Dataset uid_map and iid_map are the global ones

cornac/data/dataset.py

@@ -64,7 +64,7 @@ class Dataset(object):
 
     global_mean: float
         Average value over the rating observations.
-        
+
     uir_tuple: tuple
         Tuple three numpy arrays (user_indices, item_indices, rating_values).
 
@@ -103,8 +103,6 @@ def __init__(
         self.__total_items = None
         self.__user_ids = None
         self.__item_ids = None
-        self.__user_indices = None
-        self.__item_indices = None
 
         self.__user_data = None
         self.__item_data = None
@@ -138,23 +136,17 @@ def total_items(self, input_value):
 
     @property
     def user_ids(self):
-        """An iterator over the raw user ids"""
-        return self.uid_map.keys()
+        """Return the list of raw user ids"""
+        if self.__user_ids is None:
+            self.__user_ids = list(self.uid_map.keys())
+        return self.__user_ids
 
     @property
     def item_ids(self):
-        """An iterator over the raw item ids"""
-        return self.iid_map.keys()
-
-    @property
-    def user_indices(self):
-        """An iterator over the user indices"""
-        return self.uid_map.values()
-
-    @property
-    def item_indices(self):
-        """An iterator over the item indices"""
-        return self.iid_map.values()
+        """Return the list of raw item ids"""
+        if self.__item_ids is None:
+            self.__item_ids = list(self.iid_map.keys())
+        return self.__item_ids
 
     @property
     def user_data(self):
@@ -185,7 +177,7 @@ def item_data(self):
     @property
     def chrono_user_data(self):
         """Data organized by user sorted chronologically (timestamps required).
-        A dictionary where keys are users, values are tuples of three chronologically 
+        A dictionary where keys are users, values are tuples of three chronologically
         sorted lists (items, ratings, timestamps) interacted by the corresponding users.
         """
         if self.timestamps is None:
@@ -214,7 +206,7 @@ def chrono_user_data(self):
     @property
     def chrono_item_data(self):
         """Data organized by item sorted chronologically (timestamps required).
-        A dictionary where keys are items, values are tuples of three chronologically 
+        A dictionary where keys are items, values are tuples of three chronologically
         sorted lists (users, ratings, timestamps) interacted with the corresponding items.
         """
         if self.timestamps is None:
@@ -272,7 +264,7 @@ def dok_matrix(self):
         """The user-item interaction matrix in DOK sparse format"""
         if self.__dok_matrix is None:
             self.__dok_matrix = dok_matrix(
-                (self.num_users, self.num_items), dtype='float'
+                (self.num_users, self.num_items), dtype="float"
             )
             for u, i, r in zip(*self.uir_tuple):
                 self.__dok_matrix[u, i] = r
@@ -364,27 +356,29 @@ def build(
             raise ValueError("data is empty after being filtered!")
 
         uir_tuple = (
-            np.asarray(u_indices, dtype='int'),
-            np.asarray(i_indices, dtype='int'),
-            np.asarray(r_values, dtype='float'),
+            np.asarray(u_indices, dtype="int"),
+            np.asarray(i_indices, dtype="int"),
+            np.asarray(r_values, dtype="float"),
         )
 
         timestamps = (
-            np.fromiter((int(data[i][3]) for i in valid_idx), dtype='int')
+            np.fromiter((int(data[i][3]) for i in valid_idx), dtype="int")
             if fmt == "UIRT"
             else None
         )
 
-        return cls(
+        dataset = cls(
             num_users=len(global_uid_map),
             num_items=len(global_iid_map),
-            uid_map=uid_map,
-            iid_map=iid_map,
+            uid_map=global_uid_map,
+            iid_map=global_iid_map,
             uir_tuple=uir_tuple,
             timestamps=timestamps,
             seed=seed,
         )
 
+        return dataset
+
     @classmethod
     def from_uir(cls, data, seed=None):
         """Constructing Dataset from UIR (User, Item, Rating) triplet data.
@@ -407,7 +401,7 @@ def from_uir(cls, data, seed=None):
 
     @classmethod
     def from_uirt(cls, data, seed=None):
-        """Constructing Dataset from UIRT (User, Item, Rating, Timestamp) 
+        """Constructing Dataset from UIRT (User, Item, Rating, Timestamp)
         quadruplet data.
 
         Parameters
@@ -564,7 +558,7 @@ def user_iter(self, batch_size=1, shuffle=False):
         -------
         iterator : batch of user indices (array of 'int')
         """
-        user_indices = np.fromiter(self.user_indices, dtype='int')
+        user_indices = np.fromiter(self.user_indices, dtype="int")
         for batch_ids in self.idx_iter(len(user_indices), batch_size, shuffle):
             yield user_indices[batch_ids]
 
@@ -582,17 +576,17 @@ def item_iter(self, batch_size=1, shuffle=False):
         -------
         iterator : batch of item indices (array of 'int')
         """
-        item_indices = np.fromiter(self.item_indices, 'int')
+        item_indices = np.fromiter(self.item_indices, "int")
         for batch_ids in self.idx_iter(len(item_indices), batch_size, shuffle):
             yield item_indices[batch_ids]
 
     def is_unk_user(self, user_idx):
         """Return whether or not a user is unknown given the user index"""
-        return user_idx >= self.num_users
+        return user_idx >= self.num_users or user_idx < 0
 
     def is_unk_item(self, item_idx):
         """Return whether or not an item is unknown given the item index"""
-        return item_idx >= self.num_items
+        return item_idx >= self.num_items or item_idx < 0
 
     def add_modalities(self, **kwargs):
         self.user_feature = kwargs.get("user_feature", None)
@@ -605,4 +599,3 @@ def add_modalities(self, **kwargs):
         self.item_graph = kwargs.get("item_graph", None)
         self.sentiment = kwargs.get("sentiment", None)
         self.review_text = kwargs.get("review_text", None)
-

cornac/eval_methods/base_method.py

@@ -85,6 +85,7 @@ def rating_eval(model, metrics, test_set, user_based=False, verbose=False):
     gt_mat = test_set.csr_matrix
     pd_mat = csr_matrix((r_preds, (u_indices, i_indices)), shape=gt_mat.shape)
 
+    test_user_indices = set(u_indices)
     for mt in metrics:
         if user_based:  # averaging over users
             user_results.append(
@@ -93,7 +94,7 @@ def rating_eval(model, metrics, test_set, user_based=False, verbose=False):
                         gt_ratings=gt_mat.getrow(user_idx).data,
                         pd_ratings=pd_mat.getrow(user_idx).data,
                     ).item()
-                    for user_idx in test_set.user_indices
+                    for user_idx in test_user_indices
                 }
             )
             avg_results.append(sum(user_results[-1].values()) / len(user_results[-1]))
@@ -170,8 +171,9 @@ def pos_items(csr_row):
             if rating >= rating_threshold
         ]
 
+    test_user_indices = set(test_set.uir_tuple[0])
     for user_idx in tqdm(
-        test_set.user_indices, desc="Ranking", disable=not verbose, miniters=100
+        test_user_indices, desc="Ranking", disable=not verbose, miniters=100
     ):
         test_pos_items = pos_items(gt_mat.getrow(user_idx))
         if len(test_pos_items) == 0:
@@ -196,7 +198,7 @@ def pos_items(csr_row):
         if exclude_unknowns:
             u_gt_pos_mask = u_gt_pos_mask[: train_set.num_items]
             u_gt_neg_mask = u_gt_neg_mask[: train_set.num_items]
-            
+
         item_indices = np.nonzero(u_gt_pos_mask + u_gt_neg_mask)[0]
         u_gt_pos_items = np.nonzero(u_gt_pos_mask)[0]
         u_gt_neg_items = np.nonzero(u_gt_neg_mask)[0]

cornac/eval_methods/propensity_stratified_evaluation.py

@@ -25,38 +25,38 @@ def ranking_eval(
     props=None,
 ):
     """Evaluate model on provided ranking metrics.
-    
+
     Parameters
     ----------
     model: :obj:`cornac.models.Recommender`, required
         Recommender model to be evaluated.
-        
+
     metrics: :obj:`iterable`, required
         List of rating metrics :obj:`cornac.metrics.RankingMetric`.
-    
+
     train_set: :obj:`cornac.data.Dataset`, required
         Dataset to be used for model training. This will be used to exclude
         observations already appeared during training.
-    
+
     test_set: :obj:`cornac.data.Dataset`, required
         Dataset to be used for evaluation.
-    
+
     val_set: :obj:`cornac.data.Dataset`, optional, default: None
         Dataset to be used for model selection. This will be used to exclude
         observations already appeared during validation.
-        
+
     rating_threshold: float, optional, default: 1.0
         The threshold to convert ratings into positive or negative feedback.
-        
+
     exclude_unknowns: bool, optional, default: True
         Ignore unknown users and items during evaluation.
-        
+
     verbose: bool, optional, default: False
         Output evaluation progress.
-        
+
     props: dictionary, optional, default: None
         items propensity scores
-        
+
     Returns
     -------
     res: (List, List)
@@ -82,12 +82,13 @@ def pos_items(csr_row):
             if rating >= rating_threshold
         ]
 
-    for user_idx in tqdm.tqdm(test_set.user_indices, disable=not verbose, miniters=100):
+    test_user_indices = set(test_set.uir_tuple[0])
+    for user_idx in tqdm.tqdm(test_user_indices, disable=not verbose, miniters=100):
         test_pos_items = pos_items(gt_mat.getrow(user_idx))
         if len(test_pos_items) == 0:
             continue
 
-        u_gt_pos = np.zeros(test_set.num_items, dtype='float')
+        u_gt_pos = np.zeros(test_set.num_items, dtype="float")
         u_gt_pos[test_pos_items] = 1
 
         val_pos_items = [] if val_mat is None else pos_items(val_mat.getrow(user_idx))
@@ -97,7 +98,7 @@ def pos_items(csr_row):
             else pos_items(train_mat.getrow(user_idx))
         )
 
-        u_gt_neg = np.ones(test_set.num_items, dtype='int')
+        u_gt_neg = np.ones(test_set.num_items, dtype="int")
         u_gt_neg[test_pos_items + val_pos_items + train_pos_items] = 0
 
         item_indices = None if exclude_unknowns else np.arange(test_set.num_items)
@@ -256,7 +257,7 @@ def _estimate_propensities(self):
             item_freq[i] += 1
 
         # fit the exponential param
-        data = np.array([e for e in item_freq.values()], dtype='float')
+        data = np.array([e for e in item_freq.values()], dtype="float")
         results = powerlaw.Fit(data, discrete=True, fit_method="Likelihood")
         alpha = results.power_law.alpha
         fmin = results.power_law.xmin
@@ -276,9 +277,7 @@ def _build_stratified_dataset(self, test_data):
         self.stratified_sets = {}
 
         # match the corresponding propensity score for each feedback
-        test_props = np.array(
-            [self.props[i] for u, i, r in test_data], dtype='float'
-        )
+        test_props = np.array([self.props[i] for u, i, r in test_data], dtype="float")
 
         # stratify
         minp = min(test_props) - 0.01 * min(test_props)
@@ -338,11 +337,11 @@ def evaluate(self, model, metrics, user_based, show_validation=True):
         metrics: :obj:`iterable`
             List of metrics.
 
-        user_based: bool, required 
-            Evaluation strategy for the rating metrics. Whether results 
+        user_based: bool, required
+            Evaluation strategy for the rating metrics. Whether results
             are averaging based on number of users or number of ratings.
 
-        show_validation: bool, optional, default: True 
+        show_validation: bool, optional, default: True
             Whether to show the results on validation set (if exists).
 
         Returns