checkclassifier.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

</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="canHandleMissing(boolean, boolean, boolean, boolean, boolean, int)"><!-- --></A><H3>
canHandleMissing</H3>
<PRE>
protected boolean <B>canHandleMissing</B>(boolean&nbsp;nominalPredictor,
                                   boolean&nbsp;numericPredictor,
                                   boolean&nbsp;numericClass,
                                   boolean&nbsp;predictorMissing,
                                   boolean&nbsp;classMissing,
                                   int&nbsp;missingLevel)</PRE>
<DL>
<DD>Checks basic missing value handling of the scheme. If the missing
 values cause an exception to be thrown by the scheme, this will be
 recorded.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DD><CODE>predictorMissing</CODE> - true if the missing values may be in 
 the predictors<DD><CODE>classMissing</CODE> - true if the missing values may be in the class<DD><CODE>level</CODE> - the percentage of missing values<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="updatingEquality(boolean, boolean, boolean)"><!-- --></A><H3>
updatingEquality</H3>
<PRE>
protected boolean <B>updatingEquality</B>(boolean&nbsp;nominalPredictor,
                                   boolean&nbsp;numericPredictor,
                                   boolean&nbsp;numericClass)</PRE>
<DL>
<DD>Checks whether an updateable scheme produces the same model when
 trained incrementally as when batch trained. The model itself
 cannot be compared, so we compare the evaluation on test data
 for both models. It is possible to get a false positive on this
 test (likelihood depends on the classifier).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="doesntUseTestClassVal(boolean, boolean, boolean)"><!-- --></A><H3>
doesntUseTestClassVal</H3>
<PRE>
protected boolean <B>doesntUseTestClassVal</B>(boolean&nbsp;nominalPredictor,
                                        boolean&nbsp;numericPredictor,
                                        boolean&nbsp;numericClass)</PRE>
<DL>
<DD>Checks whether the classifier erroneously uses the class
 value of test instances (if provided). Runs the classifier with
 test instance class values set to missing and compares with results
 when test instance class values are left intact.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="instanceWeights(boolean, boolean, boolean)"><!-- --></A><H3>
instanceWeights</H3>
<PRE>
protected boolean <B>instanceWeights</B>(boolean&nbsp;nominalPredictor,
                                  boolean&nbsp;numericPredictor,
                                  boolean&nbsp;numericClass)</PRE>
<DL>
<DD>Checks whether the classifier can handle instance weights.
 This test compares the classifier performance on two datasets
 that are identical except for the training weights. If the 
 results change, then the classifier must be using the weights. It
 may be possible to get a false positive from this test if the 
 weight changes aren't significant enough to induce a change
 in classifier performance (but the weights are chosen to minimize
 the likelihood of this).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="datasetIntegrity(boolean, boolean, boolean, boolean, boolean)"><!-- --></A><H3>
datasetIntegrity</H3>
<PRE>
protected boolean <B>datasetIntegrity</B>(boolean&nbsp;nominalPredictor,
                                   boolean&nbsp;numericPredictor,
                                   boolean&nbsp;numericClass,
                                   boolean&nbsp;predictorMissing,
                                   boolean&nbsp;classMissing)</PRE>
<DL>
<DD>Checks whether the scheme alters the training dataset during
 training. If the scheme needs to modify the training
 data it should take a copy of the training data. Currently checks
 for changes to header structure, number of instances, order of
 instances, instance weights.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - if true use nominal predictor attributes<DD><CODE>numericPredictor</CODE> - if true use numeric predictor attributes<DD><CODE>numericClass</CODE> - if true use a numeric class attribute otherwise a
 nominal class attribute<DD><CODE>predictorMissing</CODE> - true if we know the classifier can handle
 (at least) moderate missing predictor values<DD><CODE>classMissing</CODE> - true if we know the classifier can handle
 (at least) moderate missing class values<DT><B>Returns:</B><DD>true if the test was passed</DL>
</DD>
</DL>
<HR>

<A NAME="runBasicTest(boolean, boolean, boolean, int, boolean, boolean, int, int, int, weka.core.FastVector)"><!-- --></A><H3>
runBasicTest</H3>
<PRE>
protected boolean <B>runBasicTest</B>(boolean&nbsp;nominalPredictor,
                               boolean&nbsp;numericPredictor,
                               boolean&nbsp;numericClass,
                               int&nbsp;missingLevel,
                               boolean&nbsp;predictorMissing,
                               boolean&nbsp;classMissing,
                               int&nbsp;numTrain,
                               int&nbsp;numTest,
                               int&nbsp;numClasses,
                               <A HREF="../../weka/core/FastVector.html">FastVector</A>&nbsp;accepts)</PRE>
<DL>
<DD>Runs a text on the datasets with the given characteristics.<DD><DL>
</DL>
</DD>
</DL>
<HR>

<A NAME="testWRTZeroR(weka.classifiers.Classifier, weka.classifiers.Evaluation, weka.core.Instances, weka.core.Instances)"><!-- --></A><H3>
testWRTZeroR</H3>
<PRE>
protected boolean <B>testWRTZeroR</B>(<A HREF="../../weka/classifiers/Classifier.html">Classifier</A>&nbsp;classifier,
                               <A HREF="../../weka/classifiers/Evaluation.html">Evaluation</A>&nbsp;evaluation,
                               <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;train,
                               <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;test)
                        throws java.lang.Exception</PRE>
<DL>
<DD>Determine whether the scheme performs worse than ZeroR during testing<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classifier</CODE> - the pre-trained classifier<DD><CODE>evaluation</CODE> - the classifier evaluation object<DD><CODE>train</CODE> - the training data<DD><CODE>test</CODE> - the test data<DT><B>Returns:</B><DD>true if the scheme performs better than ZeroR<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if there was a problem during the scheme's testing</DL>
</DD>
</DL>
<HR>

<A NAME="compareDatasets(weka.core.Instances, weka.core.Instances)"><!-- --></A><H3>
compareDatasets</H3>
<PRE>
protected void <B>compareDatasets</B>(<A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data1,
                               <A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data2)
                        throws java.lang.Exception</PRE>
<DL>
<DD>Compare two datasets to see if they differ.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>data1</CODE> - one set of instances<DD><CODE>data2</CODE> - the other set of instances<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if the datasets differ</DL>
</DD>
</DL>
<HR>

<A NAME="addMissing(weka.core.Instances, int, boolean, boolean)"><!-- --></A><H3>
addMissing</H3>
<PRE>
protected void <B>addMissing</B>(<A HREF="../../weka/core/Instances.html">Instances</A>&nbsp;data,
                          int&nbsp;level,
                          boolean&nbsp;predictorMissing,
                          boolean&nbsp;classMissing)</PRE>
<DL>
<DD>Add missing values to a dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>data</CODE> - the instances to add missing values to<DD><CODE>level</CODE> - the level of missing values to add (if positive, this
 is the probability that a value will be set to missing, if negative
 all but one value will be set to missing (not yet implemented))<DD><CODE>predictorMissing</CODE> - if true, predictor attributes will be modified<DD><CODE>classMissing</CODE> - if true, the class attribute will be modified</DL>
</DD>
</DL>
<HR>

<A NAME="makeTestDataset(int, int, int, int, int, boolean)"><!-- --></A><H3>
makeTestDataset</H3>
<PRE>
protected <A HREF="../../weka/core/Instances.html">Instances</A> <B>makeTestDataset</B>(int&nbsp;seed,
                                    int&nbsp;numInstances,
                                    int&nbsp;numNominal,
                                    int&nbsp;numNumeric,
                                    int&nbsp;numClasses,
                                    boolean&nbsp;numericClass)
                             throws java.lang.Exception</PRE>
<DL>
<DD>Make a simple set of instances, which can later be modified
 for use in specific tests.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>seed</CODE> - the random number seed<DD><CODE>numInstances</CODE> - the number of instances to generate<DD><CODE>numNominal</CODE> - the number of nominal attributes<DD><CODE>numNumeric</CODE> - the number of numeric attributes<DD><CODE>numClasses</CODE> - the number of classes (if nominal class)<DD><CODE>numericClass</CODE> - true if the class attribute should be numeric<DT><B>Returns:</B><DD>the test dataset<DT><B>Throws:</B><DD><CODE>java.lang.Exception</CODE> - if the dataset couldn't be generated</DL>
</DD>
</DL>
<HR>

<A NAME="printAttributeSummary(boolean, boolean, boolean)"><!-- --></A><H3>
printAttributeSummary</H3>
<PRE>
protected void <B>printAttributeSummary</B>(boolean&nbsp;nominalPredictor,
                                     boolean&nbsp;numericPredictor,
                                     boolean&nbsp;numericClass)</PRE>
<DL>
<DD>Print out a short summary string for the dataset characteristics<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>nominalPredictor</CODE> - true if nominal predictor attributes are present<DD><CODE>numericPredictor</CODE> - true if numeric predictor attributes are present<DD><CODE>numericClass</CODE> - true if the class attribute is numeric</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/BVDecompose.html"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../weka/classifiers/ClassificationViaRegression.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="CheckClassifier.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>