def SAmethod(max_iter=50):
T, T_min, q = 100, 1e-250, 0.99
x0 = np.array(lb) + 0.1
start_time = datetime.now()
sa = SA(func=finallFunction,
lb=lb,
ub=ub,
x0=x0,
L=max_iter,
T=T,
T_min=T_min,
q=q,
debug=True,
max_iter=max_iter) #只求解最小值
end_time = datetime.now()
print('Itreation numbers is {}, weight is '.format(max_iter) +
str(weight) +
' using time is {}'.format((end_time - start_time).total_seconds()))
best_x, best_y = sa.run()
Y_history = sa.best_y_history
tm = time.localtime(time.time())
tm_str = '{}-{}-{} {}:{}:{} '.format(tm[0], tm[1], tm[2], tm[3], tm[4],
tm[5])
return best_x, best_y, Y_history, sa
def en(code):
pop, s1, s2, t_max, t_min, l, stay = code
sa = SA(func=obj,
dim=2,
pop=pop,
x0=[s1, s2],
T_max=10**t_max,
T_min=10**t_min,
L=l,
max_stay_counter=stay)
best_x, best_y = sa.run()
return best_y
def SAmethod(max_iter=300, L=50, T=100, T_min=1e-5, q=0.95):
lb = lb
ub = ub
x0 = np.random.random(
size=np.array(lb).shape) * (np.array(ub) - np.array(lb)) + np.array(lb)
sa = SA(func=calculEffFunc,
lb=lb,
ub=ub,
x0=x0,
L=L,
T=T,
T_min=T_min,
quench=q,
debug=True,
max_iter=max_iter) #slove lowest
best_x, best_y = sa.run()
Y_history = sa.best_y_history # each temperature best solutions
return best_x, best_y, Y_history, Y_history
c2=0.5)
pso.run()
print('\n带约束的粒子群算法\n')
print('best_x is ', pso.gbest_x, 'best_y is', pso.gbest_y)
# plt.plot(pso.gbest_y_hist)
# plt.show()
pso = PSO(func=func3, dim=3)
pso.run()
print('\n不带约束的粒子群算法\n')
print('best_x is ', pso.gbest_x, 'best_y is', pso.gbest_y)
'''
模拟退火算法
'''
sa = SA(func=func3,
x0=[1, 1, 1],
T_max=1,
T_min=1e-9,
L=300,
max_stay_counter=150)
best_x, best_y = sa.run()
print('\n模拟退火算法用于多元函数优化\n')
print('best_x:', best_x, 'best_y', best_y)
# plt.plot(pd.DataFrame(sa.best_y_history).cummin(axis=0))
# plt.show()
sa_tsp = SA_TSP(func=getTotalDistance,
x0=range(NUM_POINT),
T_max=100,
T_min=1,
L=10 * NUM_POINT)
best_points, best_distance = sa_tsp.run()
print('\n模拟退火算法解决TSP问题（旅行商问题）\n')
print(best_points, '\nBest Distance:', best_distance)
from sko.SA import SA demo_func = lambda x: x[0]**2 + (x[1] - 0.05)**2 + x[2]**2 sa = SA(func=demo_func, x0=[1, 1, 1]) x_star, y_star = sa.run() print(x_star, y_star) # %% Plot the result import matplotlib.pyplot as plt import pandas as pd plt.plot(pd.DataFrame(sa.f_list).cummin(axis=0)) plt.show()
demo_func = lambda x: x[0]**2 + (x[1] - 0.05)**2 + x[2]**2
# %% Do SA
from sko.SA import SA
sa = SA(func=demo_func,
x0=[1, 1, 1],
T_max=1,
T_min=1e-9,
q=0.99,
L=300,
max_stay_counter=150)
best_x, best_y = sa.run()
print('best_x:', best_x, 'best_y', best_y)
# %% Plot the result
import matplotlib.pyplot as plt
import pandas as pd
plt.plot(pd.DataFrame(sa.best_y_history).cummin(axis=0))
plt.show()
def seir_model(N, Initial_data, data, name):
'''
This function will return fitting and prediction number of COVID-19
:param
Input: N --> The total number of people that is affected by the virus
Initial_data --> data of first day we are gonna to model, in the form of [suspected people, exposed people, infected people, recovered people]
data --> Number of infected people data extractd from formal resource
name --> the filename want to store the data in
Output : data is written to txt file and stored as well.
'''
assert isinstance(Initial_data, list) and all(isinstance(i, int) for int in Initial_data) len(Initial_data) = 4
assert isinstance(data, list) and all(isinstance(i, int) for int in data)
length = len(data)
def demo_func(x):
'''
This function is for choosing parameter.
:param
Input: x --> parameters that we need to choose
Output: least square error is the evaluator for parameter
'''
beta,beta2,alpha = x
#Infection rate, Infection rate during Incubation， Latency conversion rate
nums = Initial_data
predicted_data = []
x = np.array(x).T
least_square_error = 0
# latency conversion rate can not be larget than 1
# infection rate should be larget than Infection rate during Incubation
# parameter restriction
if(alpha < 0):
return float('inf')
if(beta < beta2):
return float('inf')
if(beta2 < 0):
return float('inf')
for i in range(length):
# use 4 functions to iterate in SEIR model
temp = np.array([[1, -beta2 / N * nums[0], -beta / N * nums[0], 0],
[beta / N * nums[2], 1 - alpha, 0, 0],
[0, alpha, 1, 0],
[0, 0, 0,1 ]])
nums = temp.dot(nums)
predicted_data.append(nums[2])
least_square_error += (predicted_data[i] - data[i]) ** 2
return least_square_error
# calculate parameters using Simulated annealing
sa = SA(func = demo_func, x0 = [3,0,0])
x_star, y_star = sa.run()
np.savetxt('qianqi_canshu.txt', [x_star], delimiter = ',')
# pass parameters to SEIR model
beta,beta2,alpha = x_star
predicted_days = 200
nums = Initial_data
predicted_data= []
recovered = []
x = np.array(x).T
least_square_error =0
for i in range(predicted_days):
# use 4 functions to iterate in SEIR model
temp = np.array([[1, -beta2 / N * nums[0], -beta / N * nums[0], 0],
[beta / N * nums[2], 1 - alpha, 0, 0],
[0, alpha, 1, 0],
[0, 0, 0,1 ]])
nums = temp.dot(nums)
recovered.append(nums[3])
predicted_data.append(nums[2])
recovered_data.append(nums[3])
np.savetxt(name + '_infected.txt', predicted_data, delimiter=',')
np.savetxt(name + '_recovered.txt', recovered_data, delimiter=',')