📄 stringtowordvector.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"><!--NewPage--><HTML><HEAD><!-- Generated by javadoc (build 1.5.0_10) on Fri Jan 26 16:34:53 NZDT 2007 --><TITLE>StringToWordVector</TITLE><META NAME="keywords" CONTENT="weka.filters.unsupervised.attribute.StringToWordVector class"><LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../stylesheet.css" TITLE="Style"><SCRIPT type="text/javascript">function windowTitle(){ parent.document.title="StringToWordVector";}</SCRIPT><NOSCRIPT></NOSCRIPT></HEAD><BODY BGCOLOR="white" onload="windowTitle();"><!-- ========= START OF TOP NAVBAR ======= --><A NAME="navbar_top"><!-- --></A><A HREF="#skip-navbar_top" title="Skip navigation links"></A><TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY=""><TR><TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1"><A NAME="navbar_top_firstrow"><!-- --></A><TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY=""> <TR ALIGN="center" VALIGN="top"> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A> </TD> <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> <FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../index-all.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A> </TD> <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1"> <A HREF="http://www.cs.waikato.ac.nz/ml/weka/" target="_blank"><FONT CLASS="NavBarFont1"><B>Weka's home</B></FONT></A> </TD> </TR></TABLE></TD><TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM></EM></TD></TR><TR><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../weka/filters/unsupervised/attribute/StringToNominal.html" title="class in weka.filters.unsupervised.attribute"><B>PREV CLASS</B></A> <A HREF="../../../../weka/filters/unsupervised/attribute/SwapValues.html" title="class in weka.filters.unsupervised.attribute"><B>NEXT CLASS</B></A></FONT></TD><TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2"> <A HREF="../../../../index.html?weka/filters/unsupervised/attribute/StringToWordVector.html" target="_top"><B>FRAMES</B></A> <A HREF="StringToWordVector.html" target="_top"><B>NO FRAMES</B></A> <SCRIPT type="text/javascript"> <!-- if(window==top) { document.writeln('<A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A>'); } //--></SCRIPT><NOSCRIPT> <A HREF="../../../../allclasses-noframe.html"><B>All Classes</B></A></NOSCRIPT></FONT></TD></TR><TR><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2"> SUMMARY: NESTED | <A HREF="#field_summary">FIELD</A> | <A HREF="#constructor_summary">CONSTR</A> | <A HREF="#method_summary">METHOD</A></FONT></TD><TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">DETAIL: <A HREF="#field_detail">FIELD</A> | <A HREF="#constructor_detail">CONSTR</A> | <A HREF="#method_detail">METHOD</A></FONT></TD></TR></TABLE><A NAME="skip-navbar_top"></A><!-- ========= END OF TOP NAVBAR ========= --><HR><!-- ======== START OF CLASS DATA ======== --><H2><FONT SIZE="-1">weka.filters.unsupervised.attribute</FONT><BR>Class StringToWordVector</H2><PRE>java.lang.Object <IMG SRC="../../../../resources/inherit.gif" ALT="extended by "><A HREF="../../../../weka/filters/Filter.html" title="class in weka.filters">weka.filters.Filter</A> <IMG SRC="../../../../resources/inherit.gif" ALT="extended by "><B>weka.filters.unsupervised.attribute.StringToWordVector</B></PRE><DL><DT><B>All Implemented Interfaces:</B> <DD>java.io.Serializable, <A HREF="../../../../weka/core/CapabilitiesHandler.html" title="interface in weka.core">CapabilitiesHandler</A>, <A HREF="../../../../weka/core/OptionHandler.html" title="interface in weka.core">OptionHandler</A>, <A HREF="../../../../weka/filters/UnsupervisedFilter.html" title="interface in weka.filters">UnsupervisedFilter</A></DD></DL><HR><DL><DT><PRE>public class <B>StringToWordVector</B><DT>extends <A HREF="../../../../weka/filters/Filter.html" title="class in weka.filters">Filter</A><DT>implements <A HREF="../../../../weka/filters/UnsupervisedFilter.html" title="interface in weka.filters">UnsupervisedFilter</A>, <A HREF="../../../../weka/core/OptionHandler.html" title="interface in weka.core">OptionHandler</A></DL></PRE><P><!-- globalinfo-start --> Converts String attributes into a set of attributes representing word occurrence information from the text contained in the strings. The set of words (attributes) is determined by the first batch filtered (typically training data). <p/> <!-- globalinfo-end --> <!-- options-start --> Valid options are: <p/> <pre> -C Output word counts rather than boolean word presence. </pre> <pre> -D <delimiter set> String containing the set of delimiter characters (default: " \n\t.,:'\"()?!")</pre> <pre> -R <index1,index2-index4,...> Specify list of string attributes to convert to words (as weka Range). (default: select all string attributes)</pre> <pre> -P <attribute name prefix> Specify a prefix for the created attribute names. (default: "")</pre> <pre> -W <number of words to keep> Specify approximate number of word fields to create. Surplus words will be discarded.. (default: 1000)</pre> <pre> -T Transform the word frequencies into log(1+fij) where fij is the frequency of word i in jth document(instance). </pre> <pre> -I Transform each word frequency into: fij*log(num of Documents/num of documents containing word i) where fij if frequency of word i in jth document(instance)</pre> <pre> -N Whether to 0=not normalize/1=normalize all data/2=normalize test data only to average length of training documents (default 0=don't normalize).</pre> <pre> -A Only form tokens from contiguous alphabetic sequences (The delimiter string is ignored if this is set).</pre> <pre> -L Convert all tokens to lowercase before adding to the dictionary.</pre> <pre> -S Ignore words that are in the stoplist.</pre> <pre> -stemmer <spec> The stemmering algorihtm (classname plus parameters) to use.</pre> <pre> -M <int> The minimum term frequency (default = 1).</pre> <pre> -O If this is set, the maximum number of words and the minimum term frequency is not enforced on a per-class basis but based on the documents in all the classes (even if a class attribute is set).</pre> <!-- options-end --><P><P><DL><DT><B>Version:</B></DT> <DD>$Revision: 1.15 $</DD><DT><B>Author:</B></DT> <DD>Len Trigg (len@reeltwo.com), Stuart Inglis (stuart@reeltwo.com)</DD><DT><B>See Also:</B><DD><A HREF="../../../../serialized-form.html#weka.filters.unsupervised.attribute.StringToWordVector">Serialized Form</A></DL><HR><P><!-- =========== FIELD SUMMARY =========== --><A NAME="field_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Field Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static int</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#FILTER_NONE">FILTER_NONE</A></B></CODE><BR> normalization: No normalization</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static int</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#FILTER_NORMALIZE_ALL">FILTER_NORMALIZE_ALL</A></B></CODE><BR> normalization: Normalize all data</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static int</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#FILTER_NORMALIZE_TEST_ONLY">FILTER_NORMALIZE_TEST_ONLY</A></B></CODE><BR> normalization: Normalize test data only</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE>static <A HREF="../../../../weka/core/Tag.html" title="class in weka.core">Tag</A>[]</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#TAGS_FILTER">TAGS_FILTER</A></B></CODE><BR> Specifies whether document's (instance's) word frequencies are to be normalized.</TD></TR></TABLE> <!-- ======== CONSTRUCTOR SUMMARY ======== --><A NAME="constructor_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Constructor Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#StringToWordVector()">StringToWordVector</A></B>()</CODE><BR> Default constructor.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#StringToWordVector(int)">StringToWordVector</A></B>(int wordsToKeep)</CODE><BR> Constructor that allows specification of the target number of words in the output.</TD></TR></TABLE> <!-- ========== METHOD SUMMARY =========== --><A NAME="method_summary"><!-- --></A><TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY=""><TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor"><TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2"><B>Method Summary</B></FONT></TH></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#attributeNamePrefixTipText()">attributeNamePrefixTipText</A></B>()</CODE><BR> Returns the tip text for this property</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#batchFinished()">batchFinished</A></B>()</CODE><BR> Signify that this batch of input to the filter is finished.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#delimitersTipText()">delimitersTipText</A></B>()</CODE><BR> Returns the tip text for this property</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#doNotOperateOnPerClassBasisTipText()">doNotOperateOnPerClassBasisTipText</A></B>()</CODE><BR> Returns the tip text for this property.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getAttributeNamePrefix()">getAttributeNamePrefix</A></B>()</CODE><BR> Get the attribute name prefix.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> <A HREF="../../../../weka/core/Capabilities.html" title="class in weka.core">Capabilities</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getCapabilities()">getCapabilities</A></B>()</CODE><BR> Returns the Capabilities of this filter.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> java.lang.String</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getDelimiters()">getDelimiters</A></B>()</CODE><BR> Get the value of delimiters.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getDoNotOperateOnPerClassBasis()">getDoNotOperateOnPerClassBasis</A></B>()</CODE><BR> Get the DoNotOperateOnPerClassBasis value.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getIDFTransform()">getIDFTransform</A></B>()</CODE><BR> Sets whether if the word frequencies in a document should be transformed into: <br> fij*log(num of Docs/num of Docs with word i) <br> where fij is the frequency of word i in document(instance) j.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getLowerCaseTokens()">getLowerCaseTokens</A></B>()</CODE><BR> Gets whether if the tokens are to be downcased or not.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> int</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getMinTermFreq()">getMinTermFreq</A></B>()</CODE><BR> Get the MinTermFreq value.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> <A HREF="../../../../weka/core/SelectedTag.html" title="class in weka.core">SelectedTag</A></CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getNormalizeDocLength()">getNormalizeDocLength</A></B>()</CODE><BR> Gets whether if the word frequencies for a document (instance) should be normalized or not.</TD></TR><TR BGCOLOR="white" CLASS="TableRowColor"><TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1"><CODE> boolean</CODE></FONT></TD><TD><CODE><B><A HREF="../../../../weka/filters/unsupervised/attribute/StringToWordVector.html#getOnlyAlphabeticTokens()">getOnlyAlphabeticTokens</A></B>()</CODE>⌨️ 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 + -