.\" 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::Experiment 3"
.TH AI::Categorizer::Experiment 3 "2008-01-14" "perl v5.8.8" "User Contributed Perl Documentation"
.SH "NAME"
AI::Categorizer::Experiment \- Coordinate experimental results
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 3
\& use AI::Categorizer::Experiment;
\& my $e = new AI::Categorizer::Experiment(categories => \e%categories);
\& my $l = AI::Categorizer::Learner->restore_state(...path...);
.Ve
.PP
.Vb 4
\& while (my $d = ... get document ...) {
\&   my $h = $l->categorize($d); # A Hypothesis
\&   $e->add_hypothesis($h, [map $_->name, $d->categories]);
\& }
.Ve
.PP
.Vb 2
\& print "Micro F1: ", $e->micro_F1, "\en"; # Access a single statistic
\& print $e->stats_table; # Show several stats in table form
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
The \f(CW\*(C`AI::Categorizer::Experiment\*(C'\fR class helps you organize the
results of categorization experiments.  As you get lots of
categorization results (Hypotheses) back from the Learner, you can
feed these results to the Experiment class, along with the correct
answers.  When all results have been collected, you can get a report
on accuracy, precision, recall, F1, and so on, with both
macro-averaging and micro-averaging over categories.
.SH "METHODS"
.IX Header "METHODS"
The general execution flow when using this class is to create an
Experiment object, add a bunch of Hypotheses to it, and then report on
the results.
.PP
Internally, \f(CW\*(C`AI::Categorizer::Experiment\*(C'\fR inherits from the
\&\f(CW\*(C`Statistics::Contingency\*(C'\fR.  Please see the documentation of
\&\f(CW\*(C`Statistics::Contingency\*(C'\fR for a description of its interface.  All of
its methods are available here, with the following additions:
.IP "new( categories => \e%categories )" 4
.IX Item "new( categories => %categories )"
.PD 0
.IP "new( categories => \e@categories, verbose => 1, sig_figs => 2 )" 4
.IX Item "new( categories => @categories, verbose => 1, sig_figs => 2 )"
.PD
Returns a new Experiment object.  A required \f(CW\*(C`categories\*(C'\fR parameter
specifies the names of all categories in the data set.  The category
names may be specified either the keys in a reference to a hash, or as
the entries in a reference to an array.
.Sp
The \f(CW\*(C`new()\*(C'\fR method accepts a \f(CW\*(C`verbose\*(C'\fR parameter which
will cause some status/debugging information to be printed to
\&\f(CW\*(C`STDOUT\*(C'\fR when \f(CW\*(C`verbose\*(C'\fR is set to a true value.
.Sp
A \f(CW\*(C`sig_figs\*(C'\fR indicates the number of significant figures that should
be used when showing the results in the \f(CW\*(C`results_table()\*(C'\fR method.  It
does not affect the other methods like \f(CW\*(C`micro_precision()\*(C'\fR.
.ie n .IP "add_result($assigned, $correct\fR, \f(CW$name)" 4
.el .IP "add_result($assigned, \f(CW$correct\fR, \f(CW$name\fR)" 4
.IX Item "add_result($assigned, $correct, $name)"
Adds a new result to the experiment.  Please see the
\&\f(CW\*(C`Statistics::Contingency\*(C'\fR documentation for a description of this
method.
.ie n .IP "add_hypothesis($hypothesis, $correct_categories)" 4
.el .IP "add_hypothesis($hypothesis, \f(CW$correct_categories\fR)" 4
.IX Item "add_hypothesis($hypothesis, $correct_categories)"
Adds a new result to the experiment.  The first argument is a
\&\f(CW\*(C`AI::Categorizer::Hypothesis\*(C'\fR object such as one generated by a
Learner's \f(CW\*(C`categorize()\*(C'\fR method.  The list of correct categories can
be given as an array of category names (strings), as a hash whose keys
are the category names and whose values are anything logically true,
or as a single string if there is only one category.  For example, all
of the following are legal:
.Sp
.Vb 3
\& $e->add_hypothesis($h, "sports");
\& $e->add_hypothesis($h, ["sports", "finance"]);
\& $e->add_hypothesis($h, {sports => 1, finance => 1});
.Ve
.SH "AUTHOR"
.IX Header "AUTHOR"
Ken Williams <ken@mathforum.org>
.SH "COPYRIGHT"
.IX Header "COPYRIGHT"
This distribution is free software; you can redistribute it and/or
modify it under the same terms as Perl itself.  These terms apply to
every file in the distribution \- if you have questions, please contact
the author.