Search code examples
pythonnon-linear-regressiongekko

GEKKO multivariate nonlinear regression

df = pd.read_csv("data.csv")

xm1 = np.array(df["T"]) #Dep Var 1
xm2 = np.array(df["t"])  #Dep Var 2
xm3 = np.array(df["L"]) #Dep Var 3
ym = np.array(df["S"])  #Indep Var

# GEKKO model
m = GEKKO()
a = m.FV(lb=-100.0,ub=100.0)
b = m.FV(lb=-100.0,ub=100.0)
c = m.FV(lb=-100.0,ub=100.0)
d = m.FV(lb=-100.0,ub=100.0)
e = m.FV(lb=-100.0,ub=100.0)
f = m.FV(lb=-100.0,ub=100.0)
g = m.FV(lb=-100.0,ub=100.0)
x1 = m.Param(value=xm1)
x2 = m.Param(value=xm2)
x3 = m.Param(value=xm3)
z = m.Param(value=ym)
y = m.Var()
m.Equation(y == a+x1*b+x2*c+x3*d+e*(x1**2)+f*(x2**2)+g*(x3**2)
m.Obj(((y-z)/z)**2)

I am getting a SyntaxError: invalid syntax on m.Obj(((y-z)/z)**2). I have followed APMonitor.com's code for this. This code works perfectly for the example there. But it shows this syntax error when I modify it to fit my regression problem with more FVs. Syntax error pic attached

Not really sure what's wrong with this. Any help would be appreciated.

Solution

  • The error occurs due to this line:

    m.Equation(y == a+x1*b+x2*c+x3*d+e*(x1**2)+f*(x2**2)+g*(x3**2)

    there is extra parenthesis before y declaration