MATLAB Answers

how to fixed specific results for times of implementation

1 view (last 30 days)
muhammad ismat
muhammad ismat on 4 Mar 2016
Edited: Walter Roberson on 4 Mar 2016
Accuracy=off(data,z)
for i=1:100
n = size(data,1);
data_rand = data(randperm(n),:);
m = ceil(n/20);
k = 1:m:n-m;
test = data_rand(k:k+m-1,:);
train = [data_rand(1:k-1,:); data_rand(k+m:end,:)];
here code for calculate auc
end
accuracy=mean(auc)
the previous code every time change the values of test and train variables, so the value of auc is changed every time.
say the final result is
accuracy=0.7654 and in another time
accuracy=0.6543 and
accuracy=0.4657
but i want to fixed the specific result say 0.6543 i.e if i run previous code more times will give the same results (0.6543)

Answers (1)

MHN
MHN on 4 Mar 2016
Edited: MHN on 4 Mar 2016
Use
rng(1,'twister')
at top of your code. It controls random number generation functions and you will always see the same result as long as you do not change the seed (e.g. 1) and generator method (e.g. twister).

Tags

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!