evaluation.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

<A NAME="marginResolution()"><!-- --></A><H3>
marginResolution</H3>
<PRE>
public final int <B>marginResolution</B>()</PRE>
<DL>
<DD>Gets the value of the marginResolution variable.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the value of the marginResolution variable</DL>
</DD>
</DL>
<HR>

<A NAME="marginCounts()"><!-- --></A><H3>
marginCounts</H3>
<PRE>
public double[] <B>marginCounts</B>()</PRE>
<DL>
<DD>Gets a copy of the marginCounts array.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>a copy of the marginCounts array</DL>
</DD>
</DL>
<HR>

<A NAME="numTrainClassVals()"><!-- --></A><H3>
numTrainClassVals</H3>
<PRE>
public final int <B>numTrainClassVals</B>()</PRE>
<DL>
<DD>Gets the value of the numTrainClassVals variable.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the value of the numTrainClassVals variable</DL>
</DD>
</DL>
<HR>

<A NAME="trainClassVals()"><!-- --></A><H3>
trainClassVals</H3>
<PRE>
public double[] <B>trainClassVals</B>()</PRE>
<DL>
<DD>Gets a copy of the trainClassVals array.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>a copy of the trainClassVals array</DL>
</DD>
</DL>
<HR>

<A NAME="trainClassWeights()"><!-- --></A><H3>
trainClassWeights</H3>
<PRE>
public double[] <B>trainClassWeights</B>()</PRE>
<DL>
<DD>Gets a copy of the trainClassWeights array.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>a copy of the trainClassWeights array</DL>
</DD>
</DL>
<HR>

<A NAME="sumPriorEntropy()"><!-- --></A><H3>
sumPriorEntropy</H3>
<PRE>
public final double <B>sumPriorEntropy</B>()</PRE>
<DL>
<DD>Gets the value of the sumPriorEntropy variable.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the value of the sumPriorEntropy variable</DL>
</DD>
</DL>
<HR>

<A NAME="sumSchemeEntropy()"><!-- --></A><H3>
sumSchemeEntropy</H3>
<PRE>
public final double <B>sumSchemeEntropy</B>()</PRE>
<DL>
<DD>Gets the value of the sumSchemeEntropy variable.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the value of the sumSchemeEntropy variable</DL>
</DD>
</DL>
<HR>

<A NAME="numInstances()"><!-- --></A><H3>
numInstances</H3>
<PRE>
public final double <B>numInstances</B>()</PRE>
<DL>
<DD>Gets the number of test instances that had a known class value
 (actually the sum of the weights of test instances with known
 class value).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the number of test instances with known class</DL>
</DD>
</DL>
<HR>

<A NAME="pctIncorrect()"><!-- --></A><H3>
pctIncorrect</H3>
<PRE>
public final double <B>pctIncorrect</B>()</PRE>
<DL>
<DD>Gets the percentage of instances incorrectly classified (that is, for
 which an incorrect prediction was made).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the percent of incorrectly classified instances
 (between 0 and 100)</DL>
</DD>
</DL>
<HR>

<A NAME="avgCost()"><!-- --></A><H3>
avgCost</H3>
<PRE>
public final double <B>avgCost</B>()</PRE>
<DL>
<DD>Gets the average cost, that is, total cost of misclassifications
 (incorrect plus unclassified) over the total number of instances.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the average cost.</DL>
</DD>
</DL>
<HR>

<A NAME="pctCorrect()"><!-- --></A><H3>
pctCorrect</H3>
<PRE>
public final double <B>pctCorrect</B>()</PRE>
<DL>
<DD>Gets the percentage of instances correctly classified (that is, for
 which a correct prediction was made).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the percent of correctly classified instances
 (between 0 and 100)</DL>
</DD>
</DL>
<HR>

<A NAME="pctUnclassified()"><!-- --></A><H3>
pctUnclassified</H3>
<PRE>
public final double <B>pctUnclassified</B>()</PRE>
<DL>
<DD>Gets the percentage of instances not classified (that is, for
 which no prediction was made by the classifier).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the percent of unclassified instances (between 0 and 100)</DL>
</DD>
</DL>
<HR>

<A NAME="aggregate(weka.classifiers.Evaluation)"><!-- --></A><H3>
aggregate</H3>
<PRE>
public void <B>aggregate</B>(<A HREF="../../weka/classifiers/Evaluation.html">Evaluation</A>&nbsp;evaluation)</PRE>
<DL>
<DD>Aggregates data obtained from running different folds on different
 machines.  Used when the -a flag is set to run the cross-validation
 in parallel.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>evaluation</CODE> - the data sent back from another machine</DL>
</DD>
</DL>
<HR>

<A NAME="crossValidateModel(weka.classifiers.Classifier, weka.core.Instances, int)"><!-- --></A><H3>
crossValidateModel</H3>
<PRE>
public void <B>crossValidateModel</B>(<A HREF="../../weka/classifiers/Classifier.html">Classifier</A>&nbsp;classifier,
                               <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data,
                               int&nbsp;numFolds)
                        throws java.lang.Exception</PRE>
<DL>
<DD>Performs a (stratified if class is nominal) cross-validation
 for a classifier on a set of instances.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classifier</CODE> - the classifier with any options set.<DD><CODE>data</CODE> - the data on which the cross-validation is to be
 performed<DD><CODE>numFolds</CODE> - the number of folds for the cross-validation<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if a classifier could not be generated
 successfully or the class is not defined</DL>
</DD>
</DL>
<HR>

<A NAME="crossValidateModelParallel(weka.classifiers.Classifier, weka.core.Instances, int, java.lang.StringBuffer)"><!-- --></A><H3>
crossValidateModelParallel</H3>
<PRE>
public void <B>crossValidateModelParallel</B>(<A HREF="../../weka/classifiers/Classifier.html">Classifier</A>&nbsp;classifier,
                                       <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data,
                                       int&nbsp;numFolds,
                                       java.lang.StringBuffer&nbsp;otherComputers)
                                throws java.lang.Exception</PRE>
<DL>
<DD>Performs a (stratified if class is nominal) cross-validation
 for a classifier on a set of instances. This cross-validation
 is run in parallel by connecting to the machines described in
 ~/.weka-parallel.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classifier</CODE> - the classifier with any options set.<DD><CODE>data</CODE> - the data on which the cross-validation is to be
 performed<DD><CODE>numFolds</CODE> - the number of folds for the cross-validation<DD><CODE>otherComputers</CODE> - will eventually hold the names of all of the
 computers that the program was actually able to connect to and
 receive data from<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if a classifier could not be generated,
 if the class is not defined, or if there was an incorrect number
 of folds selected</DL>
</DD>
</DL>
<HR>

<A NAME="crossValidateModel(java.lang.String, weka.core.Instances, int, java.lang.String[])"><!-- --></A><H3>
crossValidateModel</H3>
<PRE>
public void <B>crossValidateModel</B>(java.lang.String&nbsp;classifierString,
                               <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data,
                               int&nbsp;numFolds,
                               java.lang.String[]&nbsp;options)
                        throws java.lang.Exception</PRE>
<DL>
<DD>Performs a (stratified if class is nominal) cross-validation
 for a classifier on a set of instances.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classifier</CODE> - a string naming the class of the classifier<DD><CODE>data</CODE> - the data on which the cross-validation is to be
 performed<DD><CODE>numFolds</CODE> - the number of folds for the cross-validation<DD><CODE>options</CODE> - the options to the classifier. Any options
 accepted by the classifier will be removed from this array.<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if a classifier could not be generated
 successfully or the class is not defined</DL>
</DD>
</DL>
<HR>

<A NAME="evaluateModel(java.lang.String, java.lang.String[])"><!-- --></A><H3>
evaluateModel</H3>
<PRE>
public static java.lang.String <B>evaluateModel</B>(java.lang.String&nbsp;classifierString,
                                             java.lang.String[]&nbsp;options)
                                      throws java.lang.Exception</PRE>
<DL>
<DD>Evaluates a classifier with the options given in an array of
 strings. <p>

 Valid options are: <p>

 -t filename <br>
 Name of the file with the training data. (required) <p>

 -T filename <br>
 Name of the file with the test data. If missing a cross-validation
 is performed. <p>

 -c index <br>
 Index of the class attribute (1, 2, ...; default: last). <p>

 -x number <br>
 The number of folds for the cross-validation (default: 10). <p>

 -s seed <br>
 Random number seed for the cross-validation (default: 1). <p>

 -m filename <br>
 The name of a file containing a cost matrix. <p>

 -l filename <br>
 Loads classifier from the given file. <p>

 -d filename <br>
 Saves classifier built from the training data into the given file. <p>

 -v <br>
 Outputs no statistics for the training data. <p>

 -o <br>
 Outputs statistics only, not the classifier. <p>

 -i <br>
 Outputs detailed information-retrieval statistics per class. <p>

 -k <br>
 Outputs information-theoretic statistics. <p>

 -p range <br>
 Outputs predictions for test instances, along with the attributes in
 the specified range (and nothing else). Use '-p 0' if no attributes are
 desired. <p>

 -r <br>
 Outputs cumulative margin distribution (and nothing else). <p>

 -g <br>
 Only for classifiers that implement "Graphable." Outputs
 the graph representation of the classifier (and nothing
 else). <p><DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classifierString</CODE> - class of machine learning classifier as a string<DD><CODE>options</CODE> - the array of string containing the options<DT><B>Returns:</B><DD>a string describing the results<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if model could not be evaluated successfully</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>A test method for this class. Just extracts the first command line
 argument as a classifier class name and calls evaluateModel.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>args</CODE> - an array of command line arguments, the first of which
 must b