
LP.phase_particles(is_3d=False,
obs_inds=jj,
zoom=0.8,
Tplot=0,
**params)),
]
def LPs(jj=None, params=params):
return [
(1, LP.correlations),
(1, LP.sliding_marginals(jj, zoomy=0.8, **params)),
(1, LP.phase_particles(is_3d=True, obs_inds=jj, **params)),
]
def LP_setup(jj=None):
return [
(11, 1, LP.spatial2d(square, ind2sub, jj, cm)),
(15, 0, LP.spectral_errors),
(14, 0, LP.sliding_marginals(dims=cntr + np.arange(4))),
]
def LPs(jj=None, params=params):
return [
(12, 1, LP.correlations),
(14, 1, LP.sliding_marginals(jj, zoomy=0.8, **params)),
(13, 1, LP.phase3d(jj, **params)),
]
Dyn = {
'M': Nx+Np, # Length of (total/augmented) state vector
'model': step, # Actual model
'noise': 0, # Additive noise (variance)
# 'noise': GaussRV(C=.1*np.eye(Nx+Np)),
}
# Define observation model using convenience function partial_Id_Obs
jj = np.arange(Nx) # obs indices (y = x[jj])
Obs = modelling.partial_Id_Obs(Nx+Np, jj)
Obs['noise'] = 1
# Specify liveplotting (and replay) functionality.
LP = [
(1, LP.spatial1d(jj)),
(1, LP.sliding_marginals(
jj, zoomy=0.8, dims=[0, Nx], labels=["$x_0$", "Force"]),
),
]
# Labels for sectors of state vector.
# DAPPER will compute diagnostic statistics for the full state vector,
# but also for each sector of it (averaged in space according to the
# methods specified in your .dpr_config.yaml:field_summaries key).
# The name "sector" comes from its typical usage to distinguish
# "ocean" and "land" parts of the state vector.
# Here we use it to get individual statistics of the parameter and state.
parts = dict(state=np.arange(Nx),
param=np.arange(Np)+Nx)
# Wrap-up model specification
HMM = modelling.HiddenMarkovModel(Dyn, Obs, t, sectors=parts, LP=LP)
