to calculate minimum or maximum value of dataset

I want to calculate minimum or maximum value of three divisions of set as shown by separation line or described by diff value of fifth coloumn. please help

x_train=            [5.1  3.5  1.4  0.2  1
                    4.9  3.0  1.4  0.2  1
                    4.7  3.2  1.3  0.2  1
                   %...........................
                    6.5  2.8  4.6  1.5  2
                    5.7  2.8  4.5  1.3  2
                    6.3  3.3  4.7  1.6  2
                    4.9  2.4  3.3  1.0  2
                    %..............................
                    7.3  2.9  6.3  1.8  3
                    6.7  2.5  5.8  1.8  3
                    7.2  3.6  6.1  2.5  3
                    6.5  3.2  5.1  2.0  3]
[u1,u2,u3,u4,y]=x_train;
x=[u1 u2 u3 u4 y];
for k=1:3
  while x(:,5)==k
    w_low(k)=min(x(:,1));
    w_up(k)=max(x(:,1));
  end
end

[Azzi Abdelmalek]

What is x?

[Image Analyst]

He says what x is, but more importantly, what is u1,u2,u3,u4, & y ??? That's not standard MATLAB code. Do you want each of those to be the 2D array x_train?

Answer 1

[Image Analyst]

Perhaps you mean this:

x_train=            [5.1  3.5  1.4  0.2  1
                    4.9  3.0  1.4  0.2  1
                    4.7  3.2  1.3  0.2  1
                   %...........................
                    6.5  2.8  4.6  1.5  2
                    5.7  2.8  4.5  1.3  2
                    6.3  3.3  4.7  1.6  2
                    4.9  2.4  3.3  1.0  2
                    %..............................
                    7.3  2.9  6.3  1.8  3
                    6.7  2.5  5.8  1.8  3
                    7.2  3.6  6.1  2.5  3
                    6.5  3.2  5.1  2.0  3]
% Find unique numbers in column 5.
possibleValues = unique(int32(x_train(:, 5)))
counter = 1;
for k=1:length(possibleValues)
  thisValue = possibleValues(k);
  fprintf('\nFor column #5 = %d\n', thisValue);
  % Get all rows with this number in column 5
  matchingRows = x_train(:,5) == thisValue
  % Find the min and max in column 1 of that chunk.
  w_low(counter)=min(x_train(matchingRows,1));
  w_up(counter)=max(x_train(matchingRows,1));
  counter = counter + 1;
end
% Display results in command window
fprintf('\nFinal Results:\n');
w_low
w_up

In the command window:

Final Results:
w_low =  4.7       4.9      6.5
w_up =   5.1       6.5      7.3

[Parul]

thanx...

Answer 2

[Andrei Bobrov]

x_s = sortrows(x_train,[5,1]);
c = accumarray(x_s(:,5),x_s(:,1),[],@(x){x([1,end])});
out = cat(2,c{:});

or

c = accumarray(x_train(:,5),x_train(:,1),[],@(x){[min(x) max(x)]});
out = cat(1,c{:});