CP_Assessment_engine/scripts/final_client_deliverable_check.py

"""
Final comprehensive check of ALL client deliverables
Perfectionist-level review before client/BOD delivery
"""
import pandas as pd
from pathlib import Path
import sys
import io

if sys.platform == 'win32':
    sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

BASE_DIR = Path(__file__).resolve().parent.parent

def check_all_deliverables():
    """Comprehensive check of all files to be delivered to client"""
    print("=" * 80)
    print("🔍 FINAL CLIENT DELIVERABLE QUALITY CHECK")
    print("Perfectionist-Level Review - Zero Tolerance for Issues")
    print("=" * 80)
    print()
    
    issues_found = []
    warnings = []
    
    # 1. Check merged_personas.xlsx
    print("1️⃣ CHECKING: merged_personas.xlsx")
    print("-" * 80)
    
    personas_file = BASE_DIR / "data" / "merged_personas.xlsx"
    if personas_file.exists():
        df_personas = pd.read_excel(personas_file, engine='openpyxl')
        
        # Check row count
        if len(df_personas) != 3000:
            issues_found.append(f"merged_personas.xlsx: Expected 3000 rows, got {len(df_personas)}")
        
        # Check for redundant DB columns
        db_columns = [c for c in df_personas.columns if '_DB' in str(c)]
        if db_columns:
            issues_found.append(f"merged_personas.xlsx: Found redundant DB columns: {db_columns}")
        
        # Check for duplicate columns
        if df_personas.columns.duplicated().any():
            issues_found.append(f"merged_personas.xlsx: Duplicate column names found")
        
        # Check StudentCPID uniqueness
        if 'StudentCPID' in df_personas.columns:
            if df_personas['StudentCPID'].duplicated().any():
                issues_found.append(f"merged_personas.xlsx: Duplicate StudentCPIDs found")
            if df_personas['StudentCPID'].isna().any():
                issues_found.append(f"merged_personas.xlsx: Missing StudentCPIDs found")
        
        # Check for suspicious uniform columns
        for col in df_personas.columns:
            if col in ['Nationality', 'Native State']:
                if df_personas[col].nunique() == 1:
                    warnings.append(f"merged_personas.xlsx: '{col}' has only 1 unique value (all students same)")
        
        print(f"   ✅ Basic structure: {len(df_personas)} rows, {len(df_personas.columns)} columns")
        if db_columns:
            print(f"   ⚠️ Redundant columns found: {len(db_columns)}")
        else:
            print(f"   ✅ No redundant DB columns")
    else:
        issues_found.append("merged_personas.xlsx: FILE NOT FOUND")
    
    print()
    
    # 2. Check AllQuestions.xlsx
    print("2️⃣ CHECKING: AllQuestions.xlsx")
    print("-" * 80)
    
    questions_file = BASE_DIR / "data" / "AllQuestions.xlsx"
    if questions_file.exists():
        df_questions = pd.read_excel(questions_file, engine='openpyxl')
        
        # Check for duplicate question codes
        if 'code' in df_questions.columns:
            if df_questions['code'].duplicated().any():
                issues_found.append("AllQuestions.xlsx: Duplicate question codes found")
        
        # Check required columns
        required = ['code', 'domain', 'age-group', 'question']
        missing = [c for c in required if c not in df_questions.columns]
        if missing:
            issues_found.append(f"AllQuestions.xlsx: Missing required columns: {missing}")
        
        print(f"   ✅ Structure: {len(df_questions)} questions, {len(df_questions.columns)} columns")
        print(f"   ✅ All question codes unique")
    else:
        issues_found.append("AllQuestions.xlsx: FILE NOT FOUND")
    
    print()
    
    # 3. Check output files structure
    print("3️⃣ CHECKING: Output Files Structure")
    print("-" * 80)
    
    output_dir = BASE_DIR / "output" / "full_run"
    
    expected_files = {
        'adolescense/5_domain': [
            'Personality_14-17.xlsx',
            'Grit_14-17.xlsx',
            'Emotional_Intelligence_14-17.xlsx',
            'Vocational_Interest_14-17.xlsx',
            'Learning_Strategies_14-17.xlsx'
        ],
        'adults/5_domain': [
            'Personality_18-23.xlsx',
            'Grit_18-23.xlsx',
            'Emotional_Intelligence_18-23.xlsx',
            'Vocational_Interest_18-23.xlsx',
            'Learning_Strategies_18-23.xlsx'
        ]
    }
    
    missing_files = []
    for age_dir, files in expected_files.items():
        for file_name in files:
            file_path = output_dir / age_dir / file_name
            if not file_path.exists():
                missing_files.append(f"{age_dir}/{file_name}")
    
    if missing_files:
        issues_found.append(f"Output files missing: {missing_files}")
    else:
        print(f"   ✅ All 10 domain files present")
    
    # Check cognition files
    cog_files_adol = list((output_dir / "adolescense" / "cognition").glob("*.xlsx"))
    cog_files_adult = list((output_dir / "adults" / "cognition").glob("*.xlsx"))
    
    if len(cog_files_adol) != 12:
        warnings.append(f"Cognition files: Expected 12 for adolescents, found {len(cog_files_adol)}")
    if len(cog_files_adult) != 12:
        warnings.append(f"Cognition files: Expected 12 for adults, found {len(cog_files_adult)}")
    
    print(f"   ✅ Domain files: 10/10")
    print(f"   ✅ Cognition files: {len(cog_files_adol) + len(cog_files_adult)}/24")
    
    print()
    
    # Final summary
    print("=" * 80)
    print("📊 FINAL ASSESSMENT")
    print("=" * 80)
    
    if issues_found:
        print(f"❌ CRITICAL ISSUES FOUND: {len(issues_found)}")
        for issue in issues_found:
            print(f"   - {issue}")
        print()
    
    if warnings:
        print(f"⚠️ WARNINGS: {len(warnings)}")
        for warning in warnings:
            print(f"   - {warning}")
        print()
    
    if not issues_found and not warnings:
        print("✅ ALL CHECKS PASSED - FILES READY FOR CLIENT DELIVERY")
    elif not issues_found:
        print("⚠️ WARNINGS ONLY - Review recommended but not blocking")
    else:
        print("❌ CRITICAL ISSUES - MUST FIX BEFORE CLIENT DELIVERY")
    
    print("=" * 80)
    
    return len(issues_found) == 0

if __name__ == "__main__":
    success = check_all_deliverables()
    sys.exit(0 if success else 1)