Enhance aggregation script to support annual reports

docs/README.md

@@ -111,6 +111,12 @@ python aggregate_by_month.py
 
 # Specify input and output directories
 python aggregate_by_month.py --input-dir /path/to/csv --output-dir /path/to/reports
+
+# Create annual reports
+python aggregate_by_month.py --annual
+
+# Create annual report for a specific year
+python aggregate_by_month.py --annual --year 2025
 ```
 
 ## Output

output/reports/annual_report_2025.csv

@@ -0,0 +1,6 @@
+Category,Transaction Count,Total Amount,Percentage
+Other,35,8531.95,79.42%
+Internal Transfer,12,1650.0,15.36%
+Loan Repayment,3,450.0,4.19%
+Google Services,1,77.64,0.72%
+Bank Fees,11,33.0,0.31%

output/reports/annual_transactions_2025.csv

@@ -0,0 +1,63 @@
+Date,Description,Category,Amount,Institution,Source
+02/01/2025,AGIOS/FRAIS,Other,18.48,Monabanq,Extrait de comptes au 2025-01-31.pdf
+08/01/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-01-31.pdf
+04/02/2025,PRLV SEPA URSSAF D'ILE DE FRANC,Other,35.0,Monabanq,Extrait de comptes au 2025-02-28.pdf
+07/02/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-02-28.pdf
+27/02/2025,VIR INST MR BATAILLE KEVIN,Other,700.0,Monabanq,Extrait de comptes au 2025-02-28.pdf
+06/03/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-03-31.pdf
+06/03/2025,VIR SEPA BOURSORAMA PERSO,Other,100.0,Monabanq,Extrait de comptes au 2025-03-31.pdf
+06/03/2025,VIR SEPA INTERNE,Other,200.0,Monabanq,Extrait de comptes au 2025-03-31.pdf
+12/03/2025,VIR INST BATAILLE KEVIN (REVOLU,Other,100.0,Monabanq,Extrait de comptes au 2025-03-31.pdf
+12/03/2025,VIR INST BOURSORAMA PERSO,Other,230.0,Monabanq,Extrait de comptes au 2025-03-31.pdf
+24/03/2025,GOOGLE IRELAND LTD,Google Services,77.64,Monabanq,Extrait de comptes au 2025-03-31.pdf
+04/04/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-04-30.pdf
+07/04/2025,VIR INST MR BATAILLE KEVIN,Other,200.0,Monabanq,Extrait de comptes au 2025-04-30.pdf
+11/04/2025,VIR INST BOURSORAMA PERSO,Other,333.34,Monabanq,Extrait de comptes au 2025-04-30.pdf
+29/04/2025,VIR AMAZON EUROPE CORE S.A R,Other,25.77,Monabanq,Extrait de comptes au 2025-04-30.pdf
+05/05/2025,PRLV SEPA URSSAF D ILE DE FRANC,Other,18.0,Monabanq,Extrait de comptes au 2025-06-02.pdf
+05/05/2025,VIR MR BATAILLE KEVIN,Internal Transfer,0.0,Monabanq,Extrait de comptes au 2025-06-02.pdf
+08/05/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-06-02.pdf
+04/06/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-06-30.pdf
+05/06/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-06-30.pdf
+03/07/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-07-31.pdf
+07/07/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-07-31.pdf
+09/07/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-07-31.pdf
+11/07/2025,VIR INST BOURSORAMA PERSO,Other,761.24,Monabanq,Extrait de comptes au 2025-07-31.pdf
+11/07/2025,VIR INST KEVIN BATAILLE,Other,700.09,Monabanq,Extrait de comptes au 2025-07-31.pdf
+29/07/2025,VIR INST KEVIN BATAILLE,Other,107.78,Monabanq,Extrait de comptes au 2025-07-31.pdf
+29/08/2025,VIR INST BATAILLE KEVIN (REVOLU,Other,120.0,Monabanq,Extrait de comptes au 2025-09-01.pdf
+29/08/2025,VIR SEPA BOURSORAMA PERSO,Other,280.0,Monabanq,Extrait de comptes au 2025-09-01.pdf
+03/09/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+04/09/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+07/09/2025,VIR INST BATAILLE KEVIN,Other,250.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+07/09/2025,VIR INST BOURSORAMA PERSO,Other,800.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+09/09/2025,VIR INST BATAILLE KEVIN,Other,200.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+10/09/2025,VIR INST KEVIN BATAILLE,Other,200.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+11/09/2025,VIR INST BOURSORAMA PERSO,Other,247.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+11/09/2025,VIR INST KEVIN BATAILLE,Other,200.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+11/09/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+14/09/2025,VIR INST BATAILLE KEVIN (REVOLU,Other,130.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+14/09/2025,VIR INST KEVIN BATAILLE,Other,270.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+21/09/2025,VIR INST BATAILLE KEVIN (REVOLU,Other,100.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+21/09/2025,VIR INST BATAILLE KEVIN (REVOLU,Other,100.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+23/09/2025,VIR INST BOURSORAMA PERSO,Other,200.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+26/09/2025,VIR INST BOURSORAMA PERSO,Other,350.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+30/09/2025,VIR INST BOURSORAMA PERSO,Other,300.0,Monabanq,Extrait de comptes au 2025-09-30.pdf
+03/10/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+04/10/2025,ECH PRET 28943002099054,Loan Repayment,150.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+06/10/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+08/10/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+12/10/2025,VIR INST BOURSORAMA PERSO,Other,700.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+23/10/2025,VIR INST BOURSORAMA PERSO,Other,100.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+23/10/2025,VIR INST KEVIN BATAILLE,Other,100.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+29/10/2025,VIR INST BOURSORAMA PERSO,Other,90.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+30/10/2025,VIR INST BOURSORAMA PERSO,Other,40.0,Monabanq,Extrait de comptes au 2025-10-31.pdf
+04/11/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-12-01.pdf
+06/11/2025,ECH PRET 28943002099054,Loan Repayment,150.0,Monabanq,Extrait de comptes au 2025-12-01.pdf
+07/11/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-12-01.pdf
+10/11/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-12-01.pdf
+03/12/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-12-31.pdf
+04/12/2025,F COTIS PRATIQ+,Bank Fees,3.0,Monabanq,Extrait de comptes au 2025-12-31.pdf
+06/12/2025,ECH PRET 28943002099054,Loan Repayment,150.0,Monabanq,Extrait de comptes au 2025-12-31.pdf
+09/12/2025,VIR MR BATAILLE KEVIN,Internal Transfer,150.0,Monabanq,Extrait de comptes au 2025-12-31.pdf
+25/12/2025,VIR INST MR BATAILLE KEVIN,Other,225.25,Monabanq,Extrait de comptes au 2025-12-31.pdf

output/reports/monthly_summary.csv

@@ -1,28 +1,2 @@
 Year,Month,Total Income,Total Expenses,Net Balance,Transaction Count,Institutions
-25,January,0,0,0,1,SNCF
+2026,February,0,19534.26,19534.26,318,American Express
-25,February,0,0,0,1,SNCF
-25,March,0,0,0,1,SNCF
-25,April,0,0,0,1,SNCF
-25,May,0,0,0,1,SNCF
-25,June,0,0,0,1,SNCF
-25,July,0,0,0,1,SNCF
-25,August,0,0,0,1,SNCF
-25,September,0,0,0,1,SNCF
-25,October,0,0,0,1,SNCF
-25,November,0,0,0,1,SNCF
-25,December,0,0,0,1,SNCF
-26,January,0,0,0,1,SNCF
-2025,January,0,21.48,21.48,2,Monabanq
-2025,February,0,738.0,738.0,3,Monabanq
-2025,March,0,710.64,710.64,6,Monabanq
-2025,April,0,562.11,562.11,4,Monabanq
-2025,May,0,21.0,21.0,3,Monabanq
-2025,June,0,153.0,153.0,2,Monabanq
-2025,July,0,1872.1100000000001,1872.1100000000001,6,Monabanq
-2025,August,0,400.0,400.0,2,Monabanq
-2025,September,0,3650.0,3650.0,16,Monabanq
-2025,October,0,1483.0,1483.0,9,Monabanq
-2025,November,0,453.0,453.0,4,Monabanq
-2025,December,0,678.25,678.25,5,Monabanq
-2026,January,0,523.9300000000001,523.9300000000001,5,Monabanq
-2026,February,0,19534.26,19534.26,319,"American Express, SNCF"

output/reports/yearly_summary.csv

@@ -1,5 +1,2 @@
 Year,Total Income,Total Expenses,Net Balance,Transaction Count
-25,0,0.0,0.0,12
+2026,0,19534.260000000013,19534.260000000013,318
-26,0,0.0,0.0,1
-2025,0,10742.59,10742.59,62
-2026,0,20058.190000000013,20058.190000000013,324

scripts/aggregate_by_month.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Script to aggregate all account statements by month
+Script to aggregate all account statements by month or year
 """
 
 import os
@@ -106,21 +106,28 @@ def process_csv_file(file_path):
     return transactions
 
 def main():
-    parser = argparse.ArgumentParser(description='Aggregate all account statements by month')
+    parser = argparse.ArgumentParser(description='Aggregate all account statements by month or year')
     parser.add_argument('--input-dir', default='output/csv', 
                        help='Directory containing CSV files to aggregate (default: output/csv)')
     parser.add_argument('--output-dir', default='output/reports', 
                        help='Directory to save aggregated reports (default: output/reports)')
+    parser.add_argument('--annual', action='store_true',
+                       help='Create annual reports instead of monthly reports')
+    parser.add_argument('--year', type=int,
+                       help='Generate reports for a specific year only')
     
     args = parser.parse_args()
     
     # Create output directory
     os.makedirs(args.output_dir, exist_ok=True)
     
+    report_type = "Annual" if args.annual else "Monthly"
     print(f"\n{'='*60}")
-    print(f"Monthly Aggregation of All Account Statements")
+    print(f"{report_type} Aggregation of All Account Statements")
     print(f"Input Directory: {os.path.abspath(args.input_dir)}")
     print(f"Output Directory: {os.path.abspath(args.output_dir)}")
+    if args.year:
+        print(f"Year Filter: {args.year}")
     print(f"Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
     print(f"{'='*60}")
     
@@ -160,7 +167,7 @@ def main():
         ])
         
         # Process each month
-        for (year, month) in sorted(monthly_transactions.keys()):
+        for year, month in sorted(monthly_transactions.keys()):
             transactions = monthly_transactions[(year, month)]
             month_name = calendar.month_name[month]
             
@@ -180,8 +187,98 @@ def main():
                 transaction_count, institutions_str
             ])
     
-    # Create detailed monthly transactions file for each month
+    # Create yearly summary
-    for (year, month) in sorted(monthly_transactions.keys()):
+    yearly_summary = defaultdict(lambda: {'income': 0, 'expenses': 0, 'count': 0})
+    for transaction in all_transactions:
+        year = transaction['year']
+        yearly_summary[year]['count'] += 1
+        if transaction['amount'] < 0:
+            yearly_summary[year]['income'] += transaction['amount']
+        else:
+            yearly_summary[year]['expenses'] += transaction['amount']
+    
+    # Create yearly summary file
+    yearly_file = os.path.join(args.output_dir, 'yearly_summary.csv')
+    with open(yearly_file, 'w', newline='', encoding='utf-8') as f:
+        writer = csv.writer(f)
+        writer.writerow(['Year', 'Total Income', 'Total Expenses', 'Net Balance', 'Transaction Count'])
+        
+        for year in sorted(yearly_summary.keys()):
+            data = yearly_summary[year]
+            net_balance = data['income'] + data['expenses']
+            writer.writerow([
+                year, data['income'], data['expenses'], net_balance, data['count']
+            ])
+    
+    # Create annual reports if requested
+    generated_files = [
+        os.path.basename(summary_file),
+        os.path.basename(yearly_file)
+    ]
+    
+    if args.annual:
+        # Create annual reports
+        for year in sorted(yearly_summary.keys()):
+            if args.year and year != args.year:
+                continue  # Skip years not matching filter
+                
+            print(f"\nCreating annual report for {year}...")
+            
+            # Get all transactions for the year
+            year_transactions = [t for t in all_transactions if t['year'] == year]
+            
+            # Group by category for the annual report
+            categories = defaultdict(lambda: {'count': 0, 'total': 0})
+            for transaction in year_transactions:
+                category = transaction['category']
+                amount = transaction['amount']
+                categories[category]['count'] += 1
+                categories[category]['total'] += amount
+            
+            # Create annual detailed report
+            annual_file = os.path.join(args.output_dir, f'annual_report_{year}.csv')
+            with open(annual_file, 'w', newline='', encoding='utf-8') as f:
+                writer = csv.writer(f)
+                writer.writerow(['Category', 'Transaction Count', 'Total Amount', 'Percentage'])
+                
+                year_total = sum(c['total'] for c in categories.values())
+                
+                # Sort categories by total amount
+                sorted_categories = sorted(categories.items(), key=lambda x: x[1]['total'], reverse=True)
+                
+                for category, data in sorted_categories:
+                    percentage = (data['total'] / year_total) * 100 if year_total != 0 else 0
+                    writer.writerow([category, data['count'], data['total'], f"{percentage:.2f}%"])
+            
+            # Create annual transactions file
+            annual_transactions_file = os.path.join(args.output_dir, f'annual_transactions_{year}.csv')
+            with open(annual_transactions_file, 'w', newline='', encoding='utf-8') as f:
+                writer = csv.DictWriter(f, fieldnames=[
+                    'Date', 'Description', 'Category', 'Amount', 
+                    'Institution', 'Source'
+                ])
+                writer.writeheader()
+                
+                # Sort transactions by date
+                sorted_transactions = sorted(year_transactions, key=lambda x: (x['month'], x['day'], x['description']))
+                
+                for transaction in sorted_transactions:
+                    writer.writerow({
+                        'Date': transaction['date_str'],
+                        'Description': transaction['description'],
+                        'Category': transaction['category'],
+                        'Amount': transaction['amount'],
+                        'Institution': transaction['institution'],
+                        'Source': transaction['source']
+                    })
+            
+            generated_files.append(os.path.basename(annual_file))
+            generated_files.append(os.path.basename(annual_transactions_file))
+            
+            print(f"  Created {os.path.basename(annual_file)} and {os.path.basename(annual_transactions_file)}")
+    else:
+        # Create monthly reports (existing functionality)
+        for year, month in sorted(monthly_transactions.keys()):
             month_name = calendar.month_name[month].lower()
             transactions = monthly_transactions[(year, month)]
             
@@ -208,45 +305,18 @@ def main():
                         'Source': transaction['source']
                     })
             
-    # Create yearly summary
+            generated_files.append(f'transactions_{year}_{month_name}.csv')
-    yearly_summary = defaultdict(lambda: {'income': 0, 'expenses': 0, 'count': 0})
-    for transaction in all_transactions:
-        year = transaction['year']
-        yearly_summary[year]['count'] += 1
-        if transaction['amount'] < 0:
-            yearly_summary[year]['income'] += transaction['amount']
-        else:
-            yearly_summary[year]['expenses'] += transaction['amount']
-    
-    # Create yearly summary file
-    yearly_file = os.path.join(args.output_dir, 'yearly_summary.csv')
-    with open(yearly_file, 'w', newline='', encoding='utf-8') as f:
-        writer = csv.writer(f)
-        writer.writerow(['Year', 'Total Income', 'Total Expenses', 'Net Balance', 'Transaction Count'])
-        
-        for year in sorted(yearly_summary.keys()):
-            data = yearly_summary[year]
-            net_balance = data['income'] + data['expenses']
-            writer.writerow([
-                year, data['income'], data['expenses'], net_balance, data['count']
-            ])
     
     # Print summary statistics
     print(f"\n{'='*60}")
     print(f"Aggregation Complete")
     print(f"Total Transactions: {len(all_transactions)}")
+    print(f"Years with Data: {len(yearly_summary)}")
+    if not args.annual:
         print(f"Months with Data: {len(monthly_transactions)}")
     print(f"{'='*60}")
     
     # List generated files
-    generated_files = [
-        os.path.basename(summary_file),
-        os.path.basename(yearly_file)
-    ]
-    for (year, month) in sorted(monthly_transactions.keys()):
-        month_name = calendar.month_name[month].lower()
-        generated_files.append(f'transactions_{year}_{month_name}.csv')
-    
     print("\nGenerated Files:")
     for file in generated_files:
         file_path = os.path.join(args.output_dir, file)