ngramtokenizer.html

来自「数据挖掘的最常用工具。由于开源」· HTML 代码 · 共 649 行 · 第 1/2 页

<DL>
</DL>

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

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

<A NAME="globalInfo()"><!-- --></A><H3>
globalInfo</H3>
<PRE>
public java.lang.String <B>globalInfo</B>()</PRE>
<DL>
<DD>Returns a string describing the stemmer
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html#globalInfo()">globalInfo</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html" title="class in weka.core.tokenizers">Tokenizer</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>a description suitable for displaying in the 
                        explorer/experimenter gui</DL>
</DD>
</DL>
<HR>

<A NAME="listOptions()"><!-- --></A><H3>
listOptions</H3>
<PRE>
public java.util.Enumeration <B>listOptions</B>()</PRE>
<DL>
<DD>Returns an enumeration of all the available options..
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/OptionHandler.html#listOptions()">listOptions</A></CODE> in interface <CODE><A HREF="../../../weka/core/OptionHandler.html" title="interface in weka.core">OptionHandler</A></CODE><DT><B>Overrides:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html#listOptions()">listOptions</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html" title="class in weka.core.tokenizers">CharacterDelimitedTokenizer</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>an enumeration of all available options.</DL>
</DD>
</DL>
<HR>

<A NAME="getOptions()"><!-- --></A><H3>
getOptions</H3>
<PRE>
public java.lang.String[] <B>getOptions</B>()</PRE>
<DL>
<DD>Gets the current option settings for the OptionHandler.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/OptionHandler.html#getOptions()">getOptions</A></CODE> in interface <CODE><A HREF="../../../weka/core/OptionHandler.html" title="interface in weka.core">OptionHandler</A></CODE><DT><B>Overrides:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html#getOptions()">getOptions</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html" title="class in weka.core.tokenizers">CharacterDelimitedTokenizer</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the list of current option settings as an array of 
                        strings</DL>
</DD>
</DL>
<HR>

<A NAME="setOptions(java.lang.String[])"><!-- --></A><H3>
setOptions</H3>
<PRE>
public void <B>setOptions</B>(java.lang.String[]&nbsp;options)
                throws java.lang.Exception</PRE>
<DL>
<DD>Parses a given list of options. <p/>

   <!-- options-start -->
 Valid options are: <p/>
 
 <pre> -delimiters &lt;value&gt;
  The delimiters to use
  (default ' \r\n\t.,;:'"()?!').</pre>
 
 <pre> -max &lt;int&gt;
  The max size of the Ngram (default = 3).</pre>
 
 <pre> -min &lt;int&gt;
  The min size of the Ngram (default = 1).</pre>
 
   <!-- options-end -->
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/OptionHandler.html#setOptions(java.lang.String[])">setOptions</A></CODE> in interface <CODE><A HREF="../../../weka/core/OptionHandler.html" title="interface in weka.core">OptionHandler</A></CODE><DT><B>Overrides:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html#setOptions(java.lang.String[])">setOptions</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/CharacterDelimitedTokenizer.html" title="class in weka.core.tokenizers">CharacterDelimitedTokenizer</A></CODE></DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>options</CODE> - the list of options as an array of strings
<DT><B>Throws:</B>
<DD><CODE>java.lang.Exception</CODE> - if an option is not supported</DL>
</DD>
</DL>
<HR>

<A NAME="getNGramMaxSize()"><!-- --></A><H3>
getNGramMaxSize</H3>
<PRE>
public int <B>getNGramMaxSize</B>()</PRE>
<DL>
<DD>Gets the max N of the NGram.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>the size (N) of the NGram.</DL>
</DD>
</DL>
<HR>

<A NAME="setNGramMaxSize(int)"><!-- --></A><H3>
setNGramMaxSize</H3>
<PRE>
public void <B>setNGramMaxSize</B>(int&nbsp;value)</PRE>
<DL>
<DD>Sets the max size of the Ngram.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>value</CODE> - the size of the NGram.</DL>
</DD>
</DL>
<HR>

<A NAME="NGramMaxSizeTipText()"><!-- --></A><H3>
NGramMaxSizeTipText</H3>
<PRE>
public java.lang.String <B>NGramMaxSizeTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>tip text for this property suitable for
                        displaying in the explorer/experimenter gui</DL>
</DD>
</DL>
<HR>

<A NAME="setNGramMinSize(int)"><!-- --></A><H3>
setNGramMinSize</H3>
<PRE>
public void <B>setNGramMinSize</B>(int&nbsp;value)</PRE>
<DL>
<DD>Sets the min size of the Ngram.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>value</CODE> - the size of the NGram.</DL>
</DD>
</DL>
<HR>

<A NAME="getNGramMinSize()"><!-- --></A><H3>
getNGramMinSize</H3>
<PRE>
public int <B>getNGramMinSize</B>()</PRE>
<DL>
<DD>Gets the min N of the NGram.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>the size (N) of the NGram.</DL>
</DD>
</DL>
<HR>

<A NAME="NGramMinSizeTipText()"><!-- --></A><H3>
NGramMinSizeTipText</H3>
<PRE>
public java.lang.String <B>NGramMinSizeTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>tip text for this property suitable for
                        displaying in the explorer/experimenter gui</DL>
</DD>
</DL>
<HR>

<A NAME="hasMoreElements()"><!-- --></A><H3>
hasMoreElements</H3>
<PRE>
public boolean <B>hasMoreElements</B>()</PRE>
<DL>
<DD>returns true if there's more elements available
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE>hasMoreElements</CODE> in interface <CODE>java.util.Enumeration</CODE><DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html#hasMoreElements()">hasMoreElements</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html" title="class in weka.core.tokenizers">Tokenizer</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>true if there are more elements available</DL>
</DD>
</DL>
<HR>

<A NAME="nextElement()"><!-- --></A><H3>
nextElement</H3>
<PRE>
public java.lang.Object <B>nextElement</B>()</PRE>
<DL>
<DD>Returns N-grams and also (N-1)-grams and .... and 1-grams.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE>nextElement</CODE> in interface <CODE>java.util.Enumeration</CODE><DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html#nextElement()">nextElement</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html" title="class in weka.core.tokenizers">Tokenizer</A></CODE></DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the next element</DL>
</DD>
</DL>
<HR>

<A NAME="tokenize(java.lang.String)"><!-- --></A><H3>
tokenize</H3>
<PRE>
public void <B>tokenize</B>(java.lang.String&nbsp;s)</PRE>
<DL>
<DD>Sets the string to tokenize. Tokenization happens immediately.
<P>
<DD><DL>
<DT><B>Specified by:</B><DD><CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html#tokenize(java.lang.String)">tokenize</A></CODE> in class <CODE><A HREF="../../../weka/core/tokenizers/Tokenizer.html" title="class in weka.core.tokenizers">Tokenizer</A></CODE></DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>s</CODE> - the string to tokenize</DL>
</DD>
</DL>
<HR>

<A NAME="getRevision()"><!-- --></A><H3>
getRevision</H3>
<PRE>
public java.lang.String <B>getRevision</B>()</PRE>
<DL>
<DD>Returns the revision string.
<P>
<DD><DL>

<DT><B>Returns:</B><DD>the revision</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>Runs the tokenizer with the given options and strings to tokenize.
 The tokens are printed to stdout.
<P>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>args</CODE> - the commandline options and strings to tokenize</DL>
</DD>
</DL>
<!-- ========= END OF CLASS DATA ========= -->
<HR>


<!-- ======= START OF BOTTOM NAVBAR ====== -->
<A NAME="navbar_bottom"><!-- --></A>
<A HREF="#skip-navbar_bottom" 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_bottom_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>&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> <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>&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/core/tokenizers/CharacterDelimitedTokenizer.html" title="class in weka.core.tokenizers"><B>PREV CLASS</B></A>&nbsp;
&nbsp;<A HREF="../../../weka/core/tokenizers/Tokenizer.html" title="class in weka.core.tokenizers"><B>NEXT CLASS</B></A></FONT></TD>
<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
  <A HREF="../../../index.html?weka/core/tokenizers/NGramTokenizer.html" target="_top"><B>FRAMES</B></A>  &nbsp;
&nbsp;<A HREF="NGramTokenizer.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
&nbsp;<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:&nbsp;NESTED&nbsp;|&nbsp;FIELD&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;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
</TR>
</TABLE>
<A NAME="skip-navbar_bottom"></A>
<!-- ======== END OF BOTTOM NAVBAR ======= -->

<HR>

</BODY>
</HTML>