⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 verbrules.html

📁 由于ID3算法在实际应用中存在一些问题
💻 HTML
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD><TITLE>Manpage of C4.5</TITLE>
<META http-equiv=Content-Type content="text/html; charset=iso-8859-1">
<STYLE TYPES="text/css">DIV.section {
	MARGIN-LEFT: 2cm
}
</STYLE>
<LINK REL=StyleSheet HREF="../../../../stylesheet/main.css" TYPE="text/css">
<META content="MSHTML 6.00.2800.1276" name=GENERATOR></HEAD>
<BODY>
<blockquote>
<H1>VERBRULES</H1>
<HR>
<A name=lbAB>&nbsp;</A> 
<H2>NAME</H2>A guide to the verbose output of the C4.5 production rule generator 

<P><A name=lbAC></A> 
<H2>DESCRIPTION</H2>This document explains the output of the program 
<I>C4.5rules</I> when it is run with the verbosity level (option <B>v</B>) set 
to values from 1 to 3. <I>C4.5rules</I> converts unpruned decision trees into 
sets of pruned production rules. Each set of rules is then sifted to find a 
subset of the rules which perform as well or better on the training data (see 
<I>c4.5rules</I>).

<P><A name=lbAD></A> 
<H2>RULE PRUNING</H2>
<P><B>Verbosity level 1</B> 
<P>A decision tree is converted to a set of production rules by forming a rule 
corresponding to each path from the root of the tree to each of its leaves. 
After each rule is extracted from the tree, it is examined to see whether the 
rule can be generalised by dropping conditions. 
<P>For each rule, the verbose output shows the following figures for the rule as 
it stands, and for each of the rules that would be formed by dropping any one of 
the conditions: 
<P><BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Miss&nbsp;-&nbsp;no.&nbsp;of&nbsp;items&nbsp;misclassified&nbsp;by&nbsp;the&nbsp;rule 
<BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Hit&nbsp;&nbsp;-&nbsp;no.&nbsp;of&nbsp;items&nbsp;correctly&nbsp;classified&nbsp;by&nbsp;the&nbsp;rule 
<BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Pess&nbsp;-&nbsp;the&nbsp;pessimistic&nbsp;error&nbsp;rate&nbsp;of&nbsp;the&nbsp;rule 
<BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;(i.e.&nbsp;100*(misses+1)/(misses+hits+2)) 
<BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Gain&nbsp;-&nbsp;the&nbsp;information&nbsp;gain&nbsp;of&nbsp;the&nbsp;rule 
<BR>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Absent&nbsp;condition&nbsp;-&nbsp;the&nbsp;condition&nbsp;being&nbsp;ignored 

<P>If there are any conditions whose deletion brings about rules with 
pessimistic error rate less than the default error rate, and gain greater than 
that of the rule as it stands, then the one of these with the lowest pessimistic 
error rate is dropped. When this happens, the message: 
<P><TT>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TT>eliminate test 
<I>d</I><BR>
<P>is given and the new rule without condition <I>d</I> is examined, and so on. 
<P>When the rule has been pruned, either the rule is displayed, or the message: 
<P><TT>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TT>duplicates rule 
<I>n</I><BR>
<P>is given, where <I>n</I> is an identical rule already produced, and so the 
new rule is not added, or the message: 
<P><TT>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TT>too inaccurate<BR>
<P>is given, indicating that the pessimistic error rate of the pruned rule is 
more than 50%, or more than the proportion of the items that are of the rule's 
class, and so the rule is not added. 
<P>
<P><A name=lbAE></A> 
<H2>RULE SIFTING</H2>
<P><B>Verbosity level 1</B> 
<P>The set of pruned rules for each class is then examined. Starting with no 
rules in the ruleset, the following process is repeated until no rules can be 
added or dropped. 
<DL compact>
  <DT>1.
  <DD>If there are rules whose omission would not lead to an increase in the 
  number of items misclassified, then the least useful of these is dropped. 
  <DT>2.
  <DD>Otherwise, if there are rules which lead to a decrease in the number of 
  items misclassified, then the one with the least counterexamples is added. 
  <DT>This is shown in the output as:
  <DD>
  <P><BR>&nbsp;&nbsp;&nbsp;&nbsp;Action&nbsp;&nbsp;-&nbsp;&nbsp;the&nbsp;number&nbsp;of&nbsp;the&nbsp;rule&nbsp;added&nbsp;or&nbsp;dropped 
  <BR>&nbsp;&nbsp;&nbsp;&nbsp;Change&nbsp;&nbsp;-&nbsp;&nbsp;the&nbsp;advantage&nbsp;attributable&nbsp;to&nbsp;the&nbsp;rule 
  <BR>&nbsp;&nbsp;&nbsp;&nbsp;Worth&nbsp;&nbsp;&nbsp;-&nbsp;&nbsp;the&nbsp;included&nbsp;rules&nbsp;for&nbsp;this&nbsp;class&nbsp;as: 

  <P><I>n1</I>[<I>n2</I>|<I>n3</I>= <I>r1</I>] 
  <P><BR>&nbsp;&nbsp;&nbsp;&nbsp;with: </P>
  <DT><I>n1</I>
  <DD>- the rule number 
  <DT><I>n2</I>
  <DD>- the number of items that correctly fire this rule and are not covered by 
  any other included rule 
  <DT><I>n3</I>
  <DD>- the number of items that incorrectly fire this rule and are not covered 
  by any other included rule 
  <DT><I>r1</I>
  <DD>- the advantage attributable to the rule 
  <DT>
  <DD>After the rules have been sifted, the number of items of each class that 
  are not covered by any rules is shown, and the default class is set to the 
  class with the most uncovered items. 
  <P>
  <P><B>Verbosity level 2</B> 
  <P>When sifting rules for a particular class, the Worth of each rule which is 
  for that class but not included in the ruleset, is shown at each stage of the 
  process. 
  <P></P></DD></DL><A name=lbAF>&nbsp;</A> 
<H2>RULE SORTING</H2>
<P><B>Verbosity level 1</B> 
<P>The rules that are left are then sorted, starting with those that are for the 
class with the least number of false positives. The verbose output shows the 
number of false positives for each class (i.e. the number of items misclassified 
as being of this class). Within a class, rules with the greatest advantage are 
put first. 
<P><A name=lbAG></A> 
<H2>RULESET EVALUATION</H2>
<P><B>Verbosity level 3</B> 
<P>When evaluating a ruleset, shown are the attribute values, given class and 
class given by the ruleset for each item that is misclassified. 
<P>
<P><A name=lbAH></A> 
</blockquote></BODY></HTML>

⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -