instances.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="numDistinctValues(weka.core.Attribute)"><!-- --></A><H3>
numDistinctValues</H3>
<PRE>
public final int <B>numDistinctValues</B>(<A HREF="../../weka/core/Attribute.html">Attribute</A>&nbsp;att)</PRE>
<DL>
<DD>Returns the number of distinct values of a given attribute.
 Returns the number of instances if the attribute is a
 string attribute. The value 'missing' is not counted.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute<DT><B>Returns:</B><DD>the number of distinct values of a given attribute</DL>
</DD>
</DL>
<HR>

<A NAME="numInstances()"><!-- --></A><H3>
numInstances</H3>
<PRE>
public final int <B>numInstances</B>()</PRE>
<DL>
<DD>Returns the number of instances in the dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the number of instances in the dataset as an integer</DL>
</DD>
</DL>
<HR>

<A NAME="randomize(java.util.Random)"><!-- --></A><H3>
randomize</H3>
<PRE>
public final void <B>randomize</B>(java.util.Random&nbsp;random)</PRE>
<DL>
<DD>Shuffles the instances in the set so that they are ordered 
 randomly.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>random</CODE> - a random number generator</DL>
</DD>
</DL>
<HR>

<A NAME="readInstance(java.io.Reader)"><!-- --></A><H3>
readInstance</H3>
<PRE>
public final boolean <B>readInstance</B>(java.io.Reader&nbsp;reader)
                           throws java.io.IOException</PRE>
<DL>
<DD>Reads a single instance from the reader and appends it
 to the dataset.  Automatically expands the dataset if it
 is not large enough to hold the instance. This method does
 not check for carriage return at the end of the line.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>reader</CODE> - the reader<DT><B>Returns:</B><DD>false if end of file has been reached<DT><B>Throws:</B><DD><CODE>java.io.IOException</CODE> - if the information is not read 
 successfully</DL>
</DD>
</DL>
<HR>

<A NAME="relationName()"><!-- --></A><H3>
relationName</H3>
<PRE>
public final java.lang.String <B>relationName</B>()</PRE>
<DL>
<DD>Returns the relation's name.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the relation's name as a string</DL>
</DD>
</DL>
<HR>

<A NAME="renameAttribute(int, java.lang.String)"><!-- --></A><H3>
renameAttribute</H3>
<PRE>
public final void <B>renameAttribute</B>(int&nbsp;att,
                                  java.lang.String&nbsp;name)</PRE>
<DL>
<DD>Renames an attribute. This change only affects this
 dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute's index<DD><CODE>name</CODE> - the new name</DL>
</DD>
</DL>
<HR>

<A NAME="renameAttribute(weka.core.Attribute, java.lang.String)"><!-- --></A><H3>
renameAttribute</H3>
<PRE>
public final void <B>renameAttribute</B>(<A HREF="../../weka/core/Attribute.html">Attribute</A>&nbsp;att,
                                  java.lang.String&nbsp;name)</PRE>
<DL>
<DD>Renames an attribute. This change only affects this
 dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute<DD><CODE>name</CODE> - the new name</DL>
</DD>
</DL>
<HR>

<A NAME="renameAttributeValue(int, int, java.lang.String)"><!-- --></A><H3>
renameAttributeValue</H3>
<PRE>
public final void <B>renameAttributeValue</B>(int&nbsp;att,
                                       int&nbsp;val,
                                       java.lang.String&nbsp;name)</PRE>
<DL>
<DD>Renames the value of a nominal (or string) attribute value. This
 change only affects this dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute's index<DD><CODE>val</CODE> - the value's index<DD><CODE>name</CODE> - the new name</DL>
</DD>
</DL>
<HR>

<A NAME="renameAttributeValue(weka.core.Attribute, java.lang.String, java.lang.String)"><!-- --></A><H3>
renameAttributeValue</H3>
<PRE>
public final void <B>renameAttributeValue</B>(<A HREF="../../weka/core/Attribute.html">Attribute</A>&nbsp;att,
                                       java.lang.String&nbsp;val,
                                       java.lang.String&nbsp;name)</PRE>
<DL>
<DD>Renames the value of a nominal (or string) attribute value. This
 change only affects this dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute<DD><CODE>val</CODE> - the value<DD><CODE>name</CODE> - the new name</DL>
</DD>
</DL>
<HR>

<A NAME="resample(java.util.Random)"><!-- --></A><H3>
resample</H3>
<PRE>
public final <A HREF="../../weka/core/Instances.html">Instances</A> <B>resample</B>(java.util.Random&nbsp;random)</PRE>
<DL>
<DD>Creates a new dataset of the same size using random sampling
 with replacement.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>random</CODE> - a random number generator<DT><B>Returns:</B><DD>the new dataset</DL>
</DD>
</DL>
<HR>

<A NAME="resampleWithWeights(java.util.Random)"><!-- --></A><H3>
resampleWithWeights</H3>
<PRE>
public final <A HREF="../../weka/core/Instances.html">Instances</A> <B>resampleWithWeights</B>(java.util.Random&nbsp;random)</PRE>
<DL>
<DD>Creates a new dataset of the same size using random sampling
 with replacement according to the current instance weights. The
 weights of the instances in the new dataset are set to one.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>random</CODE> - a random number generator<DT><B>Returns:</B><DD>the new dataset</DL>
</DD>
</DL>
<HR>

<A NAME="resampleWithWeights(java.util.Random, double[])"><!-- --></A><H3>
resampleWithWeights</H3>
<PRE>
public final <A HREF="../../weka/core/Instances.html">Instances</A> <B>resampleWithWeights</B>(java.util.Random&nbsp;random,
                                           double[]&nbsp;weights)</PRE>
<DL>
<DD>Creates a new dataset of the same size using random sampling
 with replacement according to the given weight vector. The
 weights of the instances in the new dataset are set to one.
 The length of the weight vector has to be the same as the
 number of instances in the dataset, and all weights have to
 be positive.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>random</CODE> - a random number generator<DD><CODE>weights</CODE> - the weight vector<DT><B>Returns:</B><DD>the new dataset<DT><B>Throws:</B><DD><CODE>java.lang.IllegalArgumentException</CODE> - if the weights array is of the wrong
 length or contains negative weights.</DL>
</DD>
</DL>
<HR>

<A NAME="setClass(weka.core.Attribute)"><!-- --></A><H3>
setClass</H3>
<PRE>
public final void <B>setClass</B>(<A HREF="../../weka/core/Attribute.html">Attribute</A>&nbsp;att)</PRE>
<DL>
<DD>Sets the class attribute.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - attribute to be the class</DL>
</DD>
</DL>
<HR>

<A NAME="setClassIndex(int)"><!-- --></A><H3>
setClassIndex</H3>
<PRE>
public final void <B>setClassIndex</B>(int&nbsp;classIndex)</PRE>
<DL>
<DD>Sets the class index of the set.
 If the class index is negative there is assumed to be no class.
 (ie. it is undefined)<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>classIndex</CODE> - the new class index<DT><B>Throws:</B><DD><CODE>java.lang.IllegalArgumentException</CODE> - if the class index is too big or < 0</DL>
</DD>
</DL>
<HR>

<A NAME="setRelationName(java.lang.String)"><!-- --></A><H3>
setRelationName</H3>
<PRE>
public final void <B>setRelationName</B>(java.lang.String&nbsp;newName)</PRE>
<DL>
<DD>Sets the relation's name.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newName</CODE> - the new relation name.</DL>
</DD>
</DL>
<HR>

<A NAME="sort(int)"><!-- --></A><H3>
sort</H3>
<PRE>
public final void <B>sort</B>(int&nbsp;attIndex)</PRE>
<DL>
<DD>Sorts the instances based on an attribute. For numeric attributes, 
 instances are sorted in ascending order. For nominal attributes, 
 instances are sorted based on the attribute label ordering 
 specified in the header. Instances with missing values for the 
 attribute are placed at the end of the dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>attIndex</CODE> - the attribute's index</DL>
</DD>
</DL>
<HR>

<A NAME="sort(weka.core.Attribute)"><!-- --></A><H3>
sort</H3>
<PRE>
public final void <B>sort</B>(<A HREF="../../weka/core/Attribute.html">Attribute</A>&nbsp;att)</PRE>
<DL>
<DD>Sorts the instances based on an attribute. For numeric attributes, 
 instances are sorted into ascending order. For nominal attributes, 
 instances are sorted based on the attribute label ordering 
 specified in the header. Instances with missing values for the 
 attribute are placed at the end of the dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>att</CODE> - the attribute</DL>
</DD>
</DL>
<HR>

<A NAME="stratify(int)"><!-- --></A><H3>
stratify</H3>
<PRE>
public final void <B>stratify</B>(int&nbsp;numFolds)</PRE>
<DL>
<DD>Stratifies a set of instances according to its class values 
 if the class attribute is nominal (so that afterwards a 
 stratified cross-validation can be performed).<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>numFolds</CODE> - the number of folds in the cross-validation<DT><B>Throws:</B><DD><CODE><A HREF="../../weka/core/UnassignedClassException.html">UnassignedClassException</A></CODE> - if the class is not set</DL>
</DD>
</DL>
<HR>

<A NAME="sumOfWeights()"><!-- --></A><H3>
sumOfWeights</H3>
<PRE>
public final double <B>sumOfWeights</B>()</PRE>
<DL>
<DD>Computes the sum of all the instances' weights.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the sum of all the instances' weights as a double</DL>
</DD>
</DL>
<HR>

<A NAME="testCV(int, int)"><!-- --></A><H3>
testCV</H3>
<PRE>
public <A HREF="../../weka/core/Instances.html">Instances</A> <B>testCV</B>(int&nbsp;numFolds,
                        int&nbsp;numFold)</PRE>
<DL>
<DD>Creates the test set for one fold of a cross-validation on 
 the dataset.<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>numFolds</CODE> - the number of folds in the cross-validation. Must
 be greater than 1.<DD><CODE>numFold</CODE> - 0 for the first fold, 1 for the second, ...<DT><B>Returns:</B><DD>the test set as a set of weighted instances<DT><B>Throws:</B><DD><CODE>java.lang.IllegalArgumentException</CODE> - if the number of folds is less than 2
 or greater than the number of instances.</DL>
</DD>
</DL>
<HR>

<A NAME="toString()"><!-- --></A><H3>
toString</H3>
<PRE>
public final java.lang.String <B>toString</B>()</PRE>
<DL>
<DD>Returns the dataset as a string in ARFF format. Strings
 are quoted if they contain whitespace characters, or if they
 are a question mark.<DD><DL>
<DT><B>Overrides:</B><DD><CODE>toString</CODE> in class <CODE>java.lang.Object</CODE></DL>
</DD>
<DD><DL>
<DT><B>Returns:</B><DD>the dataset in ARFF format as a string</DL>
</DD>
</DL>
<HR>

<A NAME="trainCV(int, int)">