Re: (contest) Help analyze PM reputation statistics

[tachyon]

Here is a bit of code that does some basic graphing. Here is the graph. The moving averages all show the same thing. There is an unexpected data anomoly around 155-165 XP. Note I have jacked the moving averages up by 0.5 to separate them cleanly from the raw data.

#!/usr/bin/perl -w
use GD::Graph;
use GD::Graph::lines;
use strict;

my $OUTFILE = 'c:/file.png';

my %rep_stats=(1=>24694, 2=>23551, 0=>22855, 3=>21340, 4=>19598, 5=>17
+779,
6=>16575, 7=>15200, 8=>13695, 9=>12824, 10=>11722, 11=>10545, 12=>9829
+,
13=>8860, 14=>8022, 15=>7363, 16=>6692, 17=>6044, 18=>5465, 19=>5040,
-1=>4747, 20=>4575, 21=>4101, 22=>3910, 23=>3494, 24=>3135, 25=>2702,
26=>2631, 27=>2364, 28=>2233, -2=>2174, 29=>2053, 30=>1823, 31=>1775,
32=>1606, 33=>1530, 34=>1397, 35=>1269, -3=>1237, 36=>1151, 37=>1144,
38=>1059, 39=>980, 40=>961, -4=>898, 41=>885, 43=>833, 42=>761, 44=>68
+6,
45=>685, 46=>663, 47=>652, 48=>589, 49=>564, -5=>551, 51=>494, 50=>478
+,
52=>474, 54=>444, -6=>444, 53=>429, 57=>400, 55=>393, 56=>355, 58=>322
+,
59=>321, 60=>310, 61=>286, -7=>283, 62=>266, -8=>261, 64=>243, 63=>223
+,
70=>216, 66=>215, 65=>212, 67=>211, -9=>206, 68=>194, -10=>190, 71=>18
+0,
69=>176, 72=>173, 74=>163, -11=>154, 76=>148, 73=>141, 75=>138, 77=>13
+5,
-12=>134, 79=>120, 82=>120, -13=>114, 80=>109, 78=>106, -14=>106, 81=>
+100,
83=>92, -16=>90, 85=>88, 89=>87, 84=>82, 87=>74, 90=>74, 88=>74, 91=>7
+2,
92=>71, 86=>68, -15=>66, 97=>63, 98=>60, 94=>59, -17=>57, -19=>55, 93=
+>50,
96=>49, 102=>48, 105=>47, 95=>47, 99=>46, -20=>46, -18=>44, 109=>41,
101=>39, 100=>37, 104=>36, 116=>36, 111=>34, 103=>34, -22=>33, 108=>32
+,
107=>31, 106=>30, 112=>28, 121=>27, 113=>25, 110=>24, -29=>23, 120=>23
+,
117=>22, -21=>22, 118=>21, 122=>21, -23=>19, 125=>19, 129=>18, 115=>18
+,
126=>18, 132=>17, 114=>16, 124=>16, 123=>16, 128=>16, -25=>15, 137=>15
+,
-26=>14, -28=>13, 136=>13, -32=>12, -24=>12, 119=>12, -27=>12, 127=>12
+,
135=>11, 143=>11, -33=>11, 139=>11, 134=>10, -38=>10, -31=>10, 146=>10
+,
138=>10, 133=>10, -34=>9, 142=>9, 160=>9, 145=>8, 164=>8, 131=>8, -53=
+>7,
156=>7, 148=>7, 140=>7, 130=>7, 162=>7, 151=>6, 144=>6, -39=>6, -42=>6
+,
-37=>6, 147=>6, 159=>6, -40=>6, -46=>5, 155=>5, 176=>5, 167=>5, -36=>5
+,
175=>5, 166=>5, -30=>5, 172=>4, 149=>4, 150=>4, 152=>4, 161=>4, 183=>4
+,
-43=>4, 165=>4, -44=>4, 168=>4, 170=>4, 191=>4, 171=>4, -60=>3, -35=>3
+,
187=>3, 169=>3, 163=>3, 182=>3, -54=>3, -58=>3, -45=>3, 141=>3, -51=>3
+,
158=>2, -90=>2, 194=>2, 195=>2, 258=>2, 186=>2, 173=>2, 198=>2, 178=>2
+,
179=>2, -52=>2, -47=>2, -68=>2, 202=>2, -55=>2, -56=>2, 204=>2, -106=>
+2,
180=>2, 215=>2, 217=>2, 153=>2, 154=>2, 228=>2, 254=>2, -48=>1, -49=>1
+,
322=>1, 288=>1, -82=>1, -83=>1, -84=>1, -88=>1, 253=>1, 327=>1, 181=>1
+,
292=>1, 328=>1, 293=>1, 255=>1, 184=>1, 188=>1, -50=>1, -223=>1, -57=>
+1,
299=>1, -59=>1, -93=>1, 440=>1, 261=>1, 263=>1, 336=>1, 193=>1, 197=>1
+,
199=>1, -61=>1, -65=>1, -66=>1, -67=>1, 571=>1, 456=>1, 212=>1, 226=>1
+,
229=>1, 157=>1, 230=>1, 273=>1, 304=>1, 235=>1, 236=>1, 463=>1, 237=>1
+,
349=>1, 238=>1, 279=>1, -70=>1, -71=>1, 239=>1, -203=>1, 207=>1, 242=>
+1,
243=>1, 245=>1, 174=>1, -41=>1, );

my (@reps, @counts, @percent1, @percent2, @ma, @ma2, @ma4, @ma8, @ma16
+ );
my $total = 0;

my $min = 0;
for my $rep(sort { $a <=> $b } keys %rep_stats) {
    $min ||= $rep;
    $total += $rep_stats{$rep};
    push @reps, $rep;
}

my $t = $total;
my @ma = (0)x16;

for my $rep(@reps) {
    push @counts, log($rep_stats{$rep})/log(10);
    push @percent1, 5*($t-$rep_stats{$rep})/$total;
    push @percent2, 5-$percent1[-1];
    $t -= $rep_stats{$rep};
    unshift @ma, $counts[-1];
    pop @ma;
    push @ma2, calc_ma( \@ma, 2 );
    push @ma4, calc_ma( \@ma, 4 );
    push @ma8, calc_ma( \@ma, 8 );
    push @ma16, calc_ma( \@ma, 16 );
}

sub calc_ma {
    my ( $ma_ref, $num ) = @_;
    my $av = 0;
    for my $i(0..$num-1) {
        $av += $ma_ref->[$i];
    }
  return 0.5+ $av/$num;
}

my $graph = GD::Graph::lines->new(1000,750);

my @data = ( 
     \@reps,
     \@counts,
     \@percent1,
     \@percent2,
     \@ma2,
     \@ma4,
     \@ma8,
     \@ma16,
);

$graph->set_legend( 
    'Raw Count', 
    'Percent', 
    'Percent', 
    'Moving Average 2', 
    'Moving Average 4',
    'Moving Average 8',
    'Moving Average 16'
);

$graph->set( 
    x_label         => 'Reputation',
    y_label         => 'Node Count (log 10), Percent Nodes 5=100%',
    title           => 'PM Stats',
    bgclr           => 'white',
    y_max_value     => 5,
    y_tick_number   => 10,
    long_ticks      => 1,
    x_label_skip    => 10,
    legend_placement=> 'RC',
    dclrs           => [ qw(gray black black yellow green blue red) ] 
) or die $graph->error;

my $gd = $graph->plot(\@data) or die $graph->error;
open(IMG, ">$OUTFILE" ) or die $!;
binmode IMG;
print IMG $gd->png;
close IMG;

[poqui]

Nice job!

But I cannot run it... I am on a winders machine, and ActiveState doesnt have the GD package for some reason.

I also don't have a c compiler to build it.

Oh well, I will have to be contect to admire from afar...

For now.