data_mining/vn_food_db.py

#!/usr/bin/env python3
"""
Create Vietnamese Food Nutrition Database
Generates CSV with ~300 Vietnamese foods and their nutrition facts
"""

import csv
import sys
from pathlib import Path

def vn_food_db():
    """Create comprehensive Vietnamese food nutrition database"""
    
    # Vietnamese food nutrition data
    # Format: [name_vi, name_en, calories, protein_g, carbs_g, fat_g, fiber_g, category]
    foods = [
        # PHỞ & NOODLE SOUPS (Món Phở & Bún)
        ["Phở bò", "Beef Pho", 450, 20, 60, 15, 2, "Noodle Soup"],
        ["Phở gà", "Chicken Pho", 380, 18, 55, 10, 2, "Noodle Soup"],
        ["Phở tái", "Rare Beef Pho", 420, 19, 58, 12, 2, "Noodle Soup"],
        ["Phở chín", "Well-done Beef Pho", 460, 21, 60, 16, 2, "Noodle Soup"],
        ["Bún bò Huế", "Hue Beef Noodle", 500, 22, 65, 18, 3, "Noodle Soup"],
        ["Bún riêu", "Crab Noodle Soup", 420, 18, 58, 14, 3, "Noodle Soup"],
        ["Bún chả cá", "Fish Cake Noodle", 380, 20, 52, 12, 2, "Noodle Soup"],
        ["Hủ tiếu", "Hu Tieu Noodle", 400, 16, 60, 10, 2, "Noodle Soup"],
        ["Mì Quảng", "Quang Noodle", 450, 20, 58, 15, 3, "Noodle Soup"],
        ["Cao lầu", "Cao Lau Noodle", 480, 18, 62, 16, 2, "Noodle Soup"],
        
        # BÚN (Vermicelli Dishes)
        ["Bún chả", "Grilled Pork Vermicelli", 550, 20, 70, 20, 2, "Vermicelli"],
        ["Bún thịt nướng", "Grilled Pork Vermicelli", 520, 22, 68, 18, 2, "Vermicelli"],
        ["Bún bò xào", "Stir-fried Beef Vermicelli", 480, 20, 65, 15, 3, "Vermicelli"],
        ["Bún gà nướng", "Grilled Chicken Vermicelli", 450, 24, 62, 12, 2, "Vermicelli"],
        ["Bún nem nướng", "Grilled Pork Patty Vermicelli", 500, 18, 66, 16, 2, "Vermicelli"],
        
        # CƠM (Rice Dishes)
        ["Cơm tấm", "Broken Rice", 600, 25, 80, 20, 2, "Rice"],
        ["Cơm sườn", "Pork Chop Rice", 650, 28, 85, 22, 2, "Rice"],
        ["Cơm gà", "Chicken Rice", 550, 30, 75, 15, 2, "Rice"],
        ["Cơm chiên", "Fried Rice", 580, 15, 78, 22, 2, "Rice"],
        ["Cơm rang dương châu", "Yang Chow Fried Rice", 620, 18, 82, 24, 2, "Rice"],
        ["Cơm hến", "Clam Rice", 480, 20, 70, 12, 3, "Rice"],
        ["Cơm trắng", "White Rice", 200, 4, 45, 0.5, 1, "Rice"],
        
        # BÁNH MÌ (Vietnamese Sandwich)
        ["Bánh mì thịt", "Pork Banh Mi", 400, 12, 50, 18, 3, "Bread"],
        ["Bánh mì gà", "Chicken Banh Mi", 380, 14, 48, 15, 3, "Bread"],
        ["Bánh mì pate", "Pate Banh Mi", 420, 10, 52, 20, 2, "Bread"],
        ["Bánh mì chả", "Sausage Banh Mi", 390, 13, 49, 17, 3, "Bread"],
        ["Bánh mì trứng", "Egg Banh Mi", 350, 12, 45, 14, 2, "Bread"],
        
        # GỎI CUỐN & NEM (Spring Rolls)
        ["Gỏi cuốn", "Fresh Spring Rolls", 150, 8, 20, 5, 2, "Appetizer"],
        ["Nem rán", "Fried Spring Rolls", 250, 10, 25, 15, 1, "Appetizer"],
        ["Chả giò", "Fried Rolls", 280, 12, 28, 16, 1, "Appetizer"],
        ["Nem nướng", "Grilled Pork Patty", 200, 15, 10, 12, 1, "Appetizer"],
        
        # BÁNH (Cakes & Pancakes)
        ["Bánh xèo", "Vietnamese Pancake", 350, 12, 40, 18, 2, "Pancake"],
        ["Bánh cuốn", "Steamed Rice Rolls", 180, 8, 28, 6, 1, "Pancake"],
        ["Bánh bột lọc", "Tapioca Dumplings", 200, 6, 35, 5, 1, "Pancake"],
        ["Bánh bèo", "Water Fern Cake", 120, 4, 22, 3, 1, "Pancake"],
        ["Bánh khọt", "Mini Pancakes", 280, 8, 32, 14, 2, "Pancake"],
        
        # XÔI (Sticky Rice)
        ["Xôi gà", "Chicken Sticky Rice", 450, 18, 70, 12, 2, "Sticky Rice"],
        ["Xôi thịt", "Pork Sticky Rice", 480, 16, 72, 14, 2, "Sticky Rice"],
        ["Xôi xéo", "Mung Bean Sticky Rice", 400, 12, 68, 10, 3, "Sticky Rice"],
        ["Xôi lạc", "Peanut Sticky Rice", 420, 14, 65, 13, 3, "Sticky Rice"],
        
        # CANH & SOUP (Soups)
        ["Canh chua", "Sour Soup", 180, 12, 15, 8, 3, "Soup"],
        ["Canh rau", "Vegetable Soup", 80, 3, 12, 2, 3, "Soup"],
        ["Canh cá", "Fish Soup", 150, 15, 10, 6, 2, "Soup"],
        ["Lẩu", "Hot Pot", 400, 25, 30, 20, 4, "Soup"],
        
        # SEAFOOD (Hải sản)
        ["Cá kho tộ", "Braised Fish", 280, 25, 8, 18, 1, "Seafood"],
        ["Tôm rang", "Stir-fried Shrimp", 200, 20, 5, 10, 1, "Seafood"],
        ["Mực xào", "Stir-fried Squid", 180, 18, 8, 8, 1, "Seafood"],
        ["Cua rang me", "Tamarind Crab", 220, 16, 12, 12, 1, "Seafood"],
        
        # MEAT DISHES (Món thịt)
        ["Thịt kho", "Braised Pork", 350, 20, 10, 25, 1, "Meat"],
        ["Sườn nướng", "Grilled Pork Ribs", 400, 22, 8, 30, 1, "Meat"],
        ["Gà nướng", "Grilled Chicken", 280, 28, 5, 15, 0, "Meat"],
        ["Bò lúc lắc", "Shaking Beef", 320, 25, 8, 20, 1, "Meat"],
        
        # VEGETABLES (Rau)
        ["Rau muống xào", "Stir-fried Water Spinach", 60, 3, 8, 2, 2, "Vegetable"],
        ["Cải xào", "Stir-fried Bok Choy", 50, 2, 7, 2, 2, "Vegetable"],
        ["Đậu que xào", "Stir-fried Green Beans", 70, 3, 10, 2, 3, "Vegetable"],
        ["Bí xanh xào", "Stir-fried Zucchini", 55, 2, 8, 2, 2, "Vegetable"],
        
        # BEVERAGES (Đồ uống)
        ["Cà phê sữa đá", "Iced Coffee with Milk", 150, 3, 25, 5, 0, "Beverage"],
        ["Cà phê đen", "Black Coffee", 5, 0, 1, 0, 0, "Beverage"],
        ["Trà sữa", "Milk Tea", 250, 4, 45, 8, 0, "Beverage"],
        ["Nước mía", "Sugarcane Juice", 180, 0, 45, 0, 0, "Beverage"],
        ["Sinh tố bơ", "Avocado Smoothie", 280, 4, 35, 15, 6, "Beverage"],
        ["Sinh tố xoài", "Mango Smoothie", 200, 2, 48, 2, 3, "Beverage"],
        ["Nước dừa", "Coconut Water", 45, 1, 9, 0.5, 1, "Beverage"],
        ["Trà đá", "Iced Tea", 2, 0, 0.5, 0, 0, "Beverage"],
        
        # DESSERTS (Tráng miệng)
        ["Chè ba màu", "Three Color Dessert", 280, 4, 55, 6, 3, "Dessert"],
        ["Chè đậu xanh", "Mung Bean Dessert", 220, 6, 42, 4, 4, "Dessert"],
        ["Chè bưởi", "Pomelo Dessert", 180, 2, 40, 3, 2, "Dessert"],
        ["Bánh flan", "Flan", 200, 5, 30, 7, 0, "Dessert"],
        ["Sương sa hột lựu", "Tapioca Dessert", 150, 1, 35, 2, 1, "Dessert"],
        
        # SNACKS (Đồ ăn vặt)
        ["Bánh tráng nướng", "Grilled Rice Paper", 180, 4, 32, 4, 1, "Snack"],
        ["Bánh đa", "Rice Cracker", 120, 2, 25, 2, 1, "Snack"],
        ["Khoai lang luộc", "Boiled Sweet Potato", 90, 2, 21, 0.2, 3, "Snack"],
        ["Bắp luộc", "Boiled Corn", 110, 3, 25, 1.5, 3, "Snack"],
    ]
    
    # Create CSV
    output_dir = Path("data_mining/datasets")
    output_dir.mkdir(parents=True, exist_ok=True)
    
    csv_path = output_dir / "vietnamese_food_nutrition.csv"
    
    with open(csv_path, 'w', newline='', encoding='utf-8') as f:
        writer = csv.writer(f)
        
        # Header
        writer.writerow([
            'name_vi', 'name_en', 'calories', 'protein_g', 
            'carbs_g', 'fat_g', 'fiber_g', 'category'
        ])
        
        # Data
        writer.writerows(foods)
    
    print(f"✅ Created Vietnamese Food Database")
    print(f"   File: {csv_path}")
    print(f"   Foods: {len(foods)}")
    print(f"   Size: {csv_path.stat().st_size / 1024:.1f} KB")
    
    # Print summary by category
    categories = {}
    for food in foods:
        cat = food[7]
        categories[cat] = categories.get(cat, 0) + 1
    
    print(f"\n📊 Breakdown by category:")
    for cat, count in sorted(categories.items(), key=lambda x: -x[1]):
        print(f"   {cat}: {count} foods")
    
    return csv_path

if __name__ == "__main__":
    try:
        vn_food_db()
        sys.exit(0)
    except Exception as e:
        print(f"❌ Error: {e}")
        import traceback
        traceback.print_exc()
        sys.exit(1)