Update src/streamlit_app.py

src/streamlit_app.py

@@ -3,6 +3,10 @@ import requests
 import pandas as pd
 from together import Together
 import os
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.preprocessing import StandardScaler
+from sklearn.cluster import KMeans
+import numpy as np
 
 # =============================================================================
 # CONFIGURATION - Using Secrets Management
@@ -231,6 +235,68 @@ def extract_unique_names(content_list, field):
                     unique_names.add(cleaned_name)
     return sorted(list(unique_names))
 
+def prepare_movie_features(content_list):
+    """Prepare movie features for clustering"""
+    # Convert to DataFrame for easier processing
+    df = pd.DataFrame(content_list)
+    
+    # Create TF-IDF features from genres and description
+    tfidf = TfidfVectorizer(stop_words='english')
+    
+    # Combine genres and description for text features
+    df['text_features'] = df['listed_in'].fillna('') + ' ' + df['description'].fillna('')
+    text_features = tfidf.fit_transform(df['text_features']).toarray()
+    
+    # Prepare numerical features
+    df['release_year'] = pd.to_numeric(df['release_year'], errors='coerce').fillna(0)
+    
+    # Extract duration in minutes for movies
+    def extract_duration_minutes(duration):
+        if pd.isna(duration) or 'Season' in str(duration):
+            return 0
+        try:
+            return int(str(duration).split()[0])
+        except:
+            return 0
+    
+    df['duration_minutes'] = df['duration'].apply(extract_duration_minutes)
+    
+    # Scale numerical features
+    scaler = StandardScaler()
+    numerical_features = scaler.fit_transform(df[['release_year', 'duration_minutes']])
+    
+    # Combine all features
+    all_features = np.hstack([text_features, numerical_features])
+    
+    return all_features, df
+
+def find_similar_content(content_list, selected_content, n_clusters=20, n_recommendations=5):
+    """Find similar content using k-means clustering"""
+    # Prepare features
+    features, df = prepare_movie_features(content_list)
+    
+    # Perform k-means clustering
+    kmeans = KMeans(n_clusters=n_clusters, random_state=42)
+    cluster_labels = kmeans.fit_predict(features)
+    
+    # Find the cluster of the selected content
+    selected_idx = df[df['title'] == selected_content['title']].index[0]
+    selected_cluster = cluster_labels[selected_idx]
+    
+    # Get indices of content in the same cluster
+    cluster_indices = np.where(cluster_labels == selected_cluster)[0]
+    
+    # Calculate distances to all points in the same cluster
+    cluster_features = features[cluster_indices]
+    selected_features = features[selected_idx].reshape(1, -1)
+    distances = np.linalg.norm(cluster_features - selected_features, axis=1)
+    
+    # Get the indices of the most similar content (excluding the selected content)
+    similar_indices = cluster_indices[np.argsort(distances)][1:n_recommendations+1]
+    
+    # Return the similar content
+    return [content_list[idx] for idx in similar_indices]
+
 # =============================================================================
 # MAIN APP
 # =============================================================================
@@ -434,6 +500,21 @@ def main():
                     # Description
                     st.write(f"**📖 Description:**")
                     st.write(content.get('description', 'N/A'))
+                    
+                    # Add Find Similar button
+                    if st.button(f"🔍 Find Similar Content", key=f"similar_{i}"):
+                        with st.spinner("Finding similar content..."):
+                            similar_content = find_similar_content(all_content, content)
+                            
+                            if similar_content:
+                                st.write("**👥 Similar Content You Might Like:**")
+                                for sim_content in similar_content:
+                                    with st.container():
+                                        st.write(f"**{sim_content.get('title')}** ({sim_content.get('type')}, {sim_content.get('release_year')})")
+                                        st.write(f"*Genres:* {sim_content.get('listed_in')}")
+                                        st.write("---")
+                            else:
+                                st.info("No similar content found.")
             
             if filtered_count > 10:
                 st.info(f"Showing first 10 of {filtered_count:,} titles. Adjust filters to narrow results.")