Comparing Biweekly HFMD Cases with and without using the Squared Error Objective & L1-Norm Objective - gekko

Question

I wish to model the biweekly HFMD cases in Malaysia.
Then, I want to show that the model using the Squared Error Objective and L1-Norm Objective can better model the biweekly HFMD cases than the model without objectives.
My question is, is it possible to model the biweekly HFMD cases without using the Squared Error Objective and L1-Norm Objective?
With this, I have attached the coding below:
from gekko import GEKKO
import numpy as np
import matplotlib.pyplot as plt
m1 = GEKKO(remote=False)
m2 = GEKKO(remote=False)
m = m1
# Known parameters
nb = 26 # Number of biweeks in a year
ny = 3 # Number of years
biweeks = np.zeros((nb,ny*nb+1))
biweeks[0][0] = 1
for i in range(nb):
for j in range(ny):
biweeks[i][j*nb+i+1] = 1
# Write csv data file
tm = np.linspace(0,78,79)
# case data
# Malaysia weekly HFMD data from the year 2013 - 2015
cases = np.array([506,506,700,890,1158,1605,1694,1311,1490,1310,1368,\
1009,1097,934,866,670,408,481,637,749,700,648,710,\
740,627,507,516,548,636,750,1066,1339,1565,\
1464,1575,1759,1631,1601,1227,794,774,623,411,\
750,1017,976,1258,1290,1546,1662,1720,1553,1787,1291,1712,2227,2132,\
2550,2140,1645,1743,1296,1153,871,621,570,388,\
347,391,446,442,390,399,421,398,452,470,437,411])
data = np.vstack((tm,cases))
data = data.T
# np.savetxt('measles_biweek_2.csv',data,delimiter=',',header='time,cases')
np.savetxt('hfmd_biweek_2.csv',data,delimiter=',',header='time,cases')
# Load data from csv
# m.time, cases_meas = np.loadtxt('measles_biweek_2.csv', \
m.time, cases_hfmd = np.loadtxt('hfmd_biweek_2.csv', \
delimiter=',',skiprows=1,unpack=True)
# m.Vr = m.Param(value = 0)
# Variables
# m.N = m.FV(value = 3.2e6)
# m.mu = m.FV(value = 7.8e-4)
# m.N = m.FV(value = 3.11861e7)
# m.mu = m.FV(value = 6.42712e-4)
m.N = m.FV(value = 3.16141e7) # Malaysia average total population (2015 - 2017)
m.mu = m.FV(value = 6.237171519e-4) # Malaysia scaled birth rate (births/biweek/total population)
m.rep_frac = m.FV(value = 0.45) # Percentage of underreporting
# Beta values (unknown parameters in the model)
m.beta = [m.FV(value=1, lb=0.1, ub=5) for i in range(nb)]
# Predicted values
m.S = m.SV(value = 0.162492875*m.N.value, lb=0,ub=m.N) # Susceptibles (Kids from 0 - 9 YO: 5137066 people) - Average of 94.88% from total reported cases
m.I = m.SV(value = 7.907863896e-5*m.N.value, lb=0,ub=m.N) #
# m.V = m.Var(value = 2e5)
# measured values
m.cases = m.CV(value = cases_hfmd, lb=0)
# turn on feedback status for CASES
m.cases.FSTATUS = 1
# weight on prior model predictions
m.cases.WMODEL = 0
# meas_gap = deadband that represents level of
# accuracy / measurement noise
db = 100
m.cases.MEAS_GAP = db
for i in range(nb):
m.beta[i].STATUS=1
#m.gamma = m.FV(value=0.07)
m.gamma = m.FV(value=0.07)
m.gamma.STATUS = 1
m.gamma.LOWER = 0.05
m.gamma.UPPER = 0.5
m.biweek=[None]*nb
for i in range(nb):
m.biweek[i] = m.Param(value=biweeks[i])
# Intermediate
m.Rs = m.Intermediate(m.S*m.I/m.N)
# Equations
sum_biweek = sum([m.biweek[i]*m.beta[i]*m.Rs for i in range(nb)])
# m.Equation(m.S.dt()== -sum_biweek + m.mu*m.N - m.Vr)
m.Equation(m.S.dt()== -sum_biweek + m.mu*m.N)
m.Equation(m.I.dt()== sum_biweek - m.gamma*m.I)
m.Equation(m.cases == m.rep_frac*sum_biweek)
# m.Equation(m.V.dt()==-m.Vr)
# options
m.options.SOLVER = 1
m.options.NODES=3
# imode = 5, dynamic estimation
m.options.IMODE = 5
# ev_type = 1 (L1-norm) or 2 (squared error)
m.options.EV_TYPE = 2
# solve model and print solver output
m.solve()
[print('beta['+str(i+1)+'] = '+str(m.beta[i][0])) \
for i in range(nb)]
print('gamma = '+str(m.gamma.value[0]))
# export data
# stack time and avg as column vectors
my_data = np.vstack((m.time,np.asarray(m.beta),m.gamma))
# transpose data
my_data = my_data.T
# save text file with comma delimiter
beta_str = ''
for i in range(nb):
beta_str = beta_str + ',beta[' + str(i+1) + ']'
header_name = 'time,gamma' + beta_str
##np.savetxt('solution_data.csv',my_data,delimiter=',',\
## header = header_name, comments='')
np.savetxt('solution_data_EVTYPE_'+str(m.options.EV_TYPE)+\
'_gamma'+str(m.gamma.STATUS)+'.csv',\
my_data,delimiter=',',header = header_name)
plt.figure(num=1, figsize=(16,8))
plt.suptitle('Estimation')
plt.subplot(2,2,1)
plt.plot(m.time,m.cases, label='Cases (model)')
plt.plot(m.time,cases_hfmd, label='Cases (measured)')
if m.options.EV_TYPE==2:
plt.plot(m.time,cases_hfmd+db/2, 'k-.',\
lw=0.5, label=r'$Cases_{db-hi}$')
plt.plot(m.time,cases_hfmd-db/2, 'k-.',\
lw=0.5, label=r'$Cases_{db-lo}$')
plt.fill_between(m.time,cases_hfmd-db/2,\
cases_hfmd+db/2,color='gold',alpha=.5)
plt.legend(loc='best')
plt.ylabel('Cases')
plt.subplot(2,2,2)
plt.plot(m.time,m.S,'r--')
plt.ylabel('S')
plt.subplot(2,2,3)
[plt.plot(m.time,m.beta[i], label='_nolegend_')\
for i in range(nb)]
plt.plot(m.time,m.gamma,'c--', label=r'$\gamma$')
plt.legend(loc='best')
plt.ylabel(r'$\beta, \gamma$')
plt.xlabel('Time')
plt.subplot(2,2,4)
plt.plot(m.time,m.I,'g--')
plt.xlabel('Time')
plt.ylabel('I')
plt.subplots_adjust(hspace=0.2,wspace=0.4)
name = 'cases_EVTYPE_'+ str(m.options.EV_TYPE) +\
'_gamma' + str(m.gamma.STATUS) + '.png'
plt.savefig(name)
plt.show()

Answer 1

To define a custom objective, use the m.Minimize() or m.Maximize() functions instead of the squared error or l1-norm objectives that are built into the m.CV() objects. To create a custom objective, use m.Var() instead of m.CV() such as:
from gekko import GEKKO
import numpy as np
m = GEKKO()
x = m.Array(m.Var,4,value=1,lb=1,ub=5)
x1,x2,x3,x4 = x
# change initial values
x2.value = 5; x3.value = 5
m.Equation(x1*x2*x3*x4>=25)
m.Equation(x1**2+x2**2+x3**2+x4**2==40)
m.Minimize(x1*x4*(x1+x2+x3)+x3)
m.solve()
print('x: ', x)
print('Objective: ',m.options.OBJFCNVAL)
Here is a similar problem with disease prediction (Measles) that uses m.CV().
import numpy as np
from gekko import GEKKO
import matplotlib.pyplot as plt
# Import Data
# write csv data file
t_s = np.linspace(0,78,79)
# case data
cases_s = np.array([180,180,271,423,465,523,649,624,556,420,\
423,488,441,268,260,163,83,60,41,48,65,82,\
145,122,194,237,318,450,671,1387,1617,2058,\
3099,3340,2965,1873,1641,1122,884,591,427,282,\
174,127,84,97,68,88,79,58,85,75,121,174,209,458,\
742,929,1027,1411,1885,2110,1764,2001,2154,1843,\
1427,970,726,416,218,160,160,188,224,298,436,482,468])
# Initialize gekko model
m = GEKKO()
# Number of collocation nodes
nodes = 4
# Number of phases (years in this case)
n = 3
#Biweek periods per year
bi = 26
# Time horizon (for all 3 phases)
m.time = np.linspace(0,1,bi+1)
# Parameters that will repeat each year
N = m.Param(3.2e6)
mu = m.Param(7.8e-4)
rep_frac = m.Param(0.45)
Vr = m.Param(0)
beta = m.MV(2,lb = 0.1)
beta.STATUS = 1
gamma = m.FV(value=0.07)
gamma.STATUS = 1
gamma.LOWER = 0.05
gamma.UPPER = 0.5
# Data used to control objective function
casesobj1 = m.Param(cases_s[0:(bi+1)])
casesobj2 = m.Param(cases_s[bi:(2*bi+1)])
casesobj3 = m.Param(cases_s[2*bi:(3*bi+1)])
# Variables that vary between years, one version for each year
cases = [m.CV(value = cases_s[(i*bi):(i+1)*(bi+1)-i],lb=0) for i in range(n)]
for i in cases:
i.FSTATUS = 1
i.WMODEL = 0
i.MEAS_GAP = 100
S = [m.Var(0.06*N,lb = 0,ub = N) for i in range(n)]
I = [m.Var(0.001*N, lb = 0,ub = N) for i in range(n)]
V = [m.Var(2e5) for i in range(n)]
# Equations (created for each year)
for i in range(n):
R = m.Intermediate(beta*S[i]*I[i]/N)
m.Equation(S[i].dt() == -R + mu*N - Vr)
m.Equation(I[i].dt() == R - gamma*I[i])
m.Equation(cases[i] == rep_frac*R)
m.Equation(V[i].dt() == -Vr)
# Connect years together at endpoints
for i in range(n-1):
m.Connection(cases[i+1],cases[i],1,bi,1,nodes)#,1,nodes)
m.Connection(cases[i+1],'CALCULATED',pos1=1,node1=1)
m.Connection(S[i+1],S[i],1,bi,1,nodes)
m.Connection(S[i+1],'CALCULATED',pos1=1,node1=1)
m.Connection(I[i+1],I[i],1,bi,1,nodes)
m.Connection(I[i+1],'CALCULATED',pos1=1, node1=1)
# Solver options
m.options.IMODE = 5
m.options.NODES = nodes
m.EV_TYPE = 1
m.options.SOLVER = 1
# Solve
m.Obj(2*(casesobj1-cases[0])**2+(casesobj3-cases[2])**2)
m.solve()
# Calculate the start time of each phase
ts = np.linspace(1,n,n)
# Plot
plt.figure()
plt.subplot(4,1,1)
tm = np.empty(len(m.time))
for i in range(n):
tm = m.time + ts[i]
plt.plot(tm,cases[i].value,label='Cases Year %s'%(i+1))
plt.plot(tm,cases_s[(i*bi):(i+1)*(bi+1)-i],'.')
plt.legend()
plt.ylabel('Cases')
plt.subplot(4,1,2)
for i in range(n):
tm = m.time + ts[i]
plt.plot(tm,beta.value,label='Beta Year %s'%(i+1))
plt.legend()
plt.ylabel('Contact Rate')
plt.subplot(4,1,3)
for i in range(n):
tm = m.time + ts[i]
plt.plot(tm,I[i].value,label='I Year %s'%(i+1))
plt.legend()
plt.ylabel('Infectives')
plt.subplot(4,1,4)
for i in range(n):
tm = m.time + ts[i]
plt.plot(tm,S[i].value,label='S Year %s'%(i+1))
plt.legend()
plt.ylabel('Susceptibles')
plt.xlabel('Time (yr)')
plt.show()