view release on metacpan or  search on metacpan

lib/AI/Perceptron/Simple.pm  view on Meta::CPAN

=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} ? "意林\n" : "魅丽优品\n";

        # calculate the output and fine tune parameters if necessary
        while (1) {
            my $output = _calculate_output( $self, $row );
            
            #print "Sum = ", $output, "\n";
            
            # $expected_output_header to be checked together over here
            # if output >= threshold
            #    then category/result aka output is considered 1
            # else output considered 0
            
            # output expected/actual tuning
            #    0       0             -
            #    1       0             down
            #    0       1             up
            #    1       1             -
            if ( ($output >= $self->threshold) and ( $row->{$expected_output_header} eq 0 ) ) {
                _tune( $self, $row, TUNE_DOWN );

                if ( $display_stats ) {
                    print $row->{$identifier}, "\n";
                    print "   -> TUNED DOWN";
                    print "   Old sum = ", $output;
                    print "   Threshold = ", $self->threshold;
                    print "   New Sum = ", _calculate_output( $self, $row ), "\n";                
                }
                
            } elsif ( ($output < $self->threshold) and ( $row->{$expected_output_header} eq 1 ) ) {
                _tune( $self, $row, TUNE_UP );
                
                if ( $display_stats ) {
                    print $row->{$identifier}, "\n";
                    print "   -> TUNED UP";
                    print "   Old sum = ", $output;
                    print "   Threshold = ", $self->threshold;
                    print "   New Sum = ", _calculate_output( $self, $row ), "\n";
                }

            } elsif ( ($output < $self->threshold) and ( $row->{$expected_output_header} eq 0 ) ) {
            
                if ( $display_stats ) {
                    print $row->{$identifier}, "\n";
                    print "   -> NO TUNING NEEDED";
                    print "   Sum = ", _calculate_output( $self, $row );
                    print "   Threshold = ", $self->threshold, "\n";
                }
                
                next ROW;