stringtowordvector.html

weka是机器学习和数据挖掘领域最有影响力的开源项目之一

public java.lang.String <B>getDelimiters</B>()</PRE>
<DL>
<DD>Get the value of delimiters.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Value of delimiters.</DL>
</DD>
</DL>
<HR>

<A NAME="setDelimiters(java.lang.String)"><!-- --></A><H3>
setDelimiters</H3>
<PRE>
public void <B>setDelimiters</B>(java.lang.String&nbsp;newDelimiters)</PRE>
<DL>
<DD>Set the value of delimiters.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newDelimiters</CODE> - Value to assign to delimiters.</DL>
</DD>
</DL>
<HR>

<A NAME="delimitersTipText()"><!-- --></A><H3>
delimitersTipText</H3>
<PRE>
public java.lang.String <B>delimitersTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property
<P>
<DD><DL>
</DL>
</DD>
<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="getSelectedRange()"><!-- --></A><H3>
getSelectedRange</H3>
<PRE>
public <A HREF="../../../../weka/core/Range.html" title="class in weka.core">Range</A> <B>getSelectedRange</B>()</PRE>
<DL>
<DD>Get the value of m_SelectedRange.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>Value of m_SelectedRange.</DL>
</DD>
</DL>
<HR>

<A NAME="setSelectedRange(java.lang.String)"><!-- --></A><H3>
setSelectedRange</H3>
<PRE>
public void <B>setSelectedRange</B>(java.lang.String&nbsp;newSelectedRange)</PRE>
<DL>
<DD>Set the value of m_SelectedRange.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newSelectedRange</CODE> - Value to assign to m_SelectedRange.</DL>
</DD>
</DL>
<HR>

<A NAME="getAttributeNamePrefix()"><!-- --></A><H3>
getAttributeNamePrefix</H3>
<PRE>
public java.lang.String <B>getAttributeNamePrefix</B>()</PRE>
<DL>
<DD>Get the attribute name prefix.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>The current attribute name prefix.</DL>
</DD>
</DL>
<HR>

<A NAME="setAttributeNamePrefix(java.lang.String)"><!-- --></A><H3>
setAttributeNamePrefix</H3>
<PRE>
public void <B>setAttributeNamePrefix</B>(java.lang.String&nbsp;newPrefix)</PRE>
<DL>
<DD>Set the attribute name prefix.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newPrefix</CODE> - String to use as the attribute name prefix.</DL>
</DD>
</DL>
<HR>

<A NAME="attributeNamePrefixTipText()"><!-- --></A><H3>
attributeNamePrefixTipText</H3>
<PRE>
public java.lang.String <B>attributeNamePrefixTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property
<P>
<DD><DL>
</DL>
</DD>
<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="getWordsToKeep()"><!-- --></A><H3>
getWordsToKeep</H3>
<PRE>
public int <B>getWordsToKeep</B>()</PRE>
<DL>
<DD>Gets the number of words (per class if there is a class attribute
 assigned) to attempt to keep.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>the target number of words in the output vector (per class if
 assigned).</DL>
</DD>
</DL>
<HR>

<A NAME="setWordsToKeep(int)"><!-- --></A><H3>
setWordsToKeep</H3>
<PRE>
public void <B>setWordsToKeep</B>(int&nbsp;newWordsToKeep)</PRE>
<DL>
<DD>Sets the number of words (per class if there is a class attribute
 assigned) to attempt to keep.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newWordsToKeep</CODE> - the target number of words in the output 
 vector (per class if assigned).</DL>
</DD>
</DL>
<HR>

<A NAME="wordsToKeepTipText()"><!-- --></A><H3>
wordsToKeepTipText</H3>
<PRE>
public java.lang.String <B>wordsToKeepTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property
<P>
<DD><DL>
</DL>
</DD>
<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="getTFTransform()"><!-- --></A><H3>
getTFTransform</H3>
<PRE>
public boolean <B>getTFTransform</B>()</PRE>
<DL>
<DD>Gets whether if the word frequencies should be transformed into
  log(1+fij) where fij is the frequency of word i in document(instance) j.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>true if word frequencies are to be transformed.</DL>
</DD>
</DL>
<HR>

<A NAME="setTFTransform(boolean)"><!-- --></A><H3>
setTFTransform</H3>
<PRE>
public void <B>setTFTransform</B>(boolean&nbsp;TFTransform)</PRE>
<DL>
<DD>Sets whether if the word frequencies should be transformed into
  log(1+fij) where fij is the frequency of word i in document(instance) j.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>TFTransform</CODE> - true if word frequencies are to be transformed.</DL>
</DD>
</DL>
<HR>

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

<DT><B>Returns:</B><DD>true if the word frequencies are to be transformed.</DL>
</DD>
</DL>
<HR>

<A NAME="setIDFTransform(boolean)"><!-- --></A><H3>
setIDFTransform</H3>
<PRE>
public void <B>setIDFTransform</B>(boolean&nbsp;IDFTransform)</PRE>
<DL>
<DD>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.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>IDFTransform</CODE> - true if the word frequecies are to be transformed</DL>
</DD>
</DL>
<HR>

<A NAME="IDFTransformTipText()"><!-- --></A><H3>
IDFTransformTipText</H3>
<PRE>
public java.lang.String <B>IDFTransformTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property
<P>
<DD><DL>
</DL>
</DD>
<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="getNormalizeDocLength()"><!-- --></A><H3>
getNormalizeDocLength</H3>
<PRE>
public <A HREF="../../../../weka/core/SelectedTag.html" title="class in weka.core">SelectedTag</A> <B>getNormalizeDocLength</B>()</PRE>
<DL>
<DD>Gets whether if the word frequencies for a document (instance) should
  be normalized or not.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>

<DT><B>Returns:</B><DD>true if word frequencies are to be normalized.</DL>
</DD>
</DL>
<HR>

<A NAME="setNormalizeDocLength(weka.core.SelectedTag)"><!-- --></A><H3>
setNormalizeDocLength</H3>
<PRE>
public void <B>setNormalizeDocLength</B>(<A HREF="../../../../weka/core/SelectedTag.html" title="class in weka.core">SelectedTag</A>&nbsp;newType)</PRE>
<DL>
<DD>Sets whether if the word frequencies for a document (instance) should
  be normalized or not.
<P>
<DD><DL>
</DL>
</DD>
<DD><DL>
<DT><B>Parameters:</B><DD><CODE>newType</CODE> - the new type.</DL>
</DD>
</DL>
<HR>

<A NAME="normalizeDocLengthTipText()"><!-- --></A><H3>
normalizeDocLengthTipText</H3>
<PRE>
public java.lang.String <B>normalizeDocLengthTipText</B>()</PRE>
<DL>
<DD>Returns the tip text for this property
<P>
<DD><DL>
</DL>
</DD>
<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="getOnlyAlphabeticTokens()"><!-- --></A><H3>
getOnlyAlphabeticTokens</H3>
<PRE>
public boolean <B>getOnlyAlphabeticTokens</B>()</PRE>
<DL>
<DD>Gets whether if the tokens are to be formed only from contiguous 
  alphabetic sequences. The delimiter string is ignored if this is true.
<P>
<DD><DL>