#!/usr/bin/perl
use strict;
use warnings;

my $infile = 'products.txt';
my %data  = ();
my %total = ();
my $records = 0;

my $t0 = time();
open IN,'<',$infile or die "Could not open $infile $!";
while (<IN>){
  my ($date, $product, $price, $qu) = split /\s+/,$_;
  $data{$date}{$product}{'price'}   = $price;  
  $data{$date}{$product}{'qu'}      = $qu;  

  $total{$product}{'count'}        += 1;
  $total{$product}{'price'}{'sum'} += $price;
  $total{$product}{'qu'}{'sum'}    += $qu;  
  ++$records;
}
close IN;

# calculate stats
my $outfile = 'report.txt';
open OUT,'>',$outfile or die "Could not open $outfile";
for my $prod (keys %total){
  my $count = $total{$prod}{'count'};
  
  # mean
  $total{$prod}{'price'}{'mean'} = $total{$prod}{'price'}{'sum'}/$count;
  $total{$prod}{'qu'}{'mean'}    = $total{$prod}{'qu'}{'sum'}/$count;
  
  # std dev squared
  my ($sum_x2,$sum_y2);
  for my $date (keys %data){
    my $x = $data{$date}{$prod}{'price'} - $total{$prod}{'price'}{'mean'}; 
    $sum_x2 += ($x*$x);
    my $y = $data{$date}{$prod}{'qu'} - $total{$prod}{'qu'}{'mean'}; 
    $sum_y2 += ($y*$y);
  }
  
  $total{$prod}{'price'}{'stddev'} = sqrt($sum_x2/$count);
  $total{$prod}{'qu'}{'stddev'}    = sqrt($sum_y2/$count);
  
  my $line = join "\t",$prod,
  $total{$prod}{'price'}{'mean'},
  $total{$prod}{'price'}{'stddev'},
  $total{$prod}{'qu'}{'mean'},
  $total{$prod}{'qu'}{'stddev'};
  
  print OUT $line."\n";
  
}
close OUT;

# correlate first 5 products against the rest
$t0 = time;
for (1..5){
  my $p1 = sprintf 'product_%04d',$_;
  print "Correlating $p1\n";
  open OUT,'>',"correlate_${p1}.txt" or die "$!";
  for my $p2 (sort keys %total){
    correlate($p1,$p2,'price');
  }
  close OUT;
}


# summary
my $dur = time - $t0;
printf "
Products : %d
Dates    : %d
Records  : %d
Run Time : %d s",0+keys %total, 0+keys %data, $records, $dur;

sub correlate {
  my ($p1,$p2,$v) = @_;
  return if $p1 eq $p2;
  my $sigma;
  my $count = 0;
  for my $date (sort keys %data){
    # skip missing dataset
    next unless (defined $data{$date}{$p1} && defined $data{$date}{$p2});
    
    my $zee1 = ( $data{$date}{$p1}{$v} - $total{$p1}{$v}{'mean'} ) / $total{$p1}{$v}{'stddev'} ;
    my $zee2 = ( $data{$date}{$p2}{$v} - $total{$p2}{$v}{'mean'} ) / $total{$p2}{$v}{'stddev'} ;
    $sigma += ( $zee1 * $zee2 );
    ++$count;
  }
  my $cor = $sigma / ( $count - 1 ) ;
  print OUT "$p1 $p2 $v $cor\n";
}