def create_estimation_dataset(G,path_list_collection,id_list,trip_times,master_config): output_config=master_config.output_config choice_set_config=master_config.choice_set_config est_file=open(output_config['estimation_data'],'w') est_writer=csv.writer(est_file,lineterminator='\r') if output_config['path_size']: path_size_alias=['path_size'] else: path_size_alias=[] est_writer.writerow(['occ','alt','trip_id','chosen']+output_config['aliases']+path_size_alias) path_size_data=path_size(G,path_list_collection,choice_set_config) for occ_idx in range(len(path_list_collection)): for alt_idx in range(len(path_list_collection[occ_idx])): path=path_list_collection[occ_idx][alt_idx] values=[] for i in range(len(output_config['variables'])): if output_config['variables'][i] in master_config['time_dependent_relation']: key=get_time_dependent_variable(output_config['variables'][i],trip_times[id_list[occ_idx]],master_config['time_dependent_relation']) else: key=output_config['variables'][i] values.append(str(path_trace(G,path,key,output_config['trace_funs'][i],output_config['final_funs'][i],output_config['weights'][i]))) if output_config['path_size']: values.append(path_size_data[occ_idx][alt_idx]) est_writer.writerow([str(occ_idx),str(alt_idx),str(id_list[occ_idx]),str(alt_idx==0)]+values) est_file.close()
def ds_generate_master(G,chosen,choice_set_config,link_randomizer,time_dependent_relation,trip_time,ext_bound):
config=choice_set_config
source=chosen[0]
target=chosen[-1]
if ext_bound is not None:
bounding_box=ext_bound
else:
bounding_box=find_coef_bounding_box(G,source,target,config,time_dependent_relation,trip_time)
num_draws=config['ds_num_draws']
varcoef={}
master_set=[]
for i in range(num_draws):
#sample random coefficients from bounding box
for prelim_key in bounding_box:
key=get_time_dependent_variable(prelim_key,trip_time,time_dependent_relation)
if config['log_prior']:
varcoef[key]=exp(random.uniform(log(bounding_box[prelim_key][0]),log(bounding_box[prelim_key][1])))
else:
varcoef[key]=random.uniform(bounding_box[prelim_key][0],bounding_box[prelim_key][1])
to_iter=1
if config['randomize_after']:
to_iter=config['randomize_after_iters']
for i in range(to_iter):
#perform generalized cost shortest path search
master_set.append(bidirectional_dijkstra(G,source,target,varcoef,config['weights'],link_randomizer)[1])
return master_set
def create_holdback_prediction_dataset(G, path_list_collection, id_list,
trip_times, master_config,
chosen_overlap):
output_config = master_config.output_config
choice_set_config = master_config.choice_set_config
est_file = open(output_config['estimation_data'], 'w')
est_writer = csv.writer(est_file, lineterminator='\r')
if output_config['path_size']:
path_size_alias = ['path_size']
else:
path_size_alias = []
est_writer.writerow(['occ', 'alt', 'trip_id', 'chosen'] +
output_config['aliases'] + path_size_alias +
['overlap'])
sans_chosen = copy.deepcopy(path_list_collection)
for path_list in sans_chosen:
path_list.pop(0)
path_size_data = path_size(G, sans_chosen, choice_set_config)
for occ_idx in range(len(path_list_collection)):
for alt_idx in range(len(path_list_collection[occ_idx])):
path = path_list_collection[occ_idx][alt_idx]
values = []
for i in range(len(output_config['variables'])):
if output_config['variables'][i] in master_config[
'time_dependent_relation']:
key = get_time_dependent_variable(
output_config['variables'][i],
trip_times[id_list[occ_idx]],
master_config['time_dependent_relation'])
else:
key = output_config['variables'][i]
values.append(
str(
path_trace(G, path, key,
output_config['trace_funs'][i],
output_config['final_funs'][i],
output_config['weights'][i])))
if output_config['path_size']:
if alt_idx == 0:
values.append(0)
else:
values.append(path_size_data[occ_idx][alt_idx - 1])
values.append(chosen_overlap[occ_idx][alt_idx])
est_writer.writerow([
str(occ_idx),
str(alt_idx),
str(id_list[occ_idx]),
str(alt_idx == 0)
] + values)
est_file.close()
def find_coef_bounding_box(G,source,target,choice_set_config,time_dependent_relation,trip_time):
final_bound={}
config=choice_set_config
verbose=False#config['verbose']
for prelim_key in config['variables']:
key=get_time_dependent_variable(prelim_key,trip_time,time_dependent_relation)
if key==config['ref']:
final_bound[key]=[1,1]
continue
vc={config['ref']:1}
if key in config['median_compare']:
for compare_key in final_bound:
if key not in config['median_compare']:
if config['log_prior']:
vc[compare_key]=exp( (log(final_bound[compare_key][0])+log(final_bound[compare_key][1]))/2)
else:
vc[compare_key]=(final_bound[compare_key][0]+final_bound[compare_key][1])/2
link_randomizer=None
if key in config['randomize_compare']:
if not config['randomize_after']:
raise Exception, "randomize_compare not allowed without randomize_after"
link_randomizer=config['randomize_after_dev']
the_seed=random.randint(0,sys.maxint)
if verbose:
print vc
cur_wgt=None
if key in config['weights']:
cur_wgt=config['weights'][key]
myfun=lambda cur_coef: path_trace(
G,
bidirectional_dijkstra(G,source,target,dict(vc,**{key:cur_coef}),config['weights'],link_randomizer)[1],
key, 'sum', wgtvar=cur_wgt
)
coef_min_low = coef_min_high = log(config['ranges'][prelim_key][0])
coef_max_low = coef_max_high = log(config['ranges'][prelim_key][1])
val_min_low = val_min_high = myfun(exp(coef_min_low))
val_max_low = val_max_high = myfun(exp(coef_max_low))
if verbose:
print key, "coef_min_low:", exp(coef_min_low)
print key, "coef_max_low:", exp(coef_max_low)
print key, "val_min_low:", val_min_low
print key, "val_max_low:", val_max_low
if val_min_low == val_max_low:
if verbose:
print key, "no range... ignoring"
continue
if verbose:
print key, "coef_min_low:", exp(coef_min_low)
print key, "coef_max_low:", exp(coef_max_low)
print key, "val_min_low:", val_min_low
print key, "val_max_low:", val_max_low
while True:
random.seed(the_seed)
coef_mid_low = (coef_min_low+coef_max_low)/2
coef_mid_high = (coef_min_high+coef_max_high)/2
val_mid_low = myfun(exp(coef_mid_low))
val_mid_high = myfun(exp(coef_mid_high))
if verbose:
print key, "coef_mid_low:", exp(coef_mid_low)
print key, "coef_mid_high:", exp(coef_mid_high)
print key, "val_mid_low:", val_mid_low
print key, "val_mid_high:", val_mid_high
if val_mid_low==val_min_low:
coef_min_low=coef_mid_low
else:
coef_max_low=coef_mid_low
val_max_low=val_mid_low
if val_mid_high==val_max_high:
coef_max_high=coef_mid_high
else:
coef_min_high=coef_mid_high
val_min_high=val_mid_high
if verbose:
print key, "coef_low:", (exp(coef_min_low),exp(coef_max_low))
print key, "val_low:", (val_min_low,val_max_low)
print key, "coef_high:", (exp(coef_min_high),exp(coef_max_high))
print key, "val_high:", (val_min_high,val_max_high)
if (coef_max_low-coef_min_low)<config['tolerance']:
break
if coef_mid_low!=coef_mid_high:
final_bound[key]=[exp(coef_mid_low),exp(coef_mid_high)]
if verbose:
print final_bound
return final_bound
