def setup_hmm(rg, EM_params):
G, node_map = hmmconf.rg_to_nx_undirected(rg, map_nodes=True)
n_states = len(node_map)
# deal with initial marking and get start probability
is_inv = lambda t: t.name is None
startprob = hmmconf.compute_startprob(rg, node_map, n_states, is_inv)
# add epsilon mass to all states
startprob += 1e-5
hmmconf.utils.normalize(startprob, axis=1)
# remove invisible transitions
to_remove = list()
for t in rg.transitions:
if is_inv(t):
to_remove.append(t)
for t in to_remove:
rg.transitions.remove(t)
t.from_state.outgoing.remove(t)
t.to_state.incoming.remove(t)
dist_df = hmmconf.compute_distance_matrix(G, node_map, as_dataframe=True)
distmat = dist_df.values
# print('Distance df: \n{}'.format(dist_df))
obsmap = {t.name: int(t.name) for t in rg.transitions}
int2state = {val:key for key, val in node_map.items()}
int2obs = {val:key for key, val in obsmap.items()}
n_obs = len(obsmap)
logger.info('No. of states: {}'.format(n_states))
transcube = hmmconf.compute_state_trans_cube(rg, node_map, obsmap, n_obs, n_states)
emitmat = hmmconf.compute_emission_mat(rg, node_map, obsmap, n_obs, n_states)
confmat = hmmconf.compute_conformance_mat(emitmat)
conform_f = hmmconf.conform
hmm = hmmconf.HMMConf(conform_f, startprob, transcube, emitmat, confmat, distmat,
int2state, int2obs, n_states, n_obs, params='to', verbose=True,
n_jobs=EM_params[N_JOBS], tol=EM_params[TOL],
n_iter=EM_params[N_ITER], random_seed=EM_params[RANDOM_SEED_PARAM])
return hmm
is_inv)
sorted_states = sorted(list(rg.states),
key=lambda s: (s.data['disc'], s.name))
node_map = {
key: val
for val, key in enumerate(map(lambda state: state.name, sorted_states))
}
int2state = {val: key for key, val in node_map.items()}
state2int = {val: key for key, val in int2state.items()}
took_rg = time.time() - start_rg
time_dict[TIME_BUILD_RG] = took_rg
logger.info(f"Building reachability graph took: {took_rg:.3f}s")
is_inv_rg = lambda t: t.name is None
init = hmmconf.get_init_marking(rg)
startprob = hmmconf.compute_startprob(rg, state2int, is_inv_rg)
conf_obsmap = {i: i for i in obs2int.values()}
confmat = hmmconf.compute_confmat(rg, init, is_inv_rg, state2int,
conf_obsmap)
logger.info("Estimating conformining parameters")
start_conform = time.time()
params = estimate_conform_params(
filtered_event_df,
state2int,
obs2int,
net_orig,
init_marking_orig,
final_marking_orig,
is_inv,
add_prior=EXPERIMENT_CONFIGS[ADD_PRIOR],