Update app.py

app.py

@@ -3,15 +3,12 @@ import pandas as pd
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
 import joblib
-import os
 
-# Load precomputed weights
 @st.cache_data
 def load_weights():
     try:
         weights_path = 'weights'
         content_tfidf_matrix = joblib.load(f'{weights_path}/content_tfidf_matrix.joblib')
-        content_similarity_matrix = joblib.load(f'{weights_path}/content_similarity_matrix.joblib')
         title_to_index = joblib.load(f'{weights_path}/content_title_to_index.joblib')
         content_vectorizer = joblib.load(f'{weights_path}/content_vectorizer.joblib')
         movies = joblib.load(f'{weights_path}/movies_data.joblib')
@@ -22,7 +19,6 @@ def load_weights():
         return {
             "movies": movies,
             "content_tfidf_matrix": content_tfidf_matrix,
-            "content_similarity_matrix": content_similarity_matrix,
             "title_to_index": title_to_index,
             "content_vectorizer": content_vectorizer,
             "user_profiles": user_profiles,
@@ -31,17 +27,18 @@ def load_weights():
             "train_ratings": train_ratings
         }
     except FileNotFoundError as e:
-        st.error(f"Weight file missing: {e.filename}")
+        st.error(f"Missing file: {e.filename}")
         st.stop()
     except Exception as e:
-        st.error(f"An unexpected error occurred while loading weights: {str(e)}")
+        st.error(f"Error loading weights: {str(e)}")
         st.stop()
 
-# Content-based recommendation
-def get_similar_movies(title, similarity_matrix, title_to_index, movies, N=5):
+# Content-based recommendation (real-time cosine similarity)
+def get_similar_movies(title, tfidf_matrix, title_to_index, movies, N=5):
     try:
         index = title_to_index[title]
-        similarity_scores = similarity_matrix[index]
+        target_vector = tfidf_matrix[index]
+        similarity_scores = cosine_similarity(target_vector, tfidf_matrix).flatten()
         similar_indices = similarity_scores.argsort()[::-1][1:N+1]
         similar_movies = movies.iloc[similar_indices][['title', 'genres']]
         similar_scores = similarity_scores[similar_indices]
@@ -60,19 +57,20 @@ def get_top_n_recommendations(user_id, user_profiles, tfidf_matrix, movie_id_to_
     top_n_indices = [idx for idx in movie_indices if movies['id'].iloc[idx] not in rated_movies][:n]
     return [(movies['title'].iloc[idx], 1 + 4 * similarities[idx]) for idx in top_n_indices]
 
-# --- Streamlit App ---
+# Streamlit App
 st.set_page_config(page_title="Movie Recommender", page_icon="🎬")
 st.title("🎬 Movie Recommender System")
 
 st.markdown("""
-This app provides two types of movie recommendations:
-- **Content-Based Filtering**: Suggests movies similar to one you like.
-- **User Profile-Based Filtering**: Personalized recommendations based on your past ratings.
+This app supports:
+- **Content-Based Recommendations**: Find similar movies based on genre.
+- **User Profile-Based Recommendations**: Personalized picks based on your ratings.
 """)
 
 # Load all weights
 weights = load_weights()
 
+# Recommendation type selector
 recommendation_type = st.sidebar.radio("Choose Recommendation Type", ["Content-Based", "User Profile-Based"])
 
 if recommendation_type == "Content-Based":
@@ -82,17 +80,17 @@ if recommendation_type == "Content-Based":
     if movie_title:
         recommendations = get_similar_movies(
             title=movie_title,
-            similarity_matrix=weights["content_similarity_matrix"],
+            tfidf_matrix=weights["content_tfidf_matrix"],
             title_to_index=weights["title_to_index"],
             movies=weights["movies"],
             N=5
         )
         if recommendations:
-            st.subheader(f"Because you liked **{movie_title}**, you might also enjoy:")
+            st.subheader(f"If you liked **{movie_title}**, you might enjoy:")
             for i, (movie, score) in enumerate(recommendations, 1):
                 st.write(f"{i}. {movie} (Similarity Score: {score:.2f})")
         else:
-            st.warning(f"Could not find recommendations for **{movie_title}**.")
+            st.warning(f"No similar movies found for '{movie_title}'.")
 
 else:
     st.header("👤 User Profile-Based Recommendations")
@@ -109,9 +107,8 @@ else:
             n=5
         )
         if recommendations:
-            st.subheader(f"Top picks for User ID {user_id}:")
-            for i, (movie, rating) in enumerate(recommendations, 1):
-                st.write(f"{i}. {movie} (Predicted Rating: {rating:.2f})")
+            st.subheader(f"Top 5 picks for User ID {user_id}:")
+            for i, (movie, pred_rating) in enumerate(recommendations, 1):
+                st.write(f"{i}. {movie} (Predicted Rating: {pred_rating:.2f})")
         else:
-            st.warning(f"No recommendations available for User ID {user_id}. Try a different ID.")
-
+            st.warning(f"User ID {user_id} not found or not enough ratings.")