<?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')));
- Output for 4.3.0 - 4.3.11, 4.4.0 - 4.4.9, 5.0.0 - 5.0.5, 5.1.0 - 5.1.6, 5.2.0 - 5.2.17, 5.3.0 - 5.3.29, 5.4.0 - 5.4.45, 5.5.24 - 5.5.35, 5.6.8 - 5.6.28, 7.0.0 - 7.0.20, 7.1.0 - 7.1.33, 7.2.0 - 7.2.33, 7.3.0 - 7.3.33, 7.4.0 - 7.4.33, 8.0.0 - 8.0.30, 8.1.0 - 8.1.27, 8.2.0 - 8.2.17, 8.3.0 - 8.3.4
- 0.5
preferences:
225.53 ms | 405 KiB | 337 Q