AI-NaiveBayes
view release on metacpan - search on metacpan
view release on metacpan or search on metacpan
Revision history for AI::NaiveBayes
0.04 2017-01-20
Some doc fixes
Moved do my personal github repo
0.03
Synopsis example fixed
0.02
added 'train' class method for quick start
0.01
initial release
This is the Perl distribution AI-NaiveBayes.
Installing AI-NaiveBayes is straightforward.
## Installation with cpanm
If you have cpanm, you only need one line:
% cpanm AI::NaiveBayes
If it does not have permission to install modules to the current perl, cpanm
will automatically set up and install to a local::lib in your home directory.
See the local::lib documentation (https://metacpan.org/pod/local::lib) for
details on enabling it in your environment.
## Installing with the CPAN shell
Alternatively, if your CPAN shell is set up, you should just be able to do:
% cpan AI::NaiveBayes
## Manual installation
As a last resort, you can manually install it. Download the tarball, untar it,
then build it:
% perl Makefile.PL
% make && make test
Then install it:
% make install
If your perl is system-managed, you can create a local::lib in your home
directory to install modules to. For details, see the local::lib documentation:
https://metacpan.org/pod/local::lib
## Documentation
AI-NaiveBayes documentation is available as POD.
You can run perldoc from a shell to read the documentation:
% perldoc AI::NaiveBayes
This software is copyright (c) 2012 by Opera Software ASA.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
Terms of the Perl programming language system itself
a) the GNU General Public License as published by the Free
Software Foundation; either version 1, or (at your option) any
later version, or
b) the "Artistic License"
--- The GNU General Public License, Version 1, February 1989 ---
This software is Copyright (c) 2012 by Opera Software ASA.
This is free software, licensed under:
The GNU General Public License, Version 1, February 1989
GNU GENERAL PUBLIC LICENSE
Version 1, February 1989
Copyright (C) 1989 Free Software Foundation, Inc.
51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The license agreements of most software companies try to keep users
at the mercy of those companies. By contrast, our General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. The
General Public License applies to the Free Software Foundation's
software and to any other program whose authors commit to using it.
You can use it for your programs, too.
When we speak of free software, we are referring to freedom, not
price. Specifically, the General Public License is designed to make
sure that you have the freedom to give away or sell copies of free
software, that you receive source code or can get it if you want it,
that you can change the software or use pieces of it in new free
programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of a such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must tell them their rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any program or other work which
contains a notice placed by the copyright holder saying it may be
distributed under the terms of this General Public License. The
"Program", below, refers to any such program or work, and a "work based
on the Program" means either the Program or any work containing the
Program or a portion of it, either verbatim or with modifications. Each
licensee is addressed as "you".
1. You may copy and distribute verbatim copies of the Program's source
code as you receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice and
disclaimer of warranty; keep intact all the notices that refer to this
General Public License and to the absence of any warranty; and give any
other recipients of the Program a copy of this General Public License
along with the Program. You may charge a fee for the physical act of
transferring a copy.
2. You may modify your copy or copies of the Program or any portion of
it, and copy and distribute such modifications under the terms of Paragraph
1 above, provided that you also do the following:
a) cause the modified files to carry prominent notices stating that
you changed the files and the date of any change; and
b) cause the whole of any work that you distribute or publish, that
in whole or in part contains the Program or any part thereof, either
with or without modifications, to be licensed at no charge to all
third parties under the terms of this General Public License (except
that you may choose to grant warranty protection to some or all
third parties, at your option).
c) If the modified program normally reads commands interactively when
run, you must cause it, when started running for such interactive use
in the simplest and most usual way, to print or display an
announcement including an appropriate copyright notice and a notice
that there is no warranty (or else, saying that you provide a
warranty) and that users may redistribute the program under these
conditions, and telling the user how to view a copy of this General
Public License.
d) You may charge a fee for the physical act of transferring a
copy, and you may at your option offer warranty protection in
exchange for a fee.
Mere aggregation of another independent work with the Program (or its
derivative) on a volume of a storage or distribution medium does not bring
the other work under the scope of these terms.
3. You may copy and distribute the Program (or a portion or derivative of
it, under Paragraph 2) in object code or executable form under the terms of
Paragraphs 1 and 2 above provided that you also do one of the following:
a) accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of
Paragraphs 1 and 2 above; or,
b) accompany it with a written offer, valid for at least three
years, to give any third party free (except for a nominal charge
for the cost of distribution) a complete machine-readable copy of the
corresponding source code, to be distributed under the terms of
Paragraphs 1 and 2 above; or,
c) accompany it with the information you received as to where the
corresponding source code may be obtained. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form alone.)
Source code for a work means the preferred form of the work for making
modifications to it. For an executable file, complete source code means
all the source code for all modules it contains; but, as a special
exception, it need not include source code for modules which are standard
libraries that accompany the operating system on which the executable
file runs, or for standard header files or definitions files that
accompany that operating system.
4. You may not copy, modify, sublicense, distribute or transfer the
Program except as expressly provided under this General Public License.
Any attempt otherwise to copy, modify, sublicense, distribute or transfer
the Program is void, and will automatically terminate your rights to use
the Program under this License. However, parties who have received
copies, or rights to use copies, from you under this General Public
License will not have their licenses terminated so long as such parties
remain in full compliance.
5. By copying, distributing or modifying the Program (or any work based
on the Program) you indicate your acceptance of this license to do so,
and all its terms and conditions.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the original
licensor to copy, distribute or modify the Program subject to these
terms and conditions. You may not impose any further restrictions on the
recipients' exercise of the rights granted herein.
7. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of the license which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
the license, you may choose any version ever published by the Free Software
Foundation.
8. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
9. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
10. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS
Appendix: How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to humanity, the best way to achieve this is to make it
free software which everyone can redistribute and change under these
terms.
To do so, attach the following notices to the program. It is safest to
attach them to the start of each source file to most effectively convey
the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) 19yy <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 1, or (at your option)
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) 19xx name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the
appropriate parts of the General Public License. Of course, the
commands you use may be called something other than `show w' and `show
c'; they could even be mouse-clicks or menu items--whatever suits your
program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
program `Gnomovision' (a program to direct compilers to make passes
at assemblers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
That's all there is to it!
--- The Artistic License 1.0 ---
This software is Copyright (c) 2012 by Opera Software ASA.
This is free software, licensed under:
The Artistic License 1.0
The Artistic License
Preamble
The intent of this document is to state the conditions under which a Package
may be copied, such that the Copyright Holder maintains some semblance of
artistic control over the development of the package, while giving the users of
the package the right to use and distribute the Package in a more-or-less
customary fashion, plus the right to make reasonable modifications.
Definitions:
- "Package" refers to the collection of files distributed by the Copyright
Holder, and derivatives of that collection of files created through
textual modification.
- "Standard Version" refers to such a Package if it has not been modified,
or has been modified in accordance with the wishes of the Copyright
Holder.
- "Copyright Holder" is whoever is named in the copyright or copyrights for
the package.
- "You" is you, if you're thinking about copying or distributing this Package.
- "Reasonable copying fee" is whatever you can justify on the basis of media
cost, duplication charges, time of people involved, and so on. (You will
not be required to justify it to the Copyright Holder, but only to the
computing community at large as a market that must bear the fee.)
- "Freely Available" means that no fee is charged for the item itself, though
there may be fees involved in handling the item. It also means that
recipients of the item may redistribute it under the same conditions they
received it.
1. You may make and give away verbatim copies of the source form of the
Standard Version of this Package without restriction, provided that you
duplicate all of the original copyright notices and associated disclaimers.
2. You may apply bug fixes, portability fixes and other modifications derived
from the Public Domain or from the Copyright Holder. A Package modified in such
a way shall still be considered the Standard Version.
3. You may otherwise modify your copy of this Package in any way, provided that
you insert a prominent notice in each changed file stating how and when you
changed that file, and provided that you do at least ONE of the following:
a) place your modifications in the Public Domain or otherwise make them
Freely Available, such as by posting said modifications to Usenet or an
equivalent medium, or placing the modifications on a major archive site
such as ftp.uu.net, or by allowing the Copyright Holder to include your
modifications in the Standard Version of the Package.
b) use the modified Package only within your corporation or organization.
c) rename any non-standard executables so the names do not conflict with
standard executables, which must also be provided, and provide a separate
manual page for each non-standard executable that clearly documents how it
differs from the Standard Version.
d) make other distribution arrangements with the Copyright Holder.
4. You may distribute the programs of this Package in object code or executable
form, provided that you do at least ONE of the following:
a) distribute a Standard Version of the executables and library files,
together with instructions (in the manual page or equivalent) on where to
get the Standard Version.
b) accompany the distribution with the machine-readable source of the Package
with your modifications.
c) accompany any non-standard executables with their corresponding Standard
Version executables, giving the non-standard executables non-standard
names, and clearly documenting the differences in manual pages (or
equivalent), together with instructions on where to get the Standard
Version.
d) make other distribution arrangements with the Copyright Holder.
5. You may charge a reasonable copying fee for any distribution of this
Package. You may charge any fee you choose for support of this Package. You
may not charge a fee for this Package itself. However, you may distribute this
Package in aggregate with other (possibly commercial) programs as part of a
larger (possibly commercial) software distribution provided that you do not
advertise this Package as a product of your own.
6. The scripts and library files supplied as input to or produced as output
from the programs of this Package do not automatically fall under the copyright
of this Package, but belong to whomever generated them, and may be sold
commercially, and may be aggregated with this Package.
7. C or perl subroutines supplied by you and linked into this Package shall not
be considered part of this Package.
8. The name of the Copyright Holder may not be used to endorse or promote
products derived from this software without specific prior written permission.
9. THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED
WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF
MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
The End
# This file was automatically generated by Dist::Zilla::Plugin::Manifest v6.008.
Changes
INSTALL
LICENSE
MANIFEST
META.json
META.yml
Makefile.PL
README
README.pod
a
dist.ini
lib/AI/NaiveBayes.pm
lib/AI/NaiveBayes/Classification.pm
lib/AI/NaiveBayes/Learner.pm
t/01-learner.t
t/02-predict.t
t/author-pod-coverage.t
t/author-pod-syntax.t
t/default_training.t
{
"abstract" : "A Bayesian classifier",
"author" : [
"Zbigniew Lukasiak <zlukasiak@opera.com>",
"Tadeusz So\u015bnierz <tsosnierz@opera.com>",
"Ken Williams <ken@mathforum.org>"
],
"dynamic_config" : 0,
"generated_by" : "Dist::Zilla version 6.008, CPAN::Meta::Converter version 2.150005",
"license" : [
"perl_5"
],
"meta-spec" : {
"url" : "http://search.cpan.org/perldoc?CPAN::Meta::Spec",
"version" : 2
},
"name" : "AI-NaiveBayes",
"no_index" : {
"directory" : [
"examples",
"t/lib"
]
},
"prereqs" : {
"configure" : {
"requires" : {
"ExtUtils::MakeMaker" : "0"
}
},
"develop" : {
"requires" : {
"Pod::Coverage::TrustPod" : "0",
"Test::Pod" : "1.41",
"Test::Pod::Coverage" : "1.08"
}
},
"runtime" : {
"requires" : {
"File::Find::Rule" : "0.32",
"List::Util" : "0",
"Moose" : "1.15",
"MooseX::Storage" : "0.25",
"perl" : "5.010",
"strict" : "0",
"warnings" : "0"
}
},
"test" : {
"requires" : {
"Test::More" : "0"
}
}
},
"release_status" : "stable",
"resources" : {
"repository" : {
"type" : "git",
"web" : "http://github.com/zby/AI-NaiveBayes"
}
},
"version" : "0.04",
"x_contributors" : [
"schweickism <schweickism@hotmail.com>",
"Zbigniew \u0141ukasiak <zzbbyy@gmail.com>"
],
"x_serialization_backend" : "Cpanel::JSON::XS version 3.0225"
}
---
abstract: 'A Bayesian classifier'
author:
- 'Zbigniew Lukasiak <zlukasiak@opera.com>'
- 'Tadeusz Sośnierz <tsosnierz@opera.com>'
- 'Ken Williams <ken@mathforum.org>'
build_requires:
Test::More: '0'
configure_requires:
ExtUtils::MakeMaker: '0'
dynamic_config: 0
generated_by: 'Dist::Zilla version 6.008, CPAN::Meta::Converter version 2.150005'
license: perl
meta-spec:
url: http://module-build.sourceforge.net/META-spec-v1.4.html
version: '1.4'
name: AI-NaiveBayes
no_index:
directory:
- examples
- t/lib
requires:
File::Find::Rule: '0.32'
List::Util: '0'
Moose: '1.15'
MooseX::Storage: '0.25'
perl: '5.010'
strict: '0'
warnings: '0'
resources:
repository: http://github.com/zby/AI-NaiveBayes
version: '0.04'
x_contributors:
- 'schweickism <schweickism@hotmail.com>'
- 'Zbigniew Åukasiak <zzbbyy@gmail.com>'
x_serialization_backend: 'YAML::Tiny version 1.69'
Makefile.PL view on Meta::CPAN
# This file was automatically generated by Dist::Zilla::Plugin::MakeMaker v6.008.
use strict;
use warnings;
use 5.010;
use ExtUtils::MakeMaker;
my %WriteMakefileArgs = (
"ABSTRACT" => "A Bayesian classifier",
"AUTHOR" => "Zbigniew Lukasiak <zlukasiak\@opera.com>, Tadeusz So\x{15b}nierz <tsosnierz\@opera.com>, Ken Williams <ken\@mathforum.org>",
"CONFIGURE_REQUIRES" => {
"ExtUtils::MakeMaker" => 0
},
"DISTNAME" => "AI-NaiveBayes",
"LICENSE" => "perl",
"MIN_PERL_VERSION" => "5.010",
"NAME" => "AI::NaiveBayes",
"PREREQ_PM" => {
"File::Find::Rule" => "0.32",
"List::Util" => 0,
"Moose" => "1.15",
"MooseX::Storage" => "0.25",
"strict" => 0,
"warnings" => 0
},
"TEST_REQUIRES" => {
"Test::More" => 0
},
"VERSION" => "0.04",
"test" => {
"TESTS" => "t/*.t"
}
);
my %FallbackPrereqs = (
"File::Find::Rule" => "0.32",
"List::Util" => 0,
"Moose" => "1.15",
"MooseX::Storage" => "0.25",
"Test::More" => 0,
"strict" => 0,
"warnings" => 0
);
unless ( eval { ExtUtils::MakeMaker->VERSION(6.63_03) } ) {
delete $WriteMakefileArgs{TEST_REQUIRES};
delete $WriteMakefileArgs{BUILD_REQUIRES};
$WriteMakefileArgs{PREREQ_PM} = \%FallbackPrereqs;
}
delete $WriteMakefileArgs{CONFIGURE_REQUIRES}
unless eval { ExtUtils::MakeMaker->VERSION(6.52) };
WriteMakefile(%WriteMakefileArgs);
This archive contains the distribution AI-NaiveBayes,
version 0.04:
A Bayesian classifier
This software is copyright (c) 2012 by Opera Software ASA.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
This README file was generated by Dist::Zilla::Plugin::Readme v6.008.
package AI::NaiveBayes;
use strict;
use warnings;
use 5.010;
use AI::NaiveBayes::Classification;
use AI::NaiveBayes::Learner;
use Moose;
use MooseX::Storage;
use List::Util qw(max);
with Storage(format => 'Storable', io => 'File');
has model => (is => 'ro', isa => 'HashRef[HashRef]', required => 1);
sub train {
my $self = shift;
my $learner = AI::NaiveBayes::Learner->new();
for my $example ( @_ ){
$learner->add_example( %$example );
}
return $learner->classifier;
}
sub classify {
my ($self, $newattrs) = @_;
$newattrs or die "Missing parameter for classify()";
my $m = $self->model;
# Note that we're using the log(prob) here. That's why we add instead of multiply.
my %scores = %{$m->{prior_probs}};
my %features;
while (my ($feature, $value) = each %$newattrs) {
next unless exists $m->{attributes}{$feature}; # Ignore totally unseen features
while (my ($label, $attributes) = each %{$m->{probs}}) {
my $score = ($attributes->{$feature} || $m->{smoother}{$label})*$value; # P($feature|$label)**$value
$scores{$label} += $score;
$features{$feature}{$label} = $score;
}
}
rescale(\%scores);
return AI::NaiveBayes::Classification->new( label_sums => \%scores, features => \%features );
}
sub rescale {
my ($scores) = @_;
# Scale everything back to a reasonable area in logspace (near zero), un-loggify, and normalize
my $total = 0;
my $max = max(values %$scores);
foreach (values %$scores) {
$_ = exp($_ - $max);
$total += $_**2;
}
$total = sqrt($total);
foreach (values %$scores) {
$_ /= $total;
}
}
__PACKAGE__->meta->make_immutable;
1;
__END__
# ABSTRACT: A Bayesian classifier
=encoding utf8
=head1 SYNOPSIS
# AI::NaiveBayes objects are created by AI::NaiveBayes::Learner
# but for quick start you can use the 'train' class method
# that is a shortcut using default AI::NaiveBayes::Learner settings
my $classifier = AI::NaiveBayes->train(
{
attributes => {
sheep => 1, very => 1, valuable => 1, farming => 1
},
labels => ['farming']
},
{
attributes => {
vampires => 1, cannot => 1, see => 1, their => 1,
images => 1, mirrors => 1
},
labels => ['vampire']
},
);
# Classify a feature vector
my $result = $classifier->classify({bar => 3, blurp => 2});
# $result is now a AI::NaiveBayes::Classification object
my $best_category = $result->best_category;
=head1 DESCRIPTION
This module implements the classic "Naive Bayes" machine learning
algorithm. This is a low level class that accepts only pre-computed feature-vectors
as input, see L<AI::Classifier::Text> for a text classifier that uses
this class.
Creation of C<AI::NaiveBayes> classifier object out of training
data is done by L<AI::NaiveBayes::Learner>. For quick start
you can use the limited C<train> class method that trains the
classifier in a default way.
The classifier object is immutable.
It is a well-studied probabilistic algorithm often used in
automatic text categorization. Compared to other algorithms (kNN,
SVM, Decision Trees), it's pretty fast and reasonably competitive in
the quality of its results.
A paper by Fabrizio Sebastiani provides a really good introduction to
text categorization:
L<http://faure.iei.pi.cnr.it/~fabrizio/Publications/ACMCS02.pdf>
=head1 METHODS
=over 4
=item new( model => $model )
Internal. See L<AI::NaiveBayes::Learner> to learn how to create a C<AI::NaiveBayes>
classifier from training data.
=item train( LIST of HASHREFS )
Shortcut for creating a trained classifier using L<AI::NaiveBayes::Learner> default
settings.
Arguments are passed to the C<add_example> method of the L<AI::NaiveBayes::Learner>
object one by one.
=item classify( HASHREF )
Classifies a feature-vector of the form:
{ feature1 => weight1, feature2 => weight2, ... }
The result is a C<AI::NaiveBayes::Classification> object.
=item rescale
Internal
=back
=head1 ATTRIBUTES
=over 4
=item model
Internal
=back
=head1 THEORY
Bayes' Theorem is a way of inverting a conditional probability. It
states:
P(y|x) P(x)
P(x|y) = -------------
P(y)
The notation C<P(x|y)> means "the probability of C<x> given C<y>." See also
L<"http://mathforum.org/dr.math/problems/battisfore.03.22.99.html">
for a simple but complete example of Bayes' Theorem.
In this case, we want to know the probability of a given category given a
certain string of words in a document, so we have:
P(words | cat) P(cat)
P(cat | words) = --------------------
P(words)
We have applied Bayes' Theorem because C<P(cat | words)> is a difficult
quantity to compute directly, but C<P(words | cat)> and C<P(cat)> are accessible
(see below).
The greater the expression above, the greater the probability that the given
document belongs to the given category. So we want to find the maximum
value. We write this as
P(words | cat) P(cat)
Best category = ArgMax -----------------------
cat in cats P(words)
Since C<P(words)> doesn't change over the range of categories, we can get rid
of it. That's good, because we didn't want to have to compute these values
anyway. So our new formula is:
Best category = ArgMax P(words | cat) P(cat)
cat in cats
Finally, we note that if C<w1, w2, ... wn> are the words in the document,
then this expression is equivalent to:
Best category = ArgMax P(w1|cat)*P(w2|cat)*...*P(wn|cat)*P(cat)
cat in cats
That's the formula I use in my document categorization code. The last
step is the only non-rigorous one in the derivation, and this is the
"naive" part of the Naive Bayes technique. It assumes that the
probability of each word appearing in a document is unaffected by the
presence or absence of each other word in the document. We assume
this even though we know this isn't true: for example, the word
"iodized" is far more likely to appear in a document that contains the
word "salt" than it is to appear in a document that contains the word
"subroutine". Luckily, as it turns out, making this assumption even
when it isn't true may have little effect on our results, as the
following paper by Pedro Domingos argues:
L<"http://www.cs.washington.edu/homes/pedrod/mlj97.ps.gz">
=head1 SEE ALSO
Algorithm::NaiveBayes (3), AI::Classifier::Text(3)
=head1 BASED ON
Much of the code and description is from L<Algorithm::NaiveBayes>.
=cut
name = AI-NaiveBayes
author = Zbigniew Lukasiak <zlukasiak@opera.com>
author = Tadeusz Sośnierz <tsosnierz@opera.com>
author = Ken Williams <ken@mathforum.org>
[Git::Contributors]
license = Perl_5
copyright_holder = Opera Software ASA
copyright_year = 2012
version = 0.04
[@Basic]
[AutoPrereqs]
[Prereqs]
Moose = 1.15
MooseX::Storage = 0.25
File::Find::Rule = 0.32
[TestRelease]
[PkgVersion]
[MetaNoIndex]
directory = t/lib
directory = examples
[InstallGuide]
[MetaJSON]
[MetaResources]
repository.web = http://github.com/zby/AI-NaiveBayes
repository.type = git
[NextRelease]
format = %-9v %{yyyy-MM-dd}d
[CheckChangeLog]
[PodSyntaxTests]
[PodCoverageTests]
[PodWeaver]
name = AI-NaiveBayes
author = Zbigniew Lukasiak <zlukasiak@opera.com>
author = Tadeusz Sośnierz <tsosnierz@opera.com>
author = Ken Williams <ken@mathforum.org>
license = Perl_5
copyright_holder = Opera Software ASA
copyright_year = 2012
version = 0.04
[@Basic]
[AutoPrereqs]
[Prereqs]
Moose = 1.15
MooseX::Storage = 0.25
File::Find::Rule = 0.32
[TestRelease]
[PkgVersion]
[MetaNoIndex]
directory = t/lib
directory = examples
[InstallGuide]
[MetaJSON]
[MetaResources]
repository.web = http://github.com/zby/AI-NaiveBayes
repository.type = git
[NextRelease]
format = %-9v %{yyyy-MM-dd}d
[CheckChangeLog]
[PodSyntaxTests]
[PodCoverageTests]
[PodWeaver]
[Git::Contributors]
lib/AI/NaiveBayes.pm view on Meta::CPAN
package AI::NaiveBayes;
$AI::NaiveBayes::VERSION = '0.04';
use strict;
use warnings;
use 5.010;
use AI::NaiveBayes::Classification;
use AI::NaiveBayes::Learner;
use Moose;
use MooseX::Storage;
use List::Util qw(max);
with Storage(format => 'Storable', io => 'File');
has model => (is => 'ro', isa => 'HashRef[HashRef]', required => 1);
sub train {
my $self = shift;
my $learner = AI::NaiveBayes::Learner->new();
for my $example ( @_ ){
$learner->add_example( %$example );
}
return $learner->classifier;
}
sub classify {
my ($self, $newattrs) = @_;
$newattrs or die "Missing parameter for classify()";
my $m = $self->model;
# Note that we're using the log(prob) here. That's why we add instead of multiply.
my %scores = %{$m->{prior_probs}};
my %features;
while (my ($feature, $value) = each %$newattrs) {
next unless exists $m->{attributes}{$feature}; # Ignore totally unseen features
while (my ($label, $attributes) = each %{$m->{probs}}) {
my $score = ($attributes->{$feature} || $m->{smoother}{$label})*$value; # P($feature|$label)**$value
$scores{$label} += $score;
$features{$feature}{$label} = $score;
}
}
rescale(\%scores);
return AI::NaiveBayes::Classification->new( label_sums => \%scores, features => \%features );
}
sub rescale {
my ($scores) = @_;
# Scale everything back to a reasonable area in logspace (near zero), un-loggify, and normalize
my $total = 0;
my $max = max(values %$scores);
foreach (values %$scores) {
$_ = exp($_ - $max);
$total += $_**2;
}
$total = sqrt($total);
foreach (values %$scores) {
$_ /= $total;
}
}
__PACKAGE__->meta->make_immutable;
1;
=pod
=encoding UTF-8
=head1 NAME
AI::NaiveBayes - A Bayesian classifier
=head1 VERSION
version 0.04
=head1 SYNOPSIS
# AI::NaiveBayes objects are created by AI::NaiveBayes::Learner
# but for quick start you can use the 'train' class method
# that is a shortcut using default AI::NaiveBayes::Learner settings
my $classifier = AI::NaiveBayes->train(
{
attributes => {
sheep => 1, very => 1, valuable => 1, farming => 1
},
labels => ['farming']
},
{
attributes => {
vampires => 1, cannot => 1, see => 1, their => 1,
images => 1, mirrors => 1
},
labels => ['vampire']
},
);
# Classify a feature vector
my $result = $classifier->classify({bar => 3, blurp => 2});
# $result is now a AI::NaiveBayes::Classification object
my $best_category = $result->best_category;
=head1 DESCRIPTION
This module implements the classic "Naive Bayes" machine learning
algorithm. This is a low level class that accepts only pre-computed feature-vectors
as input, see L<AI::Classifier::Text> for a text classifier that uses
this class.
Creation of C<AI::NaiveBayes> classifier object out of training
data is done by L<AI::NaiveBayes::Learner>. For quick start
you can use the limited C<train> class method that trains the
classifier in a default way.
The classifier object is immutable.
It is a well-studied probabilistic algorithm often used in
automatic text categorization. Compared to other algorithms (kNN,
SVM, Decision Trees), it's pretty fast and reasonably competitive in
the quality of its results.
A paper by Fabrizio Sebastiani provides a really good introduction to
text categorization:
L<http://faure.iei.pi.cnr.it/~fabrizio/Publications/ACMCS02.pdf>
=head1 METHODS
=over 4
=item new( model => $model )
Internal. See L<AI::NaiveBayes::Learner> to learn how to create a C<AI::NaiveBayes>
classifier from training data.
=item train( LIST of HASHREFS )
Shortcut for creating a trained classifier using L<AI::NaiveBayes::Learner> default
settings.
Arguments are passed to the C<add_example> method of the L<AI::NaiveBayes::Learner>
object one by one.
=item classify( HASHREF )
Classifies a feature-vector of the form:
{ feature1 => weight1, feature2 => weight2, ... }
The result is a C<AI::NaiveBayes::Classification> object.
=item rescale
Internal
=back
=head1 ATTRIBUTES
=over 4
=item model
Internal
=back
=head1 THEORY
Bayes' Theorem is a way of inverting a conditional probability. It
states:
P(y|x) P(x)
P(x|y) = -------------
P(y)
The notation C<P(x|y)> means "the probability of C<x> given C<y>." See also
L<"http://mathforum.org/dr.math/problems/battisfore.03.22.99.html">
for a simple but complete example of Bayes' Theorem.
In this case, we want to know the probability of a given category given a
certain string of words in a document, so we have:
P(words | cat) P(cat)
P(cat | words) = --------------------
P(words)
We have applied Bayes' Theorem because C<P(cat | words)> is a difficult
quantity to compute directly, but C<P(words | cat)> and C<P(cat)> are accessible
(see below).
The greater the expression above, the greater the probability that the given
document belongs to the given category. So we want to find the maximum
value. We write this as
P(words | cat) P(cat)
Best category = ArgMax -----------------------
cat in cats P(words)
Since C<P(words)> doesn't change over the range of categories, we can get rid
of it. That's good, because we didn't want to have to compute these values
anyway. So our new formula is:
Best category = ArgMax P(words | cat) P(cat)
cat in cats
Finally, we note that if C<w1, w2, ... wn> are the words in the document,
then this expression is equivalent to:
Best category = ArgMax P(w1|cat)*P(w2|cat)*...*P(wn|cat)*P(cat)
cat in cats
That's the formula I use in my document categorization code. The last
step is the only non-rigorous one in the derivation, and this is the
"naive" part of the Naive Bayes technique. It assumes that the
probability of each word appearing in a document is unaffected by the
presence or absence of each other word in the document. We assume
this even though we know this isn't true: for example, the word
"iodized" is far more likely to appear in a document that contains the
word "salt" than it is to appear in a document that contains the word
"subroutine". Luckily, as it turns out, making this assumption even
when it isn't true may have little effect on our results, as the
following paper by Pedro Domingos argues:
L<"http://www.cs.washington.edu/homes/pedrod/mlj97.ps.gz">
=head1 SEE ALSO
Algorithm::NaiveBayes (3), AI::Classifier::Text(3)
=head1 BASED ON
Much of the code and description is from L<Algorithm::NaiveBayes>.
=head1 AUTHORS
=over 4
=item *
Zbigniew Lukasiak <zlukasiak@opera.com>
=item *
Tadeusz Sośnierz <tsosnierz@opera.com>
=item *
Ken Williams <ken@mathforum.org>
=back
=head1 COPYRIGHT AND LICENSE
This software is copyright (c) 2012 by Opera Software ASA.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
=cut
__END__
# ABSTRACT: A Bayesian classifier
lib/AI/NaiveBayes/Classification.pm view on Meta::CPAN
package AI::NaiveBayes::Classification;
$AI::NaiveBayes::Classification::VERSION = '0.04';
use strict;
use warnings;
use 5.010;
use Moose;
has features => (is => 'ro', isa => 'HashRef[HashRef]', required => 1);
has label_sums => (is => 'ro', isa => 'HashRef', required => 1);
has best_category => (is => 'ro', isa => 'Str', lazy_build => 1);
sub _build_best_category {
my $self = shift;
my $sc = $self->label_sums;
my ($best_cat, $best_score) = each %$sc;
while (my ($key, $val) = each %$sc) {
($best_cat, $best_score) = ($key, $val) if $val > $best_score;
}
return $best_cat;
}
sub find_predictors{
my $self = shift;
my $best_cat = $self->best_category;
my $features = $self->features;
my @predictors;
for my $feature ( keys %$features ) {
for my $cat ( keys %{ $features->{$feature } } ){
next if $cat eq $best_cat;
push @predictors, [ $feature, $features->{$feature}{$best_cat} - $features->{$feature}{$cat} ];
}
}
@predictors = sort { abs( $b->[1] ) <=> abs( $a->[1] ) } @predictors;
return $best_cat, @predictors;
}
__PACKAGE__->meta->make_immutable;
1;
=pod
=encoding UTF-8
=head1 NAME
AI::NaiveBayes::Classification - The result of a bayesian classification
=head1 VERSION
version 0.04
=head1 SYNOPSIS
my $result = $classifier->classify({bar => 3, blurp => 2});
# $result is an AI::NaiveBayes::Classification object
say $result->best_category;
my $predictors = $result->find_predictors;
=head1 DESCRIPTION
AI::NaiveBayes::Classification represents the result of a bayesian classification,
produced by AI::NaiveBayes classifier.
=head1 METHODS
=over 4
=item C<best_category()>
Returns a string being a label that suits given document the best.
=item C<find_predictors()>
This method returns the C<best_category()>, as well as the list of all the predictors
along with their influence on the best category selected. So the second value
returned is a list of array references, where each one contains a string being a
single feature and a number describing its influence on the result. So the
second part of the result may look like this:
(
[ 'activities', 1.2511540632952 ],
[ 'over', -1.0269523272981 ],
[ 'provide', 0.8280157033269 ],
[ 'natural', 0.7361042359385 ],
[ 'against', -0.6923354975173 ],
)
=back
=head1 SEE ALSO
AI::NaiveBayes (3), AI::Classifier(3)
=head1 AUTHORS
=over 4
=item *
Zbigniew Lukasiak <zlukasiak@opera.com>
=item *
Tadeusz Sośnierz <tsosnierz@opera.com>
=item *
Ken Williams <ken@mathforum.org>
=back
=head1 COPYRIGHT AND LICENSE
This software is copyright (c) 2012 by Opera Software ASA.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
=cut
__END__
# ABSTRACT: The result of a bayesian classification
lib/AI/NaiveBayes/Learner.pm view on Meta::CPAN
package AI::NaiveBayes::Learner;
$AI::NaiveBayes::Learner::VERSION = '0.04';
use strict;
use warnings;
use 5.010;
use List::Util qw( min sum );
use Moose;
use AI::NaiveBayes;
has attributes => (is => 'ro', isa => 'HashRef', default => sub { {} }, clearer => '_clear_attrs');
has labels => (is => 'ro', isa => 'HashRef', default => sub { {} }, clearer => '_clear_labels');
has examples => (is => 'ro', isa => 'Int', default => 0, clearer => '_clear_examples');
has features_kept => (is => 'ro', predicate => 'limit_features');
has classifier_class => ( is => 'ro', isa => 'Str', default => 'AI::NaiveBayes' );
sub add_example {
my ($self, %params) = @_;
for ('attributes', 'labels') {
die "Missing required '$_' parameter" unless exists $params{$_};
}
$self->{examples}++;
my $attributes = $params{attributes};
my $labels = $params{labels};
add_hash($self->attributes(), $attributes);
my $our_labels = $self->labels;
foreach my $label ( @$labels ) {
$our_labels->{$label}{count}++;
$our_labels->{$label}{attributes} //= {};
add_hash($our_labels->{$label}{attributes}, $attributes);
}
}
sub classifier {
my $self = shift;
my $examples = $self->examples;
my $labels = $self->labels;
my $vocab_size = keys %{ $self->attributes };
my $model;
$model->{attributes} = $self->attributes;
# Calculate the log-probabilities for each category
foreach my $label (keys %$labels) {
$model->{prior_probs}{$label} = log($labels->{$label}{count} / $examples);
# Count the number of tokens in this cat
my $label_tokens = sum( values %{ $labels->{$label}{attributes} } );
# Compute a smoothing term so P(word|cat)==0 can be avoided
$model->{smoother}{$label} = -log($label_tokens + $vocab_size);
# P(attr|label) = $count/$label_tokens (simple)
# P(attr|label) = ($count + 1)/($label_tokens + $vocab_size) (with smoothing)
# log P(attr|label) = log($count + 1) - log($label_tokens + $vocab_size)
my $denominator = log($label_tokens + $vocab_size);
while (my ($attribute, $count) = each %{ $labels->{$label}{attributes} }) {
$model->{probs}{$label}{$attribute} = log($count + 1) - $denominator;
}
if ($self->limit_features) {
my %old = %{$model->{probs}{$label}};
my @features = sort { abs($old{$a}) <=> abs($old{$b}) } keys(%old);
my $limit = min($self->features_kept, 0+@features);
if ($limit < 1) {
$limit = int($limit * keys(%old));
}
my @top = @features[0..$limit-1];
my %kept = map { $_ => $old{$_} } @top;
$model->{probs}{$label} = \%kept;
}
}
my $classifier_class = $self->classifier_class;
return $classifier_class->new( model => $model );
}
sub add_hash {
my ($first, $second) = @_;
$first //= {};
foreach my $k (keys %$second) {
$first->{$k} //= 0;
$first->{$k} += $second->{$k};
}
}
__PACKAGE__->meta->make_immutable;
1;
=pod
=encoding UTF-8
=head1 NAME
AI::NaiveBayes::Learner - Build AI::NaiveBayes classifier from a set of training examples.
=head1 VERSION
version 0.04
=head1 SYNOPSIS
my $learner = AI::NaiveBayes::Learner->new(features_kept => 0.5);
$learner->add_example(
attributes => { sheep => 1, very => 1, valuable => 1, farming => 1 },
labels => ['farming']
);
my $classifier = $learner->classifier;
=head1 DESCRIPTION
This is a trainer of AI::NaiveBayes classifiers. It saves information passed
by the C<add_example> method from
training data into internal structures and then constructs a classifier when
the C<classifier> method is called.
=head1 ATTRIBUTES
=over 4
=item C<features_kept>
Indicates how many features should remain after calculating probabilities. By
default all of them will be kept. For C<features_kept> > 1, C<features_kept> of
features will be preserved. For values lower than 1, a specified fraction of
features will be kept (e.g. top 20% of features for C<features_kept> = 0.2).
The rest of the attributes is for class' internal usage, and thus not
documented.
=item C<classifier_class>
The class of the classifier to be created. By default it is
C<AI::NaiveBayes>
=back
=head1 METHODS
=over 4
=item C<add_example( attributes => HASHREF, labels => LIST )>
Saves the information from a training example into internal data structures.
C<attributes> should be of the form of
{ feature1 => weight1, feature2 => weight2, ... }
C<labels> should be a list of strings denoting one or more classes to which the example belongs.
=item C<classifier()>
Creates an AI::NaiveBayes classifier based on the data accumulated before.
=back
=head1 UTILITY SUBS
=over 4
=item C<add_hash>
=back
=head1 BASED ON
Much of the code and description is from L<Algorithm::NaiveBayes>.
=head1 AUTHORS
=over 4
=item *
Zbigniew Lukasiak <zlukasiak@opera.com>
=item *
Tadeusz Sośnierz <tsosnierz@opera.com>
=item *
Ken Williams <ken@mathforum.org>
=back
=head1 COPYRIGHT AND LICENSE
This software is copyright (c) 2012 by Opera Software ASA.
This is free software; you can redistribute it and/or modify it under
the same terms as the Perl 5 programming language system itself.
=cut
__END__
# ABSTRACT: Build AI::NaiveBayes classifier from a set of training examples.
t/01-learner.t view on Meta::CPAN
use strict;
use warnings;
use Test::More tests => 11;
use AI::NaiveBayes::Learner;
ok(1); # If we made it this far, we're loaded.
my $learner = AI::NaiveBayes::Learner->new();
# Populate
$learner->add_example( attributes => _hash(qw(sheep very valuable farming)),
labels => ['farming'] );
is $learner->{labels}{farming}{count}, 1;
$learner->add_example( attributes => _hash(qw(farming requires many kinds animals)),
labels => ['farming'] );
is $learner->{labels}{farming}{count}, 2;
is keys %{$learner->{labels}}, 1;
$learner->add_example( attributes => _hash(qw(vampires drink blood vampires may staked)),
labels => ['vampire'] );
is $learner->{labels}{vampire}{count}, 1;
$learner->add_example( attributes => _hash(qw(vampires cannot see their images mirrors)),
labels => ['vampire'] );
is $learner->{labels}{vampire}{count}, 2;
is keys %{$learner->{labels}}, 2;
# features_kept > 1
$learner = AI::NaiveBayes::Learner->new(features_kept => 5);
$learner->add_example( attributes => _hash(qw(one two three four)),
labels => ['farming'] );
$learner->add_example( attributes => _hash(qw(five six seven eight)),
labels => ['farming'] );
$learner->add_example( attributes => _hash(qw(one two three four five)),
labels => ['farming'] );
my $model = $learner->classifier->model;
is keys %{$model->{probs}{farming}}, 5, '5 features kept';
is join(" ", sort { $a cmp $b } keys %{$model->{probs}{farming}}), 'five four one three two';
# features_kept < 1
$learner = AI::NaiveBayes::Learner->new(features_kept => 0.5);
$learner->add_example( attributes => _hash(qw(one two three four)),
labels => ['farming'] );
$learner->add_example( attributes => _hash(qw(five six seven eight)),
labels => ['farming'] );
$learner->add_example( attributes => _hash(qw(one two three four)),
labels => ['farming'] );
$model = $learner->classifier->model;
is keys %{$model->{probs}{farming}}, 4, 'half features kept';
is join(" ", sort { $a cmp $b } keys %{$model->{probs}{farming}}), 'four one three two';
sub _hash { +{ map {$_,1} @_ } }
t/02-predict.t view on Meta::CPAN
use strict;
use warnings;
use Test::More tests => 12;
use AI::NaiveBayes;
use AI::NaiveBayes::Learner;
ok(1); # If we made it this far, we're loaded.
my $lr = AI::NaiveBayes::Learner->new();
# Populate
$lr->add_example( attributes => _hash(qw(sheep very valuable farming)),
labels => ['farming'] );
$lr->add_example( attributes => _hash(qw(farming requires many kinds animals)),
labels => ['farming'] );
$lr->add_example( attributes => _hash(qw(vampires drink blood vampires may staked)),
labels => ['vampire'] );
$lr->add_example( attributes => _hash(qw(vampires cannot see their images mirrors)),
labels => ['vampire'] );
my $classifier = $lr->classifier;
ok $classifier;
# Predict
my $s = $classifier->classify( _hash(qw(i would like to begin farming sheep)) );
my $h = $s->label_sums;
ok $h;
ok $h->{farming} > 0.5;
ok $h->{vampire} < 0.5;
$s = $classifier->classify( _hash(qw(i see that many vampires may have eaten my beautiful daughter's blood)) );
$h = $s->label_sums;
ok $h;
ok $h->{farming} < 0.5;
ok $h->{vampire} > 0.5;
# Find predictors
my $p = $classifier->classify( _hash( qw(i would like to begin farming sheep)) );
my( $best_cat, @predictors ) = $p->find_predictors();
is( $best_cat, 'farming', 'Best category' );
is( scalar @predictors, 2, 'farming and sheep - two predictors' );
is( $predictors[0][0], 'farming', 'Farming is the best predictor' );
# Prior probs
$lr = AI::NaiveBayes::Learner->new();
# Populate
$lr->add_example( attributes => _hash(qw(sheep very valuable farming)),
labels => ['farming'] );
$lr->add_example( attributes => _hash(qw(farming requires many kinds animals)),
labels => ['farming'] );
$lr->add_example( attributes => _hash(qw(good soil)),
labels => ['farming'] );
$lr->add_example( attributes => _hash(qw(vampires drink blood vampires may staked)),
labels => ['vampire'] );
$classifier = $lr->classifier;
# Predict
$s = $classifier->classify( _hash(qw(jakis tekst po polsku)) );
$h = $s->label_sums;
ok(abs( 3 - $h->{farming} / $h->{vampire} ) < 0.01, 'Prior probabillities' );
################################################################
sub _hash { +{ map {$_,1} @_ } }
t/author-pod-coverage.t view on Meta::CPAN
#!perl
BEGIN {
unless ($ENV{AUTHOR_TESTING}) {
print qq{1..0 # SKIP these tests are for testing by the author\n};
exit
}
}
# This file was automatically generated by Dist::Zilla::Plugin::PodCoverageTests.
use Test::Pod::Coverage 1.08;
use Pod::Coverage::TrustPod;
all_pod_coverage_ok({ coverage_class => 'Pod::Coverage::TrustPod' });
t/author-pod-syntax.t view on Meta::CPAN
#!perl
BEGIN {
unless ($ENV{AUTHOR_TESTING}) {
print qq{1..0 # SKIP these tests are for testing by the author\n};
exit
}
}
# This file was automatically generated by Dist::Zilla::Plugin::PodSyntaxTests.
use strict; use warnings;
use Test::More;
use Test::Pod 1.41;
all_pod_files_ok();
t/default_training.t view on Meta::CPAN
use strict;
use Test::More tests => 2;
use AI::NaiveBayes;
ok(1); # If we made it this far, we're loaded.
my $classifier = AI::NaiveBayes->train(
{
attributes => _hash(qw(sheep very valuable farming)),
labels => ['farming']
},
{
attributes => _hash(qw(vampires cannot see their images mirrors)),
labels => ['vampire']
},
);
isa_ok( $classifier, 'AI::NaiveBayes' );
################################################################
sub _hash { +{ map {$_,1} @_ } }
view release on metacpan - search on metacpan
( run in 1.794 second using v1.00-cache-2.02-grep-82fe00e-cpan-cec75d87357c )