#!/usr/bin/env perl -w

use Data::Dumper;

my @work_files = qw/work1 work2 work3 work4/;
my @notwork_files = qw/notwork1 notwork2 notwork3 notwork4 notwork5 notwork6/;

my %work_tokens = ();
my %notwork_tokens = ();

foreach my $file (@work_files) {
  my %tokens = tokenize_file("training_set/" . $file);
  %work_tokens = combine_hash(\%work_tokens, \%tokens);
}

foreach my $file (@notwork_files) {
  my %tokens = tokenize_file("training_set/" . $file);
  %notwork_tokens = combine_hash(\%notwork_tokens, \%tokens);
}


my %total_tokens = combine_hash(\%work_tokens, \%notwork_tokens);


my %test_tokens = tokenize_file($ARGV[0]);

my $total_work_files = scalar(@work_files);
my $total_notwork_files = scalar(@notwork_files);
my $total_files = $total_work_files + $total_notwork_files;
my $probability_work = $total_work_files / $total_files;
my $probability_notwork = $total_notwork_files / $total_files;

my $work_accumulator = 1;
my $notwork_accumulator = 1;
my $total_tokens = scalar(keys(%test_tokens));

foreach my $token (keys(%test_tokens)) {
  if (exists($total_tokens{$token})) {
    my $p_t_w = (($work_tokens{$token} || 0) + 1) / ($total_work_files + $total_tokens);
    $work_accumulator = $work_accumulator * $p_t_w;

    my $p_t_nw = (($notwork_tokens{$token} || 0) + 1) / ($total_notwork_files + $total_tokens);
    $notwork_accumulator = $notwork_accumulator * $p_t_nw;
  }
}

my $score_work = bayes( $probability_work,
                        $total_tokens,
                        $work_accumulator);

my $score_notwork = bayes( $probability_notwork,
                           $total_tokens,
                           $notwork_accumulator);

my $likelihood_work = $score_work / ($score_work + $score_notwork);
my $likelihood_notwork = $score_notwork / ($score_work + $score_notwork);


printf("likelihood of work email: %0.2f %%\n", ($likelihood_work * 100));
printf("likelihood of notwork email: %0.2f %%\n", ($likelihood_notwork * 100));



sub bayes {
  my ($p_w, $p_t, $p_t_w) = @_;

  my $p_w_t = ($p_t_w * $p_w) / $p_t;

  return $p_w_t;
}





sub combine_hash {
  my ($hash1, $hash2) = @_;

  my %resulthash = %{ $hash1 };

  foreach my $key (keys(%{ $hash2 })) {
    if ($resulthash{$key}) {
      $resulthash{$key} += $hash2->{$key};
    } else {
      $resulthash{$key} = $hash2->{$key};
    }
  }

  return %resulthash;
}




sub tokenize {
  my $contents = shift;

  my %tokens = map { $_ => 1 } split(/\s+/, $contents);
  return %tokens;
}


sub tokenize_file {
  my $filename = shift;

  my $contents = '';
  open(FILE, $filename);
  read(FILE, $contents, -s FILE);
  close(FILE);

  return tokenize($contents);
}