php-ml/docs/machine-learning/association/apriori.md
Yuji Uchiyama 9c195559df Update apriori documentation (#245)
* Fix a wrong word

* More precise description about support and confidence
2018-02-27 18:50:07 +01:00

1.8 KiB

Apriori Associator

Association rule learning based on Apriori algorithm for frequent item set mining.

Constructor Parameters

  • $support - minimum threshold of support, i.e. the ratio of samples which contain both X and Y for a rule "if X then Y"
  • $confidence - minimum threshold of confidence, i.e. the ratio of samples containing both X and Y to those containing X
use Phpml\Association\Apriori;

$associator = new Apriori($support = 0.5, $confidence = 0.5);

Train

To train a associator simply provide train samples and labels (as array). Example:

$samples = [['alpha', 'beta', 'epsilon'], ['alpha', 'beta', 'theta'], ['alpha', 'beta', 'epsilon'], ['alpha', 'beta', 'theta']];
$labels  = [];

use Phpml\Association\Apriori;

$associator = new Apriori($support = 0.5, $confidence = 0.5);
$associator->train($samples, $labels);

You can train the associator using multiple data sets, predictions will be based on all the training data.

Predict

To predict sample label use predict method. You can provide one sample or array of samples:

$associator->predict(['alpha','theta']);
// return [['beta']]

$associator->predict([['alpha','epsilon'],['beta','theta']]);
// return [[['beta']], [['alpha']]]

Associating

Get generated association rules simply use rules method.

$associator->getRules();
// return [['antecedent' => ['alpha', 'theta'], 'consequent' => ['beta'], 'support' => 1.0, 'confidence' => 1.0], ... ]

Frequent item sets

Generating k-length frequent item sets simply use apriori method.

$associator->apriori();
// return [ 1 => [['alpha'], ['beta'], ['theta'], ['epsilon']], 2 => [...], ...]