Update app.py

app.py

@@ -1,10 +1,3 @@
-"""
-Gradio App for Hybrid Movie Recommendation System
-Deploy to Hugging Face Spaces as 'DataSynthis_Job_task'
-
-File: app.py
-"""
-
 import gradio as gr
 import pickle
 import pandas as pd
@@ -14,20 +7,13 @@ import torch.nn as nn
 import os
 from scipy.sparse import csr_matrix
 
-#==============================================================================
-# MODEL CLASS DEFINITIONS (Required for unpickling)
-#==============================================================================
-
 class ItemBasedCF:
-    """Item-Based Collaborative Filtering"""
     pass
 
 class SVDRecommender:
-    """SVD Recommender"""
     pass
 
 class NeuralCF(nn.Module):
-    """Neural Collaborative Filtering Model"""
     
     def __init__(self, n_users, n_movies, embedding_dim=50, hidden_layers=[64, 32, 16]):
         super(NeuralCF, self).__init__()
@@ -60,22 +46,14 @@ class NeuralCF(nn.Module):
             return torch.clamp(prediction, 1, 5).item()
 
 class HybridRecommender:
-    """Hybrid Recommendation System"""
     pass
 
 class MovieLensDataLoader:
-    """Data Loader"""
     pass
 
-#==============================================================================
-# LOAD MODEL AND DATA
-#==============================================================================
-
 def load_model_and_data():
-    """Load the trained model and necessary data"""
     import os
     
-    # Debug: Check what files exist
     print("Checking for files...")
     print(f"Current directory: {os.getcwd()}")
     print(f"Files in current directory: {os.listdir('.')}")
@@ -86,7 +64,6 @@ def load_model_and_data():
         print("ERROR: model_artifacts/ folder does not exist!")
     
     try:
-        # Check each file individually
         files_to_check = [
             'model_artifacts/hybrid_model.pkl',
             'model_artifacts/loader.pkl',
@@ -97,10 +74,9 @@ def load_model_and_data():
             if not os.path.exists(file_path):
                 print(f"ERROR: Missing file: {file_path}")
             else:
-                file_size = os.path.getsize(file_path) / (1024*1024)  # MB
+                file_size = os.path.getsize(file_path) / (1024*1024)
                 print(f"Found: {file_path} ({file_size:.2f} MB)")
         
-        # Load files
         with open('model_artifacts/hybrid_model.pkl', 'rb') as f:
             model = pickle.load(f)
         print("✓ Loaded hybrid_model.pkl")
@@ -113,7 +89,6 @@ def load_model_and_data():
             movies = pickle.load(f)
         print("✓ Loaded movies.pkl")
         
-        # Get list of users
         user_ids = sorted(loader.user_id_map.keys())
         print(f"✓ Model loaded successfully! {len(user_ids)} users available")
         
@@ -128,26 +103,11 @@ def load_model_and_data():
         traceback.print_exc()
         return None, None, None, []
 
-# Load everything at startup
 print("Loading model and data...")
 model, loader, movies_df, user_ids = load_model_and_data()
 print(f"Model loaded! Available users: {len(user_ids)}")
 
-#==============================================================================
-# RECOMMENDATION FUNCTION
-#==============================================================================
-
 def get_recommendations(user_id, num_recommendations):
-    """
-    Get movie recommendations for a user
-    
-    Args:
-        user_id: User ID (int)
-        num_recommendations: Number of recommendations to return
-        
-    Returns:
-        Formatted string with recommendations
-    """
     if model is None or loader is None:
         return "❌ Error: Model not loaded properly. Please check the model files."
     
@@ -155,11 +115,9 @@ def get_recommendations(user_id, num_recommendations):
         user_id = int(user_id)
         num_recommendations = int(num_recommendations)
         
-        # Check if user exists
         if user_id not in loader.user_id_map:
             return f"❌ User ID {user_id} not found! Please select a valid user ID."
         
-        # Get recommendations
         recommendations = model.recommend_movies(
             user_id=user_id,
             N=num_recommendations,
@@ -171,7 +129,6 @@ def get_recommendations(user_id, num_recommendations):
         if not recommendations:
             return f"❌ No recommendations found for User {user_id}"
         
-        # Format output
         output = f"🎬 **Top {num_recommendations} Movie Recommendations for User {user_id}**\n\n"
         output += "=" * 60 + "\n\n"
         
@@ -188,17 +145,7 @@ def get_recommendations(user_id, num_recommendations):
     except Exception as e:
         return f"❌ Error generating recommendations: {str(e)}"
 
-
 def get_user_history(user_id):
-    """
-    Show user's rating history
-    
-    Args:
-        user_id: User ID
-        
-    Returns:
-        Formatted string with user's past ratings
-    """
     if model is None or loader is None:
         return "❌ Error: Model not loaded properly."
     
@@ -210,14 +157,12 @@ def get_user_history(user_id):
         
         user_idx = loader.user_id_map[user_id]
         
-        # Get user's ratings from the training data
         user_ratings = model.item_cf.user_item_matrix[user_idx].toarray().flatten()
         rated_indices = np.where(user_ratings > 0)[0]
         
         if len(rated_indices) == 0:
             return f"No rating history found for User {user_id}"
         
-        # Get movie details
         history = []
         for movie_idx in rated_indices:
             original_movie_id = loader.reverse_movie_map[movie_idx]
@@ -225,10 +170,8 @@ def get_user_history(user_id):
             rating = user_ratings[movie_idx]
             history.append((title, rating))
         
-        # Sort by rating (highest first)
         history.sort(key=lambda x: x[1], reverse=True)
         
-        # Format output
         output = f"📊 **Rating History for User {user_id}**\n\n"
         output += f"Total movies rated: {len(history)}\n"
         output += f"Average rating: {np.mean([r for _, r in history]):.2f}\n\n"
@@ -244,22 +187,11 @@ def get_user_history(user_id):
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-
 def get_movie_info(movie_title_search):
-    """
-    Search for movies by title
-    
-    Args:
-        movie_title_search: Search query
-        
-    Returns:
-        Formatted string with matching movies
-    """
     if movies_df is None:
         return "❌ Error: Movies data not loaded"
     
     try:
-        # Search for movies
         matches = movies_df[movies_df['title'].str.contains(movie_title_search, case=False, na=False)]
         
         if len(matches) == 0:
@@ -280,12 +212,6 @@ def get_movie_info(movie_title_search):
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-
-#==============================================================================
-# GRADIO INTERFACE
-#==============================================================================
-
-# Create Gradio interface with tabs
 with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis") as demo:
     
     gr.Markdown("""
@@ -300,7 +226,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
     
     with gr.Tabs():
         
-        # TAB 1: Get Recommendations
         with gr.Tab("🎯 Get Recommendations"):
             gr.Markdown("### Get personalized movie recommendations for any user")
             
@@ -345,7 +270,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
             - Click "Get Recommendations" to see personalized movie suggestions
             """)
         
-        # TAB 2: User History
         with gr.Tab("📊 User History"):
             gr.Markdown("### View a user's rating history")
             
@@ -374,7 +298,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
                 outputs=history_output
             )
         
-        # TAB 3: Search Movies
         with gr.Tab("🔍 Search Movies"):
             gr.Markdown("### Search for movies in the database")
             
@@ -401,7 +324,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
                 outputs=search_output
             )
         
-        # TAB 4: About
         with gr.Tab("ℹ️ About"):
             gr.Markdown("""
             ## About This System
@@ -446,7 +368,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
             User IDs range from 1 to 943, and movie IDs range from 1 to 1682.
             """)
     
-    # Footer
     gr.Markdown("""
     ---
     <div style='text-align: center'>
@@ -454,20 +375,12 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
     </div>
     """)
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(
         share=False,
         server_name="0.0.0.0",
         server_port=7860
-    )"""
-Gradio App for Hybrid Movie Recommendation System
-Deploy to Hugging Face Spaces as 'DataSynthis_Job_task'
-
-File: app.py
-"""
-
-import gradio as gr
+    )import gradio as gr
 import pickle
 import pandas as pd
 import numpy as np
@@ -476,20 +389,13 @@ import torch.nn as nn
 import os
 from scipy.sparse import csr_matrix
 
-#==============================================================================
-# MODEL CLASS DEFINITIONS (Required for unpickling)
-#==============================================================================
-
 class ItemBasedCF:
-    """Item-Based Collaborative Filtering"""
     pass
 
 class SVDRecommender:
-    """SVD Recommender"""
     pass
 
 class NeuralCF(nn.Module):
-    """Neural Collaborative Filtering Model"""
     
     def __init__(self, n_users, n_movies, embedding_dim=50, hidden_layers=[64, 32, 16]):
         super(NeuralCF, self).__init__()
@@ -522,22 +428,14 @@ class NeuralCF(nn.Module):
             return torch.clamp(prediction, 1, 5).item()
 
 class HybridRecommender:
-    """Hybrid Recommendation System"""
     pass
 
 class MovieLensDataLoader:
-    """Data Loader"""
     pass
 
-#==============================================================================
-# LOAD MODEL AND DATA
-#==============================================================================
-
 def load_model_and_data():
-    """Load the trained model and necessary data"""
     import os
     
-    # Debug: Check what files exist
     print("Checking for files...")
     print(f"Current directory: {os.getcwd()}")
     print(f"Files in current directory: {os.listdir('.')}")
@@ -548,7 +446,6 @@ def load_model_and_data():
         print("ERROR: model_artifacts/ folder does not exist!")
     
     try:
-        # Check each file individually
         files_to_check = [
             'model_artifacts/hybrid_model.pkl',
             'model_artifacts/loader.pkl',
@@ -559,10 +456,9 @@ def load_model_and_data():
             if not os.path.exists(file_path):
                 print(f"ERROR: Missing file: {file_path}")
             else:
-                file_size = os.path.getsize(file_path) / (1024*1024)  # MB
+                file_size = os.path.getsize(file_path) / (1024*1024)
                 print(f"Found: {file_path} ({file_size:.2f} MB)")
         
-        # Load files
         with open('model_artifacts/hybrid_model.pkl', 'rb') as f:
             model = pickle.load(f)
         print("✓ Loaded hybrid_model.pkl")
@@ -575,7 +471,6 @@ def load_model_and_data():
             movies = pickle.load(f)
         print("✓ Loaded movies.pkl")
         
-        # Get list of users
         user_ids = sorted(loader.user_id_map.keys())
         print(f"✓ Model loaded successfully! {len(user_ids)} users available")
         
@@ -590,26 +485,11 @@ def load_model_and_data():
         traceback.print_exc()
         return None, None, None, []
 
-# Load everything at startup
 print("Loading model and data...")
 model, loader, movies_df, user_ids = load_model_and_data()
 print(f"Model loaded! Available users: {len(user_ids)}")
 
-#==============================================================================
-# RECOMMENDATION FUNCTION
-#==============================================================================
-
 def get_recommendations(user_id, num_recommendations):
-    """
-    Get movie recommendations for a user
-    
-    Args:
-        user_id: User ID (int)
-        num_recommendations: Number of recommendations to return
-        
-    Returns:
-        Formatted string with recommendations
-    """
     if model is None or loader is None:
         return "❌ Error: Model not loaded properly. Please check the model files."
     
@@ -617,11 +497,9 @@ def get_recommendations(user_id, num_recommendations):
         user_id = int(user_id)
         num_recommendations = int(num_recommendations)
         
-        # Check if user exists
         if user_id not in loader.user_id_map:
             return f"❌ User ID {user_id} not found! Please select a valid user ID."
         
-        # Get recommendations
         recommendations = model.recommend_movies(
             user_id=user_id,
             N=num_recommendations,
@@ -633,7 +511,6 @@ def get_recommendations(user_id, num_recommendations):
         if not recommendations:
             return f"❌ No recommendations found for User {user_id}"
         
-        # Format output
         output = f"🎬 **Top {num_recommendations} Movie Recommendations for User {user_id}**\n\n"
         output += "=" * 60 + "\n\n"
         
@@ -650,17 +527,7 @@ def get_recommendations(user_id, num_recommendations):
     except Exception as e:
         return f"❌ Error generating recommendations: {str(e)}"
 
-
 def get_user_history(user_id):
-    """
-    Show user's rating history
-    
-    Args:
-        user_id: User ID
-        
-    Returns:
-        Formatted string with user's past ratings
-    """
     if model is None or loader is None:
         return "❌ Error: Model not loaded properly."
     
@@ -672,14 +539,12 @@ def get_user_history(user_id):
         
         user_idx = loader.user_id_map[user_id]
         
-        # Get user's ratings from the training data
         user_ratings = model.item_cf.user_item_matrix[user_idx].toarray().flatten()
         rated_indices = np.where(user_ratings > 0)[0]
         
         if len(rated_indices) == 0:
             return f"No rating history found for User {user_id}"
         
-        # Get movie details
         history = []
         for movie_idx in rated_indices:
             original_movie_id = loader.reverse_movie_map[movie_idx]
@@ -687,10 +552,8 @@ def get_user_history(user_id):
             rating = user_ratings[movie_idx]
             history.append((title, rating))
         
-        # Sort by rating (highest first)
         history.sort(key=lambda x: x[1], reverse=True)
         
-        # Format output
         output = f"📊 **Rating History for User {user_id}**\n\n"
         output += f"Total movies rated: {len(history)}\n"
         output += f"Average rating: {np.mean([r for _, r in history]):.2f}\n\n"
@@ -706,22 +569,11 @@ def get_user_history(user_id):
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-
 def get_movie_info(movie_title_search):
-    """
-    Search for movies by title
-    
-    Args:
-        movie_title_search: Search query
-        
-    Returns:
-        Formatted string with matching movies
-    """
     if movies_df is None:
         return "❌ Error: Movies data not loaded"
     
     try:
-        # Search for movies
         matches = movies_df[movies_df['title'].str.contains(movie_title_search, case=False, na=False)]
         
         if len(matches) == 0:
@@ -742,12 +594,6 @@ def get_movie_info(movie_title_search):
     except Exception as e:
         return f"❌ Error: {str(e)}"
 
-
-#==============================================================================
-# GRADIO INTERFACE
-#==============================================================================
-
-# Create Gradio interface with tabs
 with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis") as demo:
     
     gr.Markdown("""
@@ -762,7 +608,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
     
     with gr.Tabs():
         
-        # TAB 1: Get Recommendations
         with gr.Tab("🎯 Get Recommendations"):
             gr.Markdown("### Get personalized movie recommendations for any user")
             
@@ -807,7 +652,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
             - Click "Get Recommendations" to see personalized movie suggestions
             """)
         
-        # TAB 2: User History
         with gr.Tab("📊 User History"):
             gr.Markdown("### View a user's rating history")
             
@@ -836,7 +680,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
                 outputs=history_output
             )
         
-        # TAB 3: Search Movies
         with gr.Tab("🔍 Search Movies"):
             gr.Markdown("### Search for movies in the database")
             
@@ -863,40 +706,33 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
                 outputs=search_output
             )
         
-        # TAB 4: About
         with gr.Tab("ℹ️ About"):
-            gr.Markdown("""
-            ## About This System
+            gr.Markdown(""" About This System
             
-            ### 🎯 Model Architecture
-            This is a **Hybrid Recommendation System** that combines three powerful approaches:
+            Model Architecture
+            This is a Hybrid Recommendation System that combines three powerful approaches:
             
-            1. **Item-Based Collaborative Filtering**
+            1. Item-Based Collaborative Filtering
                - Uses cosine similarity between movies
                - Recommends movies similar to what you've liked before
             
-            2. **SVD Matrix Factorization**
+            2. SVD Matrix Factorization
                - Decomposes the user-movie rating matrix
                - Discovers latent factors that explain user preferences
             
-            3. **Neural Collaborative Filtering (NCF)**
+            3. Neural Collaborative Filtering (NCF)
                - Deep learning model with user and movie embeddings
                - Learns complex non-linear patterns in user behavior
             
-            ### 📊 Dataset
-            - **MovieLens 100k** dataset
-            - 100,000 ratings from 943 users on 1,682 movies
-            - Ratings scale: 1-5 stars
-            
-            ### 🎯 Performance Metrics
-            - **Precision@10**: 26.77%
-            - **NDCG@10**: 28.50%
-            - **Model improves recommendations by 40% vs baseline**
+         
             
-            ### 👨‍💻 Created For
-            **DataSynthis Job Task**
+            Performance Metrics
+            - Precision@10: 26.77%
+            - NDCG@10: 28.50%
+            - Model improves recommendations by 40% vs baseline**
             
-            ### 🔗 Technologies Used
+         
+            Technologies Used
             - PyTorch (Neural Networks)
             - Scikit-learn (SVD, Similarity)
             - Pandas & NumPy (Data Processing)
@@ -908,7 +744,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
             User IDs range from 1 to 943, and movie IDs range from 1 to 1682.
             """)
     
-    # Footer
     gr.Markdown("""
     ---
     <div style='text-align: center'>
@@ -916,7 +751,6 @@ with gr.Blocks(theme=gr.themes.Soft(), title="Movie Recommender - DataSynthis")
     </div>
     """)
 
-# Launch the app
 if __name__ == "__main__":
     demo.launch(
         share=False,