view release on metacpan or  search on metacpan

benchmarking/bench-score.pl  view on Meta::CPAN

#!/usr/bin/perl
# benchmarking/bench-score.pl
#
# Benchmarks the five public scoring/prediction methods:
#   score_samples, predict, score_predict_samples, score_predict_split,
#   path_lengths
#
# Sections:
#   1. Scoring method comparison  -- which method has the lowest overhead
#   2. Query set size scaling     -- throughput vs number of points scored
#   3. n_trees scaling on scoring -- effect of model size on score time
#   4. Feature count 2–10         -- fine-grained column-count sweep on scoring
#
# Models are pre-trained before any timing begins.
#
# Run with:
#   perl -Ilib benchmarking/bench-score.pl

use strict;
use warnings;
use lib '../lib';
use FindBin;
use lib "$FindBin::Bin";
use BenchAccel qw(wall_cmpthese);
use Algorithm::Classifier::IsolationForest;

use constant PI => 3.14159265358979;

sub gaussian {
	my ( $mu, $sigma ) = @_;
	return $mu + $sigma * sqrt( -2 * log( rand() || 1e-12 ) ) * cos( 2 * PI * rand() );
}

sub make_data {
	my ( $n, $nf ) = @_;
	my @rows = map {
		[ map { gaussian( 0, 1 ) } 1 .. $nf ]
	} 1 .. $n;
	for ( 1 .. int( $n * 0.05 ) ) {
		my $r = 5 + rand() * 3;
		push @rows, [ map { $r * ( rand() > 0.5 ? 1 : -1 ) } 1 .. $nf ];
	}
	return \@rows;
} ## end sub make_data

print "=" x 62, "\n";
print " scoring benchmarks -- Algorithm::Classifier::IsolationForest\n";
print "=" x 62, "\n";
print "(rates shown as calls/second wall-clock; higher is faster)\n";

# -----------------------------------------------------------------------
# Pre-train models with different n_trees on the same 1000-sample dataset
# -----------------------------------------------------------------------
srand(42);
my $train = make_data( 1000, 2 );
my %model;
for my $nt ( 10, 50, 100, 200, 500 ) {
	$model{$nt} = Algorithm::Classifier::IsolationForest->new(
		n_trees     => $nt,
		sample_size => 256,
		seed        => 1,
	)->fit($train);
}