.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  | will give a
.\" real vertical bar.  \*(C+ will give a nicer C++.  Capital omega is used to
.\" do unbreakable dashes and therefore won't be available.  \*(C` and \*(C'
.\" expand to `' in nroff, nothing in troff, for use with C<>.
.tr \(*W-|\(bv\*(Tr
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "AI::Categorizer::Learner::NaiveBayes 3"
.TH AI::Categorizer::Learner::NaiveBayes 3 "2008-01-14" "perl v5.8.8" "User Contributed Perl Documentation"
.SH "NAME"
AI::Categorizer::Learner::NaiveBayes \- Naive Bayes Algorithm For AI::Categorizer
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&  use AI::Categorizer::Learner::NaiveBayes;
.Ve
.PP
.Vb 1
\&  # Here $k is an AI::Categorizer::KnowledgeSet object
.Ve
.PP
.Vb 3
\&  my $nb = new AI::Categorizer::Learner::NaiveBayes(...parameters...);
\&  $nb->train(knowledge_set => $k);
\&  $nb->save_state('filename');
.Ve
.PP
.Vb 1
\&  ... time passes ...
.Ve
.PP
.Vb 7
\&  $nb = AI::Categorizer::Learner::NaiveBayes->restore_state('filename');
\&  my $c = new AI::Categorizer::Collection::Files( path => ... );
\&  while (my $document = $c->next) {
\&    my $hypothesis = $nb->categorize($document);
\&    print "Best assigned category: ", $hypothesis->best_category, "\en";
\&    print "All assigned categories: ", join(', ', $hypothesis->categories), "\en";
\&  }
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
This is an implementation of the Naive Bayes decision-making
algorithm, applied to the task of document categorization (as defined
by the AI::Categorizer module).  See AI::Categorizer for a complete
description of the interface.
.PP
This module is now a wrapper around the stand-alone
\&\f(CW\*(C`Algorithm::NaiveBayes\*(C'\fR module.  I moved the discussion of Bayes'
Theorem into that module's documentation.
.SH "METHODS"
.IX Header "METHODS"
This class inherits from the \f(CW\*(C`AI::Categorizer::Learner\*(C'\fR class, so all
of its methods are available unless explicitly mentioned here.
.Sh "\fInew()\fP"
.IX Subsection "new()"
Creates a new Naive Bayes Learner and returns it.  In addition to the
parameters accepted by the \f(CW\*(C`AI::Categorizer::Learner\*(C'\fR class, the
Naive Bayes subclass accepts the following parameters:
.IP "* threshold" 4
.IX Item "threshold"
Sets the score threshold for category membership.  The default is
currently 0.3.  Set the threshold lower to assign more categories per
document, set it higher to assign fewer.  This can be an effective way
to trade of between precision and recall.
.Sh "\fIthreshold()\fP"
.IX Subsection "threshold()"
Returns the current threshold value.  With an optional numeric
argument, you may set the threshold.
.ie n .Sh "train(knowledge_set => $k)"
.el .Sh "train(knowledge_set => \f(CW$k\fP)"
.IX Subsection "train(knowledge_set => $k)"
Trains the categorizer.  This prepares it for later use in
categorizing documents.  The \f(CW\*(C`knowledge_set\*(C'\fR parameter must provide
an object of the class \f(CW\*(C`AI::Categorizer::KnowledgeSet\*(C'\fR (or a subclass
thereof), populated with lots of documents and categories.  See
AI::Categorizer::KnowledgeSet for the details of how to create such
an object.
.Sh "categorize($document)"
.IX Subsection "categorize($document)"
Returns an \f(CW\*(C`AI::Categorizer::Hypothesis\*(C'\fR object representing the
categorizer's \*(L"best guess\*(R" about which categories the given document
should be assigned to.  See AI::Categorizer::Hypothesis for more
details on how to use this object.
.Sh "save_state($path)"
.IX Subsection "save_state($path)"
Saves the categorizer for later use.  This method is inherited from
\&\f(CW\*(C`AI::Categorizer::Storable\*(C'\fR.
.SH "CALCULATIONS"
.IX Header "CALCULATIONS"
The various probabilities used in the above calculations are found
directly from the training documents.  For instance, if there are 5000
total tokens (words) in the \*(L"sports\*(R" training documents and 200 of
them are the word \*(L"curling\*(R", then \f(CW\*(C`P(curling|sports) = 200/5000 =
0.04\*(C'\fR .  If there are 10,000 total tokens in the training corpus and
5,000 of them are in documents belonging to the category \*(L"sports\*(R",
then \f(CW\*(C`P(sports)\*(C'\fR = 5,000/10,000 = 0.5> .
.PP
Because the probabilities involved are often very small and we
multiply many of them together, the result is often a tiny tiny
number.  This could pose problems of floating-point underflow, so
instead of working with the actual probabilities we work with the
logarithms of the probabilities.  This also speeds up various
calculations in the \f(CW\*(C`categorize()\*(C'\fR method.
.SH "TO DO"
.IX Header "TO DO"
More work on the confidence scores \- right now the winning category
tends to dominate the scores overwhelmingly, when the scores should
probably be more evenly distributed.
.SH "AUTHOR"
.IX Header "AUTHOR"
Ken Williams, ken@forum.swarthmore.edu
.SH "COPYRIGHT"
.IX Header "COPYRIGHT"
Copyright 2000\-2003 Ken Williams.  All rights reserved.
.PP
This library is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
\&\fIAI::Categorizer\fR\|(3), \fIAlgorithm::NaiveBayes\fR\|(3)
.PP
\&\*(L"A re-examination of text categorization methods\*(R" by Yiming Yang
<http://www.cs.cmu.edu/~yiming/publications.html>
.PP
\&\*(L"On the Optimality of the Simple Bayesian Classifier under Zero-One
Loss\*(R" by Pedro Domingos
\&\*(L"http://www.cs.washington.edu/homes/pedrod/mlj97.ps.gz\*(R"
.PP
A simple but complete example of Bayes' Theorem from Dr. Math
\&\*(L"http://www.mathforum.com/dr.math/problems/battisfore.03.22.99.html\*(R"