Fixed the recommenders to return the recommendations as list.

chujiaqiang · Oct 10, 2011 · 15f4056 · 15f4056
1 parent cac20f6
commit 15f4056
Show file tree

Hide file tree

Showing 3 changed files with 54 additions and 62 deletions.
diff --git a/scikits/crab/recommenders/knn/classes.py b/scikits/crab/recommenders/knn/classes.py
@@ -95,12 +95,10 @@ class ItemBasedRecommender(ItemRecommender):
     >>> recsys = ItemBasedRecommender(model, similarity, items_strategy)
     >>> #Return the recommendations for the given user.
     >>> recsys.recommend('Leopoldo Pires')
-    array(['Just My Luck', 'You, Me and Dupree'],\
-          dtype='|S18')
+    ['Just My Luck', 'You, Me and Dupree']
     >>> #Return the 2 explanations for the given recommendation.
     >>> recsys.recommended_because('Leopoldo Pires', 'Just My Luck',2)
-    array(['The Night Listener', 'Superman Returns'],\
-          dtype='|S18')
+    ['The Night Listener', 'Superman Returns']
 
     Notes
     -----------
@@ -245,21 +243,21 @@ def _top_matches(self, source_id, target_ids, how_many=None, **params):
 
         preferences = estimate_preferences(source_id, target_ids)
 
-        preferences = preferences[~np.isnan(preferences)]
+        preference_values = preferences[~np.isnan(preferences)]
         target_ids = target_ids[~np.isnan(preferences)]
 
-        sorted_preferences = np.lexsort((preferences,))[::-1]
+        sorted_preferences = np.lexsort((preference_values,))[::-1]
 
         sorted_preferences = sorted_preferences[0:how_many] \
              if how_many and sorted_preferences.size > how_many \
                 else sorted_preferences
 
         if self.with_preference:
-            top_n_recs = np.array([(target_ids[ind], \
-                     preferences[ind]) for ind in sorted_preferences])
+            top_n_recs = [(target_ids[ind], \
+                     preferences[ind]) for ind in sorted_preferences]
         else:
-            top_n_recs = np.array([target_ids[ind]
-                 for ind in sorted_preferences])
+            top_n_recs = [target_ids[ind]
+                 for ind in sorted_preferences]
 
         return top_n_recs
 
@@ -336,11 +334,11 @@ def recommended_because(self, user_id, item_id, how_many=None, **params):
                  else sorted_preferences
 
         if self.with_preference:
-            top_n_recs = np.array([(item_ids[ind], \
-                     prefs[ind]) for ind in sorted_preferences])
+            top_n_recs = [(item_ids[ind], \
+                     prefs[ind]) for ind in sorted_preferences]
         else:
-            top_n_recs = np.array([item_ids[ind]
-                 for ind in sorted_preferences])
+            top_n_recs = [item_ids[ind]
+                 for ind in sorted_preferences]
 
         return top_n_recs
 
@@ -425,12 +423,10 @@ class UserBasedRecommender(UserRecommender):
     >>> recsys = UserBasedRecommender(model, similarity, nhood_strategy)
     >>> #Return the recommendations for the given user.
     >>> recsys.recommend('Leopoldo Pires')
-    array(['Just My Luck', 'You, Me and Dupree'],\
-          dtype='|S18')
+    ['Just My Luck', 'You, Me and Dupree']
     >>> #Return the 2 explanations for the given recommendation.
     >>> recsys.recommended_because('Leopoldo Pires', 'Just My Luck',2)
-    array(['Lorena Abreu', 'Marcel Caraciolo'],\
-          dtype='|S16')
+    ['Lorena Abreu', 'Marcel Caraciolo']
 
     Notes
     -----------
@@ -635,21 +631,21 @@ def _top_matches(self, source_id, target_ids, how_many=None, **params):
 
         preferences = estimate_preferences(source_id, target_ids)
 
-        preferences = preferences[~np.isnan(preferences)]
+        preference_values = preferences[~np.isnan(preferences)]
         target_ids = target_ids[~np.isnan(preferences)]
 
-        sorted_preferences = np.lexsort((preferences,))[::-1]
+        sorted_preferences = np.lexsort((preference_values,))[::-1]
 
         sorted_preferences = sorted_preferences[0:how_many] \
              if how_many and sorted_preferences.size > how_many \
                 else sorted_preferences
 
         if self.with_preference:
-            top_n_recs = np.array([(target_ids[ind], \
-                     preferences[ind]) for ind in sorted_preferences])
+            top_n_recs = [(target_ids[ind], \
+                     preferences[ind]) for ind in sorted_preferences]
         else:
-            top_n_recs = np.array([target_ids[ind]
-                 for ind in sorted_preferences])
+            top_n_recs = [target_ids[ind]
+                 for ind in sorted_preferences]
 
         return top_n_recs
 
@@ -703,10 +699,10 @@ def recommended_because(self, user_id, item_id, how_many=None, **params):
                  else sorted_preferences
 
         if self.with_preference:
-            top_n_recs = np.array([(user_ids[ind], \
-                     prefs[ind]) for ind in sorted_preferences])
+            top_n_recs = [(user_ids[ind], \
+                     prefs[ind]) for ind in sorted_preferences]
         else:
-            top_n_recs = np.array([user_ids[ind]
-                 for ind in sorted_preferences])
+            top_n_recs = [user_ids[ind]
+                 for ind in sorted_preferences]
 
         return top_n_recs
diff --git a/scikits/crab/recommenders/knn/tests/test_classes.py b/scikits/crab/recommenders/knn/tests/test_classes.py
@@ -302,10 +302,12 @@ def test_recommend_ItemBasedRecommender():
     assert_array_equal(np.array([]), recsys.recommend('Maria Gabriela'))
 
     #with_preference
-    #recsys = ItemBasedRecommender(matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('Just My Luck', 3.20597319063), \
-    #            ('You, Me and Dupree', 3.14717875510)]), \
-    #            recsys.recommend('Leopoldo Pires'))
+    recsys = ItemBasedRecommender(matrix_model, similarity, items_strategy, True, True)
+    assert_equals('Just My Luck', recsys.recommend('Leopoldo Pires')[0][0])
+    assert_equals('You, Me and Dupree', recsys.recommend('Leopoldo Pires')[1][0])
+
+    assert_almost_equals(3.20597, recsys.recommend('Leopoldo Pires')[0][1], 2)
+    assert_almost_equals(3.147178755, recsys.recommend('Leopoldo Pires')[1][1], 2)
 
     similarity = ItemSimilarity(boolean_matrix_model, jaccard_coefficient)
     #Empty Recommendation
@@ -331,10 +333,12 @@ def test_recommend_ItemBasedRecommender():
     assert_array_equal(np.array([]), recsys.recommend('Maria Gabriela'))
 
     #with_preference
-    #recsys = ItemBasedRecommender(boolean_matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('Just My Luck', 3.20597), \
-    #            ('You, Me and Dupree', 3.1471)]), \
-    #            recsys.recommend('Leopoldo Pires'))
+    recsys = ItemBasedRecommender(boolean_matrix_model, similarity, items_strategy, True, True)
+    assert_equals('You, Me and Dupree', recsys.recommend('Leopoldo Pires')[0][0])
+    assert_equals('Just My Luck', recsys.recommend('Leopoldo Pires')[1][0])
+
+    assert_almost_equals(1.0, recsys.recommend('Leopoldo Pires')[0][1], 2)
+    assert_almost_equals(1.0, recsys.recommend('Leopoldo Pires')[1][1], 2)
 
 
 def test_recommend_UserBasedRecommender():
@@ -363,10 +367,12 @@ def test_recommend_UserBasedRecommender():
     assert_array_equal(np.array([]), recsys.recommend('Maria Gabriela'))
 
     #with_preference
-    #recsys = ItemBasedRecommender(matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('Just My Luck', 3.20597319063), \
-    #            ('You, Me and Dupree', 3.14717875510)]), \
-    #            recsys.recommend('Leopoldo Pires'))
+    recsys = UserBasedRecommender(matrix_model, similarity, nhood_strategy, True, True)
+    assert_equals('Just My Luck', recsys.recommend('Leopoldo Pires')[0][0])
+    assert_equals('You, Me and Dupree', recsys.recommend('Leopoldo Pires')[1][0])
+
+    assert_almost_equals(2.456743361464, recsys.recommend('Leopoldo Pires')[0][1], 2)
+    assert_almost_equals(2.453379, recsys.recommend('Leopoldo Pires')[1][1], 2)
 
     similarity = UserSimilarity(boolean_matrix_model, jaccard_coefficient)
     #Empty Recommendation
@@ -392,10 +398,12 @@ def test_recommend_UserBasedRecommender():
     assert_array_equal(np.array([]), recsys.recommend('Maria Gabriela'))
 
     #with_preference
-    #recsys = ItemBasedRecommender(boolean_matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('Just My Luck', 3.20597), \
-    #            ('You, Me and Dupree', 3.1471)]), \
-    #            recsys.recommend('Leopoldo Pires'))
+    recsys = UserBasedRecommender(boolean_matrix_model, similarity, nhood_strategy, True, True)
+    assert_equals('You, Me and Dupree', recsys.recommend('Leopoldo Pires')[0][0])
+    assert_equals('Just My Luck', recsys.recommend('Leopoldo Pires')[1][0])
+
+    assert_almost_equals(1.0, recsys.recommend('Leopoldo Pires')[0][1], 2)
+    assert_almost_equals(1.0, recsys.recommend('Leopoldo Pires')[1][1], 2)
 
 
 def test_recommend_because_ItemBasedRecommender():
@@ -449,11 +457,6 @@ def test_recommend_because_ItemBasedRecommender():
     assert_array_equal(np.array([]), \
         recsys.recommended_because('Maria Gabriela', 'Just My Luck', 2))
 
-    #with_preference
-    #recsys = ItemBasedRecommender(boolean_matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('The Night Listener', 1.0), \
-    #            ('Superman Returns', 1.0)]), \
-    #            recsys.recommended_because('Leopoldo Pires', 'Just My Luck', 2))
 
 
 def test_recommend_because_UserBasedRecommender():
@@ -506,10 +509,3 @@ def test_recommend_because_UserBasedRecommender():
     recsys = UserBasedRecommender(boolean_matrix_model, similarity, nhood_strategy)
     assert_array_equal(np.array([]), \
         recsys.recommended_because('Maria Gabriela', 'Just My Luck', 2))
-
-    #with_preference
-    #recsys = ItemBasedRecommender(boolean_matrix_model, similarity, items_strategy, True, True)
-    #assert_array_equal(np.array([('The Night Listener', 1.0), \
-    #            ('Superman Returns', 1.0)]), \
-    #            recsys.recommended_because('Leopoldo Pires', 'Just My Luck', 2))
-
diff --git a/scikits/crab/recommenders/svd/classes.py b/scikits/crab/recommenders/svd/classes.py
@@ -135,8 +135,8 @@ class MatrixFactorBasedRecommender(SVDRecommender):
         n_features=2)
     >>> #Return the recommendations for the given user.
     >>> recsys.recommend('Leopoldo Pires')
-    array(['Just My Luck', 'You, Me and Dupree'], \
-          dtype='|S18')
+    ['Just My Luck', 'You, Me and Dupree']
+
 
     Notes
     -----------
@@ -383,10 +383,10 @@ def _top_matches(self, source_id, target_ids, how_many=None, **params):
                 else sorted_preferences
 
         if self.with_preference:
-            top_n_recs = np.array([(target_ids[ind], \
-                     preferences[ind]) for ind in sorted_preferences])
+            top_n_recs = [(target_ids[ind], \
+                     preferences[ind]) for ind in sorted_preferences]
         else:
-            top_n_recs = np.array([target_ids[ind]
-                 for ind in sorted_preferences])
+            top_n_recs = [target_ids[ind]
+                 for ind in sorted_preferences]
 
         return top_n_recs