def graph_data_handler(self, channel, data):
msg = map_data.decode(data)
for cell in msg.vertex_:
idx = cell.idx_
self.vertex_[idx].ig_ = cell.ig_
self.vertex_[idx].p_ = cell.p_
if self.vertex_[idx].p_ == 0.0:
self.vertex_[idx].occupancy_ = "FREE"
elif self.vertex_[idx].p_ == 1.0:
self.vertex_[idx].occupancy_ = "OCCUPIED"
def graph_data_handler(self, channel, data):
msg = map_data.decode(data)
for cell in msg.vertex_:
idx = cell.idx_
self.vertex_[idx].ig_ = cell.ig_
self.vertex_[idx].p_ = cell.p_
if self.vertex_[idx].p_ == 0.0:
self.vertex_[idx].occupancy_ = "FREE"
elif self.vertex_[idx].p_ == 1.0:
self.vertex_[idx].occupancy_ = "OCCUPIED"
self.graph_vis("Origin")
self.graph_vis()
unknown_graph = Grid(False)
unknown_graph.gp(self)
def graph_data_handler(self, channel, data):
msg = map_data.decode(data)
for cell in msg.vertex_:
idx = cell.idx_
self.vertex_[idx].ig_ = cell.ig_
self.vertex_[idx].p_ = cell.p_
if self.vertex_[idx].p_ == 0.0:
self.vertex_[idx].occupancy_ = "FREE"
elif self.vertex_[idx].p_ == 1.0:
self.vertex_[idx].occupancy_ = "OCCUPIED"
self.L2_error_total_ = 0.0
self.max_ig_ = 0.0
self.max_ig_vertex_ = []
self.bayesian_opt_ = 0.0
self.bayesian_relative_err_ = 0.0
def graph_data_handler(self, channel, data):
msg = map_data.decode(data)
for cell in msg.vertex_:
idx = cell.idx_
if cell.isROIs_:
self.ROIs_.append(idx)
if cell.isSamples_:
self.training_x_.append(idx)
self.training_y_.append(cell.ig_)
self.ig_ = cell.ig_
else:
self.ig_ = math.inf
self.vertex_[idx].p_ = cell.p_
if self.vertex_[idx].p_ == 0.0:
self.vertex_[idx].occupancy_ = "FREE"
elif self.vertex_[idx].p_ == 1.0:
self.vertex_[idx].occupancy_ = "OCCUPIED"
self.L2_error_total_ = 0.0
self.max_ig_ = 0.0
self.max_ig_vertex_ = []
self.bayesian_opt_ = 0.0
self.bayesian_relative_err_ = 0.0
print("Collected all data from LCM for bayesian optimization.")
for idx in self.vertex_.keys():
vert = self.vertex_[idx]
if vert.isROIs_:
print("Vertex: {}, Inside of ROIs".format(vert.idx_))
else:
print("Vertex: {}, Outside of ROIs".format(vert.idx_))
if vert.isSamples_:
print("Vertex: {}, Is sample data".format(vert.idx_))
else:
print("Vertex: {}, Not sample data".format(vert.idx_))
print("============================================")
def graph_data_handler(self, channel, data):
self.ROIs_ = []
self.NZIG_ = []
self.samples_ = []
msg = map_data.decode(data)
for cell in msg.vertex_:
idx = cell.idx_
if cell.isROIs_:
self.ROIs_.append(idx)
self.vertex_[idx].isROIs_ = True
if cell.isNZIG_:
self.NZIG_.append(idx)
if cell.isSamples_:
self.samples_.append(idx)
self.vertex_[idx].ig_ = cell.ig_
self.vertex_[idx].isSamples_ = True
# else:
# self.vertex_[idx].ig_ = math.inf
self.set_probability(idx, round(cell.p_, 3))
self.L2_error_total_ = 0.0
self.max_ig_ = 0.0
self.max_ig_vertex_ = []
self.bayesian_opt_ = 0.0
self.bayesian_relative_err_ = 0.0
# print("The size of nzig is {}".format(len(self.NZIG_)))
for idx in self.NZIG_:
self.adjacent_prob(idx)
# print("Vertex {}. Surronding prob is {}".format(idx,self.vertex_[idx].surrounding_p_))
# print("Vertex {}, Prob is {}".format(idx,self.vertex_[idx].p_))
# Update the the surronding probability for each cell inside of ROIs and construct training_x
for idx in self.samples_:
# self.adjacent_prob(idx)
# print("Vertex {}, surrounding probability is {}".format(idx,self.vertex_[idx].surrounding_p_))
if self.vertex_[idx].surrounding_p_ not in self.training_x_:
self.training_x_.append(self.vertex_[idx].surrounding_p_)
self.training_y_.append([self.vertex_[idx].ig_])
# self.training_x_.sort()
# self.training_y_.sort()
# self.training_y_.reverse()
for kk, item in enumerate(self.training_x_):
if item == self.vertex_[idx].surrounding_p_:
if self.training_y_[kk] != [self.vertex_[idx].ig_]:
self.training_x_.remove(
self.vertex_[idx].surrounding_p_)
self.training_y_.remove([self.vertex_[idx].ig_])
# for idx,x in enumerate(self.training_x_):
# print("sample X: {}, sample Y: {}".format(x,self.training_y_[idx]))
# plt.plot(self.training_x_,self.training_y_,'b*')
# plt.show()
# print("Collected all data from LCM for bayesian optimization.")
# for idx in self.vertex_.keys():
# vert = self.vertex_[idx]
# if vert.isROIs_:
# print("Vertex: {}, Inside of ROIs".format(vert.idx_))
# else:
# print("Vertex: {}, Outside of ROIs".format(vert.idx_))
# if vert.isSamples_:
# print("Vertex: {}, Is sample data".format(vert.idx_))
# else:
# print("Vertex: {}, Not sample data".format(vert.idx_))
# print("============================================")
print("The training data is {}".format(len(self.training_x_)))
