def main(load_inter_flag=False):
if not load_inter_flag:
real_data = list(pd.read_csv(get_data_path(True))['adcode'].unique())
start_date = date(2020, 1, 24)
real_data1 = pd.read_csv(get_data_path(True))
history_real = prepareData(real_data1)
rerun_cities = None
for i in range(get_seed_num()):
total_params = pd.read_csv(
os.path.join(os.path.dirname(__file__),
'./params_foreign{}.csv'.format(int(i))))
for ind, city in enumerate(real_data):
print(i, ind, city, str(get_important_date(city)))
x = get_params(total_params, city)
if rerun_cities is None or city in rerun_cities:
run_simulation2(x,
city,
60,
60,
start_date,
get_important_date(city),
history_real,
unob_flow_num=None,
json_name='data_run_foreign{}.json'.format(
int(i)))
# choose the final parameters
max_data, min_data, mean_data, best_data, \
std_data, middle_data, xmin_data, xmax_data, \
xmean_data, xstd_data = load_and_save('./data_run_foreign{}.json', './data_run_foreign_{}.json')
"""
def load_and_save(input_format, output_format, num=None, start_ind=0):
if num is None:
num = get_seed_num()
data_buffer = [
json.load(open(input_format.format(int(i)), 'r'))
for i in range(start_ind, num + start_ind)
]
max_data, min_data, mean_data, best_data, std_data, middle_data, xmin_data, xmax_data, xmean_data, xstd_data = res_analysis(
data_buffer)
with open(output_format.format('min'), 'w') as f:
f.write(json.dumps(min_data))
with open(output_format.format('max'), 'w') as f:
f.write(json.dumps(max_data))
with open(output_format.format('mean'), 'w') as f:
f.write(json.dumps(mean_data))
with open(output_format.format('best'), 'w') as f:
f.write(json.dumps(best_data))
with open(output_format.format('std'), 'w') as f:
f.write(json.dumps(std_data))
with open(output_format.format('middle'), 'w') as f:
f.write(json.dumps(middle_data))
with open(output_format.format('xmin'), 'w') as f:
f.write(json.dumps(xmin_data))
with open(output_format.format('xmax'), 'w') as f:
f.write(json.dumps(xmax_data))
with open(output_format.format('xmean'), 'w') as f:
f.write(json.dumps(xmean_data))
with open(output_format.format('xstd'), 'w') as f:
f.write(json.dumps(xstd_data))
return max_data, min_data, mean_data, best_data, std_data, middle_data, xmin_data, xmax_data, xmean_data, xstd_data
def prepare_data_china(load_inter_flag=False):
real_data = pd.read_csv(get_data_path())['adcode'].unique()
rerun_cities = None
if rerun_cities is not None:
real_data = rerun_cities.copy()
start_date = date(2020, 1, 11)
real_data1 = pd.read_csv(get_data_path())
history_real = prepareData(real_data1)
if not load_inter_flag:
print('re-simulate the progress')
province_travel_dict = flowHubei()
for i in range(get_seed_num()):
total_params = pd.read_csv(
os.path.join(os.path.dirname(__file__),
'./params{}.csv'.format(int(i))))
unob_flow_num = initHubei(
get_params(total_params, 420000),
start_date,
important_date=[get_important_date(420000)],
travel_from_hubei=province_travel_dict)
for ind, city in enumerate(real_data):
print(i, ind, city)
x = get_params(total_params, city)
run_simulation2(x,
city,
90,
90,
start_date,
get_important_date(city),
history_real,
unob_flow_num=unob_flow_num,
json_name='data_run{}.json'.format(int(i)))
else:
print('directly load the pre-simulated data')
for i in range(get_seed_num()):
get_total_province('data_run{}.json'.format(int(i)))
# choose the final parameters
max_data, min_data, mean_data, best_data, std_data, middle_data, \
xmin_data, xmax_data, xmean_data, xstd_data = load_and_save(
'./data_run{}.json', './data_run_{}.json')
"""
lst_date = lst_date + timedelta(1)
return unob_flow_num
if __name__ == '__main__':
province_travel_dict = flowHubei()
real_data = pd.read_csv(get_data_path())['adcode'].unique()
province_code_dict = codeDict()
training_end_date = None
x_buffer = []
rerun_list = None
if rerun_list is not None:
old_param_buffer = [
pd.read_csv('params{}.csv'.format(int(i)))
for i in range(get_seed_num())
]
for i in range(get_seed_num()):
global_seed(i)
all_param = {}
if rerun_list is None or 420000 in rerun_list:
x = run_opt(420000,
200000,
start_date=date(2020, 1, 11),
important_dates=[get_important_date(420000)],
repeat_time=1,
training_date_end=training_end_date,
seed=i,
json_name='data_run{}.json'.format(int(i)))
clear_child_process()
all_param[420000] = x
f.write(json.dumps(middle_data))
with open(output_format.format('xmin'), 'w') as f:
f.write(json.dumps(xmin_data))
with open(output_format.format('xmax'), 'w') as f:
f.write(json.dumps(xmax_data))
with open(output_format.format('xmean'), 'w') as f:
f.write(json.dumps(xmean_data))
with open(output_format.format('xstd'), 'w') as f:
f.write(json.dumps(xstd_data))
return max_data, min_data, mean_data, best_data, std_data, middle_data, xmin_data, xmax_data, xmean_data, xstd_data
if __name__ == '__main__':
data_buffer = [
json.load(open('./data_run_foreign{}.json'.format(int(i)), 'r'))
for i in range(get_seed_num())
]
cities = [900003, 900004, 900005, 900006, 900007, 900008, 900009, 900010]
#data_buffer = [json.load(open('./data_run{}.json'.format(int(i)), 'r')) for i in range(get_seed_num())]
#cities = [420000]
max_data, min_data, mean_data, best_data, std_data, middle_data, xmin_data, xmax_data, xmean_data, xstd_data = res_analysis(
data_buffer)
pbnum = 3
for iitem in cities:
city = str(iitem)
print(it_code_dict()[int(city)])
x = [data_buffer[i]['x'][city] for i in range(get_seed_num())]
final_cum = [
data_buffer[i]['sim_cum_confirmed_deduction_s1'][city][-1]
for i in range(get_seed_num())
]
repeat=repeat_time, seed=seed, intermediate_freq=10000, init_samples=init_samples,
loss_ord=loss_ord)
print('best_solution: x = ', x, 'y = ', y)
simulator.set_param(x)
run_simulation(x, city, 60, 60, start_date, get_important_date(city), unob_flow_num=unob_flow_num, json_name=json_name)
return x
if __name__ == '__main__':
real_data = list(pd.read_csv(get_data_path(True))['adcode'].unique())
province_code_dict = it_code_dict()
rerun_list = None
old_param_buffer = None
training_end_date = None
if rerun_list is not None:
old_param_buffer = [pd.read_csv('params_foreign{}.csv'.format(int(i))) for i in range(get_seed_num())]
for i in range(get_seed_num()):
all_param = {}
for ind, item in enumerate(real_data):
print(i, ind, item, province_code_dict[item])
if rerun_list is None or item in rerun_list:
touch_range = [0, 0.33333]
iso_range = None
x = run_opt(item, 80000, start_date=date(2020, 2, 4), important_dates=[get_important_date(item)],
infectratio_range=[0.0, 0.05], dummy_range=[0, 400], unob_flow_num=None, repeat_time=1,
seed=i, json_name='data_run_foreign{}.json'.format(int(i)), loss_ord=1.5, touch_range=touch_range,
iso_range=iso_range, training_end_date=training_end_date)
all_param[item] = x
clear_child_process()
else:
all_param[item] = list(old_param_buffer[i][str(item)])