api

app.py

@@ -28,6 +28,7 @@ app = FastAPI()
 
 # URL of the Excel file
 EXCEL_URL = "https://huggingface.co/spaces/Vaibhav84/RecommendationAPI/resolve/main/DataSetSample.xlsx"
+
 try:
     # Download the file from URL
     logger.info(f"Attempting to download Excel file from: {EXCEL_URL}")
@@ -36,54 +37,8 @@ try:
     
     # Read the Excel file from the downloaded content
     excel_content = io.BytesIO(response.content)
-    
-    def custom_date_parser(date_str):
-        try:
-            # First try to parse as MM/DD/YYYY
-            dt = datetime.strptime(str(date_str), '%m/%d/%Y')
-            return dt
-        except ValueError:
-            try:
-                # Then try DD/MM/YYYY
-                dt = datetime.strptime(str(date_str), '%d/%m/%Y')
-                return dt
-            except ValueError:
-                try:
-                    # Then try YYYY-MM-DD
-                    dt = datetime.strptime(str(date_str), '%Y-%m-%d')
-                    return dt
-                except ValueError:
-                    # If all else fails, try pandas' flexible parser
-                    return pd.to_datetime(date_str, format='mixed', dayfirst=True)
-    
-    # Read the Excel file with the custom date parser
-    purchase_history = pd.read_excel(
-        excel_content, 
-        sheet_name='Transaction History'
-    )
-    
-    # Convert Purchase_Date column separately with error handling
-    def safe_parse_date(date_val):
-        if pd.isna(date_val):
-            return None
-        try:
-            if isinstance(date_val, (datetime, pd.Timestamp)):
-                return date_val
-            return custom_date_parser(date_val)
-        except Exception as e:
-            logger.error(f"Error parsing date {date_val}: {str(e)}")
-            return None
-
-    # Convert dates and handle any parsing errors
-    purchase_history['Purchase_Date'] = purchase_history['Purchase_Date'].apply(safe_parse_date)
-    
-    # Remove any rows where date parsing failed
-    purchase_history = purchase_history.dropna(subset=['Purchase_Date'])
-    
-    # Log some information about the dates for debugging
-    logger.info(f"Date column type: {purchase_history['Purchase_Date'].dtype}")
-    logger.info(f"Sample dates: {purchase_history['Purchase_Date'].head()}")
-    logger.info(f"Number of valid dates: {purchase_history['Purchase_Date'].count()}")
+    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
@@ -91,18 +46,9 @@ try:
 
     # Read Social Media Sentiment
     excel_content.seek(0)  # Reset buffer position
-    customer_Media = pd.read_excel(
-        excel_content, 
-        sheet_name='Social Media Sentiment',
-        parse_dates=['Timestamp']
-    )
+    customer_Media = pd.read_excel(excel_content, sheet_name='Social Media Sentiment',parse_dates=['Timestamp'])
 
     logger.info("Successfully downloaded and loaded Excel file")
-
-except Exception as e:
-    logger.error(f"Error downloading or processing data: {str(e)}")
-    raise
-
     
     # Process the data
     purchase_history['Customer_Id'] = purchase_history['Customer_Id'].astype(str)
@@ -613,233 +559,3 @@ class FinancialAnalysisResponse(BaseModel):
     financial_health_score: int
     action_items: List[str]
 
-@app.get("/financial-analysis/{customer_id}", response_model=FinancialAnalysisResponse)
-async def get_financial_analysis(customer_id: str):
-    try:
-        # Validate customer
-        if customer_id not in purchase_history['Customer_Id'].unique():
-            raise HTTPException(
-                status_code=status.HTTP_404_NOT_FOUND,
-                detail="Customer not found"
-            )
-
-        # Get customer profile and transactions
-        customer_profile = customer_profiles[customer_profiles['Customer_Id'] == customer_id].iloc[0]
-        customer_transactions = purchase_history[purchase_history['Customer_Id'] == customer_id].copy()
-
-        # Ensure Purchase_Date is in datetime format
-        if not pd.api.types.is_datetime64_any_dtype(customer_transactions['Purchase_Date']):
-            customer_transactions['Purchase_Date'] = pd.to_datetime(
-                customer_transactions['Purchase_Date'],
-                format='mixed',
-                dayfirst=False
-            )
-
-        # Print debug information
-        logger.info(f"Date column type: {customer_transactions['Purchase_Date'].dtype}")
-        logger.info(f"Sample dates: {customer_transactions['Purchase_Date'].head()}")
-
-        # Calculate basic financial metrics
-        current_date = datetime.now()
-        thirty_days_ago = current_date - timedelta(days=30)
-        sixty_days_ago = current_date - timedelta(days=60)
-
-        current_month_spending = customer_transactions[
-            customer_transactions['Purchase_Date'] >= thirty_days_ago
-        ]['Amount (In Dollars)'].sum()
-
-        previous_month_spending = customer_transactions[
-            (customer_transactions['Purchase_Date'] >= sixty_days_ago) &
-            (customer_transactions['Purchase_Date'] < thirty_days_ago)
-        ]['Amount (In Dollars)'].sum()
-
-        # Calculate monthly average spending
-        monthly_groups = customer_transactions.groupby(
-            customer_transactions['Purchase_Date'].dt.to_period('M')
-        )['Amount (In Dollars)'].sum()
-        
-        monthly_avg_spend = monthly_groups.mean() if not monthly_groups.empty else 0.0
-
-        # Calculate spend trend
-        spend_trend = ((current_month_spending - previous_month_spending) / previous_month_spending * 100) if previous_month_spending > 0 else 0
-
-        # Calculate spending categories
-        spending_categories = customer_transactions.groupby('Category')['Amount (In Dollars)'].sum().reset_index()
-        spending_categories_list = [
-            {"category": row['Category'], "amount": float(row['Amount (In Dollars)'])}
-            for _, row in spending_categories.iterrows()
-        ]
-
-        # Generate spending insights
-        spending_insights = []
-        
-        # Category-based insights
-        for category in spending_categories.itertuples():
-            category_avg = category._2 / max(1, len(monthly_groups))  # Using _2 for the Amount column
-            if category_avg > monthly_avg_spend * 0.3:
-                spending_insights.append(f"High spending in {category.Category}: ${category_avg:.2f}/month")
-
-        # Age-based recommendations
-        age = float(customer_profile['Age'])
-        income = float(customer_profile['Income per year (in dollars)'])
-
-        # Determine credit score range (simulated based on age and income)
-        base_score = min(max((age * 10 + income / 1000) / 2, 300), 850)
-        credit_score_range = f"{int(base_score-25)}-{int(base_score+25)}"
-        credit_score_change = "↑ improving" if age > 25 and income > 50000 else "stable"
-
-        # Calculate investment potential (simplified)
-        monthly_income = income / 12
-        investment_potential = max(0, monthly_income - monthly_avg_spend * 1.2)
-
-        # Generate recommendations based on age and income
-        card_recommendations = []
-        investment_recommendations = []
-        real_estate_recommendations = []
-
-        # Credit Card Recommendations
-        if income < 50000:
-            card_recommendations.append(CardRecommendation(
-                name="Cash Back Starter Card",
-                annual_fee=0,
-                rewards_rate=1.5,
-                benefits="No annual fee, 1.5% cash back on all purchases"
-            ))
-        elif income < 100000:
-            card_recommendations.append(CardRecommendation(
-                name="Premium Rewards Card",
-                annual_fee=95,
-                rewards_rate=2.5,
-                benefits="Travel insurance, cash back on all purchases, airport lounge access"
-            ))
-        else:
-            card_recommendations.append(CardRecommendation(
-                name="Elite Travel Card",
-                annual_fee=495,
-                rewards_rate=3.0,
-                benefits="Comprehensive travel benefits, concierge service, premium insurance"
-            ))
-
-        # Investment Recommendations
-        if age < 30:
-            investment_recommendations.extend([
-                InvestmentRecommendation(
-                    type="Index Fund",
-                    risk_level="High",
-                    expected_return=10.0,
-                    min_investment=1000.0
-                ),
-                InvestmentRecommendation(
-                    type="Tech Growth ETF",
-                    risk_level="High",
-                    expected_return=12.0,
-                    min_investment=2000.0
-                )
-            ])
-        elif age < 50:
-            investment_recommendations.extend([
-                InvestmentRecommendation(
-                    type="Balanced Fund",
-                    risk_level="Medium",
-                    expected_return=8.0,
-                    min_investment=5000.0
-                ),
-                InvestmentRecommendation(
-                    type="Dividend Growth Stocks",
-                    risk_level="Medium",
-                    expected_return=7.0,
-                    min_investment=10000.0
-                )
-            ])
-        else:
-            investment_recommendations.extend([
-                InvestmentRecommendation(
-                    type="Bond Fund",
-                    risk_level="Low",
-                    expected_return=5.0,
-                    min_investment=10000.0
-                ),
-                InvestmentRecommendation(
-                    type="Income Fund",
-                    risk_level="Low",
-                    expected_return=4.0,
-                    min_investment=25000.0
-                )
-            ])
-
-        # Real Estate Recommendations
-        if income > 75000:
-            mortgage_capacity = (income * 4) * 0.8  # 80% of 4x annual income
-            monthly_payment = (mortgage_capacity * 0.05) / 12  # Simplified mortgage calculation
-
-            real_estate_recommendations.extend([
-                RealEstateRecommendation(
-                    type="Starter Home",
-                    location="Suburban Area",
-                    price=mortgage_capacity,
-                    monthly_payment=monthly_payment,
-                    roi_potential=5.0
-                )
-            ])
-
-            if income > 150000:
-                real_estate_recommendations.append(
-                    RealEstateRecommendation(
-                        type="Investment Property",
-                        location="Urban Center",
-                        price=mortgage_capacity * 0.7,
-                        monthly_payment=monthly_payment * 0.7,
-                        roi_potential=8.0
-                    )
-                )
-
-        # Calculate financial health score
-        savings_ratio = max(0, min(1, (income - monthly_avg_spend * 12) / income))
-        diversity_score = len(spending_categories) / 10
-        stability_score = min(1, len(customer_transactions) / 100)
-        
-        financial_health_score = int((savings_ratio * 0.4 + diversity_score * 0.3 + stability_score * 0.3) * 100)
-
-        # Generate action items
-        action_items = []
-        if savings_ratio < 0.2:
-            action_items.append("Increase monthly savings to at least 20% of income")
-        if monthly_avg_spend > monthly_income * 0.7:
-            action_items.append("Review monthly expenses to reduce spending")
-        if len(investment_recommendations) > 0:
-            action_items.append(f"Consider investing in {investment_recommendations[0].type}")
-
-        # Get recent transactions
-        recent_transactions = [
-            {
-                "date": row['Purchase_Date'].strftime('%Y-%m-%d'),
-                "amount": float(row['Amount (In Dollars)'])
-            }
-            for _, row in customer_transactions.sort_values('Purchase_Date', ascending=False).head(10).iterrows()
-        ]
-
-        return {
-            "monthly_avg_spend": float(monthly_avg_spend),
-            "spend_trend": float(spend_trend),
-            "credit_score_range": credit_score_range,
-            "credit_score_change": credit_score_change,
-            "investment_potential": float(investment_potential),
-            "spending_categories": spending_categories_list,
-            "spending_insights": spending_insights,
-            "recent_transactions": recent_transactions,
-            "card_recommendations": card_recommendations,
-            "investment_recommendations": investment_recommendations,
-            "real_estate_recommendations": real_estate_recommendations,
-            "financial_health_score": financial_health_score,
-            "action_items": action_items
-        }
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Error processing financial analysis for customer {customer_id}: {str(e)}")
-        raise HTTPException(
-            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-            detail=f"Error processing request: {str(e)}"
-        )
-