costmatrix.html

< 数据挖掘--实用机器学习技术及java实现> 一书结合数据挖掘和机器学习的知识,作者陈述了自动挖掘模式的基础理论,并且以java语言实现了具有代表性的各类数据挖掘方法.例如:class

<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TD COLSPAN=1><FONT SIZE="+2">
<B>Field Detail</B></FONT></TD>
</TR>
</TABLE>

<A NAME="FILE_EXTENSION"><!-- --></A><H3>
FILE_EXTENSION</H3>
<PRE>
public static java.lang.String <B>FILE_EXTENSION</B></PRE>
<DL>
<DD>The filename extension that should be used for cost files</DL>

<!-- ========= CONSTRUCTOR DETAIL ======== -->

<A NAME="constructor_detail"><!-- --></A>
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TD COLSPAN=1><FONT SIZE="+2">
<B>Constructor Detail</B></FONT></TD>
</TR>
</TABLE>

<A NAME="CostMatrix(weka.classifiers.CostMatrix)"><!-- --></A><H3>
CostMatrix</H3>
<PRE>
public <B>CostMatrix</B>(<A HREF="../../weka/classifiers/CostMatrix.html">CostMatrix</A>&nbsp;toCopy)</PRE>
<DL>
<DD>Creates a cost matrix identical to an existing matrix.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>toCopy</CODE> - the matrix to copy.</DL>
</DD>
</DL>
<HR>

<A NAME="CostMatrix(int)"><!-- --></A><H3>
CostMatrix</H3>
<PRE>
public <B>CostMatrix</B>(int&nbsp;numClasses)</PRE>
<DL>
<DD>Creates a default cost matrix for the given number of classes. The 
 default misclassification cost is 1.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>numClasses</CODE> - the number of classes</DL>
</DD>
</DL>
<HR>

<A NAME="CostMatrix(java.io.Reader)"><!-- --></A><H3>
CostMatrix</H3>
<PRE>
public <B>CostMatrix</B>(java.io.Reader&nbsp;r)
           throws java.lang.Exception</PRE>
<DL>
<DD>Creates a cost matrix from a cost file.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>r</CODE> - a reader from which the cost matrix will be read<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if an error occurs</DL>
</DD>
</DL>

<!-- ============ METHOD DETAIL ========== -->

<A NAME="method_detail"><!-- --></A>
<TABLE BORDER="1" CELLPADDING="3" CELLSPACING="0" WIDTH="100%">
<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
<TD COLSPAN=1><FONT SIZE="+2">
<B>Method Detail</B></FONT></TD>
</TR>
</TABLE>

<A NAME="makeFrequencyDependentMatrix(weka.core.Instances, double)"><!-- --></A><H3>
makeFrequencyDependentMatrix</H3>
<PRE>
public static <A HREF="../../weka/classifiers/CostMatrix.html">CostMatrix</A> <B>makeFrequencyDependentMatrix</B>(<A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;instances,
                                                      double&nbsp;weight)
                                               throws java.lang.Exception</PRE>
<DL>
<DD>Creates a cost matrix for the class attribute of the supplied instances, 
 where the misclassification costs are higher for misclassifying a rare
 class as a frequent one. The cost of classifying an instance of class i 
 as class j is weight * Pj / Pi. (Pi and Pj are laplace estimates)<DD><DL>
<DT><B>Parameters:</B><DD><CODE>instances</CODE> - a value of type 'Instances'<DD><CODE>weight</CODE> - a value of type 'double'<DT><B>Returns:</B><DD>a value of type CostMatrix<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if no class attribute is assigned, or the class
 attribute is not nominal</DL>
</DD>
</DL>
<HR>

<A NAME="readOldFormat(java.io.Reader)"><!-- --></A><H3>
readOldFormat</H3>
<PRE>
public void <B>readOldFormat</B>(java.io.Reader&nbsp;reader)
                   throws java.lang.Exception</PRE>
<DL>
<DD>Reads misclassification cost matrix from given reader. 
 Each line has to contain three numbers: the index of the true 
 class, the index of the incorrectly assigned class, and the 
 weight, separated by white space characters. Comments can be 
 appended to the end of a line by using the '%' character.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>reader</CODE> - the reader from which the cost matrix is to be read<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if the cost matrix does not have the 
 right format</DL>
</DD>
</DL>
<HR>

<A NAME="initialize()"><!-- --></A><H3>
initialize</H3>
<PRE>
public void <B>initialize</B>()</PRE>
<DL>
<DD>Sets the costs to default values (i.e. 0 down the diagonal, and 1 for
 any misclassification).<DD><DL>
<DT><B>Overrides:</B><DD><CODE><A HREF="../../weka/core/Matrix.html#initialize()">initialize</A></CODE> in class <CODE><A HREF="../../weka/core/Matrix.html">Matrix</A></CODE></DL>
</DD>
</DL>
<HR>

<A NAME="size()"><!-- --></A><H3>
size</H3>
<PRE>
public int <B>size</B>()</PRE>
<DL>
<DD>Gets the number of classes.<DD><DL>
<DT><B>Returns:</B><DD>the number of classes</DL>
</DD>
</DL>
<HR>

<A NAME="normalize()"><!-- --></A><H3>
normalize</H3>
<PRE>
public void <B>normalize</B>()</PRE>
<DL>
<DD>Normalizes the cost matrix so that diagonal elements are zero. The value
 of non-zero diagonal elements is subtracted from the row containing the
 value. For example: <p>

 <pre><code>
 2  5
 3 -1
 </code></pre>
 
 <p> becomes <p>

 <pre><code>
 0  3
 4  0
 </code></pre><p>

 This normalization will affect total classification cost during 
 evaluation, but will not affect the decision made by applying minimum
 expected cost criteria during prediction.</DL>
<HR>

<A NAME="applyCostMatrix(weka.core.Instances, java.util.Random)"><!-- --></A><H3>
applyCostMatrix</H3>
<PRE>
public <A HREF="../../weka/core/Instances.html">Instances</A> <B>applyCostMatrix</B>(<A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;instances,
                                 java.util.Random&nbsp;random)
                          throws java.lang.Exception</PRE>
<DL>
<DD>Changes the dataset to reflect a given set of costs.
 Sets the weights of instances according to the misclassification
 cost matrix, or does resampling according to the cost matrix (if
 a random number generator is provided). Returns a new dataset.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>instances</CODE> - the instances to apply cost weights to.<DD><CODE>random</CODE> - a random number generator<DT><B>Returns:</B><DD>the new dataset<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if the cost matrix does not have the right
 format</DL>
</DD>
</DL>
<HR>

<A NAME="expectedCosts(double[])"><!-- --></A><H3>
expectedCosts</H3>
<PRE>
public double[] <B>expectedCosts</B>(double[]&nbsp;probabilities)
                       throws java.lang.Exception</PRE>
<DL>
<DD>Calculates the expected misclassification cost for each possible
 class value, given class probability estimates.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>probabilities</CODE> - an array containing probability estimates for each 
 class value.<DT><B>Returns:</B><DD>an array containing the expected misclassification cost for each
 class.<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if the number of probabilities does not match the 
 number of classes.</DL>
</DD>
</DL>
<HR>

<A NAME="getMaxCost(int)"><!-- --></A><H3>
getMaxCost</H3>
<PRE>
public double <B>getMaxCost</B>(int&nbsp;actualClass)</PRE>
<DL>
<DD>Gets the maximum misclassification cost possible for a given actual
 class value<DD><DL>
<DT><B>Parameters:</B><DD><CODE>actualClass</CODE> - the index of the actual class value<DT><B>Returns:</B><DD>the highest cost possible for misclassifying this class</DL>
</DD>
</DL>
<HR>

<A NAME="main(java.lang.String[])"><!-- --></A><H3>
main</H3>
<PRE>
public static void <B>main</B>(java.lang.String[]&nbsp;args)</PRE>
<DL>
<DD>Tests out creation of a frequency dependent cost matrix from the command
 line. Either pipe a set of instances into system.in or give the name of
 a dataset as an argument. The last column will be treated as the class
 attribute and a cost matrix with weight 1000 output.<DD><DL>
<DT><B>Parameters:</B><DD><CODE>[]args</CODE> - a value of type 'String'</DL>
</DD>
</DL>
<!-- ========= END OF CLASS DATA ========= -->
<HR>

<!-- ========== START OF NAVBAR ========== -->
<A NAME="navbar_bottom"><!-- --></A>
<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0">
<TR>
<TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
<A NAME="navbar_bottom_firstrow"><!-- --></A>
<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3">
  <TR ALIGN="center" VALIGN="top">
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>
  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
  </TR>
</TABLE>
</TD>
<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
</EM>
</TD>
</TR>

<TR>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
&nbsp;<A HREF="../../weka/classifiers/Classifier.html"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../weka/classifiers/CostSensitiveClassifier.html"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../index.html" TARGET="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="CostMatrix.html" TARGET="_top"><B>NO FRAMES</B></A></FONT></TD>
</TR>
<TR>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
  SUMMARY: &nbsp;INNER&nbsp;|&nbsp;<A HREF="#field_summary">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
DETAIL: &nbsp;<A HREF="#field_detail">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
</TR>
</TABLE>
<!-- =========== END OF NAVBAR =========== -->

<HR>

</BODY>
</HTML>