#!/usr/bin/perl

use Algorithm::NaiveBayes;
use Data::Dumper;

$| = 1;
$Data::Dumper::Deepcopy = 1;
$Data::Dumper::Sortkeys = 1;

my %training_files = 
    (   positive => q{/Users/Agnes/Documents/positive.txt},
        negative => q{/Users/Agnes/Documents/negative.txt},
        neutral  => q{/Users/Agnes/Documents/neutral.txt},  );

my @test_files = 
    (   q{/Users/Agnes/Documents/process_sentence.txt},
        q{/Users/Agnes/Documents/test.txt},  );

my $nb = Algorithm::NaiveBayes->new( purge => 0, );

foreach my $k ( keys %training_files ) {
    local $/;
    open my $inf, q{<}, $training_files{$k} or die $!;
        my $line = <$inf>;
    close $inf;
    $nb->add_instance( 
        attributes => str_to_array( $line ), 
        label => [ $word ], 
    );
}

$nb->train;

foreach my $tf ( @test_files ) {
    local $/;
    open my $inf, q{<}, $tf or die $!;
        my $line = <$inf>;
    close $inf;
    my $result = $nb->predict(
                        attributes => str_to_array( $line ),
                    );
    print qq{Prediction: $result - $tf\n};
}

sub str_to_array {
    my ($str) = @_;
    my %attr;
    foreach my $word ( split /\s|[\(\)!?.,:;]/, $str ) {
        $attr{$word}++;
    }
    return \%attr;
}