Upload 22 files

app.py

@@ -596,6 +596,11 @@ def verify_property():
                             image_model_used.add(result['model_used'])
                         if 'parallelization_info' in result:
                             image_parallel_info.append(result['parallelization_info'])
+        
+        # Add image count to data for cross-validation
+        data['image_count'] = len(images)
+        data['has_images'] = len(images) > 0
+        
         # Process PDFs in parallel
         pdf_texts = []
         pdf_analysis = []
@@ -621,6 +626,10 @@ def verify_property():
                         pdf_analysis.append(result)
                         if 'parallelization_info' in result:
                             pdf_parallel_info.append(result['parallelization_info'])
+        
+        # Add document count to data for cross-validation
+        data['document_count'] = len(pdf_texts)
+        data['has_documents'] = len(pdf_texts) > 0
 
         # Create consolidated text for analysis
         consolidated_text = f"""
@@ -640,6 +649,16 @@ def verify_property():
         Legal Details: {data['legal_details']}
         """
 
+        # Detect if this is a rental property
+        is_rental = any(keyword in data['status'].lower() for keyword in ['rent', 'lease', 'let', 'hiring'])
+        if not is_rental:
+            # Check description for rental keywords
+            is_rental = any(keyword in data['description'].lower() for keyword in ['rent', 'lease', 'let', 'hiring', 'monthly', 'per month'])
+        
+        # Add rental detection to data
+        data['is_rental'] = is_rental
+        data['property_status'] = 'rental' if is_rental else 'sale'
+
         # Process description translation if needed
         try:
             description = data['description']

models/cross_validation.py

@@ -747,7 +747,9 @@ def perform_cross_validation(data: Dict[str, Any]) -> List[Dict[str, Any]]:
 
         # Document analysis - More lenient
         documents = data.get('documents', [])
-        if media_analysis['total_documents'] == 0:
+        has_documents = data.get('has_documents', False) or data.get('document_count', 0) > 0
+        
+        if media_analysis['total_documents'] == 0 and not has_documents:
             if check_files_exist(documents):
                 # Files exist but couldn't be analyzed
                 analysis_sections['documents'].append({
@@ -790,7 +792,20 @@ def perform_cross_validation(data: Dict[str, Any]) -> List[Dict[str, Any]]:
 
         # Image analysis - More lenient
         images = data.get('images', [])
-        if media_analysis['total_images'] == 0:
+        has_images = data.get('has_images', False) or data.get('image_count', 0) > 0
+        
+        # If images were uploaded but media analysis didn't detect them, consider them as valid
+        if has_images and media_analysis['total_images'] == 0:
+            # Images were uploaded but not analyzed by media analysis - this is normal
+            analysis_sections['documents'].append({
+                'check': 'images_validation',
+                'status': 'valid',
+                'message': 'Property images uploaded successfully.',
+                'details': f'{data.get("image_count", 0)} images were uploaded and processed.',
+                'severity': 'low',
+                'recommendation': 'Images are being analyzed.'
+            })
+        elif media_analysis['total_images'] == 0 and not has_images:
             if check_files_exist(images):
                 # Files exist but couldn't be analyzed
                 analysis_sections['documents'].append({

models/parallel_processor.py

@@ -293,6 +293,7 @@ class ParallelProcessor:
         """Run price analysis"""
         try:
             from .price_analysis import analyze_price
+            # Pass rental information to price analysis
             return analyze_price(data, price_context, data.get('latitude'), data.get('longitude'), property_data)
         except Exception as e:
             logger.error(f"Error in price analysis: {str(e)}")

models/price_analysis.py

@@ -537,12 +537,32 @@ def analyze_price(data, context_text=None, latitude=None, longitude=None, proper
             
         city = data.get('city', '').strip() or 'Unknown'
         
+        # Detect if this is a rental property
+        is_rental = data.get('is_rental', False)
+        if not is_rental:
+            # Check status and description for rental keywords
+            status = data.get('status', '').lower()
+            description = data.get('description', '').lower()
+            is_rental = any(keyword in status for keyword in ['rent', 'lease', 'let', 'hiring']) or \
+                       any(keyword in description for keyword in ['rent', 'lease', 'let', 'hiring', 'monthly', 'per month'])
+        
         # Calculate price per sq.ft properly
         price_per_sqft = price / sq_ft if sq_ft > 0 else price
         
         # Get market data for comparison
         market_data = get_hyderabad_market_data()
-        market_avg = market_data.get('avg_price_per_sqft', 8500) if market_data else 8500
+        
+        # Adjust market data based on rental vs purchase
+        if is_rental:
+            # For rental properties, use monthly rental rates
+            market_avg = 25  # ₹25/sq ft/month average for Hyderabad rentals
+            market_min = 15  # ₹15/sq ft/month minimum
+            market_max = 80  # ₹80/sq ft/month maximum
+        else:
+            # For purchase properties, use purchase rates
+            market_avg = market_data.get('avg_price_per_sqft', 8500) if market_data else 8500
+            market_min = market_data.get('min_price_per_sqft', 4500) if market_data else 4500
+            market_max = market_data.get('max_price_per_sqft', 25000) if market_data else 25000
         
         # Calculate deviation from market average
         if market_avg > 0:
@@ -551,52 +571,101 @@ def analyze_price(data, context_text=None, latitude=None, longitude=None, proper
             deviation = 0
         
         # Determine assessment based on deviation and price reasonableness - Much more lenient
-        if price_per_sqft < 50:  # Extremely low price - increased from 100
-            assessment = "suspicious_pricing"
-            confidence = 0.2  # Increased from 0.1
-        elif price_per_sqft < market_avg * 0.2:  # Very below market - reduced from 0.3
-            assessment = "below_market"
-            confidence = 0.4  # Increased from 0.3
-        elif price_per_sqft < market_avg * 0.6:  # Below market - reduced from 0.7
-            assessment = "below_market"
-            confidence = 0.7  # Increased from 0.6
-        elif price_per_sqft <= market_avg * 1.5:  # Market rate - increased from 1.3
-            assessment = "market_rate"
-            confidence = 0.9  # Increased from 0.8
-        elif price_per_sqft <= market_avg * 2.5:  # Above market - increased from 2.0
-            assessment = "above_market"
-            confidence = 0.8  # Increased from 0.7
-        else:  # Very above market
-            assessment = "premium_pricing"
-            confidence = 0.6  # Increased from 0.5
+        if is_rental:
+            # Rental property pricing logic
+            if price_per_sqft < 5:  # Extremely low rental price
+                assessment = "suspicious_pricing"
+                confidence = 0.3  # Increased from 0.2
+            elif price_per_sqft < market_avg * 0.3:  # Very below market rental
+                assessment = "below_market"
+                confidence = 0.5  # Increased from 0.4
+            elif price_per_sqft < market_avg * 0.7:  # Below market rental
+                assessment = "below_market"
+                confidence = 0.8  # Increased from 0.7
+            elif price_per_sqft <= market_avg * 1.5:  # Market rate rental
+                assessment = "market_rate"
+                confidence = 0.9  # Increased from 0.8
+            elif price_per_sqft <= market_avg * 2.0:  # Above market rental
+                assessment = "above_market"
+                confidence = 0.8  # Increased from 0.7
+            else:  # Very above market rental
+                assessment = "premium_pricing"
+                confidence = 0.6  # Increased from 0.5
+        else:
+            # Purchase property pricing logic (existing logic)
+            if price_per_sqft < 50:  # Extremely low price - increased from 100
+                assessment = "suspicious_pricing"
+                confidence = 0.2  # Increased from 0.1
+            elif price_per_sqft < market_avg * 0.2:  # Very below market - reduced from 0.3
+                assessment = "below_market"
+                confidence = 0.4  # Increased from 0.3
+            elif price_per_sqft < market_avg * 0.6:  # Below market - reduced from 0.7
+                assessment = "below_market"
+                confidence = 0.7  # Increased from 0.6
+            elif price_per_sqft <= market_avg * 1.5:  # Market rate - increased from 1.3
+                assessment = "market_rate"
+                confidence = 0.9  # Increased from 0.8
+            elif price_per_sqft <= market_avg * 2.5:  # Above market - increased from 2.0
+                assessment = "above_market"
+                confidence = 0.8  # Increased from 0.7
+            else:  # Very above market
+                assessment = "premium_pricing"
+                confidence = 0.6  # Increased from 0.5
         
         # Generate risk indicators - Much more lenient
         risk_indicators = []
-        if price_per_sqft < 50:  # Increased from 100
-            risk_indicators.append("⚠️ Property priced extremely low (suspicious)")
-        elif price_per_sqft < market_avg * 0.2:  # Reduced from 0.3
-            risk_indicators.append("⚠️ Property priced significantly below market average")
-        elif price_per_sqft > market_avg * 2.5:  # Increased from 2.0
-            risk_indicators.append("⚠️ Property priced significantly above market average")
+        if is_rental:
+            if price_per_sqft < 5:  # Increased from 100
+                risk_indicators.append("⚠️ Property priced extremely low (suspicious)")
+            elif price_per_sqft < market_avg * 0.3:  # Reduced from 0.3
+                risk_indicators.append("⚠️ Property priced significantly below market average")
+            elif price_per_sqft > market_avg * 2.0:  # Increased from 2.0
+                risk_indicators.append("⚠️ Property priced significantly above market average")
+        else:
+            if price_per_sqft < 50:  # Increased from 100
+                risk_indicators.append("⚠️ Property priced extremely low (suspicious)")
+            elif price_per_sqft < market_avg * 0.2:  # Reduced from 0.3
+                risk_indicators.append("⚠️ Property priced significantly below market average")
+            elif price_per_sqft > market_avg * 2.5:  # Increased from 2.0
+                risk_indicators.append("⚠️ Property priced significantly above market average")
         
         # Price ranges for the city - Much more lenient
-        price_ranges = {
-            'budget': {
-                'min': market_avg * 0.3,  # Reduced from 0.5
-                'max': market_avg * 0.8,
-                'description': f'Budget properties in {city}'
-            },
-            'mid_range': {
-                'min': market_avg * 0.8,
-                'max': market_avg * 1.4,  # Increased from 1.2
-                'description': f'Mid-range properties in {city}'
-            },
-            'premium': {
-                'min': market_avg * 1.4,  # Reduced from 1.2
-                'max': market_avg * 2.5,  # Increased from 2.0
-                'description': f'Premium properties in {city}'
+        if is_rental:
+            price_ranges = {
+                'budget': {
+                    'min': market_avg * 0.4,  # Reduced from 0.5
+                    'max': market_avg * 0.8,
+                    'description': f'Budget rental properties in {city}'
+                },
+                'mid_range': {
+                    'min': market_avg * 0.8,
+                    'max': market_avg * 1.4,  # Increased from 1.2
+                    'description': f'Mid-range rental properties in {city}'
+                },
+                'premium': {
+                    'min': market_avg * 1.4,  # Reduced from 1.2
+                    'max': market_avg * 2.5,  # Increased from 2.0
+                    'description': f'Premium rental properties in {city}'
+                }
+            }
+        else:
+            price_ranges = {
+                'budget': {
+                    'min': market_avg * 0.3,  # Reduced from 0.5
+                    'max': market_avg * 0.8,
+                    'description': f'Budget properties in {city}'
+                },
+                'mid_range': {
+                    'min': market_avg * 0.8,
+                    'max': market_avg * 1.4,  # Increased from 1.2
+                    'description': f'Mid-range properties in {city}'
+                },
+                'premium': {
+                    'min': market_avg * 1.4,  # Reduced from 1.2
+                    'max': market_avg * 2.5,  # Increased from 2.0
+                    'description': f'Premium properties in {city}'
+                }
             }
-        }
         
         # Determine price range
         price_range = "unknown"
@@ -616,6 +685,7 @@ def analyze_price(data, context_text=None, latitude=None, longitude=None, proper
             'location_price_assessment': f"Price analysis: {assessment}",
             'has_price': True,
             'has_sqft': True,
+            'is_rental': is_rental,
             'market_trends': {
                 'trend': market_data.get('market_trend', 'unknown') if market_data else 'unknown',
                 'growth_rate': market_data.get('growth_rate', 0) if market_data else 0,
@@ -626,7 +696,7 @@ def analyze_price(data, context_text=None, latitude=None, longitude=None, proper
             'price_factors': {
                 'market_average': market_avg,
                 'deviation_percentage': deviation,
-                'price_reasonableness': 'suspicious' if price_per_sqft < 100 else 'reasonable'
+                'price_reasonableness': 'suspicious' if price_per_sqft < (5 if is_rental else 50) else 'reasonable'
             },
             'risk_indicators': risk_indicators,
             'market_average': market_avg,
@@ -649,6 +719,7 @@ def analyze_price(data, context_text=None, latitude=None, longitude=None, proper
             'location_price_assessment': 'unknown',
             'has_price': False,
             'has_sqft': False,
+            'is_rental': False,
             'market_trends': {},
             'price_factors': {},
             'risk_indicators': [],