Update response_formatter.py

response_formatter.py

@@ -13,45 +13,61 @@ class ResponseFormatter:
         response += "\n\n"
         
         # Data Preparation
-        response += "## 1. Data Preparation\n\n"
-        response += ResponseFormatter._generate_data_section(analysis_results)
-        response += "\n\n"
+        if "data_preparation" in analysis_results:
+            response += "## 1. Data Preparation\n\n"
+            response += ResponseFormatter._format_data_preparation(analysis_results["data_preparation"])
+            response += "\n\n"
         
-        # Analysis Sections
+        # Facility Distribution Analysis
         if "facility_distribution" in analysis_results:
             response += "## 2. Facility Distribution Analysis\n\n"
             response += ResponseFormatter._format_facility_distribution(analysis_results["facility_distribution"])
             response += "\n\n"
         
+        # Capacity Analysis
         if "capacity_analysis" in analysis_results:
             response += "## 3. Capacity Analysis\n\n"
             response += ResponseFormatter._format_capacity_analysis(analysis_results["capacity_analysis"])
             response += "\n\n"
         
+        # Long-Term Care Assessment
+        if "long_term_care_assessment" in analysis_results:
+            response += "## 4. Long-Term Care Capacity Assessment\n\n"
+            response += ResponseFormatter._format_long_term_care_assessment(analysis_results["long_term_care_assessment"])
+            response += "\n\n"
+        
+        # Resource Allocation Analysis
         if "resource_allocation" in analysis_results:
-            response += "## 4. Resource Allocation Analysis\n\n"
+            response += "## 5. Resource Allocation Analysis\n\n"
             response += ResponseFormatter._format_resource_allocation(analysis_results["resource_allocation"])
             response += "\n\n"
         
+        # Trend Analysis
         if "trends" in analysis_results:
-            response += "## 5. Trend Analysis\n\n"
+            response += "## 6. Trend Analysis\n\n"
             response += ResponseFormatter._format_trends(analysis_results["trends"])
             response += "\n\n"
         
-        # Recommendations
+        # Operational Recommendations
         if "recommendations" in analysis_results:
-            response += "## 6. Operational Recommendations\n\n"
+            response += "## 7. Operational Recommendations\n\n"
             response += ResponseFormatter._format_recommendations(analysis_results["recommendations"])
             response += "\n\n"
         
         # Future Integration
         if "future_integration" in analysis_results:
-            response += "## 7. Future Integration Opportunities\n\n"
+            response += "## 8. Future Integration Opportunities\n\n"
             response += ResponseFormatter._format_integration_opportunities(analysis_results["future_integration"])
             response += "\n\n"
         
+        # Validation Results
+        if "validation" in analysis_results:
+            response += "## 9. Analysis Validation\n\n"
+            response += ResponseFormatter._format_validation_results(analysis_results["validation"])
+            response += "\n\n"
+        
         # Provenance
-        response += "## 8. Provenance\n\n"
+        response += "## 10. Provenance\n\n"
         response += "This analysis is based on:\n"
         response += "- Scenario description provided by the user\n"
         response += "- Uploaded data files\n"
@@ -83,6 +99,10 @@ class ResponseFormatter:
             if high_priority:
                 summary.append(f"{len(high_priority)} high-priority recommendations identified")
         
+        if "validation" in results:
+            completion_rate = results["validation"].get("completion_rate", 0)
+            summary.append(f"Analysis completion rate: {completion_rate:.1%}")
+        
         return " | ".join(summary) if summary else "No key metrics identified"
     
     @staticmethod
@@ -112,6 +132,90 @@ class ResponseFormatter:
         response += "\nData quality checks and transformations were applied to ensure accuracy and consistency."
         return response
     
+    @staticmethod
+    def _format_data_preparation(data_prep_results: Dict[str, Any]) -> str:
+        """Format data preparation results"""
+        response = ""
+        
+        if "total_facilities" in data_prep_results:
+            response += f"**Total Facilities Analyzed**: {data_prep_results['total_facilities']:,}\n\n"
+        
+        if "facility_type_frequency" in data_prep_results:
+            response += "### Facility Type Frequency\n\n"
+            response += "| Facility Type | Count |\n"
+            response += "|---------------|-------|\n"
+            for ftype, count in data_prep_results["facility_type_frequency"].items():
+                response += f"| {ftype} | {count} |\n"
+            response += "\n"
+        
+        if "top_cities" in data_prep_results and "city_facility_breakdown" in data_prep_results:
+            response += "### Top Cities by Facility Count\n\n"
+            response += "| City | Hospitals | Nursing/Residential | Ambulatory | Total |\n"
+            response += "|------|-----------|-------------------|------------|-------|\n"
+            
+            for city in data_prep_results["top_cities"]:
+                if city in data_prep_results["city_facility_breakdown"]:
+                    breakdown = data_prep_results["city_facility_breakdown"][city]
+                    hospitals = breakdown.get("Hospitals", 0)
+                    nursing = breakdown.get("Nursing and residential care facilities", 0)
+                    ambulatory = breakdown.get("Ambulatory health care services", 0)
+                    total = hospitals + nursing + ambulatory
+                    response += f"| {city} | {hospitals} | {nursing} | {ambulatory} | {total} |\n"
+            
+            response += "\n"
+        
+        return response if response else "No data preparation results available"
+    
+    @staticmethod
+    def _format_long_term_care_assessment(ltc_results: Dict[str, Any]) -> str:
+        """Format long-term care assessment results"""
+        response = ""
+        
+        if "zone_with_largest_decrease" in ltc_results:
+            response += f"**Zone with Largest Percentage Decrease**: {ltc_results['zone_with_largest_decrease']}\n\n"
+        
+        if "major_city" in ltc_results:
+            response += f"**Major City in Zone**: {ltc_results['major_city']}\n\n"
+        
+        if "facility_counts" in ltc_results:
+            counts = ltc_results["facility_counts"]
+            response += "### Facility Counts in Major City\n\n"
+            response += f"- Hospitals: {counts['hospitals']}\n"
+            response += f"- Nursing/Residential Care Facilities: {counts['nursing_residential_care']}\n"
+            response += f"- Ambulatory Health Services: {counts['ambulatory']}\n\n"
+        
+        if "nursing_to_hospital_ratio" in ltc_results:
+            ratio = ltc_results["nursing_to_hospital_ratio"]
+            response += f"**Nursing/Residential to Hospital Ratio**: {ratio:.2f}\n\n"
+        
+        if "capacity_assessment" in ltc_results:
+            assessment = ltc_results["capacity_assessment"]
+            response += f"**Long-Term Care Capacity Assessment**: {assessment.upper()}\n\n"
+            
+            if assessment == "insufficient":
+                response += "The ratio of nursing/residential care facilities to hospitals is below the recommended threshold of 1.5. "
+                response += "This indicates insufficient long-term care capacity to support the healthcare system in this area.\n\n"
+            else:
+                response += "The ratio of nursing/residential care facilities to hospitals meets or exceeds the recommended threshold. "
+                response += "This indicates sufficient long-term care capacity.\n\n"
+        
+        return response if response else "No long-term care assessment results available"
+    
+    @staticmethod
+    def _format_validation_results(validation: Dict[str, Any]) -> str:
+        """Format validation results"""
+        response = f"**Analysis Completion Rate**: {validation['completion_rate']:.1%}\n\n"
+        
+        if validation["all_tasks_completed"]:
+            response += "✅ All required tasks were completed successfully.\n\n"
+        else:
+            response += "⚠️ The following tasks were not completed:\n\n"
+            for task in validation["missing_tasks"]:
+                response += f"- {task}\n"
+            response += "\n"
+        
+        return response
+    
     @staticmethod
     def _format_facility_distribution(dist_results: Dict[str, Any]) -> str:
         """Format facility distribution analysis results"""
@@ -200,173 +304,180 @@ class ResponseFormatter:
             
             if "capacity_growth_rate" in capacity_results:
                 growth = capacity_results["capacity_growth_rate"]
-                response += f"**Overall Growth Rate**: {growth:.1f}%\n\n"
-        
-        if "zone_summary" in capacity_results:
-            response += "### Bed Capacity by Zone\n\n"
-            response += "| Zone | Current Beds | Previous Beds | Absolute Change | Percentage Change |\n"
-            response += "|------|--------------|---------------|-----------------|-------------------|\n"
-            
-            for zone_data in capacity_results["zone_summary"]:
-                # Extract zone name - try different possible keys
-                zone_name = "Unknown"
-                for key in ["zone", "Zone", "ZONE", "region", "Region", "REGION"]:
-                    if key in zone_data:
-                        zone_name = zone_data[key]
-                        break
-                
-                # Extract bed counts
-                current_beds = zone_data.get("beds_current", zone_data.get("current", "N/A"))
-                prev_beds = zone_data.get("beds_prev", zone_data.get("previous", "N/A"))
-                abs_change = zone_data.get("bed_change", "N/A")
-                pct_change = zone_data.get("percent_change", "N/A")
-                
-                response += f"| {zone_name} | {current_beds} | {prev_beds} | {abs_change} | {pct_change:.1f}% |\n"
-            
-            response += "\n"
-        
-        if "max_absolute_decrease" in capacity_results and isinstance(capacity_results["max_absolute_decrease"], dict):
-            response += "### Zone with Largest Absolute Decrease\n\n"
-            max_abs = capacity_results["max_absolute_decrease"]
-            
-            # Extract zone name
-            zone_name = "Unknown"
-            for key in ["zone", "Zone", "ZONE", "region", "Region", "REGION"]:
-                if key in max_abs:
-                    zone_name = max_abs[key]
-                    break
-            
-            # Extract values
-            abs_change = max_abs.get("bed_change", "N/A")
-            pct_change = max_abs.get("percent_change", "N/A")
-            
-            response += f"**Zone**: {zone_name}\n"
-            response += f"**Absolute Decrease**: {abs_change} beds\n"
-            response += f"**Percentage Decrease**: {pct_change:.1f}%\n\n"
-        
-        if "max_percentage_decrease" in capacity_results and isinstance(capacity_results["max_percentage_decrease"], dict):
-            response += "### Zone with Largest Percentage Decrease\n\n"
-            max_pct = capacity_results["max_percentage_decrease"]
-            
-            # Extract zone name
-            zone_name = "Unknown"
-            for key in ["zone", "Zone", "ZONE", "region", "Region", "REGION"]:
-                if key in max_pct:
-                    zone_name = max_pct[key]
-                    break
-            
-            # Extract values
-            abs_change = max_pct.get("bed_change", "N/A")
-            pct_change = max_pct.get("percent_change", "N/A")
-            
-            response += f"**Zone**: {zone_name}\n"
-            response += f"**Absolute Decrease**: {abs_change} beds\n"
-            response += f"**Percentage Decrease**: {pct_change:.1f}%\n\n"
-        
-        if "facilities_with_largest_declines" in capacity_results:
-            response += "### Facilities with Largest Bed Declines\n\n"
-            response += "| Facility | Zone | Teaching Status | Beds Lost |\n"
-            response += "|----------|------|----------------|-----------|\n"
-            
-            for facility in capacity_results["facilities_with_largest_declines"]:
-                name = facility.get("facility_name", "N/A")
-                
-                # Extract zone name
-                zone_name = "Unknown"
-                for key in ["zone", "Zone", "ZONE", "region", "Region", "REGION"]:
-                    if key in facility:
-                        zone_name = facility[key]
-                        break
-                
-                teaching = facility.get("teaching_status", "N/A")
-                change = facility.get("bed_change", "N/A")
-                
-                response += f"| {name} | {zone_name} | {teaching} | {change} |\n"
-            
-            response += "\n"
+                response += f"**Annual Growth Rate**: {growth:.1%}\n\n"
         
-        return response if response else "No capacity data available"
+        return response if response else "No capacity analysis data available"
     
     @staticmethod
-    def _format_resource_allocation(resource_results: Dict[str, Any]) -> str:
-        """Format resource allocation results"""
+    def _format_resource_allocation(allocation_results: Dict[str, Any]) -> str:
+        """Format resource allocation analysis results"""
         response = ""
         
-        if "total_staff" in resource_results:
-            response += f"**Total Staff**: {resource_results['total_staff']:,} FTEs\n\n"
+        if "total_resources" in allocation_results:
+            response += f"**Total Resources**: {allocation_results['total_resources']:,} units\n\n"
         
-        if "staff_per_bed_ratio" in resource_results:
-            ratio = resource_results["staff_per_bed_ratio"]
-            response += f"**Staff per Bed Ratio**: {ratio:.2f}\n\n"
-            
-            if ratio < 1.5:
-                response += "⚠️ This ratio is below recommended levels\n\n"
+        if "allocation_by_facility" in allocation_results:
+            response += "### Allocation by Facility Type\n\n"
+            response += "| Facility Type | Resource Count | Percentage |\n"
+            response += "|---------------|----------------|------------|\n"
+            for ftype, count in allocation_results["allocation_by_facility"].items():
+                percentage = count / allocation_results.get("total_resources", 1) * 100
+                response += f"| {ftype} | {count:,} | {percentage:.1f}% |\n"
+            response += "\n"
+        
+        if "allocation_by_region" in allocation_results:
+            response += "### Allocation by Region\n\n"
+            response += "| Region | Resource Count | Percentage |\n"
+            response += "|--------|----------------|------------|\n"
+            for region, count in allocation_results["allocation_by_region"].items():
+                percentage = count / allocation_results.get("total_resources", 1) * 100
+                response += f"| {region} | {count:,} | {percentage:.1f}% |\n"
+            response += "\n"
         
-        if "equipment_summary" in resource_results:
-            response += "### Equipment Summary\n\n"
-            for equipment, count in resource_results["equipment_summary"].items():
-                response += f"- {equipment}: {count:,}\n"
+        if "efficiency_metrics" in allocation_results:
+            response += "### Efficiency Metrics\n\n"
+            response += "| Metric | Value |\n"
+            response += "|--------|-------|\n"
+            for metric, value in allocation_results["efficiency_metrics"].items():
+                if isinstance(value, float):
+                    response += f"| {metric} | {value:.2f} |\n"
+                else:
+                    response += f"| {metric} | {value} |\n"
             response += "\n"
         
         return response if response else "No resource allocation data available"
     
     @staticmethod
-    def _format_trends(trend_results: Dict[str, Any]) -> str:
+    def _format_trends(trends_results: Dict[str, Any]) -> str:
         """Format trend analysis results"""
         response = ""
         
-        if "year_over_year_trends" in trend_results:
-            response += "### Year-over-Year Changes\n\n"
-            response += "| Period | Absolute Change | Percentage Change |\n"
-            response += "|--------|-----------------|-------------------|\n"
-            
-            for period, change in trend_results["year_over_year_trends"].items():
-                abs_change = change["absolute_change"]
-                pct_change = change["percentage_change"]
-                response += f"| {period} | {abs_change:+,} | {pct_change:+.1f}% |\n"
+        if "summary" in trends_results:
+            response += f"**Trend Summary**: {trends_results['summary']}\n\n"
+        
+        if "facility_growth" in trends_results:
+            response += "### Facility Growth Trends\n\n"
+            response += "| Year | Facility Count | Growth Rate |\n"
+            response += "|------|----------------|-------------|\n"
+            prev_count = None
+            for year, count in trends_results["facility_growth"].items():
+                if prev_count is not None:
+                    growth_rate = (count - prev_count) / prev_count
+                    response += f"| {year} | {count:,} | {growth_rate:.1%} |\n"
+                else:
+                    response += f"| {year} | {count:,} | N/A |\n"
+                prev_count = count
             response += "\n"
         
+        if "capacity_trends" in trends_results:
+            response += "### Capacity Trends\n\n"
+            response += "| Year | Total Capacity | Growth Rate |\n"
+            response += "|------|----------------|-------------|\n"
+            prev_capacity = None
+            for year, capacity in trends_results["capacity_trends"].items():
+                if prev_capacity is not None:
+                    growth_rate = (capacity - prev_capacity) / prev_capacity
+                    response += f"| {year} | {capacity:,} | {growth_rate:.1%} |\n"
+                else:
+                    response += f"| {year} | {capacity:,} | N/A |\n"
+                prev_capacity = capacity
+            response += "\n"
+        
+        if "utilization_trends" in trends_results:
+            response += "### Utilization Trends\n\n"
+            response += "| Year | Average Utilization |\n"
+            response += "|------|---------------------|\n"
+            for year, utilization in trends_results["utilization_trends"].items():
+                response += f"| {year} | {utilization:.1%} |\n"
+            response += "\n"
+        
+        if "forecast" in trends_results:
+            response += "### Forecast\n\n"
+            response += trends_results["forecast"] + "\n\n"
+        
         return response if response else "No trend data available"
     
     @staticmethod
-    def _format_recommendations(recommendations: List[Dict[str, str]]) -> str:
+    def _format_recommendations(recommendations_results: List[Dict[str, Any]]) -> str:
         """Format operational recommendations"""
-        if not recommendations:
-            return "No specific recommendations generated"
-        
         response = ""
-        for i, rec in enumerate(recommendations, 1):
-            response += f"### {i}. {rec['title']}\n\n"
-            response += f"**Priority**: {rec.get('priority', 'Medium')}\n\n"
-            response += f"{rec['description']}\n\n"
-            response += f"*Data source: {rec.get('data_source', 'Analysis results')}*\n\n"
+        
+        if not recommendations_results:
+            return "No recommendations available"
+        
+        # Group by priority
+        high_priority = [r for r in recommendations_results if r.get("priority") == "High"]
+        medium_priority = [r for r in recommendations_results if r.get("priority") == "Medium"]
+        low_priority = [r for r in recommendations_results if r.get("priority") == "Low"]
+        
+        if high_priority:
+            response += "### High Priority Recommendations\n\n"
+            for i, rec in enumerate(high_priority, 1):
+                response += f"**{i}. {rec.get('title', 'Recommendation')}**\n\n"
+                response += f"{rec.get('description', '')}\n\n"
+                if "expected_impact" in rec:
+                    response += f"Expected Impact: {rec['expected_impact']}\n\n"
+                if "implementation" in rec:
+                    response += f"Implementation: {rec['implementation']}\n\n"
+                response += "---\n\n"
+        
+        if medium_priority:
+            response += "### Medium Priority Recommendations\n\n"
+            for i, rec in enumerate(medium_priority, 1):
+                response += f"**{i}. {rec.get('title', 'Recommendation')}**\n\n"
+                response += f"{rec.get('description', '')}\n\n"
+                if "expected_impact" in rec:
+                    response += f"Expected Impact: {rec['expected_impact']}\n\n"
+                if "implementation" in rec:
+                    response += f"Implementation: {rec['implementation']}\n\n"
+                response += "---\n\n"
+        
+        if low_priority:
+            response += "### Low Priority Recommendations\n\n"
+            for i, rec in enumerate(low_priority, 1):
+                response += f"**{i}. {rec.get('title', 'Recommendation')}**\n\n"
+                response += f"{rec.get('description', '')}\n\n"
+                if "expected_impact" in rec:
+                    response += f"Expected Impact: {rec['expected_impact']}\n\n"
+                if "implementation" in rec:
+                    response += f"Implementation: {rec['implementation']}\n\n"
+                response += "---\n\n"
         
         return response
     
     @staticmethod
-    def _format_integration_opportunities(opportunities: Dict[str, Any]) -> str:
+    def _format_integration_opportunities(integration_results: Dict[str, Any]) -> str:
         """Format future integration opportunities"""
         response = ""
         
-        if "data_integration" in opportunities:
-            response += "### Data Integration Opportunities\n\n"
-            for opp in opportunities["data_integration"]:
-                response += f"**{opp['opportunity']}**\n\n"
-                response += f"{opp['description']}\n\n"
-                response += f"*Expected benefit: {opp['benefit']}*\n\n"
-        
-        if "ai_applications" in opportunities:
-            response += "### AI Application Opportunities\n\n"
-            for opp in opportunities["ai_applications"]:
-                response += f"**{opp['opportunity']}**\n\n"
-                response += f"{opp['description']}\n\n"
-                response += f"*Expected benefit: {opp['benefit']}*\n\n"
-        
-        if "enhanced_metrics" in opportunities:
-            response += "### Enhanced Metrics\n\n"
-            for metric in opportunities["enhanced_metrics"]:
-                response += f"**{metric['metric']}**\n\n"
-                response += f"{metric['description']}\n\n"
-                response += f"*Expected benefit: {metric['benefit']}*\n\n"
+        if "summary" in integration_results:
+            response += f"**Integration Summary**: {integration_results['summary']}\n\n"
+        
+        if "opportunities" in integration_results:
+            response += "### Integration Opportunities\n\n"
+            for i, opp in enumerate(integration_results["opportunities"], 1):
+                response += f"**{i}. {opp.get('title', 'Opportunity')}**\n\n"
+                response += f"{opp.get('description', '')}\n\n"
+                if "benefits" in opp:
+                    response += "**Benefits:**\n"
+                    for benefit in opp["benefits"]:
+                        response += f"- {benefit}\n"
+                    response += "\n"
+                if "challenges" in opp:
+                    response += "**Challenges:**\n"
+                    for challenge in opp["challenges"]:
+                        response += f"- {challenge}\n"
+                    response += "\n"
+                if "timeline" in opp:
+                    response += f"**Timeline:** {opp['timeline']}\n\n"
+                response += "---\n\n"
+        
+        if "roadmap" in integration_results:
+            response += "### Integration Roadmap\n\n"
+            response += "| Phase | Activities | Timeline |\n"
+            response += "|-------|------------|----------|\n"
+            for phase in integration_results["roadmap"]:
+                response += f"| {phase['name']} | {phase['activities']} | {phase['timeline']} |\n"
+            response += "\n"
         
         return response if response else "No integration opportunities identified"