design the function function [x_tr, t_tr, x_te, t_te]= split_tr_te(x, t, eta) that splits the input data {x,t} set into two disjoint data set. in matlab

main.m
function [x_tr, t_tr, x_te, t_te] = split_tr_te(x, t, eta)
%SPLIT_TR_TE: Splits the input data (x, t) into two disjoint datasets.
%   The main dataset is separated into training and testing datasets.
%   The training set is determined by the value of eta.
%   
%   [x_tr, t_tr, x_te, t_te] = split_tr_te(x,t,eta) returns:
%   - x_tr: matrix that contains input data for training.
%   - t_tr: matrix that contains target data for training.
%   - x_te: matrix that contains input data for testing.
%   - t_te: matrix that contains target data for testing.
%   
%   x: matrix of size (D,N), where D is the number of dimensions and N the number of samples
%   t: matrix of size (C,N), where C is the number of classes and N the number of samples
%   eta: percentage of data to use for training (e.g., 0.8 for 80%)
%
%   Example:
%       x = randn(2,100); % 2D feature vectors of 100 samples
%       t = randn(3,100); % 3 classes of 100 samples
%       eta = 0.75; % will use 75% of the data for training
%       [x_tr, t_tr, x_te, t_te] = split_tr_te(x, t, eta);
%
%   Author: John Doe
%   Email: johndoe@example.com

% Check input arguments
if nargin ~= 3
    error('split_tr_te: invalid number of input arguments');
end

% Check values of input
if eta <= 0 || eta >= 1
    error('split_tr_te: eta must be a value between 0 and 1');
end

% Create random permutation of samples
N = size(x, 2);
idx = randperm(N);

% Determine number of samples used for training
Ntr = floor(N * eta);

% Separate the data
x_tr = x(:, idx(1:Ntr));
t_tr = t(:, idx(1:Ntr));
x_te = x(:, idx(Ntr+1:end));
t_te = t(:, idx(Ntr+1:end));
1609 chars
47 lines