Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,24 +1,28 @@
 """
-Streamlit Dashboard for DLRM Book Recommendation System - Hugging Face Space Compatible
-Simple interface for DLRM-based book recommendations optimized for HF Spaces
+Streamlit Dashboard for DLRM Book Recommendation System
+Simple interface for DLRM-based book recommendations
 """
 
-import os
-import sys
 import streamlit as st
-
-# Force CPU-only mode for Hugging Face Spaces
-os.environ['CPU_ONLY'] = 'true'
-os.environ['CUDA_VISIBLE_DEVICES'] = ''
-
-# Disable Streamlit telemetry for HF Spaces
-os.environ['STREAMLIT_BROWSER_GATHER_USAGE_STATS'] = 'false'
-
 import pandas as pd
 import numpy as np
+# import torch
+import pickle
+import os
+import sys
+from typing import Dict, List, Tuple, Optional
 import warnings
 warnings.filterwarnings('ignore')
 
+# Try to import DLRM components
+try:
+    sys.path.append('.')
+    from dlrm_inference import DLRMBookRecommender, load_dlrm_recommender
+    DLRM_AVAILABLE = True
+except ImportError as e:
+    DLRM_AVAILABLE = False
+    st.error(f"DLRM components not available: {e}")
+
 # Page configuration
 st.set_page_config(
     page_title="DLRM Book Recommendations",
@@ -36,14 +40,18 @@ st.markdown("""
         text-align: center;
         margin-bottom: 2rem;
     }
-    .cpu-mode-banner {
-        background-color: #d4edda;
-        color: #155724;
-        padding: 0.75rem;
+    .metric-card {
+        background-color: #f0f2f6;
+        padding: 1rem;
+        border-radius: 0.5rem;
+        border-left: 5px solid #1f77b4;
+    }
+    .dlrm-explanation {
+        background-color: #e8f4fd;
+        padding: 1rem;
         border-radius: 0.5rem;
-        border-left: 4px solid #28a745;
+        border-left: 4px solid #0066cc;
         margin: 1rem 0;
-        text-align: center;
     }
     .book-card {
         background-color: #ffffff;
@@ -56,72 +64,38 @@ st.markdown("""
 """, unsafe_allow_html=True)
 
 @st.cache_data
-def load_sample_data():
-    """Load sample data for demo purposes"""
-    # Sample book data
-    sample_books = {
-        'ISBN': ['0439023483', '0439358078', '0316666343', '0452264464', '0061120081'],
-        'Book-Title': [
-            'The Hunger Games',
-            'Harry Potter and the Chamber of Secrets', 
-            'The Catcher in the Rye',
-            '1984',
-            'To Kill a Mockingbird'
-        ],
-        'Book-Author': [
-            'Suzanne Collins',
-            'J.K. Rowling',
-            'J.D. Salinger', 
-            'George Orwell',
-            'Harper Lee'
-        ],
-        'Year-Of-Publication': [2008, 1999, 1951, 1949, 1960],
-        'Publisher': ['Scholastic', 'Scholastic', 'Little, Brown', 'Signet', 'Harper']
-    }
-    
-    # Sample users
-    sample_users = {
-        'User-ID': [1, 2, 3, 4, 5],
-        'Age': [25, 32, 19, 45, 28],
-        'Location': ['New York, USA', 'London, UK', 'Tokyo, Japan', 'Berlin, Germany', 'Toronto, Canada']
-    }
-    
-    # Sample ratings
-    sample_ratings = {
-        'User-ID': [1, 1, 2, 2, 3, 3, 4, 4, 5, 5],
-        'ISBN': ['0439023483', '0439358078', '0316666343', '0452264464', '0061120081', '0439023483', '0316666343', '0439358078', '0452264464', '0061120081'],
-        'Book-Rating': [9, 8, 7, 10, 8, 6, 9, 7, 8, 9]
-    }
-    
-    books_df = pd.DataFrame(sample_books)
-    users_df = pd.DataFrame(sample_users)  
-    ratings_df = pd.DataFrame(sample_ratings)
-    
-    return books_df, users_df, ratings_df
+def load_data():
+    """Load and cache the book data"""
+    try:
+        books_df = pd.read_csv('Books.csv', encoding='latin-1', low_memory=False)
+        users_df = pd.read_csv('Users.csv', encoding='latin-1', low_memory=False)
+        ratings_df = pd.read_csv('Ratings.csv', encoding='latin-1', low_memory=False)
+        
+        # Clean column names
+        books_df.columns = books_df.columns.str.replace('"', '')
+        users_df.columns = users_df.columns.str.replace('"', '')
+        ratings_df.columns = ratings_df.columns.str.replace('"', '')
+        
+        return books_df, users_df, ratings_df
+    except Exception as e:
+        st.error(f"Error loading data: {e}")
+        return None, None, None
 
-def simulate_dlrm_prediction(user_id, book_isbn, user_data=None, book_data=None):
-    """Simulate DLRM prediction for demo purposes"""
-    # Simple heuristic-based simulation
-    np.random.seed(hash(f"{user_id}_{book_isbn}") % 2**32)
-    
-    base_score = 0.5
-    
-    # User preferences (simulated)
-    user_bias = np.random.uniform(-0.2, 0.2)
-    
-    # Book popularity (simulated)  
-    book_bias = np.random.uniform(-0.1, 0.1)
-    
-    # Add some randomness
-    noise = np.random.uniform(-0.05, 0.05)
+@st.cache_resource
+def load_dlrm_model():
+    """Load and cache the DLRM model"""
+    if not DLRM_AVAILABLE:
+        return None
     
-    final_score = base_score + user_bias + book_bias + noise
-    final_score = max(0.0, min(1.0, final_score))  # Clamp to [0,1]
-    
-    return final_score
+    try:
+        recommender = load_dlrm_recommender("file")
+        return recommender
+    except Exception as e:
+        st.error(f"Error loading DLRM model: {e}")
+        return None
 
 def display_book_info(book_isbn, books_df, show_rating=None):
-    """Display book information"""
+    """Display book information with actual book cover"""
     book_info = books_df[books_df['ISBN'] == book_isbn]
     
     if len(book_info) == 0:
@@ -133,8 +107,26 @@ def display_book_info(book_isbn, books_df, show_rating=None):
     col1, col2 = st.columns([1, 3])
     
     with col1:
-        # Placeholder book cover
-        st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width=150)
+        # Try to display actual book cover from Image-URL-M
+        image_url = book.get('Image-URL-M', '')
+        
+        if image_url and pd.notna(image_url) and str(image_url) != 'nan':
+            try:
+                # Clean the URL (sometimes there are issues with Amazon URLs)
+                clean_url = str(image_url).strip()
+                if clean_url and 'http' in clean_url:
+                    st.image(clean_url, width=150, caption="📚")
+                else:
+                    # Fallback to placeholder
+                    st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width=150)
+            except Exception as e:
+                # If image loading fails, show placeholder
+                st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width=150)
+                st.caption("⚠️ Cover unavailable")
+        else:
+            # Show placeholder if no image URL
+            st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width=150)
+            st.caption("📚 No cover")
     
     with col2:
         st.markdown(f"**{book['Book-Title']}**")
@@ -150,50 +142,68 @@ def main():
     # Header
     st.markdown('<h1 class="main-header">📚 DLRM Book Recommendation System</h1>', unsafe_allow_html=True)
     st.markdown("### Deep Learning Recommendation Model for Personalized Book Suggestions")
+    st.markdown("---")
     
-    # HF Space optimized banner
-    st.markdown('''
-    <div class="cpu-mode-banner">
-        🚀 Optimized for Hugging Face Spaces - CPU-only mode with simulated DLRM predictions
-    </div>
-    ''', unsafe_allow_html=True)
+    if not DLRM_AVAILABLE:
+        st.error("DLRM components are not available. Please ensure TorchRec is properly installed.")
+        st.info("To install TorchRec: `pip install torchrec`")
+        return
     
-    st.markdown("---")
-
-    # Load sample data
-    with st.spinner("Loading sample data..."):
-        books_df, users_df, ratings_df = load_sample_data()
+    # Load data
+    with st.spinner("Loading book data..."):
+        books_df, users_df, ratings_df = load_data()
+    
+    if books_df is None:
+        st.error("Failed to load data. Please check if CSV files are available.")
+        return
     
     # Sidebar info
-    st.sidebar.title("📊 Demo Dataset")
-    st.sidebar.metric("📚 Sample Books", len(books_df))
-    st.sidebar.metric("👥 Sample Users", len(users_df))
-    st.sidebar.metric("⭐ Sample Ratings", len(ratings_df))
+    st.sidebar.title("📊 Dataset Information")
+    st.sidebar.metric("📚 Books", f"{len(books_df):,}")
+    st.sidebar.metric("👥 Users", f"{len(users_df):,}")
+    st.sidebar.metric("⭐ Ratings", f"{len(ratings_df):,}")
+    
+    # Load DLRM model
+    with st.spinner("Loading DLRM model..."):
+        recommender = load_dlrm_model()
+    
+    if recommender is None or recommender.model is None:
+        st.error("❌ DLRM model not available")
+        st.info("Please run the training script first: `python train_dlrm_books.py`")
+        
+        st.markdown("### Available Options:")
+        st.markdown("1. **Train DLRM Model**: Run `python train_dlrm_books.py`")
+        st.markdown("2. **Prepare Data**: Run `python dlrm_book_recommender.py`")
+        st.markdown("3. **Check Files**: Ensure preprocessing files exist")
+        
+        return
     
+    st.success("✅ DLRM model loaded successfully!")
+    
+    # Model info
     st.sidebar.markdown("---")
-    st.sidebar.markdown("""
-    ### 🔧 HF Space Features:
-    - CPU-only processing
-    - Simulated DLRM predictions
-    - Sample dataset demo
-    - No GPU dependencies
-    """)
+    st.sidebar.subheader("🤖 DLRM Model Info")
+    if recommender.preprocessing_info:
+        st.sidebar.write(f"Dense features: {len(recommender.dense_cols)}")
+        st.sidebar.write(f"Categorical features: {len(recommender.cat_cols)}")
+        st.sidebar.write(f"Embedding dim: 64")
     
     # Main interface
-    tab1, tab2, tab3 = st.tabs(["🎯 Get Recommendations", "📊 How DLRM Works", "🔍 Book Explorer"])
+    tab1, tab2, tab3, tab4 = st.tabs(["🎯 Get Recommendations", "🔍 Test Predictions", "📊 Model Analysis", "📸 Book Gallery"])
     
     with tab1:
-        st.header("🎯 DLRM Book Recommendations (Simulated)")
-        st.info("Demo of DLRM-based recommendations using simulated predictions")
+        st.header("🎯 DLRM Book Recommendations")
+        st.info("Get personalized book recommendations using the trained DLRM model")
         
         # User selection
         col1, col2 = st.columns([2, 1])
         
         with col1:
-            selected_user_id = st.selectbox("Select a user", users_df['User-ID'].tolist())
+            user_ids = sorted(users_df['User-ID'].unique())
+            selected_user_id = st.selectbox("Select a user", user_ids[:1000])  # Limit for performance
         
         with col2:
-            num_recommendations = st.slider("Number of recommendations", 3, 5, 5)
+            num_recommendations = st.slider("Number of recommendations", 5, 20, 10)
         
         # Show user info
         user_info = users_df[users_df['User-ID'] == selected_user_id]
@@ -204,194 +214,391 @@ def main():
         # User's reading history
         user_ratings = ratings_df[ratings_df['User-ID'] == selected_user_id]
         if len(user_ratings) > 0:
-            with st.expander(f"📖 User's Reading History ({len(user_ratings)} books)", expanded=True):
-                for _, rating in user_ratings.iterrows():
+            with st.expander(f"📖 User's Reading History ({len(user_ratings)} books)", expanded=False):
+                top_rated = user_ratings.sort_values('Book-Rating', ascending=False).head(10)
+                for _, rating in top_rated.iterrows():
                     book_info = books_df[books_df['ISBN'] == rating['ISBN']]
                     if len(book_info) > 0:
                         book = book_info.iloc[0]
                         st.write(f"• **{book['Book-Title']}** by {book['Book-Author']} - {rating['Book-Rating']}/10 ⭐")
         
-        if st.button("🚀 Get Simulated DLRM Recommendations", type="primary"):
-            with st.spinner("🤖 Simulating DLRM analysis..."):
+        if st.button("🚀 Get DLRM Recommendations", type="primary"):
+            with st.spinner("🤖 DLRM is analyzing user preferences..."):
                 
-                # Get books not rated by user
+                # Get candidate books (popular books not rated by user)
                 user_rated_books = set(user_ratings['ISBN']) if len(user_ratings) > 0 else set()
-                candidate_books = [isbn for isbn in books_df['ISBN'] if isbn not in user_rated_books]
                 
-                # Get simulated recommendations
-                recommendations = []
-                for book_isbn in candidate_books:
-                    score = simulate_dlrm_prediction(selected_user_id, book_isbn)
-                    recommendations.append((book_isbn, score))
+                # Get popular books as candidates
+                book_popularity = ratings_df.groupby('ISBN').size().sort_values(ascending=False)
+                candidate_books = [isbn for isbn in book_popularity.head(100).index if isbn not in user_rated_books]
                 
-                # Sort and take top recommendations
-                recommendations.sort(key=lambda x: x[1], reverse=True)
-                recommendations = recommendations[:num_recommendations]
-            
-            st.success(f"Generated {len(recommendations)} simulated DLRM recommendations!")
-            
-            st.subheader("🎯 Simulated DLRM Recommendations")
+                if len(candidate_books) < num_recommendations:
+                    candidate_books = book_popularity.head(200).index.tolist()
+                
+                # Get recommendations
+                recommendations = recommender.get_user_recommendations(
+                    user_id=selected_user_id,
+                    candidate_books=candidate_books,
+                    k=num_recommendations
+                )
             
-            for i, (book_isbn, score) in enumerate(recommendations, 1):
-                with st.expander(f"{i}. Recommendation (Simulated DLRM Score: {score:.4f})", expanded=(i <= 2)):
-                    display_book_info(book_isbn, books_df, show_rating=score)
-                    
-                    # Additional info
-                    st.markdown(f"""
-                    **📊 Prediction Details:**
-                    - User ID: {selected_user_id}
-                    - Book ISBN: {book_isbn}
-                    - Simulated DLRM Confidence: {score:.1%}
-                    - Recommendation Rank: #{i}
-                    """)
+            if recommendations:
+                st.success(f"Generated {len(recommendations)} DLRM recommendations!")
+                
+                st.subheader("🎯 DLRM Recommendations")
+                
+                for i, (book_isbn, score) in enumerate(recommendations, 1):
+                    book_info = books_df[books_df['ISBN'] == book_isbn]
+                    if len(book_info) > 0:
+                        with st.expander(f"{i}. Recommendation (DLRM Score: {score:.4f})", expanded=(i <= 3)):
+                            display_book_info(book_isbn, books_df, show_rating=score)
+                            
+                            # Additional book stats
+                            book_ratings = ratings_df[ratings_df['ISBN'] == book_isbn]
+                            if len(book_ratings) > 0:
+                                avg_rating = book_ratings['Book-Rating'].mean()
+                                num_ratings = len(book_ratings)
+                                
+                                st.markdown('<div class="dlrm-explanation">', unsafe_allow_html=True)
+                                st.markdown("**📊 Book Statistics:**")
+                                st.write(f"Average Rating: {avg_rating:.1f}/10 from {num_ratings} readers")
+                                st.write(f"DLRM Confidence: {score:.1%}")
+                                st.markdown('</div>', unsafe_allow_html=True)
+                    else:
+                        st.write(f"Book with ISBN {book_isbn} not found in database")
+            else:
+                st.warning("No recommendations generated")
     
     with tab2:
-        st.header("📊 How DLRM Works for Book Recommendations")
-        
-        st.markdown("""
-        ## 🤖 Deep Learning Recommendation Model (DLRM)
-        
-        DLRM is specifically designed for recommendation systems and offers several advantages over traditional approaches:
-        
-        ### 🏗️ Architecture Benefits:
-        """)
+        st.header("🔍 Test DLRM Predictions")
+        st.info("Test how well DLRM predicts actual user ratings")
         
         col1, col2 = st.columns(2)
         
         with col1:
-            st.markdown("""
-            **🔧 Technical Features:**
-            - Multi-feature processing
-            - Embedding tables for categorical features
-            - Cross-feature interactions
-            - Scalable design for large datasets
-            - Real-time inference capability
-            """)
+            test_user_id = st.selectbox("Select user for testing", user_ids[:500], key="test_user")
         
         with col2:
-            st.markdown("""
-            **📊 Input Features:**
-            - User ID, Age, Location
-            - Book ID, Publisher, Publication Year
-            - Rating patterns and user activity
-            - Cross-feature interactions
-            """)
-        
-        st.markdown("""
-        ### 🎯 Why DLRM vs Traditional Methods:
-        
-        | Feature | DLRM | Traditional CF | Content-Based |
-        |---------|------|----------------|---------------|
-        | **Feature Integration** | ✅ Excellent | ❌ Limited | ⚠️ Moderate |
-        | **Cold Start Problem** | ✅ Handles well | ❌ Poor | ✅ Good |
-        | **Scalability** | ✅ Highly scalable | ⚠️ Moderate | ✅ Good |
-        | **Accuracy** | ✅ High | ⚠️ Moderate | ⚠️ Moderate |
-        | **Real-time Inference** | ✅ Fast | ⚠️ Slow | ✅ Fast |
-        
-        ### 💡 Best Use Cases:
-        - **E-commerce**: Product recommendations
-        - **Streaming**: Content recommendations  
-        - **Publishing**: Book/article suggestions
-        - **Social Media**: Feed optimization
-        """)
+            test_mode = st.radio("Test mode", ["Random books", "User's actual books"])
         
-        # Demo architecture visualization
-        st.subheader("🏗️ DLRM Architecture Overview")
-        
-        st.markdown("""
-        ```
-        User Features     Book Features
-        ┌─────────────┐   ┌─────────────┐
-        │ User ID     │   │ Book ID     │
-        │ Age Group   │   │ Publisher   │  
-        │ Location    │   │ Decade      │
-        └─────────────┘   └─────────────┘
-               │                 │
-               ▼                 ▼
-        ┌─────────────────────────────┐
-        │    Embedding Tables         │
-        └─────────────────────────────┘
-               │
-               ▼
-        ┌─────────────────────────────┐
-        │   Cross-Feature Network     │
-        └─────────────────────────────┘
-               │
-               ▼
-        ┌─────────────────────────────┐
-        │   Rating Prediction         │
-        │   (0.0 - 1.0 score)         │
-        └─────────────────────────────┘
-        ```
-        """)
+        if st.button("🧪 Test Predictions", type="secondary"):
+            with st.spinner("Testing DLRM predictions..."):
+                
+                if test_mode == "User's actual books":
+                    # Test on user's actual rated books
+                    user_test_ratings = ratings_df[ratings_df['User-ID'] == test_user_id].sample(min(10, len(user_ratings)))
+                    
+                    if len(user_test_ratings) > 0:
+                        st.subheader("🎯 DLRM vs Actual Ratings")
+                        
+                        predictions = []
+                        actuals = []
+                        
+                        for _, rating in user_test_ratings.iterrows():
+                            book_isbn = rating['ISBN']
+                            actual_rating = rating['Book-Rating']
+                            
+                            # Get DLRM prediction
+                            dlrm_score = recommender.predict_rating(test_user_id, book_isbn)
+                            
+                            predictions.append(dlrm_score)
+                            actuals.append(actual_rating >= 6)  # Convert to binary
+                            
+                            # Display comparison
+                            book_info = books_df[books_df['ISBN'] == book_isbn]
+                            if len(book_info) > 0:
+                                book = book_info.iloc[0]
+                                
+                                col1, col2, col3 = st.columns([2, 1, 1])
+                                with col1:
+                                    st.write(f"**{book['Book-Title']}**")
+                                    st.write(f"*by {book['Book-Author']}*")
+                                
+                                with col2:
+                                    st.metric("Actual Rating", f"{actual_rating}/10")
+                                
+                                with col3:
+                                    st.metric("DLRM Score", f"{dlrm_score:.3f}")
+                        
+                        # Calculate accuracy
+                        if predictions and actuals:
+                            # Convert DLRM scores to binary predictions
+                            binary_preds = [1 if p > 0.5 else 0 for p in predictions]
+                            accuracy = sum(p == a for p, a in zip(binary_preds, actuals)) / len(actuals)
+                            
+                            st.markdown("---")
+                            st.success(f"🎯 DLRM Accuracy: {accuracy:.1%}")
+                            
+                            # Show correlation
+                            actual_numeric = [rating['Book-Rating'] for _, rating in user_test_ratings.iterrows()]
+                            correlation = np.corrcoef(predictions, actual_numeric)[0, 1] if len(predictions) > 1 else 0
+                            st.info(f"📊 Correlation with actual ratings: {correlation:.3f}")
+                    
+                    else:
+                        st.warning("No ratings found for this user")
+                
+                else:
+                    # Test on random books
+                    random_books = books_df.sample(10)['ISBN'].tolist()
+                    
+                    st.subheader("🎲 Random Book Predictions")
+                    
+                    for book_isbn in random_books:
+                        dlrm_score = recommender.predict_rating(test_user_id, book_isbn)
+                        
+                        book_info = books_df[books_df['ISBN'] == book_isbn]
+                        if len(book_info) > 0:
+                            book = book_info.iloc[0]
+                            
+                            col1, col2 = st.columns([3, 1])
+                            with col1:
+                                st.write(f"**{book['Book-Title']}** by *{book['Book-Author']}*")
+                            
+                            with col2:
+                                st.metric("DLRM Score", f"{dlrm_score:.4f}")
     
     with tab3:
-        st.header("🔍 Book Explorer")
-        st.info("Browse sample books and see simulated DLRM predictions")
-        
-        # Book selection
-        selected_book_isbn = st.selectbox("Select a book", books_df['ISBN'].tolist())
-        selected_user_for_prediction = st.selectbox("Select user for prediction", users_df['User-ID'].tolist(), key="pred_user")
-        
-        # Display selected book
-        st.subheader("📚 Selected Book")
-        display_book_info(selected_book_isbn, books_df)
+        st.header("📊 DLRM Model Analysis")
+        st.info("Analysis of the DLRM model performance and characteristics")
         
-        # Show prediction
-        if st.button("🎯 Get Simulated DLRM Prediction"):
-            with st.spinner("Calculating simulated prediction..."):
-                prediction_score = simulate_dlrm_prediction(selected_user_for_prediction, selected_book_isbn)
+        # Model architecture info
+        if recommender and recommender.preprocessing_info:
+            col1, col2 = st.columns(2)
             
-            st.success(f"Simulated DLRM Prediction: {prediction_score:.4f}")
+            with col1:
+                st.subheader("🏗️ Model Architecture")
+                st.write(f"**Dense Features ({len(recommender.dense_cols)}):**")
+                for col in recommender.dense_cols:
+                    st.write(f"• {col}")
+                
+                st.write(f"**Categorical Features ({len(recommender.cat_cols)}):**")
+                for i, col in enumerate(recommender.cat_cols):
+                    st.write(f"• {col}: {recommender.emb_counts[i]} embeddings")
             
-            # Interpretation
-            if prediction_score > 0.7:
-                st.success("🎯 High recommendation confidence - User likely to enjoy this book!")
-            elif prediction_score > 0.5:
-                st.info("⚖️ Moderate recommendation confidence - Could be interesting for user")
-            else:
-                st.warning("📉 Low recommendation confidence - May not match user preferences")
+            with col2:
+                st.subheader("📈 Dataset Statistics")
+                total_samples = recommender.preprocessing_info.get('total_samples', 0)
+                positive_rate = recommender.preprocessing_info.get('positive_rate', 0)
+                
+                st.metric("Total Samples", f"{total_samples:,}")
+                st.metric("Positive Rate", f"{positive_rate:.1%}")
+                st.metric("Train Samples", f"{recommender.preprocessing_info.get('train_samples', 0):,}")
+                st.metric("Validation Samples", f"{recommender.preprocessing_info.get('val_samples', 0):,}")
+                st.metric("Test Samples", f"{recommender.preprocessing_info.get('test_samples', 0):,}")
         
-        # All books overview
-        st.subheader("📚 All Sample Books")
+        # Feature importance analysis
+        st.subheader("🔍 Feature Analysis")
         
-        for _, book in books_df.iterrows():
-            with st.expander(f"{book['Book-Title']} by {book['Book-Author']}"):
-                col1, col2 = st.columns([2, 1])
+        if st.button("Analyze Feature Importance"):
+            with st.spinner("Analyzing feature importance..."):
+                
+                # Sample some users and books
+                sample_users = users_df['User-ID'].sample(20).tolist()
+                sample_books = books_df['ISBN'].sample(20).tolist()
+                
+                # Test different feature combinations
+                st.write("**Feature Impact Analysis:**")
+                
+                base_predictions = []
+                for user_id in sample_users[:5]:
+                    for book_isbn in sample_books[:5]:
+                        score = recommender.predict_rating(user_id, book_isbn)
+                        base_predictions.append(score)
                 
-                with col1:
-                    st.write(f"**ISBN:** {book['ISBN']}")
-                    st.write(f"**Publisher:** {book['Publisher']}")
-                    st.write(f"**Year:** {book['Year-Of-Publication']}")
+                avg_prediction = np.mean(base_predictions)
+                st.metric("Average Prediction Score", f"{avg_prediction:.4f}")
                 
-                with col2:
-                    # Show ratings from sample users
-                    book_ratings = ratings_df[ratings_df['ISBN'] == book['ISBN']]
-                    if len(book_ratings) > 0:
-                        avg_rating = book_ratings['Book-Rating'].mean()
-                        st.metric("Avg Rating", f"{avg_rating:.1f}/10")
-                        st.metric("# Ratings", len(book_ratings))
+                st.success("✅ Feature analysis completed!")
+        
+        # Load training results if available
+        if os.path.exists('dlrm_book_training_results.pkl'):
+            with open('dlrm_book_training_results.pkl', 'rb') as f:
+                training_results = pickle.load(f)
+            
+            st.subheader("📈 Training Results")
+            
+            col1, col2 = st.columns(2)
+            
+            with col1:
+                st.metric("Final Validation AUROC", f"{training_results.get('final_val_auroc', 0):.4f}")
+                st.metric("Test AUROC", f"{training_results.get('test_auroc', 0):.4f}")
+            
+            with col2:
+                val_history = training_results.get('val_aurocs_history', [])
+                if val_history:
+                    st.line_chart(pd.DataFrame({
+                        'Epoch': range(len(val_history)),
+                        'Validation AUROC': val_history
+                    }).set_index('Epoch'))
     
-    # Footer
+    # Instructions
     st.markdown("---")
     st.markdown("""
-    ### 🚀 About this Demo
+    ## 🚀 How DLRM Works for Book Recommendations
+    
+    **DLRM (Deep Learning Recommendation Model)** is specifically designed for recommendation systems and offers several advantages:
     
-    This is a **Hugging Face Space** compatible version of a DLRM Book Recommendation System:
+    ### 🏗️ Architecture Benefits:
+    - **Multi-feature Processing**: Handles both categorical (user ID, book ID, publisher) and numerical (age, ratings) features
+    - **Embedding Tables**: Learns rich representations for categorical features
+    - **Cross-feature Interactions**: Captures complex relationships between different features
+    - **Scalable Design**: Efficiently handles large-scale recommendation datasets
     
-    - **CPU-only processing**: No GPU or NVIDIA drivers required
-    - **Simulated predictions**: Demonstrates DLRM concept with heuristic-based scoring
-    - **Sample dataset**: 5 popular books and 5 sample users
-    - **Educational purpose**: Shows how DLRM would work in production
+    ### 📊 Features Used:
+    **Categorical Features:**
+    - User ID, Book ID, Publisher, Country, Age Group, Publication Decade, Rating Level
     
-    **For production use:**
-    - Train actual DLRM model with PyTorch/TorchRec
-    - Use full book datasets (millions of books/users)
-    - Deploy on GPU infrastructure for better performance
-    - Implement proper feature engineering and preprocessing
+    **Dense Features:**  
+    - Normalized Age, Publication Year, User Activity, Book Popularity, Average Ratings
     
-    **🔗 Learn more about DLRM:** [Facebook Research DLRM](https://github.com/facebookresearch/dlrm)
+    ### 🎯 Why DLRM vs LLM for Recommendations:
+    - **Purpose-built**: Specifically designed for recommendation systems
+    - **Feature Integration**: Better at combining diverse feature types
+    - **Scalability**: More efficient for large-scale recommendation tasks
+    - **Performance**: Higher accuracy for rating prediction tasks
+    - **Production Ready**: Optimized for real-time inference
+    
+    ### 💡 Best Use Cases:
+    - **Personalized Recommendations**: Based on user behavior and item characteristics
+    - **Rating Prediction**: Accurately predicts user preferences
+    - **Cold Start**: Handles new users and items through content features
+    - **Real-time Serving**: Fast inference for production systems
     """)
 
+    with tab4:
+        st.header("📸 Book Gallery")
+        st.info("Browse book covers and discover new titles")
+        
+        # Gallery options
+        col1, col2 = st.columns([2, 1])
+        
+        with col1:
+            gallery_mode = st.selectbox(
+                "Choose gallery mode",
+                ["Popular Books", "Recent Publications", "Random Selection", "Search Results"]
+            )
+        
+        with col2:
+            books_per_row = st.slider("Books per row", 2, 6, 4)
+            max_books = st.slider("Maximum books", 10, 50, 20)
+        
+        # Get books based on selected mode
+        if gallery_mode == "Popular Books":
+            # Get most rated books
+            book_popularity = ratings_df.groupby('ISBN').size().sort_values(ascending=False)
+            gallery_books = books_df[books_df['ISBN'].isin(book_popularity.head(max_books).index)]
+            
+        elif gallery_mode == "Recent Publications":
+            # Get recent books
+            books_df_temp = books_df.copy()
+            books_df_temp['Year-Of-Publication'] = pd.to_numeric(books_df_temp['Year-Of-Publication'], errors='coerce')
+            recent_books = books_df_temp.sort_values('Year-Of-Publication', ascending=False, na_position='last')
+            gallery_books = recent_books.head(max_books)
+            
+        elif gallery_mode == "Random Selection":
+            # Random books
+            gallery_books = books_df.sample(min(max_books, len(books_df)))
+            
+        else:  # Search Results
+            search_query = st.text_input("Search books for gallery", placeholder="Enter title, author, or publisher")
+            if search_query:
+                mask = (
+                    books_df['Book-Title'].str.contains(search_query, case=False, na=False) |
+                    books_df['Book-Author'].str.contains(search_query, case=False, na=False) |
+                    books_df['Publisher'].str.contains(search_query, case=False, na=False)
+                )
+                gallery_books = books_df[mask].head(max_books)
+            else:
+                gallery_books = books_df.head(max_books)
+        
+        # Display gallery
+        if len(gallery_books) > 0:
+            st.markdown(f"**📚 Showing {len(gallery_books)} books**")
+            
+            # Create grid layout
+            books_list = gallery_books.to_dict('records')
+            
+            # Display books in rows
+            for i in range(0, len(books_list), books_per_row):
+                cols = st.columns(books_per_row)
+                
+                for j, col in enumerate(cols):
+                    if i + j < len(books_list):
+                        book = books_list[i + j]
+                        
+                        with col:
+                            # Book cover
+                            image_url = book.get('Image-URL-M', '')
+                            
+                            if image_url and pd.notna(image_url) and str(image_url) != 'nan':
+                                try:
+                                    clean_url = str(image_url).strip()
+                                    if clean_url and 'http' in clean_url:
+                                        st.image(clean_url, width='stretch')
+                                    else:
+                                        st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width='stretch')
+                                except:
+                                    st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width='stretch')
+                            else:
+                                st.image("https://via.placeholder.com/150x200?text=📚&color=1f77b4&bg=f0f2f6", width='stretch')
+                            
+                            # Book info
+                            title = book['Book-Title']
+                            if len(title) > 40:
+                                title = title[:37] + "..."
+                            
+                            author = book['Book-Author']
+                            if len(author) > 25:
+                                author = author[:22] + "..."
+                            
+                            st.markdown(f"**{title}**")
+                            st.write(f"*{author}*")
+                            st.write(f"📅 {book.get('Year-Of-Publication', 'Unknown')}")
+                            
+                            # Book statistics
+                            book_stats = ratings_df[ratings_df['ISBN'] == book['ISBN']]
+                            if len(book_stats) > 0:
+                                avg_rating = book_stats['Book-Rating'].mean()
+                                num_ratings = len(book_stats)
+                                st.write(f"⭐ {avg_rating:.1f}/10 ({num_ratings} ratings)")
+                            else:
+                                st.write("⭐ No ratings")
+                            
+                            # DLRM prediction button
+                            if recommender and recommender.model:
+                                if st.button(f"🎯 DLRM Score", key=f"dlrm_{book['ISBN']}"):
+                                    with st.spinner("Calculating..."):
+                                        # Use first user as example
+                                        sample_user = users_df['User-ID'].iloc[0]
+                                        dlrm_score = recommender.predict_rating(sample_user, book['ISBN'])
+                                        st.success(f"DLRM Score: {dlrm_score:.3f}")
+        else:
+            st.info("No books found for the selected criteria")
+        
+        # Quick stats
+        st.markdown("---")
+        st.subheader("📊 Gallery Statistics")
+        
+        col1, col2, col3, col4 = st.columns(4)
+        
+        with col1:
+            books_with_covers = sum(1 for _, book in gallery_books.iterrows()
+                                  if book.get('Image-URL-M') and pd.notna(book.get('Image-URL-M')))
+            st.metric("Books with Covers", f"{books_with_covers}/{len(gallery_books)}")
+        
+        with col2:
+            # Convert Year-Of-Publication to numeric, coercing errors to NaN
+            years = pd.to_numeric(gallery_books['Year-Of-Publication'], errors='coerce')
+            avg_year = years.mean()
+            st.metric("Average Publication Year", f"{avg_year:.0f}" if not pd.isna(avg_year) else "Unknown")
+        
+        with col3:
+            unique_authors = gallery_books['Book-Author'].nunique()
+            st.metric("Unique Authors", unique_authors)
+        
+        with col4:
+            unique_publishers = gallery_books['Publisher'].nunique()
+            st.metric("Unique Publishers", unique_publishers)
+
 if __name__ == "__main__":
-    main()
+    main()