We Keep Coding

Parameter Optimization Using Minimize in Python

I have written the following two functions to calibrate a model :
The main function is:
def function_Price(para,y,t,T,tau,N,C):
# y= price array
# C = Auto and cross correlation array
# a= paramters need to be calibrated
a=para[0:]
temp=0
for j in range(N):
price_j = a[j]*C[j]*P[t:T-tau,j]
temp=temp+price_j
Price=temp
return Price
The objective function is :
def GError_function_Price(para,y,k,t,T,tau,N,C):
# k is the price need to be fitted
return sum((function_Price(para,y,t,T,tau,N,C)-k[t+tau:T]) ** 2)
Now, I am calling these two functions to do the optimization of the model:
import numpy as np
from scipy.optimize import minimize
# Prices (example)
y = np.array([[1,2,3,4,5,4], [4,5,6,7,8,9], [6,7,8,7,8,6], [13,14,15,11,12,19]])
# Correaltion (example)
Corr= np.array([[1,2,3,4,5,4], [4,5,6,7,8,9], [6,7,8,7,8,6], [13,14,15,11,12,19],[1,2,3,4,5,4],[6,7,8,7,8,6]])
# Define
tau=1
Size = y.shape
N = Size[1]
T = Size[0]
t=0
# initial Values
para=np.zeros(N)
# Bounds
B = np.zeros(shape=(N,2))
for n in range(N):
B[n][0]= float('-inf')
B[n][1]= float('inf')
# Calibration
A = np.zeros(shape=(N,N))
for i in range (N):
k=y[:,i] #fitted one
C=Corr[i,:]
parag=minimize(GError_function_Price,para,args=(y,Y,t,T,tau,N,C),method='SLSQP',bounds=B)
A[i,:]=parag.x
Once, I run the model, It should produce an N by N array of optimized values of paramters. But, except for the first column, it keeps zeros for the rest. Something is wrong.
Can you help me fix the problem, please?
I know how to do it in Matlab.
The following is Matlab Code :
main function
function Price=function_Price(para,P,t,T,tau,N,C)
a=para(:,:);
temp=0;
for j=1:N
price_j = a(j).*C(j).*P(t:T-tau,j);
temp=temp+price_j;
end
Price=temp;
end
The objective function:
function gerr=GError_function_Price(para,P,Y,t,T,tau,N,C)
gerr=sum((function_Price(para,P,t,T,tau,N,C)-Y(t+tau:T)).^2);
end
Now, I call these two functions in the following way:
P = [1,2,3,4,5,4;4,5,6,7,8,9;6,7,8,7,8,6;13,14,15,11,12,19];
AutoAndCrossCorr= [1,2,3,4,5,4;4,5,6,7,8,9;6,7,8,7,8,6;13,14,15,11,12,19;1,2,3,4,5,4;6,7,8,7,8,6];
tau=1;
Size = size(P);
N =6;
T =4;
t=1;
for i=1:N
Y=P(:,i); % fitted one
C=AutoAndCrossCorr(i,:);
para=zeros(1,N);
lb= repmat(-inf,N,1);
ub= repmat(inf ,N,1);
parag=fminsearchbnd(#(para)abs(GError_function_Price(para,P,Y,t,T,tau,N,C)),para,lb,ub);
a(i,:)=parag;
end

The problem seems to be that you're passing the result of a function call to minimize, rather than the function itself. The arguments get passed by the args parameter. So instead of:
minimize(GError_function_Price(para,y,k,t,T,tau,N,C),para,method='SLSQP',bounds=B)
the following should work
minimize(GError_function_Price,para,args=(y,k,t,T,tau,N,C),method='SLSQP',bounds=B)

Using setTermCriteria of cv2 and svm

I am trying to use setTermCriteria with SVM. But when I use it I am getting below error:
AttributeError: 'cv2.ml_SVM' object has no attribute 'setTermCritera_MAX_ITER'
This is how I am using it
svm.setTermCritera_MAX_ITER=10000
svm.setTermCriteria_EPS = 1e-3
I am not getting error but not finding it useful when I use it below way:
cv2.setTermCritera_MAX_ITER=10000
cv2.setTermCriteria_EPS = 1e-3
When I try below method
svm.setTermCriteria(10000)
SystemError: new style getargs format but argument is not a tuple
Which is the right way to use it in Python with OpenCV

The error message is clear, a tuple is needed. Let's see the default value:
svm = cv2.ml.SVM_create()
svm.getTermCriteria()
returns (3, 1000, 1.1920928955078125e-07). So if you want to set only the maximum number of iterations should call:
svm.setTermCriteria((cv2.TermCriteria_MAX_ITER, 10000, 0))
and if want to keep the same epsilon criterion and also set max iter:
svm.setTermCriteria((cv2.TermCriteria_MAX_ITER + cv2.TermCriteria_EPS, 10000, 1.1920928955078125e-07))

pasing arguments in global optimization in scipy.optimize

I am trying to solve an optimization problem with scipy global optimization. I am using differential evolution.
code
def objective(x,*args):
x = np.append(x,args)
res = MLmodel.predict(x)
return res
fun_history = []
x_values = []
def callback(x,convergence):
fobj = objective(x)
x_values.append(x)
fun_history.append(fobj)
bounds = [(5.5,8.8),(29,40)]
load = (50,)
res = optimize.differential_evolution(objective,bounds,args=load,disp=True,callback = callback)
My objective function takes these three parameters as input and gives an output. I want to optimize on only the first two parameters. So the third parameter I am passing as an argument.
When I run the optimizer I get an error after the first run, which says
ValueError: operands could not be broadcast together with shapes (1,2) (3,) (1,2)
I guess the argument is not being appended to the x value from the second run.
Can someone help me with how to solve this problem?

Forecasting using ARMAX(0,2) model yields identical results regardless of exogenous variable array being passed

I'm using the statsmodels ARMA functionality to produce a forecast using an ARMAX(0,2) model with 1 exogenous variable and am getting counterintuitive results.
Regardless of the exogenous variables passed to exog in the forecast function (e.g. arma_res.forecast(steps=5, exog=f_exog)), an identical forecast array is returned except for the last element.
For example:
arparams = np.array([0])
maparams = np.array([.65, .35])
arparams = np.r_[1, -arparams]
maparam = np.r_[1, maparams]
nobs = 250
y = arma_generate_sample(arparams, maparams, nobs)
exog = np.random.normal(size=nobs)
arma_mod = sm.tsa.ARMA(y, order=(0, 2), exog=exog)
arma_res = arma_mod.fit(trend='nc', disp=-1)
# Exogenous vars for forecasts
f_exog = [10, 10, 10, 10, 10]
f_exog_2 = [x * 5 for x in f_exog]
forecast_1 = arma_res.forecast(steps=5, exog=f_exog)[0]
forecast_2 = arma_res.forecast(steps=5, exog=f_exog_2)[0]
Produces forecasts of:
array([-0.0884847 , -0.03223685, -0.00190045, -0.00860229, 0.0987421 ])
array([-0.0884847 , -0.03223685, -0.00190045, -0.00860229, 0.49371049])
A notebook with the setup for this is here: https://github.com/dbrodSq/ARMA_Test/blob/master/Statsmodels_forecast_example.ipynb
The above pattern holds regardless of the "steps" parameter. Does anyone have an idea of why?
I believe that ARMAX forecasting for multiple periods is possible with Statsmodels and I don't believe similar problems as above occur as long as k_ar != 0 (i.e. there's at least one AR parameter).
Apologies if I'm missing something obvious and thanks a lot for any help.

Libsvm python error

I'm trying to figure out what is the proper format of a python list to be given as input to a svm_problem function in python. I got the following program from the web, stackoverflow.
I have the following:
from svm import *
x=[ [1,0,1],[-1,0,-1],[1,0,0]]
#x=[ [1,0,1],[-1,0,-1]]
prob = svm_problem( [1,-1],x )
param = svm_parameter(kernel_type = LINEAR, C = 10)
m = svm_model(prob, param)
print m.predict([ 1,1, 1])
It raises an assertion error, says assert failed: assert len(x)==len(y).
But if x=[ [1,0,1],[-1,0,-1]], the program works perfectly. Am I not supposed to give a train-data problem of length more than 2?
Also I don't understand what in x=[[1,0,1],[-1,0,-1]] is a label and what is the data?
Any help is highly appreciated.

svm_problem() takes two parameters: the first parameter of a vector of labels, and the second is a matrix of features. You get this assertion error because you are only specifying 2 labels, [1, -1], as the first parameter in your call to svm_problem.
Example:
y = [1,-1,1,1]
x = [[1,0,1], [-1,0,-1], [1,2,3], [4,5,6]]
prob = svm_problem(y, x)

If you give 3 examples, you need to give the classes for the three inputs as well, so you need to do
prob = svm_problem( [1,1,-1],x )
or something similar.