Update app.py

app.py

@@ -2,116 +2,172 @@ import gradio as gr
 import pandas as pd
 from transformers import pipeline
 import torch
-import PyPDF2
+import sys
+import logging
 import io
 
+# Setup logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Try importing PyPDF2
+try:
+    import PyPDF2
+    logger.info("PyPDF2 imported successfully")
+except ImportError as e:
+    logger.error(f"Error importing PyPDF2: {str(e)}")
+    logger.info("Falling back to text-only mode")
+    PyPDF2 = None
+
 class FinancialAnalyzer:
     def __init__(self):
-        """Initialize models"""
-        # 1. Llama 2 for strategic analysis
-        self.strategic_analyzer = pipeline(
-            "text-generation",
-            model="meta-llama/Llama-2-7b-chat-hf",
-            device_map="auto"
-        )
-        
-        # 2. FinBERT for financial sentiment
-        self.financial_analyzer = pipeline(
-            "text-classification",
-            model="ProsusAI/finbert",
-            return_all_scores=True
-        )
-        
-        # 3. Falcon for recommendations
-        self.recommendation_generator = pipeline(
-            "text-generation",
-            model="tiiuae/falcon-7b-instruct",
-            device_map="auto"
-        )
+        """Initialize models with error handling"""
+        try:
+            # 1. Llama 2 for strategic analysis
+            self.strategic_analyzer = pipeline(
+                "text-generation",
+                model="meta-llama/Llama-2-7b-chat-hf",
+                device_map="auto"
+            )
+            logger.info("Llama 2 initialized successfully")
+            
+            # 2. FinBERT for financial sentiment
+            self.financial_analyzer = pipeline(
+                "text-classification",
+                model="ProsusAI/finbert",
+                return_all_scores=True
+            )
+            logger.info("FinBERT initialized successfully")
+            
+            # 3. Falcon for recommendations
+            self.recommendation_generator = pipeline(
+                "text-generation",
+                model="tiiuae/falcon-7b-instruct",
+                device_map="auto"
+            )
+            logger.info("Falcon initialized successfully")
+            
+        except Exception as e:
+            logger.error(f"Error initializing models: {str(e)}")
+            raise
     
+    def read_file(self, file_obj):
+        """Safely read file content"""
+        try:
+            # If file_obj is a string (file path)
+            if isinstance(file_obj, str):
+                return open(file_obj, 'rb')
+            # If file_obj is bytes
+            elif isinstance(file_obj, bytes):
+                return io.BytesIO(file_obj)
+            # If file_obj is already a file object
+            elif hasattr(file_obj, 'read'):
+                return file_obj
+            else:
+                raise ValueError(f"Unsupported file object type: {type(file_obj)}")
+        except Exception as e:
+            logger.error(f"Error reading file: {str(e)}")
+            raise
+
     def extract_text_from_pdf(self, pdf_file):
-        """Extract text from PDF file"""
+        """Extract text from PDF file with fallback"""
+        if PyPDF2 is None:
+            logger.warning("PyPDF2 not available, skipping PDF processing")
+            return "PDF processing not available"
+            
         try:
-            pdf_reader = PyPDF2.PdfReader(pdf_file)
+            # Handle the file object properly
+            pdf_file_obj = self.read_file(pdf_file)
+            pdf_reader = PyPDF2.PdfReader(pdf_file_obj)
             text = ""
             for page in pdf_reader.pages:
                 text += page.extract_text() + "\n"
             return text
         except Exception as e:
-            print(f"Error extracting PDF text: {str(e)}")
-            return None
+            logger.error(f"Error extracting PDF text: {str(e)}")
+            return "Error processing PDF"
+
+    def read_csv_file(self, file_obj):
+        """Safely read CSV file"""
+        try:
+            # Handle the file object properly
+            if isinstance(file_obj, (str, bytes)):
+                return pd.read_csv(self.read_file(file_obj))
+            return pd.read_csv(file_obj)
+        except Exception as e:
+            logger.error(f"Error reading CSV file: {str(e)}")
+            raise
 
     def generate_strategic_analysis(self, financial_data, kpi_data=None):
         """Generate strategic analysis using Llama 2"""
-        # Include KPI data if available
-        kpi_section = f"\nKPI Information:\n{kpi_data}" if kpi_data else ""
-        
-        prompt = f"""[INST] As a senior financial analyst, analyze these financial statements and KPIs:
+        try:
+            # Include KPI data if available
+            kpi_section = f"\nKPI Information:\n{kpi_data}" if kpi_data else ""
+            
+            prompt = f"""[INST] As a senior financial analyst, analyze these financial statements:
 
-        Financial Data:
-        {financial_data}
-        {kpi_section}
+            Financial Data:
+            {financial_data}
+            {kpi_section}
 
-        Provide a comprehensive analysis including:
-        1. Business Health Assessment
-        2. Key Strategic Insights
-        3. Market Position Analysis
-        4. Growth Opportunities
-        5. Risk Factors
-        6. KPI Performance and Trends
-        7. Financial Ratio Analysis
-        8. Operational Efficiency Assessment [/INST]"""
-        
-        response = self.strategic_analyzer(
-            prompt,
-            max_length=1500,  # Increased for more comprehensive analysis
-            temperature=0.7
-        )
-        return response[0]['generated_text']
+            Provide:
+            1. Business Health Assessment
+            2. Key Strategic Insights
+            3. Market Position Analysis
+            4. Growth Opportunities
+            5. Risk Factors [/INST]"""
+            
+            response = self.strategic_analyzer(
+                prompt,
+                max_length=1000,
+                temperature=0.7
+            )
+            return response[0]['generated_text']
+        except Exception as e:
+            logger.error(f"Error in strategic analysis: {str(e)}")
+            return "Error generating strategic analysis"
     
     def analyze_sentiment(self, text):
         """Analyze financial sentiment using FinBERT"""
-        return self.financial_analyzer(text)
+        try:
+            return self.financial_analyzer(text)
+        except Exception as e:
+            logger.error(f"Error in sentiment analysis: {str(e)}")
+            return [{"label": "error", "score": 1.0}]
     
-    def generate_recommendations(self, analysis, kpi_data=None):
+    def generate_recommendations(self, analysis):
         """Generate recommendations using Falcon"""
-        kpi_context = f"\nKPI Context:\n{kpi_data}" if kpi_data else ""
-        
-        prompt = f"""Based on this financial analysis and KPI data:
-        {analysis}
-        {kpi_context}
-        
-        Provide specific, actionable recommendations covering:
-        1. Strategic Initiatives
-        2. Operational Improvements
-        3. Financial Management
-        4. Risk Mitigation
-        5. Growth Strategy
-        6. KPI Optimization
-        7. Performance Enhancement
-        8. Resource Allocation"""
-        
-        response = self.recommendation_generator(
-            prompt,
-            max_length=1000,
-            temperature=0.6
-        )
-        return response[0]['generated_text']
+        try:
+            prompt = f"""Based on this financial analysis:
+            {analysis}
+            
+            Provide specific, actionable recommendations covering:
+            1. Strategic Initiatives
+            2. Operational Improvements
+            3. Financial Management
+            4. Risk Mitigation
+            5. Growth Strategy"""
+            
+            response = self.recommendation_generator(
+                prompt,
+                max_length=800,
+                temperature=0.6
+            )
+            return response[0]['generated_text']
+        except Exception as e:
+            logger.error(f"Error generating recommendations: {str(e)}")
+            return "Error generating recommendations"
 
 def analyze_financial_statements(income_statement, balance_sheet, kpi_pdf=None):
-    """Main analysis function"""
+    """Main analysis function with error handling"""
     try:
-        # Read financial statements
-        income_df = pd.read_csv(income_statement.name)
-        balance_df = pd.read_csv(balance_sheet.name)
-        
         # Initialize analyzer
         analyzer = FinancialAnalyzer()
         
-        # Extract KPI data if provided
-        kpi_data = None
-        if kpi_pdf:
-            kpi_data = analyzer.extract_text_from_pdf(kpi_pdf.name)
+        # Read CSV files safely
+        logger.info("Reading input files...")
+        income_df = analyzer.read_csv_file(income_statement)
+        balance_df = analyzer.read_csv_file(balance_sheet)
         
         # Prepare financial data
         financial_data = f"""
@@ -122,47 +178,61 @@ def analyze_financial_statements(income_statement, balance_sheet, kpi_pdf=None):
         {balance_df.to_string()}
         """
         
-        # Generate strategic analysis
-        strategic_analysis = analyzer.generate_strategic_analysis(financial_data, kpi_data)
+        # Process KPI PDF if provided
+        kpi_data = None
+        if kpi_pdf is not None:
+            logger.info("Processing KPI PDF...")
+            kpi_data = analyzer.extract_text_from_pdf(kpi_pdf)
         
-        # Analyze sentiment
+        # Generate analyses
+        logger.info("Generating analysis...")
+        strategic_analysis = analyzer.generate_strategic_analysis(financial_data, kpi_data)
         sentiment = analyzer.analyze_sentiment(strategic_analysis)
-        
-        # Generate recommendations
-        recommendations = analyzer.generate_recommendations(strategic_analysis, kpi_data)
+        recommendations = analyzer.generate_recommendations(strategic_analysis)
         
         # Format output
-        output = format_results(strategic_analysis, sentiment, recommendations, kpi_data)
-        
-        return output
+        logger.info("Formatting results...")
+        return format_results(strategic_analysis, sentiment, recommendations, kpi_data)
         
     except Exception as e:
-        return f"Error analyzing files: {str(e)}"
+        logger.error(f"Error in analysis: {str(e)}")
+        return f"""Error analyzing files: {str(e)}
+        
+Please check:
+1. Files are in correct format (CSV for financial statements, PDF for KPI)
+2. Files are not corrupted
+3. Files contain the expected data
+
+If the problem persists, try uploading the files again."""
 
 def format_results(analysis, sentiment, recommendations, kpi_data=None):
     """Format analysis results"""
-    output = "# Financial Analysis Report\n\n"
-    
-    # Strategic Analysis
-    output += "## Strategic Analysis\n\n"
-    output += analysis.split('[/INST]')[-1].strip() + "\n\n"
-    
-    # KPI Analysis (if available)
-    if kpi_data:
-        output += "## KPI Analysis\n\n"
-        output += "Analysis includes KPI data from provided documentation.\n\n"
-    
-    # Sentiment Analysis
-    output += "## Market Sentiment\n\n"
-    for score in sentiment[0]:
-        output += f"- {score['label']}: {score['score']:.2%}\n"
-    output += "\n"
-    
-    # Recommendations
-    output += "## Strategic Recommendations\n\n"
-    output += recommendations
-    
-    return output
+    try:
+        output = "# Financial Analysis Report\n\n"
+        
+        # Strategic Analysis
+        output += "## Strategic Analysis\n\n"
+        output += analysis + "\n\n"
+        
+        # Sentiment Analysis
+        output += "## Market Sentiment\n\n"
+        for score in sentiment[0]:
+            output += f"- {score['label']}: {score['score']:.2%}\n"
+        output += "\n"
+        
+        # Recommendations
+        output += "## Strategic Recommendations\n\n"
+        output += recommendations
+        
+        # KPI Analysis (if available)
+        if kpi_data:
+            output += "\n\n## KPI Analysis\n\n"
+            output += "KPI data was included in the analysis.\n"
+        
+        return output
+    except Exception as e:
+        logger.error(f"Error formatting results: {str(e)}")
+        return "Error formatting analysis results"
 
 # Create Gradio interface
 iface = gr.Interface(
@@ -170,28 +240,29 @@ iface = gr.Interface(
     inputs=[
         gr.File(label="Income Statement (CSV)"),
         gr.File(label="Balance Sheet (CSV)"),
-        gr.File(label="KPI Documentation (PDF, Optional)", file_types=[".pdf"])
+        gr.File(label="KPI Documentation (PDF, Optional)", 
+               file_types=[".pdf"], 
+               optional=True)
     ],
     outputs=gr.Markdown(),
     title="AI-Powered Financial Statement Analysis",
-    description="""Upload your financial statements and optional KPI documentation for comprehensive analysis using:
+    description="""Upload your financial statements for comprehensive analysis using:
     - Llama 2: Strategic Analysis
     - FinBERT: Financial Sentiment Analysis
-    - Falcon: Strategic Recommendations
-    
-    Supports:
-    - Income Statement (CSV)
-    - Balance Sheet (CSV)
-    - KPI Documentation (PDF)""",
+    - Falcon: Strategic Recommendations""",
     examples=[
         [
             "OFINTECH-Income Statement-template.csv",
             "OFINTECH Balance Sheet template.csv",
-            None  # Optional KPI PDF
+            None
         ]
     ]
 )
 
 # Launch the interface
 if __name__ == "__main__":
-    iface.launch()
+    try:
+        iface.launch()
+    except Exception as e:
+        logger.error(f"Error launching application: {str(e)}")
+        sys.exit(1)