Update app.py

app.py

@@ -15,7 +15,7 @@ def load_data():
     movies = pd.read_csv(zip_file.open('ml-latest-small/movies.csv'))
     
     data = pd.merge(ratings, movies, on='movieId')
-    return data
+    return data, movies
 
 # Function to build user-item matrix and similarity matrix
 def build_matrices(data):
@@ -25,29 +25,42 @@ def build_matrices(data):
     return user_item_matrix, user_similarity_df
 
 # Function to get recommendations
-def get_recommendations(user_id, user_item_matrix, user_similarity_df, num_recommendations=5):
-    user_sim_scores = user_similarity_df[user_id]
-    similar_users = user_sim_scores.sort_values(ascending=False)
-    similar_users_ratings = user_item_matrix.loc[similar_users.index]
-    weighted_ratings = similar_users_ratings.T.dot(similar_users)
-    weighted_ratings = weighted_ratings / similar_users.sum()
+def get_recommendations(selected_movies, user_item_matrix, num_recommendations=5):
+    # Calculate the mean ratings for the selected movies
+    movie_ratings = user_item_matrix[selected_movies].mean(axis=1)
+    
+    # Find the most similar users based on the selected movies
+    similar_users = movie_ratings.sort_values(ascending=False).index
+    
+    # Get the movies rated by similar users
+    similar_users_ratings = user_item_matrix.loc[similar_users]
+    
+    # Calculate the weighted sum of ratings
+    weighted_ratings = similar_users_ratings.T.dot(movie_ratings)
+    
+    # Normalize the ratings
+    weighted_ratings = weighted_ratings / movie_ratings.sum()
+    
+    # Get the top N recommendations
     recommendations = weighted_ratings.sort_values(ascending=False).head(num_recommendations)
+    
     return recommendations
 
 # Load data and build matrices
-data = load_data()
+data, movies = load_data()
 user_item_matrix, user_similarity_df = build_matrices(data)
 
 # Streamlit app
 st.title("Collaborative Filtering Recommendation System")
 
-user_id = st.number_input("Enter User ID", min_value=1, max_value=user_similarity_df.index.max(), step=1)
+# Let user select favorite movies
+selected_movies = st.multiselect("Select your favorite movies", movies['title'].unique())
 
 if st.button("Get Recommendations"):
-    if user_id in user_similarity_df.index:
-        recommendations = get_recommendations(user_id, user_item_matrix, user_similarity_df)
+    if selected_movies:
+        recommendations = get_recommendations(selected_movies, user_item_matrix)
         st.write("Top Recommendations:")
         for movie, score in recommendations.items():
             st.write(f"{movie}: {score:.2f}")
     else:
-        st.write("User ID not found.")
+        st.write("Please select at least one movie.")