Delete movies from the containers after iteration

Author: anttipham

assignment3/README.md

@@ -170,18 +170,18 @@ Movie number: 260,      Predicted rating: 3.59
 Movie number: 4963,     Predicted rating: 3.57
 Movie number: 2028,     Predicted rating: 3.54
 
-## Iteration 3, alpha=0.11 ##
+## Iteration 3, alpha=0.38 ##
 Top-10 Hybrid Recommendations for group [233, 9, 242]
-Movie number: 4306,     Predicted rating: 3.37
-Movie number: 32,       Predicted rating: 3.35
-Movie number: 3897,     Predicted rating: 3.33
-Movie number: 46578,    Predicted rating: 3.3
-Movie number: 377,      Predicted rating: 3.21
-Movie number: 1270,     Predicted rating: 3.2
-Movie number: 3578,     Predicted rating: 3.14
-Movie number: 4643,     Predicted rating: 3.11
-Movie number: 733,      Predicted rating: 3.09
-Movie number: 1193,     Predicted rating: 3.01
+Movie number: 3897,     Predicted rating: 3.58
+Movie number: 4306,     Predicted rating: 3.5
+Movie number: 46578,    Predicted rating: 3.49
+Movie number: 32,       Predicted rating: 3.46
+Movie number: 1270,     Predicted rating: 3.46
+Movie number: 377,      Predicted rating: 3.32
+Movie number: 1198,     Predicted rating: 3.23
+Movie number: 3578,     Predicted rating: 3.23
+Movie number: 733,      Predicted rating: 3.2
+Movie number: 1193,     Predicted rating: 3.13
 ```
 
 ### Prepare also a short presentation (about 5 slides) to show how your method works (Score: 10%)

assignment3/assignment3.py

@@ -123,7 +123,6 @@ def main():
 
     # set alpha for first iteration to 0 so only consider average aggregation
     alphas = [0.0]
-    already_recommended = set()
     for iteration in range(ITERATIONS):
         # Hybrid aggregation
         hybrid_group_recs = weighted_combination(
@@ -135,14 +134,10 @@ def main():
         print(f"\n## Iteration {iteration+1}, alpha={alphas[iteration]:.2} ##")
         print(f"Top-{N} Hybrid Recommendations for group {GROUP}")
 
-        printed = 0
-        for movie, rating in hybrid_group_recs:
-            if printed >= N:
-                break
-            if movie not in already_recommended:
-                print(f"Movie number: {movie},\tPredicted rating: {rating:.3}")
-                printed += 1
-                already_recommended.add(movie)
+        for movie, rating in hybrid_group_recs[:N]:
+            print(f"Movie number: {movie},\tPredicted rating: {rating:.3}")
+            del avg_group_recs[movie]
+            del least_misery_group_recs[movie]
 
         # Update alpha for future iterations
         satisfactions = [