view release on metacpan or  search on metacpan

benchmarking/bench-sklearn-scoring.pl  view on Meta::CPAN

#!/usr/bin/perl
# benchmarking/bench-sklearn-scoring.pl
#
# Compares scoring throughput among three Perl backends and scikit-learn's
# IsolationForest across two axes:
#   * query-set size       (fixed feature count)
#   * feature-vector width (fixed query-set size)
#
# Perl backends benchmarked (when available):
#   pure perl   -- no Inline::C  (use_c => 0)
#   C serial    -- Inline::C, single-threaded  (use_c => 1, use_openmp => 0)
#   C+OpenMP    -- Inline::C + OpenMP parallel (use_c => 1, use_openmp => 1)
#
# The same training CSV and query CSVs are used by all sides so the
# comparison is on identical data.  Models are pre-trained before any
# timing starts.
#
# Method correspondence:
#   Perl score_samples         <-->  clf.score_samples(X)      (same formula, opposite sign)
#   Perl predict               <-->  clf.predict(X)            (same semantics, 0/1 vs -1/+1)
#   Perl score_predict_samples <-->  (no sklearn equivalent)
#   Perl score_predict_split   <-->  (no sklearn equivalent)
#   Perl path_lengths          <-->  (no sklearn equivalent)
#   (no Perl equivalent)       <-->  clf.decision_function(X)  (threshold-shifted score)
#
# The ratio column shows sklearn ops/s / best-Perl ops/s.
# >1 means sklearn is faster; <1 means Perl is faster.
#
# Unavailable backends (Inline::C not installed, OpenMP not linked,
# scikit-learn not installed) are omitted from the table.
#
# Run with:
#   perl -Ilib benchmarking/bench-sklearn-scoring.pl

use strict;
use warnings;
use lib '../lib';
use FindBin;
use lib "$FindBin::Bin";
use BenchAccel  qw(wall_rate);
use File::Temp  qw(tempfile);
use JSON::PP    ();
use Algorithm::Classifier::IsolationForest;

use constant PI => 3.14159265358979;

my $HAS_C      = $Algorithm::Classifier::IsolationForest::HAS_C;
my $HAS_OPENMP = $Algorithm::Classifier::IsolationForest::HAS_OPENMP;

# -----------------------------------------------------------------------
# Data generation
# -----------------------------------------------------------------------
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;
}

# -----------------------------------------------------------------------
# Parameters
# -----------------------------------------------------------------------
my $N_TRAIN    = 1000;
my $N_FEATURES = 2;       # used for the query-size sweep
my $N_TREES    = 100;
my $PSI        = 256;
my $BENCH_SECS = 2;

my @query_sizes        = ( 100, 500, 1_000, 5_000, 10_000 );