Since you didn't provide a small test data set I had to guess about it and then fake it (I may have guessed wrong).
You were doing the ranking sort for each column for each line when it only had to be done once per column.
I am reading through the file twice so that the whole file does not have to be stored in memory. Because of that I had to change your file handle names.
I had to change your I/O because a) I'm not on windows, and b) debug. I think I labeled all those changes with FIXME.
Of course, comment out the Data::Dump before running on a large file. You'll find Data::Dump is extremely slow on huge data structures.
As I've said to others here, at least my code does not fail any of your provided test cases :)
#!/usr/bin/perl
use strict; # https://perlmonks.org/?node_id=11135101
use warnings;
use List::Util qw( uniq );
my $x="Room_reserve.csv";
my $in = "D:\\package properties\\${x}.csv";
$in = "D:\\package properties\\${x}.csv"; # ????????? duplicate line??
+?
my $out = "D:\\package properties\\output\\${x}_output.csv";
print my $testdata = <<END; # FIXME
x,x,x,x,x,x,x,one,two,three
x,x,x,x,x,x,x,foo,bar,baz
x,x,x,x,x,x,x,foo2,bar7,baz3
x,x,x,x,x,x,x,foo2,bar7,baz3
x,x,x,x,x,x,x,foo,bax,baz
x,x,x,x,x,x,x,foo,bar,baz
x,x,x,x,x,x,x,foo,bar,baz
END
$in = \$testdata; #FIXME
open(my $infh, '<', $in) or die "Could not open file '$in' $!";
my @columns;
my $lines = 0;
<$infh>; # skip first line
while( <$infh> )
{
my @rows = split /[,\n]/;
$columns[$_]{$rows[$_]}++ for 0..$#rows;
$lines++;
}
my @ranksbycolumn;
for ( @columns )
{
my @dat_val = sort { $b <=> $a } uniq values %$_;
my %ranks;
@ranks{ @dat_val } = 1 .. @dat_val;
push @ranksbycolumn, \%ranks;
}
use Data::Dump 'dd'; dd 'columns', \@columns, 'ranksbycolumn', \@ranks
+bycolumn; # FIXME
my $first = 1; #output
#open(my $outfh, '>', $out) or die "Could not open file '$out' $!"; #F
+IXME
open(my $outfh, ">&STDOUT") or die "Could not open file STDOUT$!"; #FI
+XME
seek $infh, 0, 0 or die "Could not seek file '$in' $!";
while( <$infh> )
{
my @rows = split /[,\n]/;
foreach my $i (0..$#rows)
{
if ($i > 6)
{
if ( $first == 1 ) # for modifying name
{
my $line = join( ",", "Rank_$rows[$i]", "Percent_$rows[$i]",
"Count_$rows[$i]", $rows[$i]);
print $outfh "$line,";
if ( $i == $#rows ) { $first = 0; }
}
else
{
my $cnt = $columns[$i]{$rows[$i]};
my $rank = $ranksbycolumn[$i]{$cnt};
# my $ave = ($cnt / 14000000) * 100; # FIXME
my $ave = int +($cnt / $lines) * 100; # FIXME
my $line = join( ",", $rank, $ave, $cnt, $rows[$i]);
print $outfh "$line,";
}
}
else
{
print $outfh "$rows[$i],";
}
}
print $outfh "\n";
}
close $outfh;
Outputs:
x,x,x,x,x,x,x,one,two,three
x,x,x,x,x,x,x,foo,bar,baz
x,x,x,x,x,x,x,foo2,bar7,baz3
x,x,x,x,x,x,x,foo2,bar7,baz3
x,x,x,x,x,x,x,foo,bax,baz
x,x,x,x,x,x,x,foo,bar,baz
x,x,x,x,x,x,x,foo,bar,baz
(
"columns",
[
{ x => 6 },
{ x => 6 },
{ x => 6 },
{ x => 6 },
{ x => 6 },
{ x => 6 },
{ x => 6 },
{ foo => 4, foo2 => 2 },
{ bar => 3, bar7 => 2, bax => 1 },
{ baz => 4, baz3 => 2 },
],
"ranksbycolumn",
[
{ 6 => 1 },
{ 6 => 1 },
{ 6 => 1 },
{ 6 => 1 },
{ 6 => 1 },
{ 6 => 1 },
{ 6 => 1 },
{ 2 => 2, 4 => 1 },
{ 1 => 3, 2 => 2, 3 => 1 },
{ 2 => 2, 4 => 1 },
],
)
x,x,x,x,x,x,x,Rank_one,Percent_one,Count_one,one,Rank_two,Percent_two,
+Count_two,two,Rank_three,Percent_three,Count_three,three,
x,x,x,x,x,x,x,1,66,4,foo,1,50,3,bar,1,66,4,baz,
x,x,x,x,x,x,x,2,33,2,foo2,2,33,2,bar7,2,33,2,baz3,
x,x,x,x,x,x,x,2,33,2,foo2,2,33,2,bar7,2,33,2,baz3,
x,x,x,x,x,x,x,1,66,4,foo,3,16,1,bax,1,66,4,baz,
x,x,x,x,x,x,x,1,66,4,foo,1,50,3,bar,1,66,4,baz,
x,x,x,x,x,x,x,1,66,4,foo,1,50,3,bar,1,66,4,baz,
|