<?php
/**
* K-means clustering with centroid and normalize value
*
* @see http://phpir.com/clustering
* @see
*/
define(WITH_NORMALIZE, false);
$data = array(array(0.05, 0.95), array(0.1, 0.9), array(0.2, 0.8), array(0.25, 0.75), array(0.45, 0.55), array(0.5, 0.5), array(0.55, 0.45), array(0.85, 0.15), array(0.9, 0.1), array(0.95, 0.05));
var_dump(kMeans($data, 3, WITH_NORMALIZE));
function initialiseCentroids(array $data, $k, $normalize = false)
{
$dimensions = count($data[0]);
$centroids = array();
$dimmax = array();
$dimmin = array();
foreach ($data as $document) {
foreach ($document as $dim => $val) {
if (!isset($dimmax[$dim]) || $val > $dimmax[$dim]) {
$dimmax[$dim] = $val;
}
if (!isset($dimmin[$dim]) || $val < $dimmin[$dim]) {
$dimmin[$dim] = $val;
}
}
}
for ($i = 0; $i < $k; $i++) {
$centroids[$i] = initialiseCentroid($dimensions, $dimmax, $dimmin, $normalize);
}
return $centroids;
<?php
$data = array(array(0.05, 0.95), array(0.1, 0.9), array(0.2, 0.8), array(0.25, 0.75), array(0.45, 0.55), array(0.5, 0.5), array(0.55, 0.45), array(0.85, 0.15), array(0.9, 0.1), array(0.95, 0.05));
// Lets normalise the input data
foreach ($data as $key => $d) {
$data[$key] = normaliseValue($d, sqrt($d[0] * $d[0] + $d[1] * $d[1]));
}
var_dump(kMeans($data, 3));
function initialiseCentroids(array $data, $k)
{
$dimensions = count($data[0]);
$centroids = array();
$dimmax = array();
$dimmin = array();
foreach ($data as $document) {
foreach ($document as $dim => $val) {
if (!isset($dimmax[$dim]) || $val > $dimmax[$dim]) {
$dimmax[$dim] = $val;
}
if (!isset($dimmin[$dim]) || $val < $dimmin[$dim]) {
$dimmin[$dim] = $val;
}
}
}
for ($i = 0; $i < $k; $i++) {
$centroids[$i] = initialiseCentroid($dimensions, $dimmax, $dimmin);
}
return $centroids;
}
function initialiseCentroid($dimensions, $dimmax, $dimmin)
{
$resultsTfidf = getTfidf($resultsIndex, $nonAggregatedTotalSet);
// Normalise input data for centroids
$normalisedTfidf = normaliseTfidf($resultsTfidf);
/*
// test
foreach ( $normalisedTfidf as $docID => $value )
{
foreach ( $value as $term => $tfidfValue )
{
$normal .= "docId: " . $docID . " , term: " . $term . " , tf-idf: " . $tfidfValue . "<br />";
}
}
*/
// Calculate centroids, map docs to them
$numClusters = 5;
$mapDocToClusterID = kMeans($normalisedTfidf, $numClusters);
// Get the clustered results list
$clusteredList = getClusteredResults($nonAggregated, $mapDocToClusterID);
/*
// test
$tfidfmax = array();
$tfidfmin = array();
$centroidsCoord = initialiseCentroids( $normalisedTfidf , $numClusters , $tfidfmax, $tfidfmin );
foreach ( $tfidfmax as $term => $tfidfMax )
{
$maxmin .= $term . " => Max:" . $tfidfMax . " Min:" . $tfidfmin[$term] . "<br />";
if( $tfidfMax != $tfidfmin[$term] )
$maxmin .= "HOLY SHIT!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! <br/>";
}
foreach ( $centroidsCoord as $clusterID => $value )
{
