dtree.html

it is tree Dtree algorithm. so see it. it is in c++

option, e.g. <tt>-p decision_tree_class</tt>.</p>

<p>If the table contains preclassified data and the name of the column
containing the preclassification is the same as for the training data,
the error rate of the decision tree is determined and printed to the
terminal.</p>

<p>The contents of the file drug.cls should look like this:</p>

<pre>  Sex    Age Blood_pressure Drug dt
  male   20  normal         A    A
  female 73  normal         B    B
  female 37  high           A    A
  male   33  low            B    B
  female 48  high           A    A
  male   29  normal         A    A
  female 52  normal         B    B
  male   42  low            B    B
  male   61  normal         B    B
  female 30  normal         A    A
  female 26  low            B    B
  male   54  high           A    A
</pre>

<p>That is, the classification is perfect, which is not surprising
for such a simple example. The columns are neatly aligned because of
the <tt>-a</tT> option. Without it, there would only be a single
space between two column values.</p>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="xmat">Computing a Confusion Matrix</a></h3>

<p>The classification quality can be inspected in more detail with
the program <tt>xmat</tt> (determine a confusion matrix, to be found
in the table package, see below):</p>

<pre>  xmat drug.cls</pre>

<p>This program reads the output of the program <tt>dtx</tt> and
computes a confusion matrix from two columns of this file. It uses
the last two columns by default (the last column for the x- and the
semi-last for the y-direction), which is fine for our example. Other
columns can be selected via the options <tt>-x</tt> and <tt>-y</tt>
followed by the name of the column that is to be used for the x- or
y-direction of the confusion matrix. The output of the program
<tt>xmat</tt>, which by default is written to the terminal, should
read like this:</p>

<pre>  confusion matrix for Drug vs. dt:
   no | value  |      1      2 | errors
  ----+--------+---------------+-------
    1 | A      |      6      0 |      0
    2 | B      |      0      6 |      0
  ----+--------+---------------+-------
      | errors |      0      0 |      0
</pre>

<p>In this matrix the x-direction corresponds to the column <tt>dt</tt>
and the y-direction to the column <tt>Drug</tt>. Since in our simple
example the classification is perfect, only the fields in the diagonal
differ from zero. If the classification is not perfect, the other
fields show what errors are made by the decision tree classifier.</p>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="rules">Extracting Rules from a Decision Tree</a></h3>

<p>If you like rules better than trees, you can extract rules from a
learned decision tree with the program <tt>dtr</tt> (<tt>dtr</tt> is
simply an abbreviation for Decision Tree Rule Extraction).</p>

<pre>  dtr -sc drug.dt drug.rs</pre>

<p><tt>drug.dt</tt> is the decision tree file, <tt>drug.rs</tt> the
file to which the rules shall be written. The option <tt>-s</tt>
instructs the program to print the support of each rule, i.e., the
number of cases in the training data set the rule applies to, and
the option <tt>-c</tt> instructs it to print the confidence of each
rule, i.e., the percentage of cases in which a rule is correct
relative to the number of cases in which it is applicable. The file
<tt>drug.rs</tt> should contain the following set of rules:</p>

<pre>  Drug = A <- Blood_pressure = high [3/100.0%];
  Drug = B <- Blood_pressure = low [3/100.0%];
  Drug = A <- Age < 41 & Blood_pressure = normal [3/100.0%];
  Drug = B <- Age > 41 & Blood_pressure = normal [3/100.0%];
</pre>

<p>The numbers in brackets are the number of cases in the training
data set the rule applies to (first number) and the confidence
(second number). Note that there is one rule for each leaf of the
decision tree. The program tries to simplify the rules by combining
conditions on numeric attributes if possible, but it will not
simplify the rule set by merging rules.</p>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="other">Other Decision Tree Examples</a></h3>

<p>The decision trees in the directory <tt>dtree/ex</tt> (files with
extensions <tt>.dt</tt> and <tt>.pdt</tt>) were created with the
following commands:</p>

<pre>  dti -a drug.dom drug.tab drug.dt
  dti iris.dom iris.tab iris.dt
  dti -s monk1.dom monk1.tab monk1.dt
  dtp monk1.dt monk1.pdt monk1.tab
  dti vote.dom vote.tab vote.dt
  dtp vote.dt vote.pdt
  dti wine.dom wine.tab wine.dt
</pre>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="copying">Copying</a></h3>

<p>dti/dtp/dtx/dtr/rsx -
   induce, prune, and execute decision and regression trees<br>
   copyright &copy; 1996-2003 Christian Borgelt</p>

<p>These programs are free software; you can redistribute them
and/or modify them under the terms of the
<a href="http://www.fsf.org/copyleft/lesser.html">
GNU Lesser (Library) General Public License</a> as published by the
<a href="http://www.fsf.org">Free Software Foundation</a>.</p>

<p>These programs are distributed in the hope that they will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
<a href="http://www.fsf.org/copyleft/lesser.html">
GNU Lesser (Library) General Public License</a> for more details.</p>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="download">Download</a></h3>

<p><a href="http://fuzzy.cs.uni-magdeburg.de/~borgelt/dtree.html">
Download page</a> with most recent version.</p>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<h3><a name="contact">Contact</a></h3>

<table border=0 cellpadding=0 cellspacing=0>
<tr><td valign=top>Snail mail:</td><td width=10></td>
    <td><a href="http://fuzzy.cs.uni-magdeburg.de/~borgelt/index.html">
        Christian Borgelt</a><br>
        <a href="http://fuzzy.cs.uni-magdeburg.de/index.html">
        Working Group Neural Networks and Fuzzy Systems</a><br>
        <a href="http://www-iws.cs.uni-magdeburg.de/iws.html"> 
        Department of Knowledge Processing and Language Engineering</a><br>
        <a href="http://www.cs.uni-magdeburg.de/">
        School of Computer Science</a><br>
        <a href="http://www.uni-magdeburg.de/">
        Otto-von-Guericke-University of Magdeburg</a><br>
        Universit&auml;tsplatz 2<br>
        D-39106 Magdeburg<br>
        Germany</td></tr>
<tr><td valign=top>E-mail:</td><td></td>
    <td><a href="mailto:[e-mail]">
        [e-mail]</a><br>
        <a href="mailto:[e-mail]">
        [e-mail]</a></td></tr>
<tr><td>Phone:</td><td></td>
    <td>[phone]</td></tr>
<tr><td>Fax:</td><td></td>
    <td>[phone]</td></tr>
<tr><td>Office:</td><td></td>
    <td>29.015</td></tr>
</table>

<table width="100%" border=0 cellpadding=0 cellspacing=0>
<tr><td width="95%" align=right><a href="#top">back to the top</a></td>
    <td width=5></td>
    <td><a href="#top"><img src="uparrow.gif" border=0></a></td></tr>
</table>

<!-- =============================================================== -->
<p><img src="line.gif" alt="" height=7 width=704></p>

<address>&copy; 1999-2003
<a href="mailto:[e-mail]">Christian Borgelt</a>
</address>
<!-- Created: Thu May 24 12:28:05 CEST 2001 -->
<!-- hhmts start -->
Last modified: Sat Apr 26 16:40:45 PDT 2003
<!-- hhmts end -->
</body>
</html>