view release on metacpan or  search on metacpan

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

  {"cmd": "mode", "mode": "score"}           -> {"ok": {"mode": "score"}}
  {"cmd": "ping"}                            -> {"ok": "pong"}
  {"cmd": "stats"}                           -> {"ok": {"seen": ..., ...}}
  {"cmd": "save"}                            -> {"ok": {"saved": "oiforest-....json"}}
  {"cmd": "relearn-threshold"}               -> {"ok": {"threshold": 0.61}}
  anything invalid                           -> {"error": "...", "tag": ...}

The array row form is positional (scalar mungers applied, like stream
CSV input); the object form is a tagged row and runs the full munger
plan, including expanding and combining mungers -- and, being JSON, the
raw values may safely contain commas, newlines, or any unicode.

A worked tagged example.  Create the daemon around raw HTTP request
data, with mungers turning the raw values into numbers (mungers.json
here; a --prototype carrying the same schema works identically):

  { "method":       { "munger": "http_method_enum", "default": -1 },
    "path_len":     { "munger": "length",  "from": "path" },
    "host_entropy": { "munger": "entropy", "from": "host" } }

  iforest streamd --set web -t method -t path_len -t host_entropy \

t/91-streamd.t  view on Meta::CPAN

	$daemon = start_daemon(
		'--save-interval' => 60,
		'--model-dir'     => $mdir2,
		'-s'              => 7,
		'--prototype'     => $proto
	);
	my $c4 = connect_client();

	# Raw values with embedded commas, quotes, newline escapes, and
	# unicode -- the reason the protocol is JSON.
	my @raw = map { { method => 'GET', path => '/a,b/"c"/' . ( 'p' x ( 3 + $_ % 15 ) ) . "\x{2603}" } } 1 .. 60;
	is_deeply(
		rt( $c4, { rows => \@raw, mode => 'learn' } ),
		{ ok => { learned => 60 } },
		'raw tagged rows with hostile content learn cleanly'
	);
	my $r = rt( $c4, { row => { method => 'BREW', path => '/' . ( 'a' x 90 ) . ',oh no' }, tag => "t,\x{2603}" } );
	like( $r->{score}, qr/\A[\d.eE+-]+\z/, 'raw anomalous row scores' );
	is( $r->{tag}, "t,\x{2603}", 'unicode/comma tag round-trips' );

	close $c4;
	is( stop_daemon($daemon), 0, 'munged daemon exits 0' );
	undef $daemon;
}; ## end 'raw munged values that CSV could never carry' => sub

subtest '--set runs named instances side by side' => sub {
	my $sdir  = "$tmp/sets";
	my @knobs = ( '--save-interval' => 60, '-n' => 10, '--window' => 64, '--eta' => 8 );
	my $alpha = spawn_daemon(