Add success rate to PDF codebook summary

app.py

@@ -58,7 +58,7 @@ def is_free_model(model, model_tier):
     return model_tier == "Free Models"
 
 
-def generate_codebook_pdf(categories, model, column_name, num_rows, model_source, filename):
+def generate_codebook_pdf(categories, model, column_name, num_rows, model_source, filename, success_rate):
     """Generate a PDF codebook explaining the output columns."""
     from reportlab.lib.pagesizes import letter
     from reportlab.lib import colors
@@ -89,6 +89,7 @@ def generate_codebook_pdf(categories, model, column_name, num_rows, model_source
         ["Model Used", model],
         ["Rows Classified", str(num_rows)],
         ["Number of Categories", str(len(categories))],
+        ["Success Rate", f"{success_rate:.2f}%"],
     ]
     summary_table = Table(summary_data, colWidths=[150, 300])
     summary_table.setStyle(TableStyle([
@@ -326,8 +327,15 @@ def classify_data(spreadsheet_file, spreadsheet_column,
         # Get original filename for codebook
         original_filename = file_path.split("/")[-1]
 
+        # Calculate success rate
+        if 'processing_status' in result.columns:
+            success_count = (result['processing_status'] == 'success').sum()
+            success_rate = (success_count / len(result)) * 100
+        else:
+            success_rate = 100.0
+
         # Generate PDF codebook
-        pdf_path = generate_codebook_pdf(categories, actual_model, spreadsheet_column, len(input_data), model_source, original_filename)
+        pdf_path = generate_codebook_pdf(categories, actual_model, spreadsheet_column, len(input_data), model_source, original_filename, success_rate)
 
         return result, [csv_path, pdf_path], f"**Success!** Classified {len(input_data)} responses"