source: prdatasets/biomed.m @ 125

Last change on this file since 125 was 123, checked in by bduin, 7 years ago
File size: 1.3 KB
RevLine 
[80]1%BIOMED 194 objects with 5 features in 2 classes
2%
3%       X = BIOMED;
4%
5% The biomed dataset to develop screening methods to identify carriers
6% of a rare genetic disorder.  Because the disease is rare, there are
7% only a few carriers of the disease from whom data are available.
8%
[94]9%       X = BIOMED(VAL)
[80]10%
[94]11% By default objects with missing values are removed. When something else
[123]12% is desired, use one of the options in MISVAL for VAL.
[80]13%
[94]14% This is the ''biomed' dataset of the <a href="http://lib.stat.cmu.edu/datasets/">StatLib Datasets Archive</a>.
[123]15% Just the original features 3, 5, 6, 7 and 8 are used.
[94]16%
17% SEE ALSO <a href="http://37steps.com/prtools">PRTools Guide</a>, <a href="http://archive.ics.uci.edu/ml/">UCI Website</a>
18% PRTOOLS, DATASETS, MISVAL
[80]19
[94]20% Copyright: R.P.W. Duin, r.p.w.duin@prtools.org
21
[80]22function x = biomed(val)
23
[123]24if nargin < 1, val = 'remove'; end
25a = pr_getdata('http://37steps.com/data/prdatasets/biomed.dat',1);
[80]26
27user.desc = 'The purpose of the analysis is to develop a screening procedure to detect carriers and to describe its effectiveness. ';
28user.link = 'http://lib.stat.cmu.edu/datasets/';
29cl = {'carrier' 'normal'};
30fl = {'age' 'measurement 1' 'measurement 2' 'measurement 3' 'measurement 4'};
31
[81]32x = pr_dataset(a(:,[3 5 6 7 8]),cl(a(:,end)));
[80]33x = setfeatlab(x,fl);
34x = setname(x,'Biomed');
35x = setuser(x,user);
[123]36x = misval(x,val);
[80]37
38return
Note: See TracBrowser for help on using the repository browser.