source: prdatasets/pendigits.m @ 144

Last change on this file since 144 was 142, checked in by bduin, 5 years ago

Updated collection of datasets

File size: 969 bytes
RevLine 
[142]1%PENDIGITS Pen-based recognition of handwritten digits
2%PRTools dataset import from UCI, 7494+3498 objects, 16 features, 10 classes
3%
4%  [TRAIN,TEST] = PENDIGITS
5%   TRAIN_TEST  = PENDIGITS
6%
7%DESCRIPTION
8%This command downloads one of the UCI data sets, converts it into PRTools
9%format and stores it locally for future use. Consult the <a href="http://archive.ics.uci.edu/ml/datasets/Pen-Based+Recognition+of+Handwritten+Digits">related website</a>
10%for further information. Please make the appropriate references in
11%publications that make use of this dataset.
12%
13%SEE ALSO <a href="http://37steps.com/prtools">PRTools Guide</a>, <a href="http://archive.ics.uci.edu/ml/">UCI Website</a>
14
15function [a,b] = pendigits
16
17[a,b] = pr_download_uci('Pen-Based+Recognition+of+Handwritten+Digits',{'pendigits.tra','pendigits.tes'});
18a = setname(a,'Pen Based Handwritten Digits');
19b = setname(b,'Pen Based Handwritten Digits');
20if nargout < 2, a = [a;b]; end
Note: See TracBrowser for help on using the repository browser.