How to fix error "Model parameter must be a string" in Run a Neural network sample Code

hello in this sample code this error " Model parameter must be a string" occurs when run section for plot regression graphs for 3 data type (train, validation,test)

codes :

data=xlsread('sarvak_normalized.xlsx');  % Input File
corrplot(data)
input=[1:9]; % Input Layer
p=data(:,input);
output=[10:11];                        % Output Layer
t=data(:,output);
p=p'; t=t';                         % Transposing Matrices

% t=log(t);
% Defining Validation Dataset
trainRatio1=.6;
valRatio1=.2;
testRatio1=.2;

%%Network Definition

nnn1=5;                             % First Number of Neurons in Hidden Layer
nnnj=5;                             % Jump in Number of Neurons in Hidden Layer
nnnf=100;                           % Last Number of Neurons in Hidden Layer

% net1.trainparam.lr=0.1;
% net1.trainParam.epochs=500;

% Training Network

it=20;                                             % Max Number of Iteration
ii=0;
netopt{:}=1:nnnf;
for nnn=nnn1:nnnj:nnnf
    ii=ii+1; nnn
    net1=newff(p,t,[nnn nnn],{'purelin','purelin'},'traingd'); % For more functions see: 'Function Reference' in 'Neural Network Toolbox' of Matlab help

      evalopt(ii)=1000;

      for i=1:it
          [net1,tr,y,et]=train(net1,p,t);             % Training
          net1.divideParam.trainRatio=trainRatio1;
          net1.divideParam.valRatio=valRatio1;
          net1.divideParam.testRatio=testRatio1;
          estval=sim(net1,p(:,tr.valInd)); 
          eval=mse(estval-t(:,tr.valInd));
          if  eval<evalopt(ii)
              netopt{(ii)}=net1; tropt(ii)=tr; evalopt(ii)=eval;
          end
      end
  end

plot(nnn1:nnnj:nnnf,evalopt)
%%Output
%clear
%load('run1');

nn=17

ptrain=p(:,tropt(nn).trainInd);     ttrain=t(:,tropt(nn).trainInd);     esttrain=sim(netopt{nn},ptrain);
ptest=p(:,tropt(nn).testInd);       ttest=t(:,tropt(nn).testInd);       esttest=sim(netopt{nn},ptest);
pval=p(:,tropt(nn).valInd);         tval=t(:,tropt(nn).valInd);         estval=sim(netopt{nn},pval);
estwhole=sim(netopt{nn},p);

% ttrain=exp(ttrain); ttest=exp(ttest); tval=exp(tval); t=exp(t);
% esttrain=exp(esttrain); esttest=exp(esttest); estval=exp(estval); estwhole=exp(estwhole);

plotregression(ttrain,esttrain,'Train',tval,estval,'Validation',...
    ttest,esttest,'Test',t,estwhole,'Whole Data');

[Greg Heath]

 size(input)  =  [ I  N ] = [ 9 N ]
 size(target) = [ O N ] = [ 2 N ]
 Ntrneq       = 0.6*O*N ~ 1.2*N

 1. What is N ?
 2. What versions of MATLAB and NN Toolbox do you have?
   ---- Using NEWFF suggests your version of NNToolbox is obsolete 
   ---- This can be verified using the doc and help commands
 3. Why are you using 2 hidden layers??? One is sufficient.
 4. PURELIN IS WORTHLESS IN HIDDEN LAYERS! Only use purelin 
     as the UNSPECIFIED default in the output layer of a regression net!
 5. Why not use the default TRAINLM?
 6. Assign nondefault subset division ratios BEFORE training!
 7. Evalopt is dimension dependent. Better to use a fraction (e.g., <= 0.010) 
     of the average target variance.

Hope this helps.

Greg

[Greg Heath]

COMMENT BY THE AUTHOR ERRONEOUSLY PLACED IN AN ANSWER BOX:

by seyed hosein alhoseiny on 1 Sep 2017

hello this sample code is designed for Estimation of Petrophysical properties of oil Reservoir rock using Logs Values as Input data (9 input variables)

[Greg Heath]

ANOTHER COMMENT ERRONEOUSLY PLACED IN AN ANSWER BOX!

by Rafik on 16 Oct 2017

Please I need the full program could you please share It ? Thanks

THE RESPONSE:

seyed hosein alhoseiny about 18 hours ago hello I wrote full Program in this post. thank you...

[Rafik]

could you please help ? Thanks sayed hocein el hoceiny

[Rafik]

Error is: error using corrplot (line 119)

the value of X is invalidv . observed data is empty.

error corrplot (data)

Answer 1

[Rafik]

Please I need the full program could you please share It ? Thanks

[seyed hosein alhoseiny]

hello I wrote full Program in this post. thank you...

[Greg Heath]

ANOTHER COMMENT ERRONEOUSLY PLACED IN AN ANSWER BOX!

 by Rafik on 16 Oct 2017

Please I need the full program could you please share It ? Thanks

THE RESPONSE BY SEYID (above)

hello I wrote full Program in this post. thank you...

[Rafik]

Thank you very much