API

app.py

@@ -14,7 +14,8 @@ import os
 import logging
 import requests
 import io
-
+from sklearn.preprocessing import StandardScaler
+from collections import defaultdict
 
 warnings.filterwarnings('ignore')
 
@@ -37,6 +38,11 @@ try:
     excel_content = io.BytesIO(response.content)
     purchase_history = pd.read_excel(excel_content, sheet_name='Transaction History', 
                                    parse_dates=['Purchase_Date'])
+    
+    # Read Customer Profile sheet
+    excel_content.seek(0)  # Reset buffer position
+    customer_profiles = pd.read_excel(excel_content, sheet_name='Customer Profile (Individual)')
+
     logger.info("Successfully downloaded and loaded Excel file")
     
     # Process the data
@@ -45,6 +51,14 @@ try:
     purchase_counts = purchase_history.groupby(['Customer_Id', 'Product_Id']).size().unstack(fill_value=0)
     sparse_purchase_counts = sparse.csr_matrix(purchase_counts)
     cosine_similarities = cosine_similarity(sparse_purchase_counts.T)
+
+     # Process customer profiles data
+    customer_profiles['Customer_Id'] = customer_profiles['Customer_Id'].astype(str)
+    
+    # Normalize numerical features if they exist
+    numerical_features = ['Age', 'Income']  # Add or modify based on your actual columns
+    scaler = StandardScaler()
+    customer_profiles[numerical_features] = scaler.fit_transform(customer_profiles[numerical_features])
     
     logger.info("Data processing completed successfully")
     
@@ -208,3 +222,135 @@ async def login(customer_id: str, password: str):
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail=f"Error during login process: {str(e)}"
         )
+# Add content recommendation function
+def get_content_recommendations(customer_id: str, n: int = 5) -> List[Dict]:
+    """
+    Get content recommendations based on customer profile
+    """
+    try:
+        # Get customer profile
+        customer_profile = customer_profiles[customer_profiles['Customer_Id'] == customer_id].iloc[0]
+        
+        # Define content rules based on customer attributes
+        content_suggestions = []
+        
+        # Age-based recommendations
+        age = customer_profile['Age'] * scaler.scale_[0] + scaler.mean_[0]  # Denormalize age
+        
+        if age < 25:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Getting Started with Personal Finance", "category": "Financial Education"},
+                {"type": "Article", "title": "Budgeting Basics for Young Adults", "category": "Financial Planning"},
+                {"type": "Interactive", "title": "Investment 101 Quiz", "category": "Education"}
+            ])
+        elif age < 40:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Investment Strategies for Growing Wealth", "category": "Investment"},
+                {"type": "Article", "title": "Family Financial Planning Guide", "category": "Financial Planning"},
+                {"type": "Webinar", "title": "Real Estate Investment Basics", "category": "Investment"}
+            ])
+        else:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Retirement Planning Strategies", "category": "Retirement"},
+                {"type": "Article", "title": "Estate Planning Essentials", "category": "Financial Planning"},
+                {"type": "Webinar", "title": "Tax Optimization for Retirement", "category": "Tax Planning"}
+            ])
+        
+        # Income-based recommendations
+        income = customer_profile['Income'] * scaler.scale_[1] + scaler.mean_[1]  # Denormalize income
+        
+        if income < 50000:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Debt Management Strategies", "category": "Debt Management"},
+                {"type": "Article", "title": "Saving on a Tight Budget", "category": "Budgeting"}
+            ])
+        elif income < 100000:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Tax-Efficient Investment Strategies", "category": "Investment"},
+                {"type": "Article", "title": "Maximizing Your 401(k)", "category": "Retirement"}
+            ])
+        else:
+            content_suggestions.extend([
+                {"type": "Video", "title": "Advanced Tax Planning Strategies", "category": "Tax Planning"},
+                {"type": "Article", "title": "High-Net-Worth Investment Guide", "category": "Investment"}
+            ])
+        
+        # Add personalization based on purchase history
+        if customer_id in purchase_history['Customer_Id'].unique():
+            customer_purchases = purchase_history[purchase_history['Customer_Id'] == customer_id]
+            categories = customer_purchases['Category'].unique()
+            
+            for category in categories:
+                if category == 'Investment':
+                    content_suggestions.append({
+                        "type": "Video",
+                        "title": f"Advanced {category} Strategies",
+                        "category": category
+                    })
+                elif category == 'Insurance':
+                    content_suggestions.append({
+                        "type": "Article",
+                        "title": f"Understanding Your {category} Options",
+                        "category": category
+                    })
+        
+        # Remove duplicates and limit to n recommendations
+        seen = set()
+        unique_suggestions = []
+        for suggestion in content_suggestions:
+            key = (suggestion['title'], suggestion['type'])
+            if key not in seen:
+                seen.add(key)
+                unique_suggestions.append(suggestion)
+        
+        return unique_suggestions[:n]
+        
+    except Exception as e:
+        logger.error(f"Error generating content recommendations: {str(e)}")
+        return []
+
+# Add new endpoint for content recommendations
+@app.get("/content-recommendations/{customer_id}")
+async def get_customer_content_recommendations(customer_id: str, n: int = 5):
+    """
+    Get personalized content recommendations for a customer
+    
+    Parameters:
+    - customer_id: The ID of the customer
+    - n: Number of recommendations to return (default: 5)
+    
+    Returns:
+    - JSON object containing personalized content recommendations
+    """
+    try:
+        # Validate customer
+        if customer_id not in customer_profiles['Customer_Id'].unique():
+            raise HTTPException(
+                status_code=status.HTTP_404_NOT_FOUND,
+                detail="Customer ID not found"
+            )
+        
+        # Get customer profile summary
+        customer_profile = customer_profiles[customer_profiles['Customer_Id'] == customer_id].iloc[0]
+        profile_summary = {
+            "age_group": "Young" if customer_profile['Age'] < 25 else "Middle" if customer_profile['Age'] < 40 else "Senior",
+            "income_level": "Low" if customer_profile['Income'] < 50000 else "Medium" if customer_profile['Income'] < 100000 else "High"
+        }
+        
+        # Get content recommendations
+        recommendations = get_content_recommendations(customer_id, n)
+        
+        return {
+            "customer_id": customer_id,
+            "profile_summary": profile_summary,
+            "recommendations": recommendations
+        }
+        
+    except HTTPException:
+        raise
+    except Exception as e:
+        logger.error(f"Error processing content recommendations for customer {customer_id}: {str(e)}")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail=f"Error processing request: {str(e)}"
+        )