def tt_graph():
global tt_graph_
if not tt_graph_:
if not os.path.exists(tt_graph_fname):
tic("creating empty tt graph", experiment_name)
tt_graph_ = createTravelTimeGraph(hmm_graph(), radius=2e-4)
tt_graph_.checkInvariants()
save_ttg_structure(tt_graph_, experiment_name=experiment_name)
else:
tic("reading tt graph from %s"%tt_graph_fname, experiment_name)
tt_graph_ = pickle.load(open(tt_graph_fname,'r'))
return tt_graph_
traj_conv_one_mode = createTrajectoryConversion(graph_type=graph_type,
process='mixture_auto',
params=traj_conv_param,
network=net,
max_nb_mixture=1)
# mode_counts = dict([(link_id,1) for link_id in net.keys()])
if graph_type == 'simple':
hmm_graph = model.createHMMGraphFromNetwork(net, mode_counts=traj_conv.modeCounts())
hmm_graph_one_mode = model.createHMMGraphFromNetwork(net, mode_counts=traj_conv_one_mode.modeCounts())
# hmm_graph = model.createHMMGraphFromNetwork(net, mode_counts=mode_counts)
else:
# Complex model not implemented
assert False
tt_graph = createTravelTimeGraph(hmm_graph, radius=2e-4)
tt_graph.checkInvariants()
tt_graph_one_mode = createTravelTimeGraph(hmm_graph_one_mode, radius=2e-4)
tt_graph_one_mode.checkInvariants()
gmrf = emptyValues(tt_graph)
gmrf_one_mode = emptyValues(tt_graph)
# Checkpoint: save the structures
save_ttg_structure(tt_graph, experiment_name=experiment_name)
# The TTG structure is required when loading the GMRF (and the GMRF estimators)
# Make sure they are saved in all the directories
save_ttg_structure(tt_graph_one_mode, experiment_name='{0}_one_mode'.format(experiment_name))
def createFillTTGraph(hmm_graph, traj_observations): tt_graph = createTravelTimeGraph(hmm_graph, 1e-3) fillTTGraph(tt_graph, traj_observations) return tt_graph
