Phpml\Helper Namespace Reference

  More...

Namespaces
namespace	Optimizer

Functions
	getClassifierCopy ()
	Returns an instance of the current class after cleaning up OneVsRest stuff.
	predictProbability (array $sample, string $label)
	Each classifier that make use of OvR approach should be able to return a probability for a sample to belong to the given label.
	predictSample (array $sample)
	predictSampleBinary (array $sample)
	Each classifier should implement this method instead of predictSample()
	reset ()
	Resets the classifier and the vars internally used by OneVsRest to create multiple classifiers.
	resetBinary ()
	To be overwritten by OneVsRest classifiers.
	train (array $samples, array $targets)
	Train a binary classifier in the OvR style.
	trainBinary (array $samples, array $targets, array $labels)
	Each classifier should implement this method instead of train(samples, targets)
	trainByLabel (array $samples, array $targets, array $allLabels=[])

Variables
array	$allLabels = []
	All provided training targets' labels.
array	$costValues = []
trait	OneVsRest
trait	Predictable
trait	Trainable

Detailed Description

 

Function Documentation

predictProbability()

Phpml\Helper\predictProbability ( array $sample, string $label )

abstractprotected

Each classifier that make use of OvR approach should be able to return a probability for a sample to belong to the given label.

Return values

mixed

predictSample()

Phpml\Helper\predictSample ( array $sample )

protected

Return values

mixed

predictSampleBinary()

Phpml\Helper\predictSampleBinary ( array $sample )

abstractprotected

Each classifier should implement this method instead of predictSample()

Return values

mixed

Variable Documentation

OneVsRest

trait Phpml::Helper\OneVsRest

Initial value:

{
    
    protected array $classifiers = []

Predictable

trait Phpml::Helper\Predictable

Initial value:

{
    
    public function predict(array $samples)
    {
        if (!is_array($samples[0])) {
            return $this->predictSample($samples);
        }
 
        $predicted = [];
        foreach ($samples as $index => $sample) {
            $predicted[$index] = $this->predictSample($sample);
        }
 
        return $predicted;
    }
 
    
    abstract protected function predictSample(array $sample)

Trainable

trait Phpml::Helper\Trainable

Initial value:

{
    
    private array $samples = []