view release on metacpan or  search on metacpan

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

			{ 'completion' => 'files' }
		],
		[
			'prototype=s',
			'JSON prototype file to create the model from (new models only): the variable schema and '
				. 'schema_version/schema_description come from it, and its params supply knob defaults that the '
				. 'creation switches override. May not be combined with -t or --mungers. See PROTOTYPES in the '
				. 'module POD.',
			{ 'completion' => 'files' }
		],
	);
} ## end sub opt_spec

sub abstract { 'Stream CSV rows through an Online Isolation Forest model, scoring and learning as it goes' }

sub description {
	'Streams the input rows, in order, through an Online Isolation Forest
model (Algorithm::Classifier::IsolationForest::Online).

The default operation is prequential: each row is scored against the
model as it stood before that row was learned, then learned, and the
model state (including its sliding window) is saved back to -m so the
next invocation resumes the stream where this one left off.  --learn-only
skips the scoring (warm-up) and --score-only skips the learning.

If -m does not exist yet a new model is created using the creation knobs
(-n, --window, --eta, --growth, --subsample, -s, -c, -t, --mungers,
--prototype); when it does exist those knobs are ignored.  With
--prototype the schema and schema_version/schema_description come from
the prototype file, its params supply knob defaults, and the other
creation switches override those params.

The input format matches `iforest fit`: CSV, all columns numeric
features, one sample per row.

Output format is one line per input row.

$score,$label

If -d is specified all input feature columns are prepended.

$feat1,...,$featN,$score,$label

Switches to new args for new models are like below...

-n        -> n_trees
--window  -> window_size
--eta     -> max_leaf_samples
--growth  -> growth
--subsample -> subsample
-s        -> seed
-c        -> contamination
-t        -> feature_names
';
} ## end sub description

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

	if ( !defined( $opt->{'i'} ) ) {
		$self->usage_error('-i has not been specified for a file to process');
	} elsif ( !-f $opt->{'i'} ) {
		$self->usage_error( '-i, "' . $opt->{'i'} . '", is not a file or does not exist' );
	} elsif ( !-r $opt->{'i'} ) {
		$self->usage_error( '-i, "' . $opt->{'i'} . '", is not readable' );
	}

	if ( -e $opt->{'m'} && !-r $opt->{'m'} ) {
		$self->usage_error( '-m, "' . $opt->{'m'} . '", exists but is not readable' );
	}

	if ( $opt->{'learn_only'} && $opt->{'score_only'} ) {
		$self->usage_error('--learn-only and --score-only may not be combined');
	}

	if ( defined( $opt->{'o'} ) && !$opt->{'w'} && -e $opt->{'o'} ) {
		$self->usage_error( '-o, "' . $opt->{'o'} . '", already exists and -w is not specified' );
	}

	if ( defined( $opt->{'threshold'} ) && ( $opt->{'threshold'} <= 0 || $opt->{'threshold'} >= 1 ) ) {
		$self->usage_error( '--threshold, "' . $opt->{'threshold'} . '", needs to be greater than 0 and less than 1' );
	}

	if ( defined( $opt->{'growth'} ) && $opt->{'growth'} !~ /\A(?:adaptive|fixed)\z/ ) {
		$self->usage_error( '--growth, "' . $opt->{'growth'} . '", must be either adaptive or fixed' );
	}

	if ( defined( $opt->{'mungers'} ) ) {
		if ( !-f $opt->{'mungers'} ) {
			$self->usage_error( '--mungers, "' . $opt->{'mungers'} . '", is not a file or does not exist' );
		} elsif ( !-r $opt->{'mungers'} ) {
			$self->usage_error( '--mungers, "' . $opt->{'mungers'} . '", is not readable' );
		} elsif ( !defined( $opt->{'t'} ) ) {
			$self->usage_error('--mungers requires feature tags (-t) to compile against');
		}
	}

	if ( defined( $opt->{'prototype'} ) ) {
		if ( !-f $opt->{'prototype'} ) {
			$self->usage_error( '--prototype, "' . $opt->{'prototype'} . '", is not a file or does not exist' );
		} elsif ( !-r $opt->{'prototype'} ) {
			$self->usage_error( '--prototype, "' . $opt->{'prototype'} . '", is not readable' );
		}
		if ( defined( $opt->{'t'} ) || defined( $opt->{'mungers'} ) ) {
			$self->usage_error(
				'--prototype may not be combined with -t or --mungers; the schema comes only from the prototype');
		}
	} ## end if ( defined( $opt->{'prototype'} ) )

	return 1;
} ## end sub validate

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

	# --- resume an existing model first ------------------------------------
	# Loaded before the CSV is read because a munger-bearing model changes
	# how the CSV is validated (munged columns hold raw values).
	my $oif;
	if ( -f $opt->{'m'} ) {
		$oif = Algorithm::Classifier::IsolationForest->load( $opt->{'m'} );