diff --git a/heuristic.py b/heuristic.py
index 004fe26..0ed9802 100644
--- a/heuristic.py
+++ b/heuristic.py
@@ -19,10 +19,10 @@ def __col_fil_movies(self, user, item):
             else:
                 continue
             data = self.graph.get_edge_data(movie['label'], item['label'])
-            print(data)
+            # print(data)
             if data is None:
                 continue
-            print(edge, data)
+            # print(edge, data)
             k += data['similarity']
             sim_r += data['similarity'] * edge[2]['rating']
         return (1 / k) * sim_r if k else 0
@@ -40,10 +40,10 @@ def __col_fil_users(self, user, item):
             else:
                 continue
             data = self.graph.get_edge_data(user_1['label'], user['label'])
-            print(data)
+            # print(data)
             if data is None:
                 continue
-            print(edge, data)
+            # print(edge, data)
             k += data['similarity']
             sim_r += data['similarity'] * edge[2]['rating']
         return (1 / k) * sim_r if k else 0
diff --git a/learning.py b/learning.py
index a66b94b..31bb4b7 100644
--- a/learning.py
+++ b/learning.py
@@ -63,7 +63,7 @@ def get_x_y(self, edges):
                         self.clustering[movie['label']], self.degree_centrality[movie['label']],
                         self.closeness_centrality[movie['label']], self.betweenness_centrality[movie['label']]]
             for genre in self.embedding.transform(movie['genres']):
-                print(genre)
+                # print(genre)
                 features.append(float(genre))
             # print(features)
             x.append(features)  # [useId, movieId, genre1, genre2, ...]
diff --git a/main.py b/main.py
index ce56e38..19d828d 100644
--- a/main.py
+++ b/main.py
@@ -29,7 +29,7 @@ def get_mlps(input_1, input_2):
     # graph.init(dataset_directory='data/dataset/')
     # graph.export_gexf(directory='data/graph/')
     # exit(0)
-    graph.read_gexf('data/graph/graph.gexf')
+    graph.read_gexf('data/graph/graph0_6.gexf')
     graph_train, test_edges = graph.split_train_test(0.2)
     print(len(test_edges))
 
@@ -54,11 +54,13 @@ def get_mlps(input_1, input_2):
     hybrid_features, hybrid_target = hybrid.get_x_y(graph_train.edges(data=True))
     mlps = get_mlps(learning_features, hybrid_features)
     mlps.fit([learning_features, hybrid_features], learning_target, batch_size=1000, epochs=70)
-    loss = mlps.evaluate([test_x_l, test_x_h], test_y_h)
+    rec_m = mlps.predict([test_x_l, test_x_h])
+    # loss = mlps.evaluate([test_x_l, test_x_h], test_y_h)
 
     ##### EVALUATION #####
     Evaluation.model_evaluation(test_edges, rec_e)
     Evaluation.model_evaluation(test_edges, rec_l)
     Evaluation.model_evaluation(test_edges, rec_h)
+    Evaluation.model_evaluation(test_edges, rec_m)
 
-    print(f"Mean squared error: {loss}")
+    # print(f"Mean squared error: {loss}")