#! perl -slw
use strict;
use Time::HiRes qw[ time ];


sub MI {
    my( $string_es, $string_en, $hash_es, $hash_en ) = @_;
    my @array_es = split ' ', $hash_es->{ $string_es };
    my @array_en = split ' ', $hash_en->{ $string_en };
    my $prob_es = ( @array_es ) / 6939873;
    my $prob_en = ( @array_en ) / 6939873;
    my $intersection = Intersection( \@array_es, \@array_en );
    my $prob_es_en=  $intersection / 6939873;
    $prob_es_en = ($prob_es_en + ($prob_es * $prob_en * 0.1 ) ) / 1.1;
    my $mi = $prob_es_en * log( $prob_es_en / ( $prob_es * $prob_en) );
    return $mi;
}

sub Intersection {
    my( $refA, $refB ) = @_;

    my %counts;
    ++$counts{ $_ } for @$refA;
    ++$counts{ $_ } for @$refB;

    my $intersects = 0;
    $counts{ $_ } > 1 and ++$intersects for keys %counts;

    return $intersects;
}


our $N //= 1e4;

my $hypo = 'fred';
my $text = 'bill';

my %hash_es; $hash_es{ $hypo } = join ' ', 1 .. $N;
my %hash_en; $hash_en{ $text } = join ' ', 1 .. $N;

my $start = time;
my $MI_T = MI( $hypo, $text, \%hash_es, \%hash_en );
printf "Took: %f seconds\n", time() - $start;

__END__
C:\test>888162
Took: 0.046187 seconds

C:\test>888162 -N=1e5
Took: 0.677000 seconds

C:\test>888162 -N=1e6
Took: 7.680000 seconds

C:\test>888162 -N=2e6
Took: 15.748000 seconds

C:\test>888162 -N=3e6
Took: 25.244000 seconds