def __init__(self,
species_name=None,
block_size=1,
transfer_emissions=np.array([0.1]),
transfer_rate=1e-2,
clonal_emission=1e-3,
transfer_length=5e2,
transition_prior=None,
algorithm="viterbi",
n_iter=10,
tol=1e-2,
verbose=False,
params="m"):
if species_name is not None:
self.transfer_emissions, self.transition_prior = self.get_empirical_emissions(
species_name, block_size)
else:
self._init_emissions_manual(transfer_emissions, transition_prior)
n_components = 1 + len(self.transfer_emissions)
# normalizing the transition prior
self.transition_prior = self.transition_prior.astype(
np.float32) / np.sum(self.transition_prior)
self.transfer_rate = transfer_rate
self.clonal_emission = clonal_emission
self.exit_rate = 1. / transfer_length # rate of leaving the transferred state
self.all_emissions = np.concatenate([[self.clonal_emission],
self.transfer_emissions])
_BaseHMM.__init__(self,
n_components,
algorithm=algorithm,
n_iter=n_iter,
tol=tol,
verbose=verbose,
params=params)
def __init__(self,
n_components=1,
startprob=None,
transmat=None,
startprob_prior=None,
transmat_prior=None,
algorithm="viterbi",
random_state=None,
n_iter=10,
thresh=1e-2,
params=string.ascii_letters,
init_params=string.ascii_letters):
"""Create a hidden Markov model with multinomial emissions.
Parameters
----------
n_components : int
Number of states.
"""
_BaseHMM.__init__(self,
n_components,
startprob,
transmat,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter,
thresh=thresh,
params=params,
init_params=init_params)
def __init__(self,
mlp,
aucoustic_model,
observation_count,
n_components=1,
startprob_prior=1.0,
transmat_prior=1.0,
algorithm="viterbi",
random_state=None,
n_iter=10,
tol=1e-2,
verbose=False,
params="stmc",
init_params="stmc"):
_BaseHMM.__init__(self,
n_components,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter,
tol=tol,
params=params,
verbose=verbose,
init_params=init_params)
self.aucoustic_model = aucoustic_model
self.observation_count = observation_count
self.mlp = mlp
self.mlp.info()
def __init__(self, n_components: int=1,
startprob_prior:float=1.0, transmat_prior:float=1.0,
diffusion_degrees_of_freedom:int = 4,
tau:float = 0.02,
algorithm:str="viterbi", random_state:int=42,
n_iter:int=10, tol:float=1e-2, verbose:bool=False,
params:str="std", init_params:str="std"):
"""
Parameters
----------
n_components : int, optional
Number of states. The default is 1.
startprob_prior : float, optional
Parameters of the Dirichlet prior distribution for startprob_. The default is 1.0.
transmat_prior : float, optional
Parameters of the Dirichlet prior distribution for each row of the transition probabilities transmat_. The default is 1.0.
diffusion_degrees_of_freedom : int, optional
Translational degrees of freedom. The default is 4.
tau : float, optional
Time interval between two consecutive measurements. The default is 0.02.
algorithm : str, optional
Decoder algorithm. The default is "viterbi".
random_state : int, optional
A random number generator instance. The default is 42.
n_iter : int, optional
Maximum number of iterations to perform. The default is 10.
tol : float, optional
Convergence threshold. EM will stop if the gain in log-likelihood is below this value. The default is 1e-2.
verbose : bool, optional
Whether per-iteration convergence reports are printed to sys.stderr. Convergence can also be diagnosed using the monitor_ attribute. The default is False.
params : str, optional
The parameters that get updated during training.
Can contain any combination of ‘s’ for startprob, ‘t’ for transmat, ‘d’ for diffusion coefficients. Defaults to all parameters. The default is "std".
init_params : str, optional
The parameters that get initialized prior to training.
Can contain any combination of ‘s’ for startprob, ‘t’ for transmat, ‘d’ for diffusion coefficients. Defaults to all parameters. The default is "std".
Returns
-------
None.
"""
_BaseHMM.__init__(self, n_components=n_components, startprob_prior=startprob_prior,
transmat_prior=transmat_prior, algorithm=algorithm,
random_state=random_state, n_iter=n_iter,
tol=tol, params=params, verbose=verbose, init_params=init_params)
self._tau_ = tau
self._diffusion_degrees_of_freedom_ = diffusion_degrees_of_freedom
self._diffusion_coefficients_ = np.zeros([self.n_components])
self._mu_ = np.zeros([self.n_components])
self.n_features = 1
def __init__(self, n_components=2,
startprob_prior=1.0, transmat_prior=1.0,
algorithm="viterbi", random_state=None,
n_iter=10, tol=1e-2, verbose=False,
params="str", init_params="str"):
_BaseHMM.__init__(self, n_components,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter, tol=tol, verbose=verbose,
params=params, init_params=init_params)
def __init__(self, n_components=1,
startprob_prior=1.0, transmat_prior=1.0,
algorithm='viterbi', random_state=None,
n_iter=10, tol=1e-2, verbose=False,
params="ste", init_params="ste"):
_BaseHMM.__init__(self, n_components,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter, tol=tol, verbose=verbose,
params=params, init_params=init_params)
def __init__(self,
n_components=1,
loc_covariance_type='full',
time_covariance_type='full',
loc_min_covar=1e-3,
time_min_covar=1e-3,
startprob_prior=1.0,
transmat_prior=1.0,
loc_means_prior=0,
loc_means_weight=0,
loc_covars_prior=1e-2,
loc_covars_weight=1,
time_means_prior=0,
time_means_weight=0,
time_covars_prior=1e-2,
time_covars_weight=1,
algorithm="viterbi",
random_state=None,
n_iter=10,
tol=1e-2,
verbose=False,
params="stmc",
init_params="stmc",
weights=None):
_BaseHMM.__init__(self,
n_components,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter,
tol=tol,
params=params,
verbose=verbose,
init_params=init_params)
self.loc_covariance_type = loc_covariance_type
self.time_covariance_type = time_covariance_type
self.loc_min_covar = loc_min_covar
self.time_min_covar = time_min_covar
self.loc_means_prior = loc_means_prior
self.time_means_prior = time_means_prior
self.loc_means_weight = loc_means_weight
self.time_means_weight = time_means_weight
self.loc_covars_prior = loc_covars_prior
self.time_covars_prior = time_covars_prior
self.loc_covars_weight = loc_covars_weight
self.time_covars_weight = time_covars_weight
self._weights = weights
self.X_loc = []
def __init__(self,
n_components=1,
n_mix=1,
startprob=None,
transmat=None,
startprob_prior=None,
transmat_prior=None,
algorithm="viterbi",
gmms=None,
covariance_type='diag',
covars_prior=1e-2,
random_state=None,
n_iter=10,
thresh=1e-2,
params=string.ascii_letters,
init_params=string.ascii_letters):
"""Create a hidden Markov model with GMM emissions.
Parameters
----------
n_components : int
Number of states.
"""
_BaseHMM.__init__(self,
n_components,
startprob,
transmat,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter,
thresh=thresh,
params=params,
init_params=init_params)
# XXX: Hotfit for n_mix that is incompatible with the scikit's
# BaseEstimator API
self.n_mix = n_mix
self._covariance_type = covariance_type
self.covars_prior = covars_prior
self.gmms = gmms
if gmms is None:
gmms = []
for x in range(self.n_components):
if covariance_type is None:
g = GMM(n_mix)
else:
g = GMM(n_mix, covariance_type=covariance_type)
gmms.append(g)
self.gmms_ = gmms
def __init__(self,
n_components=1,
covariance_type='diag',
startprob=None,
transmat=None,
startprob_prior=None,
transmat_prior=None,
algorithm="viterbi",
means_prior=0,
means_weight=0,
covars_prior=1e-2,
covars_weight=1,
random_state=None,
n_iter=10,
thresh=1e-2,
params=string.ascii_letters,
init_params=string.ascii_letters):
_BaseHMM.__init__(self,
n_components,
startprob,
transmat,
startprob_prior=startprob_prior,
transmat_prior=transmat_prior,
algorithm=algorithm,
random_state=random_state,
n_iter=n_iter,
thresh=thresh,
params=params,
init_params=init_params)
self._covariance_type = covariance_type
if covariance_type not in ['spherical', 'tied', 'diag', 'full']:
raise ValueError('bad covariance_type')
self.means_prior = means_prior
self.means_weight = means_weight
self.covars_prior = covars_prior
self.covars_weight = covars_weight
def __init__(self, framelogprob, rates, M, *args, **kwargs):
_BaseHMM.__init__(self, *args, **kwargs)
# rates for each state
self.rates = rates
self.M = M
self.framelogprob = framelogprob
