Added neighbourhood support (kNN)

Refactored MockDataSet into own class, and added full critics array

Interfaces/UserNeighbourhood.interface.php

@@ -0,0 +1,5 @@
+<?php 
+
+interface UserNeighbourhood {
+ public function userNeighbourhood($userId);
+} 

Neighbourhood/UserNeighbourhoodNN.class.php

@@ -0,0 +1,44 @@
+<?php
+
+require_once(dirname(__FILE__) . '/../Interfaces/UserNeighbourhood.interface.php');
+
+class UserNeighbourhoodNN implements UserNeighbourhood {
+ private $_dataSet;
+ private $_neighbours;
+ private $_similarity;
+
+ public function __construct(DataSet $dataSet,
+ $neighbours,
+ UserSimilarity $similarity = null) {
+ if (!is_integer($neighbours) || $neighbours < 0)
+ throw new InvalidArgumentException('Neighbours must be numeric and >= 0');
+
+ $this->_dataSet = $dataSet;
+ $this->_neighbours = $neighbours;
+
+ if ($similarity) {
+ $this->_similarity = $similarity;
+ }
+ else {
+ require_once(dirname(__FILE__) . '/../Similarity/PearsonCorrelationSimilarity.class.php');
+
+ $this->_similarity = new PearsonCorrelationSimilarity($this->_dataSet);
+ }
+ }
+
+ public function userNeighbourhood($userId) {
+ $users = $this->_dataSet->getUserIds();
+ $scores = array();
+
+ foreach ($users as $user) {
+ if ($user == $userId) continue;
+
+ $scores[$user] = $this->_similarity->userSimilarity($userId, $user); 
+ }
+
+ arsort($scores, SORT_NUMERIC); // reverse sort
+
+ // return top n (key = userId, value = similarity value)
+ return array_slice($scores, 0, $this->_neighbours, true);
+ }
+}

Test/DataSet/MockDataSet.class.php

@@ -0,0 +1,64 @@
+<?php
+
+require_once(dirname(__FILE__) . '/../DataSet/MockDataSet.class.php');
+
+class MockDataSet implements DataSet {
+ private $_users;
+
+ public function __construct() {
+ $this->_users = array('Lisa Rose' => array('Lady in the Water' => 2.5,
+ 'Snakes on a Plane' => 3.5,
+ 'Just My Luck' => 3.0,
+ 'Superman Returns' => 3.5,
+ 'You, Me and Dupree' => 2.5,
+ 'The Night Listener' => 3.0),
+
+ 'Gene Seymour' => array('Lady in the Water' => 3.0,
+ 'Snakes on a Plane' => 3.5,
+ 'Just My Luck' => 1.5,
+ 'Superman Returns' => 5.0,
+ 'The Night Listener' => 3.0,
+ 'You, Me and Dupree' => 3.5),
+
+ 'Michael Phillips' => array('Lady in the Water' => 2.5,
+ 'Snakes on a Plane' => 3.0,
+ 'Superman Returns' => 3.5,
+ 'The Night Listener' => 4.0),
+
+ 'Claudia Puig' => array('Snakes on a Plane' => 3.5,
+ 'Just My Luck' => 3.0,
+ 'The Night Listener' => 4.5,
+ 'Superman Returns' => 4.0, 
+ 'You, Me and Dupree' => 2.5),
+
+ 'Mick LaSalle' => array('Lady in the Water' => 3.0,
+ 'Snakes on a Plane' => 4.0, 
+ 'Just My Luck' => 2.0,
+ 'Superman Returns' => 3.0,
+ 'The Night Listener' => 3.0,
+ 'You, Me and Dupree' => 2.0), 
+
+ 'Jack Matthews' => array('Lady in the Water' => 3.0,
+ 'Snakes on a Plane' => 4.0,
+ 'The Night Listener' => 3.0,
+ 'Superman Returns' => 5.0,
+ 'You, Me and Dupree' => 3.5),
+
+ 'Toby' => array('Snakes on a Plane' => 4.5,
+ 'You, Me and Dupree' => 1.0,
+ 'Superman Returns' => 4.0));
+ }
+
+ public function getUserIds() { return array_keys($this->_users); }
+
+ public function getUserRatingsArray($user) { return $this->_users[$user]; }
+
+ public function getItemIds() { }
+ public function getNumUsers() { }
+ public function getNumItems() { }
+ public function isUser($a) { }
+ public function isItem($a) { }
+ public function getUser($a) { }
+ public function getItem($a) { }
+ public function getItemRatingsArray($a) { }
+}

Test/Neighbourhood/UserNeighbourhood.test.php

@@ -0,0 +1,20 @@
+<?php
+
+require_once(dirname(__FILE__) . '/../settings.php');
+require_once(dirname(__FILE__) . '/../../Neighbourhood/UserNeighbourhoodNN.class.php');
+
+class UserNeighbourhoodTest extends CollabFiltrTest {
+ private $_dataSet;
+
+ public function setUp() {
+ $this->_dataSet = new MockDataSet();
+ }
+
+ public function testNN() {
+ $userNeighbouurNN = new UserNeighbourhoodNN($this->_dataSet, 3);
+ $neighbourhood = $userNeighbouurNN->userNeighbourhood('Toby');
+
+ $top3 = array('Lisa Rose', 'Mick LaSalle', 'Claudia Puig');
+ $this->assertEquals(array_keys($neighbourhood), $top3);
+ }
+}

Test/Similarity/UserSimilarity.test.php

@@ -1,6 +1,8 @@
 <?php
 
 require_once(dirname(__FILE__) . '/../settings.php');
+require_once(dirname(__FILE__) . '/../DataSet/MockDataSet.class.php');
+
 require_once(dirname(__FILE__) . '/../../Similarity/PearsonCorrelationSimilarity.class.php');
 require_once(dirname(__FILE__) . '/../../Similarity/EuclideanDistanceSimilarity.class.php');
 
@@ -24,36 +26,4 @@ public function testEuclidean() {
 
  $this->assertEquals(round($similarity, 6), 0.148148);
  }
-}
-
-class MockDataSet implements DataSet {
- private $_users;
-
- public function __construct() {
- $this->_users = array('Lisa Rose' => array('Lady in the Water' => 2.5,
- 'Snakes on a Plane' => 3.5,
- 'Just My Luck' => 3.0,
- 'Superman Returns' => 3.5,
- 'You, Me and Dupree' => 2.5,
- 'The Night Listener' => 3.0),
-
- 'Gene Seymour' => array('Lady in the Water' => 3.0,
- 'Snakes on a Plane' => 3.5,
- 'Just My Luck' => 1.5,
- 'Superman Returns' => 5.0,
- 'The Night Listener' => 3.0,
- 'You, Me and Dupree' => 3.5));
- }
-
- public function getUserIds() { }
- public function getItemIds() { }
- public function getNumUsers() { }
- public function getNumItems() { }
- public function isUser($a) { }
- public function isItem($a) { }
- public function getUser($a) { }
- public function getItem($a) { }
- public function getItemRatingsArray($a) { }
-
- public function getUserRatingsArray($user) { return $this->_users[$user]; }
 }

apiDesign.php

@@ -4,6 +4,7 @@
 
 require_once(dirname(__FILE__) . '/DataSet/FileDataSet.class.php');
 require_once(dirname(__FILE__) . '/Similarity/PearsonCorrelationSimilarity.class.php');
+require_once(dirname(__FILE__) . '/Neighbourhood/UserNeighbourhoodNN.class.php');
 
 $dataSet = new FileDataSet('/Volumes/Data/Work/Work/Uni/Dissertation/100k.data');
 
@@ -18,9 +19,8 @@
 $similarity = new PearsonCorrelationSimilarity($dataSet);
 #$similarity = new EuclideanDistanceSimilarity();
 
-#$users = new UserNeighbourhoodNN($data);
-#$users->setSimilarity($similarity); // dependency injection
-#$users->setNeighbours(30);
+$userNN = new UserNeighbourhoodNN($data, 30, $similarity);
+
 #
 #$recommender = new UserBasedRecommender($data);
 #$recommender->setNeighbourhood($users);