📄 learnparam.html
字号:
Factor to multiply C for positive examples.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> double</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#svm_costratio_unlab">svm_costratio_unlab</A></B></CODE>
<BR>
</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#svm_iter_to_shrink">svm_iter_to_shrink</A></B></CODE>
<BR>
Iterations h after which an example can be removed by shrinking.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#svm_maxqpsize">svm_maxqpsize</A></B></CODE>
<BR>
Size q of working set.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#svm_newvarsinqp">svm_newvarsinqp</A></B></CODE>
<BR>
New variables to enter the working set in each iteration.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> double</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#svm_unlabbound">svm_unlabbound</A></B></CODE>
<BR>
</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#totwords">totwords</A></B></CODE>
<BR>
Total amount of features.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> double</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#transduction_posratio">transduction_posratio</A></B></CODE>
<BR>
Fraction of unlabeled examples to be classified as positives.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#type">type</A></B></CODE>
<BR>
Selects between CLASSIFICATION, REGRESSION, RANKING, or OPTIMIZATION mode.</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="../jnisvmlight/LearnParam.html#verbosity">verbosity</A></B></CODE>
<BR>
The level of SVM-light debugging infos.</TD>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
<CODE> long</CODE></FONT></TD>
<TD><CODE><B><A HREF="../jnisvmlight/LearnParam.html#xa_depth">xa_depth</A></B></CODE>
<BR>
Parameter in xi/alpha-estimates upper bounding the number of SV the current alpha_t is distributed over.</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="../jnisvmlight/LearnParam.html#LearnParam()">LearnParam</A></B>()</CODE>
<BR>
Initializes the learning parameters with the default SVM-light values.</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>
</TABLE>
<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
<TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH>
</TR>
<TR BGCOLOR="white" CLASS="TableRowColor">
<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
</TR>
</TABLE>
<P>
<!-- ============ FIELD DETAIL =========== -->
<A NAME="field_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>Field Detail</B></FONT></TH>
</TR>
</TABLE>
<A NAME="CLASSIFICATION"><!-- --></A><H3>
CLASSIFICATION</H3>
<PRE>
public static final int <A HREF="../src-html/jnisvmlight/LearnParam.html#line.32"><B>CLASSIFICATION</B></A></PRE>
<DL>
<DD>Trains a classification model.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../constant-values.html#jnisvmlight.LearnParam.CLASSIFICATION">Constant Field Values</A></DL>
</DL>
<HR>
<A NAME="OPTIMIZATION"><!-- --></A><H3>
OPTIMIZATION</H3>
<PRE>
public static final int <A HREF="../src-html/jnisvmlight/LearnParam.html#line.35"><B>OPTIMIZATION</B></A></PRE>
<DL>
<DD>Trains on general set of constraints.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../constant-values.html#jnisvmlight.LearnParam.OPTIMIZATION">Constant Field Values</A></DL>
</DL>
<HR>
<A NAME="RANKING"><!-- --></A><H3>
RANKING</H3>
<PRE>
public static final int <A HREF="../src-html/jnisvmlight/LearnParam.html#line.38"><B>RANKING</B></A></PRE>
<DL>
<DD>Trains a ranking model.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../constant-values.html#jnisvmlight.LearnParam.RANKING">Constant Field Values</A></DL>
</DL>
<HR>
<A NAME="REGRESSION"><!-- --></A><H3>
REGRESSION</H3>
<PRE>
public static final int <A HREF="../src-html/jnisvmlight/LearnParam.html#line.41"><B>REGRESSION</B></A></PRE>
<DL>
<DD>Trains a regression model.
<P>
<DL>
<DT><B>See Also:</B><DD><A HREF="../constant-values.html#jnisvmlight.LearnParam.REGRESSION">Constant Field Values</A></DL>
</DL>
<HR>
<A NAME="alphafile"><!-- --></A><H3>
alphafile</H3>
<PRE>
public java.lang.String <A HREF="../src-html/jnisvmlight/LearnParam.html#line.47"><B>alphafile</B></A></PRE>
<DL>
<DD>File to store optimal alphas in. use empty string if alphas should not be output.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="argc"><!-- --></A><H3>
argc</H3>
<PRE>
public int <A HREF="../src-html/jnisvmlight/LearnParam.html#line.50"><B>argc</B></A></PRE>
<DL>
<DD>The cardinality of the command line parameters.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="argv"><!-- --></A><H3>
argv</H3>
<PRE>
public java.lang.String[] <A HREF="../src-html/jnisvmlight/LearnParam.html#line.56"><B>argv</B></A></PRE>
<DL>
<DD>Optionally simulates a simple command shell-like usage and transfers the command line parameters to SVM-light.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="biased_hyperplane"><!-- --></A><H3>
biased_hyperplane</H3>
<PRE>
public long <A HREF="../src-html/jnisvmlight/LearnParam.html#line.59"><B>biased_hyperplane</B></A></PRE>
<DL>
<DD>If nonzero, use hyperplane w*x+b=0 otherwise w*x=0.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="compute_loo"><!-- --></A><H3>
compute_loo</H3>
<PRE>
public long <A HREF="../src-html/jnisvmlight/LearnParam.html#line.62"><B>compute_loo</B></A></PRE>
<DL>
<DD>If nonzero, computes leave-one-outestimates.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="eps"><!-- --></A><H3>
eps</H3>
<PRE>
public double <A HREF="../src-html/jnisvmlight/LearnParam.html#line.65"><B>eps</B></A></PRE>
<DL>
<DD>Regression epsilon (eps=1.0 for classification).
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="epsilon_a"><!-- --></A><H3>
epsilon_a</H3>
<PRE>
public double <A HREF="../src-html/jnisvmlight/LearnParam.html#line.68"><B>epsilon_a</B></A></PRE>
<DL>
<DD>Tolerable error on alphas at bounds.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="epsilon_const"><!-- --></A><H3>
epsilon_const</H3>
<PRE>
public double <A HREF="../src-html/jnisvmlight/LearnParam.html#line.71"><B>epsilon_const</B></A></PRE>
<DL>
<DD>Tolerable error on eq-constraint.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="epsilon_crit"><!-- --></A><H3>
epsilon_crit</H3>
<PRE>
public double <A HREF="../src-html/jnisvmlight/LearnParam.html#line.74"><B>epsilon_crit</B></A></PRE>
<DL>
<DD>Tolerable error for distances used in stopping criterion.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="epsilon_shrink"><!-- --></A><H3>
epsilon_shrink</H3>
<PRE>
public double <A HREF="../src-html/jnisvmlight/LearnParam.html#line.77"><B>epsilon_shrink</B></A></PRE>
<DL>
<DD>How much a multiplier should be above zero for shrinking.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="kernel_cache_size"><!-- --></A><H3>
kernel_cache_size</H3>
<PRE>
public long <A HREF="../src-html/jnisvmlight/LearnParam.html#line.80"><B>kernel_cache_size</B></A></PRE>
<DL>
<DD>Size of kernel cache in megabytes.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="maxiter"><!-- --></A><H3>
maxiter</H3>
<PRE>
public long <A HREF="../src-html/jnisvmlight/LearnParam.html#line.86"><B>maxiter</B></A></PRE>
<DL>
<DD>Number of iterations after which the optimizer terminates, if there was no progress in maxdiff.
<P>
<DL>
</DL>
</DL>
<HR>
<A NAME="opt_precision"><!-- --></A><H3>
opt_precision</H3>
<PRE>
⌨️ 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 + -