Trying to train a k-means clustering algorithm

Hello, I'm trying to follow this example to training a k-means clustering algorithm for a data set of my own. My attached data file is a 73x2 double. I am running into trouble with these specific lines in the example:

x1 = min(X(:,1)):0.01:max(X(:,1));
x2 = min(X(:,2)):0.01:max(X(:,2));
[x1G,x2G] = meshgrid(x1,x2);
XGrid = [x1G(:),x2G(:)]; % Defines a fine grid on the plot

Specifically, I keep getting errors that the arrays I am trying to create exceed the maximum array size preference. I'm not really sure how to manipulate the arguments for x1 and x2 such that they properly fit my data and don't give extremely large matrices. The meshgrid command especially is giving me trouble, as I get the error : Error using repmat Requested 536389556x21511164 (85967508.8GB) array exceeds maximum array size preference.

Any help would be greatly appreciated!

Answer 1

[Von Duesenberg]

Your numbers are much much bigger than those of the original example. So you should increase the step size between your min and max value before you create the grid. For example:

x1 = min(X(:,1)):10e7:max(X(:,1));
x2 = min(X(:,2)):10e7:max(X(:,2));

[Josh Hershman]

Thank you so much!