2.3.2 ピアソン相関によるスコア

コード

$critics = array( 
  'Lisa Rose' => array( 
    'Lady in the Water' => 2.5,
    'Snakes on a Plane' => 3.5,
    'Just My Luck' => 3.0,
    'Superman Returns' => 3.5,
    'You, Me and Dupree' => 2.5,
    'The Night Listener' => 3.0,
  ),
  'Gene Seymour' => array( 
    'Lady in the Water' => 3.0,
    'Snakes on a Plane' => 3.5,
    'Just My Luck' => 1.5,
    'Superman Returns' => 5.0,
    'You, Me and Dupree' => 3.5,
    'The Night Listener' => 3.0,
  ),
  'Michael Phillips' => array( 
    'Lady in the Water' => 2.5,
    'Snakes on a Plane' => 3.0,
    'Superman Returns' => 3.5,
    'The Night Listener' => 4.0,
  ),
  'Claudia Puig' => array( 
    'Snakes on a Plane' => 3.5,
    'Just My Luck' => 3.0,
    'Superman Returns' => 4.0,
    'You, Me and Dupree' => 2.5,
    'The Night Listener' => 4.5,
  ),
  'Mick LaSalle' => array( 
    'Lady in the Water' => 3.0,
    'Snakes on a Plane' => 4.0,
    'Just My Luck' => 2.0,
    'Superman Returns' => 3.0,
    'You, Me and Dupree' => 2.0,
    'The Night Listener' => 3.0,
  ),
  'Jack Matthews' => array( 
    'Lady in the Water' => 3.0,
    'Snakes on a Plane' => 4.0,
    'Superman Returns' => 5.0,
    'You, Me and Dupree' => 3.5,
    'The Night Listener' => 3.0,
  ),
  'Toby' => array( 
    'Snakes on a Plane' => 4.5,
    'Superman Returns' => 4.0,
    'You, Me and Dupree' => 1.0,
  ),
);



//P1とP2のピアソン相関係数を返す。
function sim_pearson($prefs,$p1,$p2){

  //両者が互いに評価しているアイテムのリストを取得
  $si = array();
  foreach($prefs["$p1"] as $item => $val){
    if(isset($prefs["$p2"]["$item"])){
      $si["$item"] = 1;
    }
  }

  //要素の数を調べる。
  $n = count($si);

  //すべての嗜好,平方,積を合計する

  //嗜好の合計
  $sum1 = 0;
  $sum2 = 0;

  //平方の合計
  $sum1Sq = 0;
  $sum2Sq = 0;

  //積の合計
  $pSum = 0;

  foreach($si as $item => $val){
    $sum1 += $prefs["$p1"]["$item"];
    $sum2 += $prefs["$p2"]["$item"];
    $sum1Sq += pow($prefs["$p1"]["$item"],2);
    $sum2Sq += pow($prefs["$p2"]["$item"],2);
    $pSum += $prefs["$p1"]["$item"] * $prefs["$p2"]["$item"];
  }

  //ピアソンスコアを計算する
  $num = $pSum - ($sum1 * $sum2 / $n);
  $den = sqrt(($sum1Sq - pow($sum1,2) / $n) * ($sum2Sq - pow($sum2,2) / $n));

  if($den == 0){ return 0;}

  $r = $num / $den;
  return $r;
}


var_dump( sim_pearson($critics,'Lisa Rose','Gene Seymour') ); //float(0.39605901719067)
var_dump( sim_pearson($critics,'Lisa Rose','Lisa Rose') ); //float(1)
var_dump( sim_pearson($critics,'Lisa Rose','Toby') ); //float(0.99124070716193)