view release on metacpan or  search on metacpan

lib/Algorithm/Classifier/IsolationForest/App/Command/fit.pm  view on Meta::CPAN

package Algorithm::Classifier::IsolationForest::App::Command::fit;

use strict;
use warnings;
use Algorithm::Classifier::IsolationForest ();
use Algorithm::Classifier::IsolationForest::App -command;
use File::Slurp  qw(read_file write_file);
use Scalar::Util qw(looks_like_number);

sub opt_spec {
	return (
		[ 'i=s',      'CSV to use.',                 { completion => 'files' } ],
		[ 'o=s',      'Output JSON file path/name.', { 'default'  => 'iforest_model.json', 'completion' => 'files' } ],
		[ 'p',        'Print the results instead of saving it.' ],
		[ 'w',        'Overwrite the file if it already exists.' ],
		[ 's=i',      'Seed int' ],
		[ 'extended', 'Use EIF instead of IF.' ],
		[ 'n=i',      'Number of isolation trees in the ensemble' ],
		[ 'm=i',      'Sub-sample size used to build each tree... max samples' ],
		[ 'd=i',      'per-tree height limit... if not defined is set to ceil(log2(psi))' ],
		[
			'e=f',
			'How many features take partin each split. 0 behaves like a single-feature (axis) cut; the maximum (n_features - 1) uses every varying feature. undef => maximum. Clamped to [0, n_features - 1] at fit time. May only be used with -e.'
		],
		[
			'c=f',
			'Contamination. Expected fraction of anomalies, in (0, 0.5]. When given, fit() learns a score threshold that flags this fraction of the training set, and predict() uses it by default. undef => no learned threshold (predict() falls back to 0.5).'
		],
		[
			't=s@',
			'Feature name tag. Pass once per feature (e.g. -t cpu -t mem -t disk); the count must match the number of CSV columns or the command will die.'
		],
		[
			'voting=s',
			"Scoring-time aggregation: 'mean' (classic averaged score, the default) or 'majority' (MVIForest: each tree votes against the decision threshold and the label is the majority vote).",
		],
		[
			'mungers=s',
			'JSON file of Algorithm::ToNumberMunger specs, keyed by feature tag. Requires -t. '
				. 'Munged CSV columns may hold raw (non-numeric) values; they are munged before fitting '
				. 'and the spec is saved with the model. Scalar mungers only (no into/from lists) for CSV input.',
			{ 'completion' => 'files' }
		],
		[
			'prototype=s',
			'JSON prototype file to create the model from: the variable schema (feature names, '
				. 'descriptions, mungers, missing policy) plus schema_version/schema_description come from it, '
				. 'and its params supply knob defaults that explicit switches override. May not be combined '
				. 'with -t or --mungers (the schema is the prototype\'s). See PROTOTYPES in the module POD.',
			{ 'completion' => 'files' }
		],
	);
} ## end sub opt_spec

sub abstract { 'Fits the model using the specified data and save it' }

sub description {
	'Fits the model using the specified data and save it

The input format is expected to be CSV. All columns are used as features;
each row becomes one sample. Every row must have the same number of columns
and every value must be numeric.

Switches to new args are like below...

-n -> n_trees
-s -> seed
-m -> sample_size
-e -> extension_level
-c -> contamination
--voting -> voting

With --prototype the schema (feature names, descriptions, mungers,
missing policy) and schema_version/schema_description come from the
prototype file, its params supply knob defaults, and the switches above
override those params. See PROTOTYPES in the module POD for the format.

';
} ## end sub description

sub validate {
	my ( $self, $opt, $args ) = @_;

	if ( !defined( $opt->{'i'} ) ) {
		$self->usage_error('-i has not been specified');
	} elsif ( !-f $opt->{'i'} ) {
		$self->usage_error( '-i, "' . $opt->{'i'} . '", is not a file' );