<?php
/**
* Return the coefficient of two items based on Jaccard index
* http://en.wikipedia.org/wiki/Jaccard_index
*
* Example:
*
* $tags1 = "code, php, jaccard, test, items";
* $tags2 = "test, code";
* echo getSimilarityCoefficient( $tags1, $tags2 ); // 0.28
*
* $str1 = "similarity coefficient of two items";
* $str2 = "two items are cool";
* echo getSimilarityCoefficient( $str1, $str2, " " ); // 0.44
*
* @param string $item1
* @param string $item2
* @param string $separator
* @return float
* @author Henrique Hohmann
* @version 0.1
*/
function getSimilarityCoefficient( $item1, $item2, $separator = "," ) {
$item1 = explode( $separator, $item1 );
$item2 = explode( $separator, $item2 );
$arr_intersection = array_intersect( $item2, $item2 );
$arr_union = array_merge( $item1, $item2 );
$coefficient = count( $arr_intersection ) / count( $arr_union );
return $coefficient;
}
print(getSimilarityCoefficient('SA PRESTASHOP', strtoupper('PrestaShop SA')));
preferences:
49.72 ms | 402 KiB | 5 Q