def _update_dvect(cls, state: SiteInstanceState,
rand: np.random.RandomState):
'''
Update the distance vector (approximated using the geometric
distribution) and dposterior based on the new state
:param state: The current state variables of the algorithm
:param rand: The random number generator to use
:return: The modified dvector (will also modify state.dvect and
state.dposterior)
'''
# only update if there is at least 1 recrudescent infection
if np.sum(state.classification == SampleType.RECRUDESCENCE.value) == 0:
return
d_prior_alpha = 0
d_prior_beta = 0
min_recrudescence_distances = state.mindistance[
state.classification == SampleType.RECRUDESCENCE.value, :]
d_posterior_alpha = d_prior_alpha + min_recrudescence_distances.size
d_posterior_beta = d_prior_beta + np.sum(
np.round(min_recrudescence_distances))
if d_posterior_beta == 0:
d_posterior_beta = np.sum(min_recrudescence_distances)
if d_posterior_beta == 0: # algorithm will get stuck if dposterior is allowed to go to 1 (TODO: Wait, so why is it setting d_posterior_beta to 1??)
d_posterior_beta = 1
# TODO: Verify how this update actually works?
state.dposterior = rand.beta(d_posterior_alpha, d_posterior_beta)
# update dvect (approximate using geometric distribution)
state.dvect = state.dposterior * (np.array(1 - state.dposterior)**
np.arange(0, state.dvect.size))
state.dvect = state.dvect / np.sum(state.dvect)
return state.dvect
def _update_q(cls, state: SiteInstanceState, rand: np.random.RandomState):
'''
TODO: Possibly move this to the state object itself?
Propose a new value for q (the proportion of alleles that are hidden/
not directly observed) and update it appropriately, based on the
current state
:param state: The current state variables of the algorithm
:param rand: The random number generator to use
:return: The updated q value (will also modify state.q)
'''
# TODO: What are the alpha/beta used for, in high-level terms? They seem
# to be counts of observed/missing alleles in the hidden state?
q_prior_alpha = 0
q_prior_beta = 0
q_posterior_alpha = (
q_prior_alpha +
np.nansum(state.hidden0 == HiddenAlleleType.MISSING.value) +
np.nansum(state.hiddenf == HiddenAlleleType.MISSING.value))
q_posterior_beta = (
q_prior_beta +
np.nansum(state.hidden0 == HiddenAlleleType.OBSERVED.value) +
np.nansum(state.hiddenf == HiddenAlleleType.OBSERVED.value))
# Edge case if there are no missing/observed alleles, to avoid div by 0
if q_posterior_alpha == 0:
q_posterior_alpha = 1
if q_posterior_beta == 0: # TODO: Added this due to numpy warning, possibly remove?
q_posterior_beta = 1
# propose new q (beta distribution is conjugate distribution for
# binomial process)
state.qq = rand.beta(q_posterior_alpha, q_posterior_beta)
return state.qq
