@ngocsangairvds/vsaf 3.2.14 → 3.2.15

package/tools/vds-scripts/excel_orchestrator/remove_base_multiplier_and_check_duplicates.py

@@ -1,310 +0,0 @@
-"""
-Remove Base Multiplier (1.59x -> 1.0x) and Check for Duplicates/Overlaps
-
-This script:
-1. Removes the 1.59x base multiplier from all tasks
-2. Recalculates final efforts with only specific multipliers
-3. Checks for duplicate tasks
-4. Checks for overlapping tasks
-5. Updates summary section
-"""
-
-import re
-from pathlib import Path
-
-from openpyxl import load_workbook
-
-EXCEL_PATH = Path(
-    "../../insurance-document/projects/INSURANCE/analysis/reference/vietin/estimation/Estimation_HTBH.xlsx"
-)
-
-
-def normalize_task_name(name: str) -> str:
-    """Normalize task name for comparison."""
-    if not name:
-        return ""
-    normalized = re.sub(r"[^\w\s]", "", str(name).lower().strip())
-    normalized = " ".join(normalized.split())
-    return normalized
-
-
-def calculate_final_effort_no_base(base_effort: float, multiplier_str: str) -> tuple:
-    """Calculate final effort WITHOUT base 1.59x multiplier."""
-    if not multiplier_str:
-        return base_effort, base_effort * 8, "1.0x"
-
-    multiplier_str_clean = str(multiplier_str).strip()
-
-    # First, try to extract numeric multipliers from string (e.g., "1.05x × 1.05x")
-    mult_matches = re.findall(r"(\d+\.?\d*)x", multiplier_str_clean, re.IGNORECASE)
-
-    if mult_matches:
-        # Multiply all found multipliers
-        total_multiplier = 1.0
-        for m in mult_matches:
-            total_multiplier *= float(m)
-    else:
-        # Fallback: check for keywords
-        multipliers = {
-            "performance": 1.05,
-            "compliance": 1.05,
-            "renewal": 1.3,
-            "logic": 1.3,
-            "dynamic pricing": 1.2,
-            "workflow": 1.25,
-            "ai": 1.4,
-            "claims": 1.25,
-            "payment": 1.15,
-            "comparison": 1.1,
-        }
-
-        total_multiplier = 1.0
-        multiplier_str_lower = multiplier_str_clean.lower()
-
-        for key, value in multipliers.items():
-            if key in multiplier_str_lower:
-                total_multiplier *= value
-
-        # If no keywords found, default to 1.0
-        if total_multiplier == 1.0 and "1.0x" not in multiplier_str_clean:
-            # Try to find any number in the string
-            num_match = re.search(r"(\d+\.?\d*)", multiplier_str_clean)
-            if num_match:
-                total_multiplier = float(num_match.group(1))
-
-    final_days = base_effort * total_multiplier
-    final_hours = final_days * 8
-
-    multiplier_display = f"{total_multiplier:.2f}x" if total_multiplier != 1.0 else "1.0x"
-
-    return final_days, final_hours, multiplier_display
-
-
-def find_duplicates(ws):
-    """Find duplicate tasks."""
-    duplicates = []
-    task_signatures = {}
-
-    for row in range(9, ws.max_row + 1):
-        service_id = ws.cell(row, 1).value
-        task_name = ws.cell(row, 6).value
-
-        if service_id and task_name:
-            signature = f"{service_id}_{normalize_task_name(task_name)}"
-
-            if signature in task_signatures:
-                duplicates.append(
-                    {
-                        "row1": task_signatures[signature],
-                        "row2": row,
-                        "service_id": service_id,
-                        "task_name": task_name,
-                    }
-                )
-            else:
-                task_signatures[signature] = row
-
-    return duplicates
-
-
-def find_overlaps(ws):
-    """Find overlapping tasks (similar tasks in same service)."""
-    overlaps = []
-    service_tasks = {}
-
-    # Group tasks by service
-    for row in range(9, ws.max_row + 1):
-        service_id = ws.cell(row, 1).value
-        task_name = ws.cell(row, 6).value
-
-        if service_id and task_name:
-            if service_id not in service_tasks:
-                service_tasks[service_id] = []
-
-            task_words = set(normalize_task_name(task_name).split())
-            service_tasks[service_id].append({"row": row, "name": task_name, "words": task_words})
-
-    # Find overlaps
-    for service_id, tasks in service_tasks.items():
-        for i, task1 in enumerate(tasks):
-            for task2 in tasks[i + 1 :]:
-                common_words = task1["words"] & task2["words"]
-                total_words = task1["words"] | task2["words"]
-
-                if len(total_words) > 0:
-                    overlap_ratio = len(common_words) / len(total_words)
-                    # Consider overlap if >70% word overlap and at least 3 common words
-                    if overlap_ratio > 0.7 and len(common_words) >= 3:
-                        overlaps.append(
-                            {
-                                "service_id": service_id,
-                                "row1": task1["row"],
-                                "row2": task2["row"],
-                                "task1": task1["name"],
-                                "task2": task2["name"],
-                                "overlap": overlap_ratio,
-                            }
-                        )
-
-    return overlaps
-
-
-def remove_base_multiplier(excel_path: Path):
-    """Remove 1.59x base multiplier and recalculate efforts."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    print("=" * 80)
-    print("Removing Base Multiplier (1.59x -> 1.0x)")
-    print("=" * 80)
-
-    updated_count = 0
-
-    for row in range(9, ws.max_row + 1):
-        base_effort = ws.cell(row, 9).value  # Column I: Base Effort
-        multiplier_str = ws.cell(row, 10).value  # Column J: Multiplier Applied
-
-        if base_effort and isinstance(base_effort, (int, float)):
-            # Remove 1.59x from multiplier string
-            if multiplier_str:
-                multiplier_str_clean = str(multiplier_str).replace("1.59x", "").replace("(base)", "").strip()
-                multiplier_str_clean = re.sub(r"\s*×\s*", " × ", multiplier_str_clean)
-                multiplier_str_clean = re.sub(r"^\s*×\s*", "", multiplier_str_clean)
-                multiplier_str_clean = multiplier_str_clean.strip()
-
-                if not multiplier_str_clean or multiplier_str_clean == "×":
-                    multiplier_str_clean = "1.0x"
-            else:
-                multiplier_str_clean = "1.0x"
-
-            # Recalculate final effort
-            final_days, final_hours, multiplier_applied = calculate_final_effort_no_base(
-                float(base_effort), multiplier_str_clean
-            )
-
-            # Update cells
-            ws.cell(row, 10, multiplier_str_clean)  # Multiplier
-            ws.cell(row, 11, final_days)  # Final Days
-            ws.cell(row, 12, final_hours)  # Final Hours
-
-            # Format numbers
-            ws.cell(row, 11).number_format = "#,##0.00"
-            ws.cell(row, 12).number_format = "#,##0"
-
-            updated_count += 1
-
-    wb.save(excel_path)
-    print(f"✅ Updated {updated_count} tasks")
-    return updated_count
-
-
-def check_and_report_duplicates(excel_path: Path):
-    """Check for duplicates and overlaps."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    print("\n" + "=" * 80)
-    print("Checking for Duplicates and Overlaps")
-    print("=" * 80)
-
-    duplicates = find_duplicates(ws)
-    overlaps = find_overlaps(ws)
-
-    print(f"\nDuplicate Tasks: {len(duplicates)}")
-    if duplicates:
-        for dup in duplicates[:20]:
-            print(f"  Row {dup['row1']} and {dup['row2']}: Service {dup['service_id']}")
-            print(f"    Task: {dup['task_name'][:70]}...")
-
-    print(f"\nOverlapping Tasks: {len(overlaps)}")
-    if overlaps:
-        for ov in overlaps[:20]:
-            print(f"  Service {ov['service_id']}: Row {ov['row1']} vs {ov['row2']} ({ov['overlap']:.0%} overlap)")
-            print(f"    Task1: {ov['task1'][:60]}...")
-            print(f"    Task2: {ov['task2'][:60]}...")
-
-    return duplicates, overlaps
-
-
-def update_summary(excel_path: Path):
-    """Update summary section with recalculated totals."""
-    wb = load_workbook(excel_path, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    print("\n" + "=" * 80)
-    print("Updating Summary Section")
-    print("=" * 80)
-
-    # Recalculate totals
-    total_tasks = 0
-    total_days = 0.0
-    total_hours = 0.0
-
-    for row in range(9, ws.max_row + 1):
-        task_id = ws.cell(row, 5).value
-        days = ws.cell(row, 11).value
-        hours = ws.cell(row, 12).value
-
-        if task_id:
-            total_tasks += 1
-
-        if isinstance(days, (int, float)):
-            total_days += float(days)
-
-        if isinstance(hours, (int, float)):
-            total_hours += float(hours)
-
-    # Update summary rows
-    ws.cell(2, 2, total_tasks)  # Row 2: Total Tasks
-    ws.cell(3, 2, total_days)  # Row 3: Total Days
-    ws.cell(4, 2, total_hours)  # Row 4: Total Hours
-
-    # Format summary values
-    ws.cell(3, 2).number_format = "#,##0.00"
-    ws.cell(4, 2).number_format = "#,##0"
-
-    wb.save(excel_path)
-
-    print("✅ Summary updated:")
-    print(f"   Total Tasks: {total_tasks}")
-    print(f"   Total Days: {total_days:.2f}")
-    print(f"   Total Hours: {total_hours:.0f}")
-
-
-def main():
-    """Main execution."""
-    print("=" * 80)
-    print("Remove Base Multiplier and Check Duplicates")
-    print("=" * 80)
-
-    # Step 1: Check for duplicates/overlaps BEFORE changes
-    print("\nStep 1: Checking for duplicates/overlaps...")
-    duplicates, overlaps = check_and_report_duplicates(EXCEL_PATH)
-
-    # Step 2: Remove base multiplier
-    print("\nStep 2: Removing base multiplier (1.59x -> 1.0x)...")
-    updated_count = remove_base_multiplier(EXCEL_PATH)
-
-    # Step 3: Update summary
-    print("\nStep 3: Updating summary section...")
-    update_summary(EXCEL_PATH)
-
-    # Step 4: Final verification
-    print("\nStep 4: Final verification...")
-    duplicates_after, overlaps_after = check_and_report_duplicates(EXCEL_PATH)
-
-    print("\n" + "=" * 80)
-    print("SUMMARY")
-    print("=" * 80)
-    print(f"✅ Tasks updated: {updated_count}")
-    print(f"⚠️ Duplicates found: {len(duplicates_after)}")
-    print(f"⚠️ Overlaps found: {len(overlaps_after)}")
-
-    if len(duplicates_after) == 0 and len(overlaps_after) == 0:
-        print("\n✅ No duplicates or overlaps found!")
-    else:
-        print("\n⚠️ Please review duplicates and overlaps above")
-
-
-if __name__ == "__main__":
-    main()

package/tools/vds-scripts/excel_orchestrator/remove_duplicate_brd_tasks.py

@@ -1,137 +0,0 @@
-"""
-Remove Duplicate BRD-Specific Tasks
-
-This script removes BRD-specific tasks that were incorrectly added to services
-that shouldn't have them. Standard tasks (like API Design, Unit Testing) are
-kept in all services as they are legitimate.
-"""
-
-from pathlib import Path
-
-from openpyxl import load_workbook
-
-EXCEL_PATH = Path(
-    "../../insurance-document/projects/INSURANCE/analysis/reference/vietin/estimation/Estimation_HTBH.xlsx"
-)
-
-# BRD-specific tasks that should only be in specific services
-BRD_SPECIFIC_TASKS = {
-    # Renewal tasks - should only be in Renewal Process, Policy Business
-    "thiết kế workflow gia hạn": ["Renewal Process", "Policy Business"],
-    "triển khai workflow gia hạn": ["Renewal Process", "Policy Business"],
-    "logic tự động gia hạn": ["Renewal Process", "Policy Business"],
-    "thông báo gia hạn": ["Renewal Process", "Policy Business", "Notification Spi"],
-    # Claims tasks - should only be in Claim Business
-    "thiết kế state machine bồi thường": ["Claim Business"],
-    "triển khai state machine bồi thường": ["Claim Business"],
-    "workflow gửi yêu cầu bồi thường": ["Claim Business"],
-    "hành động khách hàng": ["Claim Business"],
-    "tích hợp api bồi thường nhà bảo hiểm": ["Claim Business", "Insurer Service"],
-    "tích hợp thanh toán cho bồi thường": ["Claim Business", "Payment Service"],
-    # Purchase/Proposal tasks - should only be in Proposal Business, Product Catalog
-    "luồng mua hàng": ["Proposal Business", "Customer Business"],
-    "so sánh sản phẩm": ["Proposal Business", "Product Catalog"],
-    "tích hợp ocr": ["Proposal Business", "Ocr Service"],
-    "engine voucher": ["Proposal Business", "Promotion Business"],
-    # AI/Intelligent tasks - should only be in specific services
-    "nghiên cứu ml model": [
-        "Intelligent Recommendation Service",
-        "Intelligent Filtering Service",
-        "Targeted Customer Service",
-    ],
-    "engine gợi ý": ["Intelligent Recommendation Service"],
-    "tích hợp hệ thống bi": ["Intelligent Recommendation Service", "Analytics Service"],
-    "engine phân tích khách hàng": ["Targeted Customer Service", "Crm Service"],
-    "engine tính giá động": ["Rating Engine", "Proposal Business"],
-    "thuật toán đánh giá rủi ro": ["Underwriting Engine", "Auto Underwriting Process"],
-    "cấu hình công thức giá": [
-        "Rating Engine",
-        "Product Catalog",
-        "Business Rules Engine",
-    ],
-    # Chatbot tasks - should only be in Chatbot Service
-    "tích hợp nlp": ["Chatbot Service"],
-    "luồng hội thoại": ["Chatbot Service"],
-    "cơ sở tri thức": ["Chatbot Service", "Document Management Service"],
-    "xử lý fallback": ["Chatbot Service"],
-    # Payment tasks - should only be in Payment services
-    "tích hợp payment gateway": ["Payment Service", "Payment Integration Hub"],
-    "engine tự động thanh toán": ["Payment Service", "Billing Service"],
-    "xử lý thanh toán một phần": ["Payment Service", "Billing Service"],
-    "workflow xử lý hoàn tiền": ["Payment Service", "Billing Service"],
-    "đối soát thanh toán": ["Payment Service", "Reconcile Process"],
-}
-
-
-def should_keep_task(task_name: str, service_name: str) -> bool:
-    """Check if task should be kept for this service."""
-    task_lower = task_name.lower() if task_name else ""
-    service_lower = service_name.lower() if service_name else ""
-
-    # Check if it's a BRD-specific task
-    for task_keyword, allowed_services in BRD_SPECIFIC_TASKS.items():
-        if task_keyword in task_lower:
-            # Check if service is in allowed list
-            return any(allowed_service.lower() in service_lower for allowed_service in allowed_services)
-
-    # Not a BRD-specific task - keep it (standard tasks)
-    return True
-
-
-def remove_duplicate_brd_tasks():
-    """Remove duplicate BRD-specific tasks."""
-    wb = load_workbook(EXCEL_PATH, data_only=False)
-    ws = wb["VDS_Task_Breakdown_Detailed"]
-
-    rows_to_delete = []
-    removed_count = 0
-
-    # Scan all rows
-    for row in range(2, ws.max_row + 1):
-        service_name = ws.cell(row, 2).value
-        task_name = ws.cell(row, 6).value
-
-        if service_name and task_name and not should_keep_task(task_name, service_name):
-            rows_to_delete.append(row)
-            removed_count += 1
-
-    # Delete rows in reverse order to maintain row numbers
-    print(f"Found {removed_count} duplicate BRD-specific tasks to remove")
-
-    for row in reversed(rows_to_delete):
-        ws.delete_rows(row)
-
-    # Update task IDs for remaining tasks
-    current_service_id = None
-    task_counter = 1
-
-    for row in range(2, ws.max_row + 1):
-        service_id = ws.cell(row, 1).value
-
-        if service_id and isinstance(service_id, (int, float)):
-            service_id_int = int(service_id)
-
-            if service_id_int != current_service_id:
-                current_service_id = service_id_int
-                task_counter = 1
-
-            task_id = f"S{service_id_int}-T{task_counter:03d}"
-            ws.cell(row, 5, task_id)
-            task_counter += 1
-
-    wb.save(EXCEL_PATH)
-    print(f"Removed {removed_count} duplicate tasks")
-    print("Updated task IDs for remaining tasks")
-    print(f"Total tasks remaining: {ws.max_row - 1}")
-
-
-if __name__ == "__main__":
-    print("=" * 80)
-    print("Remove Duplicate BRD-Specific Tasks")
-    print("=" * 80)
-
-    remove_duplicate_brd_tasks()
-
-    print("\n" + "=" * 80)
-    print("Cleanup completed!")
-    print("=" * 80)