Update app.py

app.py

@@ -16,6 +16,64 @@ with zipfile.ZipFile('ml-latest-small.zip') as z:
     with z.open('ml-latest-small/ratings.csv') as f:
         ratings = pd.read_csv(f)
 
+######################################
+#
+# Content-based Filtering
+#
+######################################
+
+# Define a TF-IDF Vectorizer Object. Remove all english stop words such as 'the', 'a'
+tfidf = TfidfVectorizer(stop_words='english')
+
+# Replace NaN with an empty string
+movies['genres'] = movies['genres'].fillna('')
+
+# Construct the required TF-IDF matrix by fitting and transforming the data
+tfidf_matrix = tfidf.fit_transform(movies['genres'])
+
+# Compute the cosine similarity matrix
+cosine_sim = linear_kernel(tfidf_matrix, tfidf_matrix)
+
+# Construct a reverse map of indices and movie titles
+indices = pd.Series(movies.index, index=movies['title']).drop_duplicates()
+
+# Function that takes in movie title as input and outputs most similar movies
+def get_cb_recommendations(title, cosine_sim=cosine_sim):
+    
+    # Get the index of the movie that matches the title
+    idx = indices[title]
+
+    # Get the pairwise similarity scores of all movies with that movie
+    sim_scores = list(enumerate(cosine_sim[idx]))
+
+    # Sort the movies based on the similarity scores
+    sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True)
+
+    # Get the scores of the 20 most similar movies
+    sim_scores = sim_scores[1:result_count]
+
+    # Get the movie indices
+    movie_indices = [i[0] for i in sim_scores]
+
+    # Return the top 20 most similar movies with their scores
+    recommendations = [(movies['title'].iloc[i], sim_scores[idx][1]) for idx, i in enumerate(movie_indices)]
+    return recommendations
+
+# Gradio interface
+def recommend_movies_cb(movie):
+    if not movie:
+        return "No movie selected. Please select one from the dropdown."
+        
+    recommendations = get_cb_recommendations(movie)
+    format_string = "{:>5.2f}       {:<20}"
+    return "Score     Title\n" + "\n".join([format_string.format(score, title) for title, score in recommendations])
+
+
+######################################
+#
+# Collaborative Filtering (Item-based)
+#
+######################################
 # Create a movie-user matrix
 movie_user_matrix = ratings.pivot(index='movieId', columns='userId', values='rating').fillna(0)
 
@@ -68,13 +126,11 @@ total_movies = len(movies)
 # Update the Gradio interface
 with gr.Blocks() as iface:
     with gr.Tab("Content-Based Filtering"):
-        gr.Markdown("## Recommendation - Collaborative Filtering")
-        gr.Markdown("### In construction")
-        # gr.Interface(fn=recommend_movies, 
-        #              inputs=gr.Dropdown(movie_list, label=f"Select a Movie (Total movies: {total_movies}, randomly list {input_count} for demo purpose.)"), 
-        #              outputs=[gr.Textbox(label="Recommended Movies:")],
-        #              title="Movie Recommender - Content-Based Filtering", 
-        #              description="Select a movie to get recommendations based on content filtering.")
+        gr.Interface(fn=recommend_movies_cb, 
+                     inputs=gr.Dropdown(movie_list, label=f"Select a Movie (Total movies: {total_movies}, randomly list {input_count} for demo purpose.)"), 
+                     outputs=[gr.Textbox(label="Recommended Movies:")],
+                     title="Movie Recommender - Content-Based Filtering", 
+                     description="Select a movie to get recommendations based on content filtering.")
     
     with gr.Tab("Collaborative Filtering"):
         gr.Interface(fn=recommend_movies_cf,