AI-NaiveBayes1

 view release on metacpan or  search on metacpan

NaiveBayes1.pm  view on Meta::CPAN

		attvals    => {},
		real_stat  => {},
		numof_instances => 0,
		stat_labels => {},
		stat_attributes => {},
		smoothing => {},
		attribute_type => {},
	       }, $package;
}

sub set_real {
    my ($self, @attr) = @_;
    foreach my $a (@attr) { $self->{attribute_type}{$a} = 'real' }
}

sub import_from_YAML {
    my $package = shift;
    my $yaml = shift;
    my $self = YAML::Load($yaml);
    return bless $self, $package;
}

NaiveBayes1.pm  view on Meta::CPAN

=head2 Attribute Smoothing

For an attribute A one can specify:

    $nb->{smoothing}{A} = 'unseen count=0.5';

to provide a count for unseen data.  The count is taken into
consideration in training and prediction, when any unseen attribute
values are observed.  Zero probabilities can be prevented in this way.
A count other than 0.5 can be provided, but if it is <=0 it will be
set to 0.5.  The method is similar to add-one smoothing.  A special
attribute value '*' is used for all unseen data. 

=head1 METHODS

=head2 Constructor Methods

=over 4

=item new()

NaiveBayes1.pm  view on Meta::CPAN

=item add_csv_file($filename)

Add instances from a CSV file.  Primitive format implementation (e.g.,
no commas allowed in attribute names or values).

=item drop_attributes(@attributes)

Delete attributes after adding instances.

=item set_real(list_of_attributes)

Delares a list of attributes to be real-valued.  During training,
their conditional probabilities will be modeled with Gaussian (normal)
distributions. 

=item C<add_instance(attributes=E<gt>HASH,label=E<gt>STRING|ARRAY)>

Adds a training instance to the categorizer.

=item C<add_instances(attributes=E<gt>HASH,label=E<gt>STRING|ARRAY,cases=E<gt>NUMBER)>

NaiveBayes1.pm  view on Meta::CPAN

 # rainy,65,70,TRUE,no
 # overcast,64,65,TRUE,yes
 # sunny,72,95,FALSE,no
 # sunny,69,70,FALSE,yes
 # rainy,75,80,FALSE,yes
 # sunny,75,70,TRUE,yes
 # overcast,72,90,TRUE,yes
 # overcast,81,75,FALSE,yes
 # rainy,71,91,TRUE,no
 
 $nb->set_real('temperature', 'humidity');
 
 $nb->add_instance(attributes=>{outlook=>'sunny',temperature=>85,humidity=>85,windy=>'FALSE'},label=>'play=no');
 $nb->add_instance(attributes=>{outlook=>'sunny',temperature=>80,humidity=>90,windy=>'TRUE'},label=>'play=no');
 $nb->add_instance(attributes=>{outlook=>'overcast',temperature=>83,humidity=>86,windy=>'FALSE'},label=>'play=yes');
 $nb->add_instance(attributes=>{outlook=>'rainy',temperature=>70,humidity=>96,windy=>'FALSE'},label=>'play=yes');
 $nb->add_instance(attributes=>{outlook=>'rainy',temperature=>68,humidity=>80,windy=>'FALSE'},label=>'play=yes');
 $nb->add_instance(attributes=>{outlook=>'rainy',temperature=>65,humidity=>70,windy=>'TRUE'},label=>'play=no');
 $nb->add_instance(attributes=>{outlook=>'overcast',temperature=>64,humidity=>65,windy=>'TRUE'},label=>'play=yes');
 $nb->add_instance(attributes=>{outlook=>'sunny',temperature=>72,humidity=>95,windy=>'FALSE'},label=>'play=no');
 $nb->add_instance(attributes=>{outlook=>'sunny',temperature=>69,humidity=>70,windy=>'FALSE'},label=>'play=yes');

t/4.t  view on Meta::CPAN

# overcast,64,65,TRUE,yes
# sunny,72,95,FALSE,no
# sunny,69,70,FALSE,yes
# rainy,75,80,FALSE,yes
# sunny,75,70,TRUE,yes
# overcast,72,90,TRUE,yes
# overcast,81,75,FALSE,yes
# rainy,71,91,TRUE,no
#

$nb->set_real('temperature', 'humidity');

$nb->add_instance(attributes=>{outlook=>'sunny',temperature=>85,humidity=>85,windy=>'FALSE'},label=>'play=no');
$nb->add_instance(attributes=>{outlook=>'sunny',temperature=>80,humidity=>90,windy=>'TRUE'},label=>'play=no');
$nb->add_instance(attributes=>{outlook=>'overcast',temperature=>83,humidity=>86,windy=>'FALSE'},label=>'play=yes');
$nb->add_instance(attributes=>{outlook=>'rainy',temperature=>70,humidity=>96,windy=>'FALSE'},label=>'play=yes');
$nb->add_instance(attributes=>{outlook=>'rainy',temperature=>68,humidity=>80,windy=>'FALSE'},label=>'play=yes');
$nb->add_instance(attributes=>{outlook=>'rainy',temperature=>65,humidity=>70,windy=>'TRUE'},label=>'play=no');
$nb->add_instance(attributes=>{outlook=>'overcast',temperature=>64,humidity=>65,windy=>'TRUE'},label=>'play=yes');
$nb->add_instance(attributes=>{outlook=>'sunny',temperature=>72,humidity=>95,windy=>'FALSE'},label=>'play=no');
$nb->add_instance(attributes=>{outlook=>'sunny',temperature=>69,humidity=>70,windy=>'FALSE'},label=>'play=yes');

t/5.t  view on Meta::CPAN

$nb->add_instance(attributes=>{morning=>'N',html=>'Y',size=>2042},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'Y',html=>'Y',size=>3893},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'N',html=>'Y',size=>3601},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'Y',html=>'Y',size=>2176},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'N',html=>'Y',size=>877},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'N',html=>'Y',size=>272},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'Y',html=>'Y',size=>2740},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'Y',html=>'Y',size=>514},label=>'spam=Y');
$nb->add_instance(attributes=>{morning=>'N',html=>'N',size=>1321},label=>'spam=Y');

$nb->set_real('size');
$nb->train;

my $printedmodel =  "Model:\n" . $nb->print_model;
$printedmodel = &shorterdecimals($printedmodel);

#putfile('t/5-1.out', $printedmodel);
&compare_by_line($printedmodel, 't/5-1.out', __FILE__, __LINE__);

#putfile('t/5-2.out', $nb->export_to_YAML());
#is($nb->export_to_YAML(), getfile('t/5-2.out'));

t/6.t  view on Meta::CPAN

$nb->add_instances(attributes=>{C=>'Y',F=>2},label=>'S=Y',cases=>30);
$nb->add_instances(attributes=>{C=>'Y',F=>2},label=>'S=N',cases=>10);
$nb->add_instances(attributes=>{C=>'Y',F=>0},label=>'S=Y',cases=>18);
$nb->add_instances(attributes=>{C=>'Y',F=>0},label=>'S=N',cases=>16);
$nb->add_instances(attributes=>{C=>'N',F=>2},label=>'S=Y',cases=>22);
$nb->add_instances(attributes=>{C=>'N',F=>2},label=>'S=N',cases=>14);
$nb->add_instances(attributes=>{C=>'N',F=>0},label=>'S=Y',cases=> 6);
$nb->add_instances(attributes=>{C=>'N',F=>0},label=>'S=N',cases=>84);

$nb->set_real('F');
$nb->train;

$printedmodel =  "Model:\n" . $nb->print_model;
$printedmodel = &shorterdecimals($printedmodel);

#putfile('t/6-3.out', $printedmodel);
&compare_by_line($printedmodel, 't/6-3.out', __FILE__, __LINE__);

$nb->export_to_YAML_file('t/tmp6-2');
$nb1 = AI::NaiveBayes1->import_from_YAML_file('t/tmp6-2');

t/7.t  view on Meta::CPAN

$nb->add_instances(attributes=>{C=>'N',F=>2},label=>'S=Y',cases=>22);
$nb->add_instances(attributes=>{C=>'N',F=>2},label=>'S=N',cases=>14);
#$nb->add_instances(attributes=>{C=>'N',F=>0},label=>'S=Y',cases=> 6);
#$nb->add_instances(attributes=>{C=>'N',F=>0},label=>'S=N',cases=>84);
$nb->add_table("  C   F   S  count\n".
               "------------------\n".
	       "  N   0   Y    6  \n".
	       "  N   0   N   84  \n".
	       '');

$nb->set_real('F');
$nb->train;

$printedmodel =  &shorterdecimals("Model:\n" . $nb->print_model);

#putfile('t/7-3.out', $printedmodel);
&compare_by_line($printedmodel, 't/7-3.out', __FILE__, __LINE__);

$nb->export_to_YAML_file('t/tmp7-2');
$nb1 = AI::NaiveBayes1->import_from_YAML_file('t/tmp7-2');