AI-Perceptron-Simple
view release on metacpan or search on metacpan
lib/AI/Perceptron/Simple.pm view on Meta::CPAN
package AI::Perceptron::Simple;
use 5.008001;
use strict;
use warnings;
use Carp "croak";
use utf8;
binmode STDOUT, ":utf8";
require local::lib; # no local::lib in tests, this is also to avoid loading local::lib multiple times
use Text::CSV qw( csv );
use Text::Matrix;
use File::Basename qw( basename );
use List::Util qw( shuffle );
=head1 NAME
AI::Perceptron::Simple
A Newbie Friendly Module to Create, Train, Validate and Test Perceptrons / Neurons
=head1 VERSION
Version 1.04
=cut
our $VERSION = '1.04';
# default values
use constant LEARNING_RATE => 0.05;
use constant THRESHOLD => 0.5;
use constant TUNE_UP => 1;
use constant TUNE_DOWN => 0;
=head1 SYNOPSIS
#!/usr/bin/perl
use AI::Perceptron::Simple qw(...);
# create a new nerve / neuron / perceptron
$nerve = AI::Perceptron::Simple->new( {
initial_value => $size_of_each_dendrite,
learning_rate => 0.3, # optional
threshold => 0.85, # optional
attribs => \@dendrites,
} );
# train
$nerve->tame( ... );
$nerve->exercise( ... );
$nerve->train( $training_data_csv, $expected_column_name, $save_nerve_to );
# or
$nerve->train(
$training_data_csv, $expected_column_name, $save_nerve_to,
$show_progress, $identifier); # these two parameters must go together
# validate
$nerve->take_lab_test( ... );
$nerve->take_mock_exam( ... );
# fill results to original file
$nerve->validate( {
stimuli_validate => $validation_data_csv,
predicted_column_index => 4,
} );
# or
# fill results to a new file
$nerve->validate( {
stimuli_validate => $validation_data_csv,
predicted_column_index => 4,
results_write_to => $new_csv
} );
# test - see "validate" method, same usage
$nerve->take_real_exam( ... );
$nerve->work_in_real_world( ... );
$nerve->test( ... );
# confusion matrix
my %c_matrix = $nerve->get_confusion_matrix( {
full_data_file => $file_csv,
actual_output_header => $header_name,
predicted_output_header => $predicted_header_name,
more_stats => 1, # optional
} );
# accessing the confusion matrix
my @keys = qw( true_positive true_negative false_positive false_negative
total_entries accuracy sensitivity );
for ( @keys ) {
print $_, " => ", $c_matrix{ $_ }, "\n";
}
# output to console
$nerve->display_confusion_matrix( \%c_matrix, {
zero_as => "bad apples", # cat milk green etc.
one_as => "good apples", # dog honey pink etc.
} );
# saving and loading data of perceptron locally
# NOTE: nerve data is automatically saved after each trainning process
use AI::Perceptron::Simple ":local_data";
my $nerve_file = "apples.nerve";
preserve( ... );
save_perceptron( $nerve, $nerve_file );
# load data of percpetron for use in actual program
my $apple_nerve = revive( ... );
my $apple_nerve = load_perceptron( $nerve_file );
# for portability of nerve data
use AI::Perceptron::Simple ":portable_data";
my $yaml_nerve_file = "pearls.yaml";
preserve_as_yaml ( ... );
save_perceptron_yaml ( $nerve, $yaml_nerve_file );
# load nerve data on the other computer
my $pearl_nerve = revive_from_yaml ( ... );
my $pearl_nerve = load_perceptron_yaml ( $yaml_nerve_file );
# processing data
use AI::Perceptron::Simple ":process_data";
shuffle_stimuli ( ... )
shuffle_data ( ORIGINAL_STIMULI, $new_file_1, $new_file_2, ... );
shuffle_data ( $original_stimuli => $new_file_1, $new_file_2, ... );
=head1 EXPORT
None by default.
All the subroutines from C<DATA PROCESSING RELATED SUBROUTINES>, C<NERVE DATA RELATED SUBROUTINES> and C<NERVE PORTABILITY RELATED SUBROUTINES> sections are importable through tags or manually specifying them.
The tags available include the following:
=over 4
=item C<:process_data> - subroutines under C<DATA PROCESSING RELATED SUBROUTINES> section.
=item C<:local_data> - subroutines under C<NERVE DATA RELATED SUBROUTINES> section.
=item C<:portable_data> - subroutines under C<NERVE PORTABILITY RELATED SUBROUTINES> section.
=back
Most of the stuff are OO.
=cut
use Exporter qw( import );
our @EXPORT_OK = qw(
shuffle_data shuffle_stimuli
preserve save_perceptron revive load_perceptron
preserve_as_yaml save_perceptron_yaml revive_from_yaml load_perceptron_yaml
);
our %EXPORT_TAGS = (
process_data => [ qw( shuffle_data shuffle_stimuli ) ],
local_data => [ qw( preserve save_perceptron revive load_perceptron ) ],
portable_data => [ qw( preserve_as_yaml save_perceptron_yaml revive_from_yaml load_perceptron_yaml ) ],
);
=head1 DESCRIPTION
This module provides methods to build, train, validate and test a perceptron. It can also save the data of the perceptron for future use for any actual AI programs.
This module is also aimed to help newbies grasp hold of the concept of perceptron, training, validation and testing as much as possible. Hence, all the methods and subroutines in this module are decoupled as much as possible so that the actual script...
The implementation here is super basic as it only takes in input of the dendrites and calculate the output. If the output is higher than the threshold, the final result (category) will
be 1 aka perceptron is activated. If not, then the result will be 0 (not activated).
Depending on how you view or categorize the final result, the perceptron will fine tune itself (aka train) based on the learning rate until the desired result is met. Everything from
here on is all mathematics and numbers which only makes sense to the computer and not humans anymore.
Whenever the perceptron fine tunes itself, it will increase/decrease all the dendrites that is significant (attributes labelled 1) for each input. This means that even when the
perceptron successfully fine tunes itself to suite all the data in your file for the first round, the perceptron might still get some of the things wrong for the next round of training.
Therefore, the perceptron should be trained for as many rounds as possible. The more "confusion" the perceptron is able to correctly handle, the more "mature" the perceptron is.
No one defines how "mature" it is except the programmer himself/herself :)
=head1 CONVENTIONS USED
Please take note that not all subroutines/method must be used to make things work. All the subroutines and methods are listed out for the sake of writing the documentation.
Private methods/subroutines are prefixed with C<_> or C<&_> and they aren't meant to be called directly. You can if you want to. There are quite a number of them to be honest, just ignore them if you happen to see them :)
Synonyms are placed before the actual ie. technical subroutines/methods. You will see C<...> as the parameters if they are synonyms. Move to the next subroutine/method until you find something like C<\%options> as the parameter or anything that isn't...
=head1 DATASET STRUCTURE
I<This module can only process CSV files.>
lib/AI/Perceptron/Simple.pm view on Meta::CPAN
=head2 shuffle_stimuli ( ... )
The parameters and usage are the same as C<shuffled_data>. See the next two subroutines.
=head2 shuffle_data ( $original_data => $shuffled_1, $shuffled_2, ... )
=head2 shuffle_data ( ORIGINAL_DATA, $shuffled_1, $shuffled_2, ... )
Shuffles C<$original_data> or C<ORIGINAL_DATA> and saves them to other files.
=cut
sub shuffle_stimuli {
shuffle_data( @_ );
}
sub shuffle_data {
my $stimuli = shift or croak "Please specify the original file name";
my @shuffled_stimuli_names = @_
or croak "Please specify the output files for the shuffled data";
my @aoa;
for ( @shuffled_stimuli_names ) {
# copied from _real_validate_or_test
# open for shuffling
my $aoa = csv (in => $stimuli, encoding => ":encoding(utf-8)");
my $attrib_array_ref = shift @$aoa; # 'remove' the header, it's annoying :)
@aoa = shuffle( @$aoa ); # this can only process actual array
unshift @aoa, $attrib_array_ref; # put back the headers before saving file
csv( in => \@aoa, out => $_, encoding => ":encoding(utf-8)" )
and
print "Saved shuffled data into ", basename($_), "!\n";
}
}
=head1 CREATION RELATED SUBROUTINES/METHODS
=head2 new ( \%options )
Creates a brand new perceptron and initializes the value of each attribute / dendrite aka. weight. Think of it as the thickness or plasticity of the dendrites.
For C<%options>, the followings are needed unless mentioned:
=over 4
=item initial_value => $decimal
The value or thickness of ALL the dendrites when a new perceptron is created.
Generally speaking, this value is usually between 0 and 1. However, it all depend on your combination of numbers for the other options.
=item attribs => $array_ref
An array reference containing all the attributes / dendrites names. Yes, give them some names :)
=item learning_rate => $decimal
Optional. The default is C<0.05>.
The learning rate of the perceptron for the fine-tuning process.
This value is usually between 0 and 1. However, it all depends on your combination of numbers for the other options.
=item threshold => $decimal
Optional. The default is C<0.5>
This is the passing rate to determine the neuron output (C<0> or C<1>).
Generally speaking, this value is usually between C<0> and C<1>. However, it all depend on your combination of numbers for the other options.
=back
=cut
sub new {
my $class = shift;
my $data_ref = shift;
my %data = %{ $data_ref };
# check keys
$data{ learning_rate } = LEARNING_RATE if not exists $data{ learning_rate };
$data{ threshold } = THRESHOLD if not exists $data{ threshold };
#####
# don't pack this key checking process into a subroutine for now
# this is also used in &_real_validate_or_test
my @missing_keys;
for ( qw( initial_value attribs ) ) {
push @missing_keys, $_ unless exists $data{ $_ };
}
croak "Missing keys: @missing_keys" if @missing_keys;
#####
# continue to process the rest of the data
my %attributes;
for ( @{ $data{ attribs } } ) {
$attributes{ $_ } = $data{ initial_value };
}
my %processed_data = (
learning_rate => $data{ learning_rate },
threshold => $data{ threshold },
attributes_hash_ref => \%attributes,
);
bless \%processed_data, $class;
}
=head2 get_attributes
Obtains a hash of all the attributes of the perceptron
=cut
sub get_attributes {
my $self = shift;
%{ $self->{attributes_hash_ref} };
}
=head2 learning_rate ( $value )
=head2 learning_rate
If C<$value> is given, sets the learning rate to C<$value>. If not, then it returns the learning rate.
=cut
sub learning_rate {
my $self = shift;
if ( @_ ) {
$self->{learning_rate} = shift;
} else {
$self->{learning_rate}
}
}
=head2 threshold ( $value )
=head2 threshold
If C<$value> is given, sets the threshold / passing rate to C<$value>. If not, then it returns the passing rate.
=cut
sub threshold {
my $self = shift;
if ( @_ ) {
$self->{ threshold } = shift;
} else {
$self->{ threshold };
}
}
=head1 TRAINING RELATED SUBROUTINES/METHODS
All the training methods here have the same parameters as the two actual C<train> method and they all do the same stuff. They are also used in the same way.
=head2 tame ( ... )
=head2 exercise ( ... )
=head2 train ( $stimuli_train_csv, $expected_output_header, $save_nerve_to_file )
=head2 train ( $stimuli_train_csv, $expected_output_header, $save_nerve_to_file, $display_stats, $identifier )
Trains the perceptron.
C<$stimuli_train_csv> is the set of data / input (in CSV format) to train the perceptron while C<$save_nerve_to_file> is
the filename that will be generate each time the perceptron finishes the training process. This data file is the data of the C<AI::Perceptron::Simple>
object and it is used in the C<validate> method.
C<$expected_output_header> is the header name of the columns in the csv file with the actual category or the exepcted values. This is used to determine to tune the nerve up or down. This value should only be 0 or 1 for the sake of simplicity.
C<$display_stats> is B<optional> and the default is 0. It will display more output about the tuning process. It will show the followings:
=over 4
=item tuning status
Indicates the nerve was tuned up, down or no tuning needed
=item old sum
The original sum of all C<weightage * input> or C<dendrite_size * binary_input>
=item threshold
The threshold of the nerve
=item new sum
The new sum of all C<weightage * input> after fine-tuning the nerve
=back
If C<$display_stats> is specified ie. set to C<1>, then you B<MUST> specify the C<$identifier>. C<$identifier> is the column / header name that is used to identify a specific row of data in C<$stimuli_train_csv>.
=cut
sub tame {
train( @_ );
}
sub exercise {
train( @_ );
}
sub train {
my $self = shift;
my( $stimuli_train_csv, $expected_output_header, $save_nerve_to_file, $display_stats, $identifier ) = @_;
$display_stats = 0 if not defined $display_stats;
if ( $display_stats and not defined $identifier ) {
croak "Please specifiy a string for \$identifier if you are trying to display stats";
}
# CSV processing is all according to the documentation of Text::CSV
open my $data_fh, "<:encoding(UTF-8)", $stimuli_train_csv
or croak "Can't open $stimuli_train_csv: $!";
my $csv = Text::CSV->new( {auto_diag => 1, binary => 1} );
my $attrib = $csv->getline($data_fh);
$csv->column_names( $attrib );
# individual row
ROW: while ( my $row = $csv->getline_hr($data_fh) ) {
# print $row->{book_name}, " -> ";
# print $row->{$expected_output_header} ? "æ„æž—\n" : "é…丽优å“\n";
# calculate the output and fine tune parameters if necessary
while (1) {
my $output = _calculate_output( $self, $row );
lib/AI/Perceptron/Simple.pm view on Meta::CPAN
sub _tune {
my $self = shift;
my ( $stimuli_hash_ref, $tuning_status ) = @_;
my %dendrites = $self->get_attributes;
for ( keys %dendrites ) {
if ( $tuning_status == TUNE_DOWN ) {
if ( $stimuli_hash_ref->{ $_ } ) { # must check this one, it must be 1 before we can alter the actual dendrite size in the nerve :)
$self->{ attributes_hash_ref }{ $_ } -= $self->learning_rate;
}
#print $_, ": ", $self->{ attributes_hash_ref }{ $_ }, "\n";
} elsif ( $tuning_status == TUNE_UP ) {
if ( $stimuli_hash_ref->{ $_ } ) {
$self->{ attributes_hash_ref }{ $_ } += $self->learning_rate;
}
#print $_, ": ", $self->{ attributes_hash_ref }{ $_ }, "\n";
}
}
}
=head1 VALIDATION RELATED METHODS
All the validation methods here have the same parameters as the actual C<validate> method and they all do the same stuff. They are also used in the same way.
=head2 take_mock_exam (...)
=head2 take_lab_test (...)
=head2 validate ( \%options )
This method validates the perceptron against another set of data after it has undergone the training process.
This method calculates the output of each row of data and write the result into the predicted column. The data begin written into the new file or the original file will maintain it's sequence.
Please take note that this method will load all the data of the validation stimuli, so please split your stimuli into multiple files if possible and call this method a few more times.
For C<%options>, the followings are needed unless mentioned:
=over 4
=item stimuli_validate => $csv_file
This is the CSV file containing the validation data, make sure that it contains a column with the predicted values as it is needed in the next key mentioned: C<predicted_column_index>
=item predicted_column_index => $column_number
This is the index of the column that contains the predicted output values. C<$index> starts from C<0>.
This column will be filled with binary numbers and the full new data will be saved to the file specified in the C<results_write_to> key.
=item results_write_to => $new_csv_file
Optional.
The default behaviour will write the predicted output back into C<stimuli_validate> ie the original data. The sequence of the data will be maintained.
=back
I<*This method will call C<_real_validate_or_test> to do the actual work.>
=cut
sub take_mock_exam {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
sub take_lab_test {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
sub validate {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
=head1 TESTING RELATED SUBROUTINES/METHODS
All the testing methods here have the same parameters as the actual C<test> method and they all do the same stuff. They are also used in the same way.
=head2 take_real_exam (...)
=head2 work_in_real_world (...)
=head2 test ( \%options )
This method is used to put the trained nerve to the test. You can think of it as deploying the nerve for the actual work or maybe putting the nerve into an empty brain and see how
well the brain survives :)
This method works and behaves the same way as the C<validate> method. See C<validate> for the details.
I<*This method will call &_real_validate_or_test to do the actual work.>
=cut
# redirect to _real_validate_or_test
sub take_real_exam {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
sub work_in_real_world {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
sub test {
my ( $self, $data_hash_ref ) = @_;
$self->_real_validate_or_test( $data_hash_ref );
}
=head2 _real_validate_or_test ( $data_hash_ref )
This is where the actual validation or testing takes place.
lib/AI/Perceptron/Simple.pm view on Meta::CPAN
sub _calculate_false_positive_rate {
my $c_matrix = shift;
my $numerator = $c_matrix->{ false_positive };
my $denominator = $numerator + $c_matrix->{ true_negative };
$c_matrix->{ false_positive_rate } = $numerator / $denominator * 100;
}
=head2 &_calculate_false_discovery_rate( $c_matrix_ref )
Calculates and adds the data for the C<false_discovery_rate> key in the confusion matrix hash.
=cut
sub _calculate_false_discovery_rate {
my $c_matrix = shift;
my $numerator = $c_matrix->{ false_positive };
my $denominator = $numerator + $c_matrix->{ true_positive };
$c_matrix->{ false_discovery_rate } = $numerator / $denominator * 100;
}
=head2 &_calculate_false_omission_rate( $c_matrix_ref )
Calculates and adds the data for the C<false_omission_rate> key in the confusion matrix hash.
=cut
sub _calculate_false_omission_rate {
my $c_matrix = shift;
my $numerator = $c_matrix->{ false_negative };
my $denominator = $numerator + $c_matrix->{ true_negative };
$c_matrix->{ false_omission_rate } = $numerator / $denominator * 100;
}
=head2 &_calculate_balanced_accuracy( $c_matrix_ref )
Calculates and adds the data for the C<balanced_accuracy> key in the confusion matrix hash.
=cut
sub _calculate_balanced_accuracy {
my $c_matrix = shift;
my $numerator = $c_matrix->{ sensitivity } + $c_matrix->{ specificity };
my $denominator = 2;
$c_matrix->{ balanced_accuracy } = $numerator / $denominator; # numerator already in %
}
=head2 display_exam_results ( ... )
The parameters are the same as C<display_confusion_matrix>. See the next method.
=head2 display_confusion_matrix ( \%confusion_matrix, \%labels )
Display the confusion matrix. If C<%confusion_matrix> has C<more_stats> elements, it will display them if they exists. The default elements ie C<accuracy> and C<sensitivity> must be present, while the rest can be absent.
C<%confusion_matrix> is the same confusion matrix returned by the C<get_confusion_matrix> method.
For C<%labels>, since C<0>'s and C<1>'s won't make much sense as the output labels in most cases, therefore, the following keys must be specified:
=over 4
=item zero_as => $category_zero_name
=item one_as => $category_one_name
=back
Please take note that non-ascii characters ie. non-English alphabets B<might> cause the output to go off :)
For the C<%labels>, there is no need to enter "actual X", "predicted X" etc. It will be prefixed with C<A: > for actual and C<P: > for the predicted values by default.
=cut
sub display_exam_results {
my ( $self, $c_matrix, $labels ) = @_;
$self->display_confusion_matrix( $c_matrix, $labels );
}
sub display_confusion_matrix {
my ( $self, $c_matrix, $labels ) = @_;
#####
my @missing_keys;
for ( qw( zero_as one_as ) ) {
push @missing_keys, $_ unless exists $labels->{ $_ };
}
croak "Missing keys: @missing_keys" if @missing_keys;
#####
_print_extended_matrix ( _build_matrix( $c_matrix, $labels ) );
}
=head2 &_build_matrix ( $c_matrix, $labels )
Builds the matrix using C<Text::Matrix> module.
C<$c_matrix> and C<$labels> are the same as the ones passed to C<display_exam_results> and C<>display_confusion_matrix.
Returns a list C<( $matrix, $c_matrix )> which can directly be passed to C<_print_extended_matrix>.
=cut
sub _build_matrix {
my ( $c_matrix, $labels ) = @_;
my $predicted_columns = [ "P: ".$labels->{ zero_as }, "P: ".$labels->{ one_as }, "Sum" ];
my $actual_rows = [ "A: ".$labels->{ zero_as }, "A: ".$labels->{ one_as }, "Sum"];
# row sum
my $actual_0_sum = $c_matrix->{ true_negative } + $c_matrix->{ false_positive };
my $actual_1_sum = $c_matrix->{ false_negative } + $c_matrix->{ true_positive };
# column sum
my $predicted_0_sum = $c_matrix->{ true_negative } + $c_matrix->{ false_negative };
my $predicted_1_sum = $c_matrix->{ false_positive } + $c_matrix->{ true_positive };
my $data = [
[ $c_matrix->{ true_negative }, $c_matrix->{ false_positive }, $actual_0_sum ],
[ $c_matrix->{ false_negative }, $c_matrix->{ true_positive }, $actual_1_sum ],
[ $predicted_0_sum, $predicted_1_sum, $c_matrix->{ total_entries } ],
];
my $matrix = Text::Matrix->new(
rows => $actual_rows,
columns => $predicted_columns,
data => $data,
);
( run in 1.152 second using v1.01-cache-2.11-cpan-39bf76dae61 )