split data into 5 train and test data

Hello , i'm trying to split my data that has 392 row and 9 colums into 5 train and test datas to do a cross validation on an ANFIS

since i just want to do it on my dataset i thought about creating

traindata1= the rows from 1 to 312 and testdata1 = from 312 to 392

traindata 2 = rows from .....

is there any function to do it automatically , if no how to copy a certain number of rows to a table ?

Answer 1

[the cyclist]

You can use the cvpartition function to do this, if you have the Statistics and Machine Learning Toolbox.

If you don't have that toolbox, you might want to use randperm instead of just choosing the first rows for training, and the rest for testing, in case the order of the data in your dataset is not already random.

[redha wassim brahimi]

i'll look for it thank you , and about the question on how to copy X rows of a table into another one please ?

[the cyclist]

You can copy from one matrix to another by indexing in.

M = [ 2  3;
      5  7;
     11 13;
     17 19;
     23 29];

M1 = M([1,3],:)

M2 = M([2,4,5],:)

You might want to watch the MATLAB Onramp tutorial for basics like this.

[redha wassim brahimi]

ok thank you