codedheartinside/apriori

Apriori data analysing algorithm written within PHP.

PHP Apriori

, _(*1)

This package is meant for implementing the Apriori algorithm as a microservice., _(*2)

Installation:

Enable composer in your project

curl -s http://getcomposer.org/installer | php

Add the package to your composer.json file, _(*3)

{
    "require": {
        "codedheartinside/apriori": "1.*"
    }
}

Load the files and create the autoload file

Download the files, _(*4)

php composer.phar install

Add the autoloader for the files into your project, _(*5)

require 'vendor/autoload.php';

Set up the running environment

To set up the running environment for the package, run the installer, _(*6)

$installer = new \CodedHeartInside\DataMining\Apriori\Installer();
$installer->createRunningEnvironment();

Usage

Configuration

You first need to create a configuration with the rules for the algorithm, _(*7)

$aprioriConfiguration = new \CodedHeartInside\DataMining\Apriori\Configuration();

// Configuring the boundries is optional
$aprioriConfiguration->setDisplayDebugInformation();
$aprioriConfiguration->setMinimumThreshold(2) // Default is 2
    ->setMinimumSupport(0.2) // Default is 0.1
    ->setMinimumConfidence(5) // Default is 0.2
;

Defining the data set

After that, all is set to run the algorithm on a data set. The data set can be added through the addDataSet function., _(*8)

$dataSet = array(
    array(1, 3, 4),
    array(2, 4, 6),
    array(1, 2),
    array(5),
);

$dataInput = new \CodedHeartInside\DataMining\Apriori\Data\Input($aprioriConfiguration);
$dataInput->flushDataSet()
    ->addDataSet($dataSet)
    ->addDataSet($dataSet) // In this case, the data set is added twice to create more testing data
;

Running the algorithm

To run the the algorithm on the data set, provide the Apriori class with the configuration and call the run function., _(*9)

$aprioriClass = new \CodedHeartInside\DataMining\Apriori\Apriori($aprioriConfiguration);
$aprioriClass->run();

Retrieving the data

After running the algorithm, the records with the statistics for support and confidence become retrievable., _(*10)

Support is the time a item combination occurs in all of the provided item sets., _(*11)

To get the records with the support statistics:, _(*12)

foreach ($aprioriClass->getSupportRecords() as $record) {
    print_r($record);
    // Outputs:
    // Array
    // (
    //     [itemIds] => Array
    //     (
    //         [0] => 1
    //         [1] => 4
    //         [2] => 6
    //         [3] => 7
    //     )
    //
    //     [support] => 0.060606060606061
    // )
}

Confidence is the times a article occurs in combination with the other items, _(*13)

To get the records with the confidence statistics, _(*14)

foreach ($aprioriClass->getConfidenceRecords() as $record) {
    print_r($record);
    // Outputs
    // Array
    // (
    //     [if] => Array
    //     (
    //       [0] => 1
    //       [1] => 7
    //     )
    //
    //     [then] => 3
    //     [confidence] => 1
    // )
}