Merge pull request #213 from pirogramming/develop

[Feat] db 꼬인 문제 해결하고 제조사 추출하는 코드 작성

Author: mnjese

diets/views.py

@@ -54,7 +54,7 @@ def food_to_dict(food):
         "trans_fatty_acids": safe_float(getattr(food, "trans_fatty_acids", 0)),
         "serving_size": safe_float(getattr(food, "serving_size", 0)),
         "weight": safe_float(getattr(food, "weight", 0)),
-        "company_name": safe_str(getattr(food, "mallName", "") or getattr(food, "company_name", "") or ""),
+        "company_name": safe_str(getattr(food, "company_name", "") or ""),
         "score": safe_float(getattr(food, "nutrition_score", 0)),
         "letter_grade": safe_str(getattr(food, "nutri_score_grade", "") or letterGrade(food) or ""),
         "nutri_score_grade": safe_str(getattr(food, "nutri_score_grade", "") or letterGrade(food) or "")
@@ -181,7 +181,7 @@ def diet_list(request):
             recent_foods.append({
                 "food_id": str(cur_food.food_id),
                 "food_name" : cur_food.food_name,
-                "company_name": cur_food.mallName or cur_food.company_name,
+                "company_name": cur_food.company_name,
                 "food_img": cur_food.image_url or cur_food.food_img
                 })
             cnt += 1 #식품 카운팅
@@ -212,7 +212,7 @@ def diet_search(request):
         food_data = dict() #food의 정보를 담을 dict
         food_data['food_id'] = str(food.food_id)
         food_data['food_name'] = food.food_name
-        food_data['company_name'] = food.mallName or food.company_name
+        food_data['company_name'] = food.company_name
         food_data['food_img'] = food.image_url or food.food_img
         ret['foods'].append(food_data) #food_data 에 정보를 모두 담았으니 ret['foods']에 추가
 

foods/admin.py

@@ -4,8 +4,8 @@
 
 @admin.register(Food)
 class FoodAdmin(admin.ModelAdmin):
-    list_display = ['food_id', 'food_name', 'company_name', 'food_category', 'mallName', 'lprice']
-    list_filter = ['food_category', 'company_name', 'mallName']
+    list_display = ['food_id', 'food_name', 'company_name', 'food_category', 'lprice']
+    list_filter = ['food_category', 'company_name']
     search_fields = ['food_name', 'company_name', 'representative_food']
     readonly_fields = ['food_id']
 
@@ -29,7 +29,7 @@ class FoodAdmin(admin.ModelAdmin):
             'classes': ('collapse',)
         }),
         ('가격 정보', {
-            'fields': ('mallName', 'lprice', 'discount_price', 'shop_url', 'image_url'),
+            'fields': ('lprice', 'discount_price', 'shop_url', 'image_url'),
             'classes': ('collapse',)
         }),
         ('기타 정보', {

foods/migrations/0011_remove_food_mallname.py

@@ -0,0 +1,17 @@
+# Generated by Django 5.2.4 on 2025-08-18 10:38
+
+from django.db import migrations
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('foods', '0010_remove_food_shop_name'),
+    ]
+
+    operations = [
+        migrations.RemoveField(
+            model_name='food',
+            name='mallName',
+        ),
+    ]

foods/models.py

@@ -53,7 +53,6 @@ class Food(models.Model):
     # 가격 정보 (CSV 칼럼에 맞춰 추가)
     lprice = models.BigIntegerField(null=True, blank=True)  # 네이버 쇼핑 최저가
     discount_price = models.BigIntegerField(null=True, blank=True)
-    mallName = models.CharField(max_length=100, null=True, blank=True)  # 쇼핑몰 이름
     shop_url = models.URLField(null=True, blank=True)
     image_url = models.URLField(null=True, blank=True)
 

mypage/views.py

@@ -114,7 +114,7 @@ def favorite_food_list(request):
             "food_id": str(food.food_id),
             "food_name": food.food_name,
             "food_img": getattr(food, 'image_url', '') or getattr(food, 'food_img', '') or "http://example.com/default_food.png",
-            "company_name": getattr(food, 'mallName', '') or getattr(food, 'company_name', '') or "Unknown",
+            "company_name": getattr(food, 'company_name', '') or "Unknown",
             "calorie": int(food.calorie) if getattr(food, 'calorie', None) else 0,
             "created_at": getattr(f, 'created_at', None),
         })

products/views.py

@@ -73,11 +73,10 @@ def _product_dict(food, is_favorite: bool):
         "trans_fatty_acids": safe_float(food.trans_fatty_acids),
         "nutritional_value_standard_amount": safe_int(food.nutritional_value_standard_amount),
         "weight": safe_float(food.weight),
-        "company_name": safe_str(food.mallName) or safe_str(food.company_name),
+        "company_name": safe_str(food.company_name),
         "nutrition_score": safe_float(food.nutrition_score),
         "nutri_score_grade": safe_str(food.nutri_score_grade),
         "lprice": safe_int(food.lprice),
-        "shop_name": safe_str(food.mallName),
         "shop_url": safe_str(food.shop_url),
         "sugar_level": None,
         "saturated_fatty_acids_level": None,

scripts/extract_manufacturer_info.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+"""
+20250327_가공식품DB_147999건.xlsx에서 제조사 정보를 추출하여
+food_clean_data.csv의 company_name을 업데이트하는 스크립트
+"""
+
+import pandas as pd
+
+def main():
+    print("제조사 정보 추출 및 매핑 시작...")
+    
+    try:
+        # 1. 원본 Excel 파일 읽기
+        print("20250327_가공식품DB_147999건.xlsx 로딩 중...")
+        df_original = pd.read_excel('/Users/kimminji/Desktop/Healthtant/20250327_가공식품DB_147999건.xlsx')
+        print(f"원본 데이터: {len(df_original)}개 행")
+        
+        # 2. food_clean_data.csv 읽기
+        print("food_clean_data.csv 로딩 중...")
+        df_food = pd.read_csv('/Users/kimminji/Desktop/Healthtant/food_clean_data.csv')
+        print(f"현재 식품 데이터: {len(df_food)}개 행")
+        
+        # 3. 제조사 정보 추출 (식품코드 -> 제조사명)
+        manufacturer_mapping = {}
+        for idx, row in df_original.iterrows():
+            food_code = str(row['식품코드']).strip()
+            manufacturer = str(row['제조사명']).strip() if pd.notna(row['제조사명']) else ''
+            
+            # 제조사명이 없으면 수입업체명이나 유통업체명 사용
+            if not manufacturer or manufacturer == 'nan':
+                manufacturer = str(row['수입업체명']).strip() if pd.notna(row['수입업체명']) else ''
+            if not manufacturer or manufacturer == 'nan':
+                manufacturer = str(row['유통업체명']).strip() if pd.notna(row['유통업체명']) else ''
+                
+            if manufacturer and manufacturer != 'nan':
+                manufacturer_mapping[food_code] = manufacturer
+        
+        print(f"제조사 정보를 찾은 식품: {len(manufacturer_mapping)}개")
+        
+        # 4. food_clean_data.csv의 company_name 업데이트
+        updated_count = 0
+        for idx, row in df_food.iterrows():
+            food_id = str(row['food_id']).strip()
+            if food_id in manufacturer_mapping:
+                df_food.at[idx, 'company_name'] = manufacturer_mapping[food_id]
+                updated_count += 1
+        
+        print(f"업데이트된 식품: {updated_count}개")
+        
+        # 5. 업데이트된 CSV 저장
+        output_file = '/Users/kimminji/Desktop/Healthtant/food_clean_data_updated.csv'
+        df_food.to_csv(output_file, index=False, encoding='utf-8')
+        print(f"업데이트된 파일 저장: {output_file}")
+        
+        # 6. 통계 출력
+        total_foods = len(df_food)
+        foods_with_manufacturer = len(df_food[df_food['company_name'].notna() & (df_food['company_name'] != '') & (df_food['company_name'] != 'UNKNOWN')])
+        print(f"\n=== 통계 ===")
+        print(f"전체 식품: {total_foods}개")
+        print(f"제조사 정보 있음: {foods_with_manufacturer}개 ({foods_with_manufacturer/total_foods*100:.1f}%)")
+        
+        # 7. 샘플 데이터 확인
+        print(f"\n=== 업데이트된 샘플 데이터 ===")
+        sample = df_food[df_food['company_name'].notna() & (df_food['company_name'] != '') & (df_food['company_name'] != 'UNKNOWN')].head(10)
+        for _, row in sample.iterrows():
+            print(f"ID: {row['food_id']}, 식품명: {row['food_name']}, 제조사: {row['company_name']}")
+        
+    except Exception as e:
+        print(f"오류 발생: {e}")
+        import traceback
+        traceback.print_exc()
+
+if __name__ == "__main__":
+    main()

scripts/extract_manufacturers.py

@@ -148,7 +148,6 @@ def main():
     # 2) 매핑 - food_clean_data.csv 칼럼에 맞춰 수정
     csv_to_db = {
         'food_id': 'food_id',
-        'shop_name': 'mallName',
         'price': 'lprice',
         'discount_price': 'discount_price',
         'shop_url': 'shop_url',