diff --git a/best_shuttle_bus_route.ipynb b/best_shuttle_bus_route.ipynb
deleted file mode 100644
index 3d7ed0a..0000000
--- a/best_shuttle_bus_route.ipynb
+++ /dev/null
@@ -1,2317 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# 최적 셔틀버스 노선 탐색"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 데이터 준비"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 54,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "import pandas as pd\n",
-    "\n",
-    "# 'data/raw_data' 경로 설정\n",
-    "root_dir = 'data/'\n",
-    "visitor_city = pd.read_csv(os.path.join(root_dir, \"city_of_festival_visitors.csv\"))  # 무주축제 방문객 top 18 지역들 (시군구명,od_cnts,시도명,행정동코드,위도,경도)\n",
-    "address = pd.read_csv(os.path.join(root_dir, \"address_with_lon_lat_final.csv\"))  # 행정동코드 + 위도경도 (행정동코드,시도명,시군구명,읍면동명,동리명,위도,경도)\n",
-    "mooju = set(list(address[address['시군구명'] == '무주군']['행정동코드']))  # 무주군 행정동코드\n",
-    "other_city = list(address.merge(visitor_city, on=['시도명', '시군구명'])['행정동코드_x'])  # 다른 지역들 행정동코드 모음"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>시군구명</th>\n",
-       "      <th>od_cnts</th>\n",
-       "      <th>시도명</th>\n",
-       "      <th>행정동코드</th>\n",
-       "      <th>위도</th>\n",
-       "      <th>경도</th>\n",
-       "      <th>시도 시군구</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>전주시 덕진구</td>\n",
-       "      <td>2834</td>\n",
-       "      <td>전라북도</td>\n",
-       "      <td>4511300000</td>\n",
-       "      <td>35.847561</td>\n",
-       "      <td>127.117672</td>\n",
-       "      <td>전라북도 전주시 덕진구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>서구</td>\n",
-       "      <td>1813</td>\n",
-       "      <td>대전광역시</td>\n",
-       "      <td>3017000000</td>\n",
-       "      <td>36.355179</td>\n",
-       "      <td>127.383849</td>\n",
-       "      <td>대전광역시 서구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>전주시 완산구</td>\n",
-       "      <td>1561</td>\n",
-       "      <td>전라북도</td>\n",
-       "      <td>4511100000</td>\n",
-       "      <td>35.795512</td>\n",
-       "      <td>127.132447</td>\n",
-       "      <td>전라북도 전주시 완산구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>유성구</td>\n",
-       "      <td>1379</td>\n",
-       "      <td>대전광역시</td>\n",
-       "      <td>3020000000</td>\n",
-       "      <td>36.362073</td>\n",
-       "      <td>127.356410</td>\n",
-       "      <td>대전광역시 유성구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>동구</td>\n",
-       "      <td>1207</td>\n",
-       "      <td>대전광역시</td>\n",
-       "      <td>3011000000</td>\n",
-       "      <td>35.886500</td>\n",
-       "      <td>128.635500</td>\n",
-       "      <td>대전광역시 동구</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "      시군구명  od_cnts    시도명       행정동코드         위도          경도        시도 시군구\n",
-       "0  전주시 덕진구     2834   전라북도  4511300000  35.847561  127.117672  전라북도 전주시 덕진구\n",
-       "1       서구     1813  대전광역시  3017000000  36.355179  127.383849      대전광역시 서구\n",
-       "2  전주시 완산구     1561   전라북도  4511100000  35.795512  127.132447  전라북도 전주시 완산구\n",
-       "3      유성구     1379  대전광역시  3020000000  36.362073  127.356410     대전광역시 유성구\n",
-       "4       동구     1207  대전광역시  3011000000  35.886500  128.635500      대전광역시 동구"
-      ]
-     },
-     "execution_count": 55,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "visitor_city['시도 시군구'] = visitor_city['시도명'].fillna('') + ' ' + visitor_city['시군구명'].fillna('')\n",
-    "\n",
-    "# 양쪽 값이 모두 null인 경우 빈 문자열 처리\n",
-    "visitor_city['시도 시군구'] = visitor_city['시도 시군구'].str.strip()\n",
-    "visitor_city.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>행정동코드</th>\n",
-       "      <th>시도명</th>\n",
-       "      <th>시군구명</th>\n",
-       "      <th>읍면동명</th>\n",
-       "      <th>동리명</th>\n",
-       "      <th>위도</th>\n",
-       "      <th>경도</th>\n",
-       "      <th>시도 시군구</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1100000000</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>37.566679</td>\n",
-       "      <td>126.978291</td>\n",
-       "      <td>서울특별시</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1111000000</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>종로구</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>종로구</td>\n",
-       "      <td>37.580695</td>\n",
-       "      <td>126.982799</td>\n",
-       "      <td>서울특별시 종로구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>종로구</td>\n",
-       "      <td>청운효자동</td>\n",
-       "      <td>세종로</td>\n",
-       "      <td>37.579997</td>\n",
-       "      <td>126.976930</td>\n",
-       "      <td>서울특별시 종로구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>종로구</td>\n",
-       "      <td>청운효자동</td>\n",
-       "      <td>옥인동</td>\n",
-       "      <td>37.583480</td>\n",
-       "      <td>126.963850</td>\n",
-       "      <td>서울특별시 종로구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>종로구</td>\n",
-       "      <td>청운효자동</td>\n",
-       "      <td>누하동</td>\n",
-       "      <td>37.578998</td>\n",
-       "      <td>126.967561</td>\n",
-       "      <td>서울특별시 종로구</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21772</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>양양군</td>\n",
-       "      <td>강현면</td>\n",
-       "      <td>정암리</td>\n",
-       "      <td>38.143050</td>\n",
-       "      <td>128.607330</td>\n",
-       "      <td>강원특별자치도 양양군</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21773</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>양양군</td>\n",
-       "      <td>강현면</td>\n",
-       "      <td>용호리</td>\n",
-       "      <td>38.132320</td>\n",
-       "      <td>128.610700</td>\n",
-       "      <td>강원특별자치도 양양군</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21774</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>양양군</td>\n",
-       "      <td>강현면</td>\n",
-       "      <td>전진리</td>\n",
-       "      <td>38.124830</td>\n",
-       "      <td>128.624220</td>\n",
-       "      <td>강원특별자치도 양양군</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21775</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>양양군</td>\n",
-       "      <td>강현면</td>\n",
-       "      <td>물치리</td>\n",
-       "      <td>38.158083</td>\n",
-       "      <td>128.608889</td>\n",
-       "      <td>강원특별자치도 양양군</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21776</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>양양군</td>\n",
-       "      <td>강현면</td>\n",
-       "      <td>적은리</td>\n",
-       "      <td>38.118555</td>\n",
-       "      <td>128.598405</td>\n",
-       "      <td>강원특별자치도 양양군</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>21777 rows × 8 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "            행정동코드      시도명 시군구명   읍면동명    동리명         위도          경도  \\\n",
-       "0      1100000000    서울특별시  NaN    NaN  서울특별시  37.566679  126.978291   \n",
-       "1      1111000000    서울특별시  종로구    NaN    종로구  37.580695  126.982799   \n",
-       "2      1111051500    서울특별시  종로구  청운효자동    세종로  37.579997  126.976930   \n",
-       "3      1111051500    서울특별시  종로구  청운효자동    옥인동  37.583480  126.963850   \n",
-       "4      1111051500    서울특별시  종로구  청운효자동    누하동  37.578998  126.967561   \n",
-       "...           ...      ...  ...    ...    ...        ...         ...   \n",
-       "21772  5183035000  강원특별자치도  양양군    강현면    정암리  38.143050  128.607330   \n",
-       "21773  5183035000  강원특별자치도  양양군    강현면    용호리  38.132320  128.610700   \n",
-       "21774  5183035000  강원특별자치도  양양군    강현면    전진리  38.124830  128.624220   \n",
-       "21775  5183035000  강원특별자치도  양양군    강현면    물치리  38.158083  128.608889   \n",
-       "21776  5183035000  강원특별자치도  양양군    강현면    적은리  38.118555  128.598405   \n",
-       "\n",
-       "            시도 시군구  \n",
-       "0            서울특별시  \n",
-       "1        서울특별시 종로구  \n",
-       "2        서울특별시 종로구  \n",
-       "3        서울특별시 종로구  \n",
-       "4        서울특별시 종로구  \n",
-       "...            ...  \n",
-       "21772  강원특별자치도 양양군  \n",
-       "21773  강원특별자치도 양양군  \n",
-       "21774  강원특별자치도 양양군  \n",
-       "21775  강원특별자치도 양양군  \n",
-       "21776  강원특별자치도 양양군  \n",
-       "\n",
-       "[21777 rows x 8 columns]"
-      ]
-     },
-     "execution_count": 56,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "address['시도 시군구'] = address['시도명'].fillna('') + ' ' + address['시군구명'].fillna('')\n",
-    "\n",
-    "# 양쪽 값이 모두 null인 경우 빈 문자열 처리\n",
-    "address['시도 시군구'] = address['시도 시군구'].str.strip()\n",
-    "address"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "  0%|          | 0/9 [00:00<?, ?it/s]"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "100%|██████████| 9/9 [00:37<00:00,  4.20s/it]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>dest_hdong_cd</th>\n",
-       "      <th>date</th>\n",
-       "      <th>start_time</th>\n",
-       "      <th>end_time</th>\n",
-       "      <th>gender</th>\n",
-       "      <th>age</th>\n",
-       "      <th>modal</th>\n",
-       "      <th>origin_purpose</th>\n",
-       "      <th>dest_purpose</th>\n",
-       "      <th>od_dist_avg</th>\n",
-       "      <th>od_duration_avg</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1096</th>\n",
-       "      <td>4311374100</td>\n",
-       "      <td>4573031000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>09:00</td>\n",
-       "      <td>11:00</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>163782</td>\n",
-       "      <td>109</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2269</th>\n",
-       "      <td>4573033000</td>\n",
-       "      <td>4573025000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>20:00</td>\n",
-       "      <td>20:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>20247</td>\n",
-       "      <td>28</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3874</th>\n",
-       "      <td>4812965000</td>\n",
-       "      <td>4573034000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>16:00</td>\n",
-       "      <td>18:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>424072</td>\n",
-       "      <td>131</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4218</th>\n",
-       "      <td>4817073000</td>\n",
-       "      <td>4573032000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>13:00</td>\n",
-       "      <td>16:00</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>119100</td>\n",
-       "      <td>141</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4773</th>\n",
-       "      <td>4573032000</td>\n",
-       "      <td>4573025000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>17:00</td>\n",
-       "      <td>19:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>128030</td>\n",
-       "      <td>118</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3237279</th>\n",
-       "      <td>4574036000</td>\n",
-       "      <td>4573034000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>12:00</td>\n",
-       "      <td>12:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>38926</td>\n",
-       "      <td>27</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3238635</th>\n",
-       "      <td>4573033000</td>\n",
-       "      <td>4573025000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>12:00</td>\n",
-       "      <td>12:00</td>\n",
-       "      <td>1</td>\n",
-       "      <td>5</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>9476</td>\n",
-       "      <td>13</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3239981</th>\n",
-       "      <td>4572025000</td>\n",
-       "      <td>4573033000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>18:00</td>\n",
-       "      <td>18:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>50623</td>\n",
-       "      <td>33</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3246027</th>\n",
-       "      <td>4573025000</td>\n",
-       "      <td>4573034000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>11:00</td>\n",
-       "      <td>12:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>46949</td>\n",
-       "      <td>51</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3249613</th>\n",
-       "      <td>4783025300</td>\n",
-       "      <td>4573032000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>10:00</td>\n",
-       "      <td>11:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>218374</td>\n",
-       "      <td>100</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>4173 rows × 13 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         origin_hdong_cd  dest_hdong_cd      date start_time end_time  gender  \\\n",
-       "1096          4311374100     4573031000  20230902      09:00    11:00       1   \n",
-       "2269          4573033000     4573025000  20230902      20:00    20:00       0   \n",
-       "3874          4812965000     4573034000  20230902      16:00    18:00       0   \n",
-       "4218          4817073000     4573032000  20230902      13:00    16:00       1   \n",
-       "4773          4573032000     4573025000  20230902      17:00    19:00       0   \n",
-       "...                  ...            ...       ...        ...      ...     ...   \n",
-       "3237279       4574036000     4573034000  20230910      12:00    12:00       0   \n",
-       "3238635       4573033000     4573025000  20230910      12:00    12:00       1   \n",
-       "3239981       4572025000     4573033000  20230910      18:00    18:00       0   \n",
-       "3246027       4573025000     4573034000  20230910      11:00    12:00       0   \n",
-       "3249613       4783025300     4573032000  20230910      10:00    11:00       0   \n",
-       "\n",
-       "         age  modal  origin_purpose  dest_purpose  od_dist_avg  \\\n",
-       "1096       0    0.0             0.0             5       163782   \n",
-       "2269       3    1.0             5.0             5        20247   \n",
-       "3874       4    0.0             4.0             5       424072   \n",
-       "4218       0    0.0             0.0             5       119100   \n",
-       "4773       4    0.0             5.0             5       128030   \n",
-       "...      ...    ...             ...           ...          ...   \n",
-       "3237279    1    1.0             5.0             5        38926   \n",
-       "3238635    5    0.0             5.0             5         9476   \n",
-       "3239981    3    0.0             5.0             5        50623   \n",
-       "3246027    3    0.0             5.0             5        46949   \n",
-       "3249613    1    0.0             5.0             5       218374   \n",
-       "\n",
-       "         od_duration_avg  od_cnts  \n",
-       "1096                 109        6  \n",
-       "2269                  28        9  \n",
-       "3874                 131        7  \n",
-       "4218                 141        9  \n",
-       "4773                 118        9  \n",
-       "...                  ...      ...  \n",
-       "3237279               27        5  \n",
-       "3238635               13        5  \n",
-       "3239981               33        6  \n",
-       "3246027               51        5  \n",
-       "3249613              100        5  \n",
-       "\n",
-       "[4173 rows x 13 columns]"
-      ]
-     },
-     "execution_count": 57,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from tqdm import tqdm\n",
-    "\n",
-    "data_frames = []\n",
-    "muju_codes = [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-    "\n",
-    "for i in tqdm(range(2, 11)):\n",
-    "    # print(f\"{i}번째 \", end=\" \")\n",
-    "    index = str(i).rjust(2, '0')\n",
-    "    df_tmp = pd.read_csv(f\"EDA/jiwon/data/od_20230901_10/od_202309{index}_1.csv\")\n",
-    "    to_muju = df_tmp['dest_hdong_cd'].isin(muju_codes) & (df_tmp['dest_purpose'] == 5)\n",
-    "    data_frames.append(df_tmp[to_muju])\n",
-    "del df_tmp\n",
-    "\n",
-    "df_od = pd.concat(data_frames, axis=0)\n",
-    "df_od"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "100%|██████████| 9/9 [00:18<00:00,  2.08s/it]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>hdong_cd</th>\n",
-       "      <th>date</th>\n",
-       "      <th>age</th>\n",
-       "      <th>stay_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>0</td>\n",
-       "      <td>15738</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>1</td>\n",
-       "      <td>26248</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>2</td>\n",
-       "      <td>21350</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>3</td>\n",
-       "      <td>32200</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>4</td>\n",
-       "      <td>37772</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31252</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>4</td>\n",
-       "      <td>5202</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31253</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>5</td>\n",
-       "      <td>7813</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31254</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>6</td>\n",
-       "      <td>6296</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31255</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>7</td>\n",
-       "      <td>5745</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31256</th>\n",
-       "      <td>5183035000</td>\n",
-       "      <td>20230910</td>\n",
-       "      <td>8</td>\n",
-       "      <td>2541</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>281450 rows × 4 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         hdong_cd      date  age  stay_cnts\n",
-       "0      1111051500  20230902    0      15738\n",
-       "1      1111051500  20230902    1      26248\n",
-       "2      1111051500  20230902    2      21350\n",
-       "3      1111051500  20230902    3      32200\n",
-       "4      1111051500  20230902    4      37772\n",
-       "...           ...       ...  ...        ...\n",
-       "31252  5183035000  20230910    4       5202\n",
-       "31253  5183035000  20230910    5       7813\n",
-       "31254  5183035000  20230910    6       6296\n",
-       "31255  5183035000  20230910    7       5745\n",
-       "31256  5183035000  20230910    8       2541\n",
-       "\n",
-       "[281450 rows x 4 columns]"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data_frames = []\n",
-    "for i in tqdm(range(2, 11)):\n",
-    "    # print(f\"9월 {i}일 \", end=\" \")\n",
-    "    index = str(i).rjust(2, '0')\n",
-    "    df_tmp = pd.read_csv(f\"EDA/jiwon/data/stay_20230901_15/stay_202309{index}_1.csv\")\n",
-    "    residents = df_tmp[(df_tmp['purpose'] == 0)]\n",
-    "    grouped_residents = residents.groupby(['hdong_cd', 'date', 'age'])['stay_cnts'].sum().reset_index()\n",
-    "    data_frames.append(grouped_residents)\n",
-    "del df_tmp\n",
-    "\n",
-    "df_stay = pd.concat(data_frames, axis=0)\n",
-    "df_stay"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 지역별 거주인원"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>hdong_cd</th>\n",
-       "      <th>stay_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>205476.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1111053000</td>\n",
-       "      <td>101129.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1111054000</td>\n",
-       "      <td>38539.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1111055000</td>\n",
-       "      <td>135173.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1111056000</td>\n",
-       "      <td>183499.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     hdong_cd  stay_cnts\n",
-       "0  1111051500   205476.0\n",
-       "1  1111053000   101129.0\n",
-       "2  1111054000    38539.0\n",
-       "3  1111055000   135173.0\n",
-       "4  1111056000   183499.0"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 지역별 전체 거주민 수\n",
-    "df_stay_all = df_stay.groupby(['hdong_cd', 'date'])['stay_cnts'].sum().reset_index()  # 날짜별 거주인구 합산\n",
-    "avg_stay_cnts_all = round(df_stay_all.groupby('hdong_cd')['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 거주인구\n",
-    "avg_stay_cnts_all.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 60,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>hdong_cd</th>\n",
-       "      <th>stay_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1111051500</td>\n",
-       "      <td>22012.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1111053000</td>\n",
-       "      <td>11963.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1111054000</td>\n",
-       "      <td>5773.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1111055000</td>\n",
-       "      <td>18550.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1111056000</td>\n",
-       "      <td>24343.0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     hdong_cd  stay_cnts\n",
-       "0  1111051500    22012.0\n",
-       "1  1111053000    11963.0\n",
-       "2  1111054000     5773.0\n",
-       "3  1111055000    18550.0\n",
-       "4  1111056000    24343.0"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 지역별 20대,50대,60대 거주민 수\n",
-    "df_stay_age = df_stay[df_stay['age'].isin([2,5,6])]  # 날짜별 20대 거주인구\n",
-    "avg_stay_cnts_age = round(df_stay_age.groupby(['hdong_cd'])['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 20대 거주인구\n",
-    "avg_stay_cnts_age.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 지역별 무주축제방문객 인원"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>dest_hdong_cd</th>\n",
-       "      <th>date</th>\n",
-       "      <th>start_time</th>\n",
-       "      <th>end_time</th>\n",
-       "      <th>gender</th>\n",
-       "      <th>age</th>\n",
-       "      <th>modal</th>\n",
-       "      <th>origin_purpose</th>\n",
-       "      <th>dest_purpose</th>\n",
-       "      <th>od_dist_avg</th>\n",
-       "      <th>od_duration_avg</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>1096</th>\n",
-       "      <td>4311374100</td>\n",
-       "      <td>4573031000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>09:00</td>\n",
-       "      <td>11:00</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>163782</td>\n",
-       "      <td>109</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2269</th>\n",
-       "      <td>4573033000</td>\n",
-       "      <td>4573025000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>20:00</td>\n",
-       "      <td>20:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>5.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>20247</td>\n",
-       "      <td>28</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3874</th>\n",
-       "      <td>4812965000</td>\n",
-       "      <td>4573034000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>16:00</td>\n",
-       "      <td>18:00</td>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>5</td>\n",
-       "      <td>424072</td>\n",
-       "      <td>131</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "      origin_hdong_cd  dest_hdong_cd      date start_time end_time  gender  \\\n",
-       "1096       4311374100     4573031000  20230902      09:00    11:00       1   \n",
-       "2269       4573033000     4573025000  20230902      20:00    20:00       0   \n",
-       "3874       4812965000     4573034000  20230902      16:00    18:00       0   \n",
-       "\n",
-       "      age  modal  origin_purpose  dest_purpose  od_dist_avg  od_duration_avg  \\\n",
-       "1096    0    0.0             0.0             5       163782              109   \n",
-       "2269    3    1.0             5.0             5        20247               28   \n",
-       "3874    4    0.0             4.0             5       424072              131   \n",
-       "\n",
-       "      od_cnts  \n",
-       "1096        6  \n",
-       "2269        9  \n",
-       "3874        7  "
-      ]
-     },
-     "execution_count": 61,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df_od.head(3)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>date</th>\n",
-       "      <th>age</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1117068500</td>\n",
-       "      <td>20230908</td>\n",
-       "      <td>0</td>\n",
-       "      <td>12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1120067000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>4</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1121584000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>0</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1132051100</td>\n",
-       "      <td>20230909</td>\n",
-       "      <td>4</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1135064000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>0</td>\n",
-       "      <td>64</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1703</th>\n",
-       "      <td>5113066000</td>\n",
-       "      <td>20230902</td>\n",
-       "      <td>0</td>\n",
-       "      <td>12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1704</th>\n",
-       "      <td>5113067500</td>\n",
-       "      <td>20230907</td>\n",
-       "      <td>3</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1705</th>\n",
-       "      <td>5113067500</td>\n",
-       "      <td>20230909</td>\n",
-       "      <td>3</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1706</th>\n",
-       "      <td>5113067500</td>\n",
-       "      <td>20230909</td>\n",
-       "      <td>4</td>\n",
-       "      <td>12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1707</th>\n",
-       "      <td>5181033000</td>\n",
-       "      <td>20230908</td>\n",
-       "      <td>0</td>\n",
-       "      <td>50</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>1708 rows × 4 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "      origin_hdong_cd      date  age  od_cnts\n",
-       "0          1117068500  20230908    0       12\n",
-       "1          1120067000  20230902    4        6\n",
-       "2          1121584000  20230902    0        9\n",
-       "3          1132051100  20230909    4        6\n",
-       "4          1135064000  20230902    0       64\n",
-       "...               ...       ...  ...      ...\n",
-       "1703       5113066000  20230902    0       12\n",
-       "1704       5113067500  20230907    3        6\n",
-       "1705       5113067500  20230909    3        6\n",
-       "1706       5113067500  20230909    4       12\n",
-       "1707       5181033000  20230908    0       50\n",
-       "\n",
-       "[1708 rows x 4 columns]"
-      ]
-     },
-     "execution_count": 62,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 그룹화\n",
-    "df_od_group = df_od.groupby(['origin_hdong_cd', 'date', 'age'])['od_cnts'].sum().reset_index()\n",
-    "df_od_group"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1117068500</td>\n",
-       "      <td>12</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1120067000</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1121584000</td>\n",
-       "      <td>9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1132051100</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1135064000</td>\n",
-       "      <td>70</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "   origin_hdong_cd  od_cnts\n",
-       "0       1117068500       12\n",
-       "1       1120067000        6\n",
-       "2       1121584000        9\n",
-       "3       1132051100        6\n",
-       "4       1135064000       70"
-      ]
-     },
-     "execution_count": 63,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 지역별 전체 무주축제방문객 수\n",
-    "df_od_all = df_od_group.groupby(['origin_hdong_cd', 'date'])['od_cnts'].sum().reset_index()  # 날짜별 방문객수 합산\n",
-    "sum_od_cnts_all = round(df_od_all.groupby(['origin_hdong_cd'])['od_cnts'].sum().reset_index(), 0)  # 해당 지역에서 온 전체 방문객수\n",
-    "sum_od_cnts_all.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1135064000</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1138051000</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1141062000</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1141072000</td>\n",
-       "      <td>14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1144060000</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>310</th>\n",
-       "      <td>4888034000</td>\n",
-       "      <td>13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>311</th>\n",
-       "      <td>4888035000</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>312</th>\n",
-       "      <td>4888037000</td>\n",
-       "      <td>13</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>313</th>\n",
-       "      <td>4888040000</td>\n",
-       "      <td>17</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>314</th>\n",
-       "      <td>4889045000</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>315 rows × 2 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     origin_hdong_cd  od_cnts\n",
-       "0         1135064000        6\n",
-       "1         1138051000        5\n",
-       "2         1141062000        7\n",
-       "3         1141072000       14\n",
-       "4         1144060000        8\n",
-       "..               ...      ...\n",
-       "310       4888034000       13\n",
-       "311       4888035000        6\n",
-       "312       4888037000       13\n",
-       "313       4888040000       17\n",
-       "314       4889045000        8\n",
-       "\n",
-       "[315 rows x 2 columns]"
-      ]
-     },
-     "execution_count": 64,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 지역별 20대,50대,60대 무주축제방문객 수\n",
-    "df_od_age = df_od_group[df_od_group['age'].isin([2,5,6])]\n",
-    "sum_od_cnts_age = round(df_od_age.groupby('origin_hdong_cd')['od_cnts'].sum().reset_index(), 0)\n",
-    "sum_od_cnts_age"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 함수"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 노드 간 정보"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 65,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 시도시군구명으로 위경도 좌표를 반환하는 함수\n",
-    "def get_coordinates(lst):\n",
-    "    coordinates = []\n",
-    "    for name in lst:\n",
-    "        try:\n",
-    "            # '시도 시군구'로 '위도', '경도' 가져옴\n",
-    "            target = address[address['시도 시군구'] == name][['위도','경도']].iloc[0]\n",
-    "            x, y = target.iloc[0], target.iloc[1]\n",
-    "            coordinates.append((x,y))\n",
-    "        except IndexError:\n",
-    "            # 해당 '시도 시군구'에 대한 데이터가 없는 경우\n",
-    "            print(f\"{name} 지역의 위도, 경도 정보가 없습니다.\")\n",
-    "    return coordinates"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 66,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import yaml\n",
-    "import requests\n",
-    "\n",
-    "# api 사용을 위한 key값 가져오기 \n",
-    "with open(\"config.yaml\", \"r\") as file:\n",
-    "    config = yaml.safe_load(file)\n",
-    "naver_api_id = config['naver api']['id']\n",
-    "naver_api_key = config['naver api']['key']\n",
-    "kakao_api_key = config['kakao api']['key']\n",
-    "\n",
-    "# 네이버 api 요청 함수\n",
-    "def naver_request(start, goal):\n",
-    "    # 요청\n",
-    "    url = 'https://naveropenapi.apigw.ntruss.com/map-direction/v1/driving'\n",
-    "    params = {\n",
-    "        'goal': f'{goal[1]},{goal[0]}',\n",
-    "        'start': f'{start[1]},{start[0]}',\n",
-    "    }\n",
-    "    headers = {\n",
-    "        'x-ncp-apigw-api-key-id': naver_api_id,\n",
-    "        'x-ncp-apigw-api-key': naver_api_key\n",
-    "    }\n",
-    "    response = requests.get(url, headers=headers, params=params)\n",
-    "\n",
-    "    # 응답\n",
-    "    data = response.json()\n",
-    "    if data['code'] == 0:\n",
-    "        if data['route']['traoptimal']:\n",
-    "            summary = data['route']['traoptimal'][0]['summary']\n",
-    "            distance = summary['distance']\n",
-    "            duration = summary['duration']\n",
-    "            return distance, duration\n",
-    "        else:\n",
-    "            print(\"응답 에러: 'traoptimal' 데이터가 없습니다.\")\n",
-    "            return -1, -1\n",
-    "    else:\n",
-    "        print(\"요청 실패: \", data['message'])\n",
-    "        return -1, -1\n",
-    "\n",
-    "# 카카오 api 요청 함수\n",
-    "def kakao_request(start, goal):\n",
-    "    # 요청\n",
-    "    url = 'https://apis-navi.kakaomobility.com/v1/directions'\n",
-    "    params = {\n",
-    "        'origin': f'{start[1]},{start[0]}',\n",
-    "        'destination': f'{goal[1]},{goal[0]}',\n",
-    "        'alternatives': True,\n",
-    "    }\n",
-    "    headers = {\n",
-    "        'Authorization': f'KakaoAK {kakao_api_key}'\n",
-    "    }\n",
-    "    response = requests.get(url, headers=headers, params=params)\n",
-    "\n",
-    "    # 응답\n",
-    "    if response.status_code == 200:\n",
-    "        data = response.json()\n",
-    "        if data['routes']:\n",
-    "            summary = data['routes'][0]['summary']\n",
-    "            distance = summary.get('distance')\n",
-    "            duration = summary.get('duration')\n",
-    "            return distance, duration\n",
-    "        else:\n",
-    "            print(\"응답 에러: 'routes' 데이터가 없습니다.\")\n",
-    "            return -1, -1\n",
-    "    else:\n",
-    "        print(\"요청 실패\")\n",
-    "        return -1, -1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 67,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 노드 간 이동시간, 이동거리 테이블 반환하는 함수\n",
-    "def get_path_info(coordinates, request_func):\n",
-    "    n = len(coordinates)\n",
-    "    distance_table = [[0] * n for _ in range(n)]\n",
-    "    duration_table = [[0] * n for _ in range(n)]\n",
-    "\n",
-    "    for i in range(n):\n",
-    "        for j in range(n):\n",
-    "            if j > i:\n",
-    "                start = coordinates[i]\n",
-    "                goal = coordinates[j]\n",
-    "                distance, duration = request_func(start, goal)\n",
-    "                distance_table[i][j], distance_table[j][i] = distance, distance\n",
-    "                duration_table[i][j], duration_table[j][i] = duration, duration\n",
-    "\n",
-    "    return distance_table, duration_table"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 가중치"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 68,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "지역명: 세종특별자치시\n",
-      "관련 행정동코드:  [3600000000, 3611000000, 3611025000, 3611031000, 3611032000, 3611033000, 3611034000, 3611035000, 3611036000, 3611037000, 3611038000, 3611039000, 3611051000, 3611051500, 3611051800, 3611052000, 3611052300, 3611052500, 3611053000, 3611054000, 3611055000, 3611055500, 3611055600, 3611056000, 3611057000, 3611058000]\n",
-      "총 거주인원: 3048131.0 ,  20/50/60대 거주인원: 290518.0 \n",
-      "\n",
-      "지역명: 대전광역시 유성구\n",
-      "관련 행정동코드:  [3020000000, 3020052000, 3020052600, 3020052700, 3020053000, 3020054000, 3020054600, 3020054700, 3020054800, 3020055000, 3020057000, 3020058000, 3020060000, 3020061000]\n",
-      "총 거주인원: 3820791.0 ,  20/50/60대 거주인원: 424653.0 \n",
-      "\n",
-      "지역명: 대전광역시 서구\n",
-      "관련 행정동코드:  [3017000000, 3017051000, 3017052000, 3017053000, 3017053500, 3017054000, 3017055000, 3017055500, 3017056000, 3017057000, 3017057500, 3017058100, 3017058200, 3017058600, 3017058700, 3017058800, 3017059000, 3017059300, 3017059600, 3017059700, 3017060000, 3017063000, 3017064000, 3017065000, 3017066000]\n",
-      "총 거주인원: 5536840.0 ,  20/50/60대 거주인원: 674439.0 \n",
-      "\n",
-      "지역명: 대전광역시 대덕구\n",
-      "관련 행정동코드:  [3023000000, 3023051000, 3023052000, 3023052500, 3023053300, 3023054300, 3023054600, 3023055000, 3023056000, 3023057000, 3023058000, 3023060000, 3023061000]\n",
-      "총 거주인원: 2377042.0 ,  20/50/60대 거주인원: 306052.0 \n",
-      "\n",
-      "지역명: 대전광역시 중구\n",
-      "관련 행정동코드:  [3014000000, 3014053500, 3014055000, 3014056000, 3014057500, 3014060500, 3014062000, 3014063000, 3014064000, 3014065500, 3014067000, 3014068000, 3014069000, 3014070000, 3014071000, 3014072000, 3014073000, 3014074000]\n",
-      "총 거주인원: 2922017.0 ,  20/50/60대 거주인원: 354956.0 \n",
-      "\n",
-      "지역명: 충청남도 금산군\n",
-      "관련 행정동코드:  [4471000000, 4471025000, 4471031000, 4471032000, 4471033000, 4471034000, 4471035000, 4471036000, 4471037000, 4471038000, 4471039000]\n",
-      "총 거주인원: 554830.0 ,  20/50/60대 거주인원: 76765.0 \n",
-      "\n",
-      "지역명: 충청북도 영동군\n",
-      "관련 행정동코드:  [4374000000, 4374025000, 4374031000, 4374032000, 4374033500, 4374034000, 4374035000, 4374036000, 4374037000, 4374038000, 4374039000, 4374040000]\n",
-      "총 거주인원: 450046.0 ,  20/50/60대 거주인원: 61760.0 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 거주인원: 211731.0 ,  20/50/60대 거주인원: 26123.0 \n",
-      "\n",
-      "[3048131, 3820791, 5536840, 2377042, 2922017, 554830, 450046, 211731]\n",
-      "[290518, 424653, 674439, 306052, 354956, 76765, 61760, 26123]\n"
-     ]
-    }
-   ],
-   "source": [
-    "# 각 지역 거주인원\n",
-    "def get_residents_num(lst):\n",
-    "    residents_num = []\n",
-    "    residents_num_256 = []\n",
-    "    for name in lst:\n",
-    "        print(\"지역명:\", name)\n",
-    "        codes = address[address['시도 시군구'] == name]['행정동코드'].unique().tolist()\n",
-    "        print(\"관련 행정동코드: \", codes)\n",
-    "        # 지역 내 행정동코드들의 거주인원 합산\n",
-    "        cnt_all = 0\n",
-    "        cnt_256 = 0\n",
-    "        for code in codes:\n",
-    "            tmp_for_all = avg_stay_cnts_all[avg_stay_cnts_all['hdong_cd']==code]\n",
-    "            if not tmp_for_all.empty:\n",
-    "                cnt_all += tmp_for_all['stay_cnts'].iloc[0]\n",
-    "            tmp_for_256 = avg_stay_cnts_age[avg_stay_cnts_age['hdong_cd']==code]\n",
-    "            if not tmp_for_256.empty:\n",
-    "                cnt_256 += tmp_for_256['stay_cnts'].iloc[0]\n",
-    "        residents_num.append(int(cnt_all))\n",
-    "        residents_num_256.append(int(cnt_256))\n",
-    "        print(\"총 거주인원:\", cnt_all, \",  20/50/60대 거주인원:\", cnt_256, \"\\n\")\n",
-    "    return residents_num, residents_num_256\n",
-    "\n",
-    "# 대전 지역으로 테스트\n",
-    "daejun = ['세종특별자치시', '대전광역시 유성구', '대전광역시 서구', '대전광역시 대덕구', '대전광역시 중구', '충청남도 금산군', '충청북도 영동군', '전라북도 무주군']\n",
-    "\n",
-    "daejun_residents_num, daejun_residents_num_256 = get_residents_num(daejun)\n",
-    "\n",
-    "print(daejun_residents_num)\n",
-    "print(daejun_residents_num_256)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 69,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "지역명: 세종특별자치시\n",
-      "관련 행정동코드:  [3600000000, 3611000000, 3611025000, 3611031000, 3611032000, 3611033000, 3611034000, 3611035000, 3611036000, 3611037000, 3611038000, 3611039000, 3611051000, 3611051500, 3611051800, 3611052000, 3611052300, 3611052500, 3611053000, 3611054000, 3611055000, 3611055500, 3611055600, 3611056000, 3611057000, 3611058000]\n",
-      "총 방문객 수: 758 ,  20/50/60대 방문객 수: 41 \n",
-      "\n",
-      "지역명: 대전광역시 유성구\n",
-      "관련 행정동코드:  [3020000000, 3020052000, 3020052600, 3020052700, 3020053000, 3020054000, 3020054600, 3020054700, 3020054800, 3020055000, 3020057000, 3020058000, 3020060000, 3020061000]\n",
-      "총 방문객 수: 895 ,  20/50/60대 방문객 수: 189 \n",
-      "\n",
-      "지역명: 대전광역시 서구\n",
-      "관련 행정동코드:  [3017000000, 3017051000, 3017052000, 3017053000, 3017053500, 3017054000, 3017055000, 3017055500, 3017056000, 3017057000, 3017057500, 3017058100, 3017058200, 3017058600, 3017058700, 3017058800, 3017059000, 3017059300, 3017059600, 3017059700, 3017060000, 3017063000, 3017064000, 3017065000, 3017066000]\n",
-      "총 방문객 수: 1182 ,  20/50/60대 방문객 수: 304 \n",
-      "\n",
-      "지역명: 대전광역시 대덕구\n",
-      "관련 행정동코드:  [3023000000, 3023051000, 3023052000, 3023052500, 3023053300, 3023054300, 3023054600, 3023055000, 3023056000, 3023057000, 3023058000, 3023060000, 3023061000]\n",
-      "총 방문객 수: 375 ,  20/50/60대 방문객 수: 60 \n",
-      "\n",
-      "지역명: 대전광역시 중구\n",
-      "관련 행정동코드:  [3014000000, 3014053500, 3014055000, 3014056000, 3014057500, 3014060500, 3014062000, 3014063000, 3014064000, 3014065500, 3014067000, 3014068000, 3014069000, 3014070000, 3014071000, 3014072000, 3014073000, 3014074000]\n",
-      "총 방문객 수: 602 ,  20/50/60대 방문객 수: 109 \n",
-      "\n",
-      "지역명: 충청남도 금산군\n",
-      "관련 행정동코드:  [4471000000, 4471025000, 4471031000, 4471032000, 4471033000, 4471034000, 4471035000, 4471036000, 4471037000, 4471038000, 4471039000]\n",
-      "총 방문객 수: 538 ,  20/50/60대 방문객 수: 92 \n",
-      "\n",
-      "지역명: 충청북도 영동군\n",
-      "관련 행정동코드:  [4374000000, 4374025000, 4374031000, 4374032000, 4374033500, 4374034000, 4374035000, 4374036000, 4374037000, 4374038000, 4374039000, 4374040000]\n",
-      "총 방문객 수: 618 ,  20/50/60대 방문객 수: 129 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 방문객 수: 24957 ,  20/50/60대 방문객 수: 4768 \n",
-      "\n",
-      "[758, 895, 1182, 375, 602, 538, 618, 24957]\n",
-      "[41, 189, 304, 60, 109, 92, 129, 4768]\n"
-     ]
-    }
-   ],
-   "source": [
-    "# 각 지역 방문객\n",
-    "def get_visitors_num(lst):\n",
-    "    visitors_num = []\n",
-    "    visitors_num_256 = []\n",
-    "    for name in lst:\n",
-    "        print(\"지역명:\", name)\n",
-    "        codes = address[address['시도 시군구'] == name]['행정동코드'].unique().tolist()\n",
-    "        print(\"관련 행정동코드: \", codes)\n",
-    "        # 지역 내 행정동코드들의 방문객 합산\n",
-    "        cnt_all = 0\n",
-    "        cnt_256 = 0\n",
-    "        for code in codes:\n",
-    "            tmp_for_all = sum_od_cnts_all[sum_od_cnts_all['origin_hdong_cd']==code]\n",
-    "            if not tmp_for_all.empty:\n",
-    "                cnt_all += tmp_for_all['od_cnts'].iloc[0]\n",
-    "            tmp_for_256 = sum_od_cnts_age[sum_od_cnts_age['origin_hdong_cd']==code]\n",
-    "            if not tmp_for_256.empty:\n",
-    "                cnt_256 += tmp_for_256['od_cnts'].iloc[0]\n",
-    "        visitors_num.append(int(cnt_all))\n",
-    "        visitors_num_256.append(int(cnt_256))\n",
-    "        print(\"총 방문객 수:\", cnt_all, \",  20/50/60대 방문객 수:\", cnt_256, \"\\n\")\n",
-    "    return visitors_num, visitors_num_256\n",
-    "\n",
-    "# 대전 지역으로 테스트\n",
-    "daejun_visitors_num, daejun_visitors_num_256 = get_visitors_num(daejun)\n",
-    "\n",
-    "print(daejun_visitors_num)\n",
-    "print(daejun_visitors_num_256)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 70,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>origin_hdong_cd</th>\n",
-       "      <th>시도 시군구</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1135064000</td>\n",
-       "      <td>서울특별시 노원구</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1138051000</td>\n",
-       "      <td>서울특별시 은평구</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1141062000</td>\n",
-       "      <td>서울특별시 서대문구</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1141072000</td>\n",
-       "      <td>서울특별시 서대문구</td>\n",
-       "      <td>14</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1144060000</td>\n",
-       "      <td>서울특별시 마포구</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>273</th>\n",
-       "      <td>4888025000</td>\n",
-       "      <td>경상남도 거창군</td>\n",
-       "      <td>45</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>274</th>\n",
-       "      <td>4888034000</td>\n",
-       "      <td>경상남도 거창군</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>275</th>\n",
-       "      <td>4888037000</td>\n",
-       "      <td>경상남도 거창군</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>276</th>\n",
-       "      <td>4888040000</td>\n",
-       "      <td>경상남도 거창군</td>\n",
-       "      <td>7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>277</th>\n",
-       "      <td>4889045000</td>\n",
-       "      <td>경상남도 합천군</td>\n",
-       "      <td>8</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>278 rows × 3 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "     origin_hdong_cd      시도 시군구  od_cnts\n",
-       "0         1135064000   서울특별시 노원구        6\n",
-       "1         1138051000   서울특별시 은평구        5\n",
-       "2         1141062000  서울특별시 서대문구        7\n",
-       "3         1141072000  서울특별시 서대문구       14\n",
-       "4         1144060000   서울특별시 마포구        8\n",
-       "..               ...         ...      ...\n",
-       "273       4888025000    경상남도 거창군       45\n",
-       "274       4888034000    경상남도 거창군        8\n",
-       "275       4888037000    경상남도 거창군        8\n",
-       "276       4888040000    경상남도 거창군        7\n",
-       "277       4889045000    경상남도 합천군        8\n",
-       "\n",
-       "[278 rows x 3 columns]"
-      ]
-     },
-     "execution_count": 70,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 전체 데이터에서 20대 어디서 오는지 확인\n",
-    "age20 = df_od[df_od['age']==2][['origin_hdong_cd', 'date', 'age', 'od_cnts']]\n",
-    "age20 = age20.groupby(['origin_hdong_cd'])['od_cnts'].sum().reset_index()\n",
-    "unique_address = address.drop_duplicates(subset=['행정동코드'])\n",
-    "age20eng = pd.merge(age20, unique_address[['행정동코드','시도 시군구']], 'left', left_on='origin_hdong_cd', right_on='행정동코드')\n",
-    "age20eng = age20eng[['origin_hdong_cd', '시도 시군구', 'od_cnts']]\n",
-    "age20eng"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 71,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 지역별 20/50/60대 방문율\n",
-    "def get_proportion(a, b, n):\n",
-    "    lst = []\n",
-    "    for i in range(n):\n",
-    "        lst.append(a[i] / b[i])\n",
-    "    return lst"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 72,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "\n",
-    "def softmax(weights):\n",
-    "    e = np.exp(weights - np.max(weights))  # 오버플로 방지를 위해 최대값을 빼줌\n",
-    "    return e / e.sum()\n",
-    "\n",
-    "def get_weights(nodes, weights):    \n",
-    "    residents_num, residents_num_256 = get_residents_num(nodes)\n",
-    "    visitors_num, visitors_num_256 = get_visitors_num(nodes)\n",
-    "    # 방식1: 해당 지역의 2/5/60대 거주민 중 축제방문객 비율. (2/5/60대 축제 관심도가 높은 곳을 우선)\n",
-    "    # weight_age = get_proportion(visitors_num_256, residents_num_256, len(nodes))\n",
-    "    # 방식2: 해당 지역의 전체 축제방문객 중 2/5/60대 비율. ()\n",
-    "    weight_age = get_proportion(visitors_num_256, visitors_num, len(nodes))\n",
-    "    # 방식3: 해당 지역의 거주민 중 2/5/60대 거주민 비율. (단순히 2/5/60대가 많은 곳을 우선)\n",
-    "    # weight_age = get_proportion(residents_num_256, residents_num, len(nodes))\n",
-    "\n",
-    "    for i, w in enumerate(weight_age):\n",
-    "        weights[i] += w\n",
-    "\n",
-    "    softmax_weights = softmax(weights)\n",
-    "    \n",
-    "    stations = {nodes: weight for nodes, weight in zip(nodes, softmax_weights)}\n",
-    "    print(stations)\n",
-    "\n",
-    "    return stations"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 탐색"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 73,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import networkx as nx\n",
-    "\n",
-    "# 모든 경로 찾기\n",
-    "def find_all_routes(G, start, target, visited=None, path=None):\n",
-    "    if visited is None:\n",
-    "        visited = set()\n",
-    "    if path is None:\n",
-    "        path = []\n",
-    "\n",
-    "    visited.add(start)\n",
-    "    path.append(start)\n",
-    "\n",
-    "    if start == target:\n",
-    "        yield path.copy()\n",
-    "    else:\n",
-    "        for neighbor in G.neighbors(start):\n",
-    "            if neighbor not in visited:\n",
-    "                yield from find_all_routes(G, neighbor, target, visited, path)\n",
-    "\n",
-    "    path.pop()\n",
-    "    visited.remove(start)\n",
-    "\n",
-    "# 최적 경로 탐색 함수\n",
-    "def find_optimal_routes(G, stations, min_threshold, max_threshold, step):\n",
-    "    optimal_routes = []\n",
-    "    max_stops = 0\n",
-    "    explored_routes = set()  # 탐색된 경로를 저장할 집합\n",
-    "\n",
-    "    # 여러 배수 값을 탐색\n",
-    "    for threshold in np.arange(min_threshold, max_threshold + step, step):\n",
-    "\n",
-    "        for station in stations.keys():\n",
-    "            if station != \"전라북도 무주군\":  # 목적지가 아니면\n",
-    "                routes = list(find_all_routes(G, station, \"전라북도 무주군\"))\n",
-    "\n",
-    "                for route in routes:\n",
-    "                    valid_route = True\n",
-    "                    total_distance = 0\n",
-    "                    total_time = 0\n",
-    "                    total_weight = 0  # 가중치 누적\n",
-    "\n",
-    "                    # 각 경로의 모든 구간에 대해 확인\n",
-    "                    for i in range(len(route) - 1):\n",
-    "                        current_station = route[i]\n",
-    "\n",
-    "                        # 현재 노드에서 무주군으로 바로 이동할 때의 거리와 시간\n",
-    "                        if \"전라북도 무주군\" in G[current_station]:  # 직접 경로가 있는 경우에만\n",
-    "                            direct_distance = G[current_station][\"전라북도 무주군\"]['distance']\n",
-    "                            direct_time = G[current_station][\"전라북도 무주군\"]['time']\n",
-    "\n",
-    "                            # 현재 구간의 거리와 시간을 누적\n",
-    "                            total_distance += G[route[i]][route[i + 1]]['distance']\n",
-    "                            total_time += G[route[i]][route[i + 1]]['time']\n",
-    "\n",
-    "                            # 각 중간 노드에서도 주어진 배수(factor) 조건 확인\n",
-    "                            if total_distance > direct_distance * threshold or total_time > direct_time * threshold:\n",
-    "                                valid_route = False\n",
-    "                                break\n",
-    "\n",
-    "                        # 가중치 누적 (출발지 제외)\n",
-    "                        if i > 0:\n",
-    "                            total_weight += stations[current_station]\n",
-    "\n",
-    "                    if valid_route:\n",
-    "                        # 경로를 집합에 저장할 수 있는 형태로 변환 (정렬하여 순서 상관없이 비교 하기 위함)\n",
-    "                        route_tuple = tuple(sorted(route))\n",
-    "\n",
-    "                        # 만약 해당 경로가 이전 배수에서 이미 탐색되었다면 제외\n",
-    "                        if route_tuple not in explored_routes:\n",
-    "                            explored_routes.add(route_tuple)  # 새로운 경로로 저장\n",
-    "\n",
-    "                            # 최대 정거장 수 확인\n",
-    "                            if len(route) > max_stops:\n",
-    "                                max_stops = len(route)\n",
-    "                                optimal_routes = [(route, total_distance, total_time, total_weight, threshold)]\n",
-    "                            elif len(route) == max_stops:\n",
-    "                                optimal_routes.append((route, total_distance, total_time, total_weight, threshold))\n",
-    "\n",
-    "    return optimal_routes\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 74,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def print_optimal_routes(optimal_routes, name):\n",
-    "    print(f\"{name}지역 최적의 셔틀 노선\")\n",
-    "    if optimal_routes:\n",
-    "        for route, total_distance, total_time, total_weight, threshold in optimal_routes:\n",
-    "            # 총 거리를 km로 변환하고 소수점 아래 두째 자리까지 포맷\n",
-    "            total_distance_km = total_distance / 1000  # 미터를 킬로미터로 변환\n",
-    "            total_distance_formatted = f\"{total_distance_km:.2f} km\"\n",
-    "\n",
-    "            # 총 시간을 시간과 분으로 변환 (반올림)\n",
-    "            total_time_hours = total_time // 60\n",
-    "            total_time_minutes = round(total_time % 60)\n",
-    "\n",
-    "            print(f\"최적의 셔틀 노선: {route} | 총 거리: {total_distance_formatted} | 총 시간: {total_time_hours}시간 {total_time_minutes}분 | 총 가중치: {total_weight} | threshold: {threshold:.2f}\")\n",
-    "    else:\n",
-    "        print(\"유효한 경로가 없습니다.\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 메인"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# 경유지 리스트\n",
-    "daejun = ['세종특별자치시', '대전광역시 유성구', '대전광역시 서구', '대전광역시 대덕구', '대전광역시 중구', '충청남도 금산군', '충청북도 영동군', '전라북도 무주군']\n",
-    "jeonbuk = ['전라북도 군산시', '전라북도 익산시', '전라북도 전주시 완산구', '전라북도 전주시 덕진구', '전라북도 진안군', '전라북도 장수군', '전라북도 무주군']\n",
-    "# 방문객 수에 근거한 노드별 초기 가중치\n",
-    "daejun_weights = [1, 2, 2, 1, 1, 1, 2, 0]  \n",
-    "jeonbuk_weights = [1, 1, 2, 2, 1, 2, 0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 76,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def search(nodes, weights, name):\n",
-    "    # 1. 위경도 좌표 기반으로 경유지 간 이동거리, 이동시간 테이블 만듦\n",
-    "\n",
-    "    # 경유지 위경도 좌표 \n",
-    "    coordinates = get_coordinates(nodes) \n",
-    "\n",
-    "    # 네이버 api\n",
-    "    # n_distance_table, n_duration_table = get_path_info(coordinates, naver_request)\n",
-    "    # n_duration_min_table = [[round(value / 3600, 2) for value in row] for row in n_duration_table]\n",
-    "\n",
-    "    # 카카오 api\n",
-    "    k_distance_table, k_duration_table = get_path_info(coordinates, kakao_request)\n",
-    "    k_duration_min_table = [[round(value / 60, 2) for value in row] for row in k_duration_table]\n",
-    "\n",
-    "\n",
-    "    distance_table = k_distance_table\n",
-    "    duration_table = k_duration_min_table\n",
-    "\n",
-    "    # 2. 정거장 후보지와 가중치\n",
-    "    stations = get_weights(nodes, weights)  \n",
-    "\n",
-    "    # 3. 탐색\n",
-    "    # 그래프 생성\n",
-    "    G = nx.DiGraph()\n",
-    "\n",
-    "    # 그래프에 엣지 추가\n",
-    "    for i, from_station in enumerate(stations.keys()):\n",
-    "        for j, to_station in enumerate(stations.keys()):\n",
-    "            if i != j:\n",
-    "                G.add_edge(from_station, to_station, \n",
-    "                        distance=distance_table[i][j], \n",
-    "                        time=duration_table[i][j])\n",
-    "                \n",
-    "    # 탐색 범위 설정 (예: 1.1부터 1.5까지 0.1 간격으로 탐색)\n",
-    "    min_factor = 1.1\n",
-    "    max_factor = 1.5\n",
-    "    step = 0.1\n",
-    "\n",
-    "    # 최적 경로 탐색 실행\n",
-    "    optimal_routes = find_optimal_routes(G, stations, min_factor, max_factor, step)\n",
-    "\n",
-    "    # 결과 출력\n",
-    "    print_optimal_routes(optimal_routes, name)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "지역명: 세종특별자치시\n",
-      "관련 행정동코드:  [3600000000, 3611000000, 3611025000, 3611031000, 3611032000, 3611033000, 3611034000, 3611035000, 3611036000, 3611037000, 3611038000, 3611039000, 3611051000, 3611051500, 3611051800, 3611052000, 3611052300, 3611052500, 3611053000, 3611054000, 3611055000, 3611055500, 3611055600, 3611056000, 3611057000, 3611058000]\n",
-      "총 거주인원: 3048131.0 ,  20/50/60대 거주인원: 290518.0 \n",
-      "\n",
-      "지역명: 대전광역시 유성구\n",
-      "관련 행정동코드:  [3020000000, 3020052000, 3020052600, 3020052700, 3020053000, 3020054000, 3020054600, 3020054700, 3020054800, 3020055000, 3020057000, 3020058000, 3020060000, 3020061000]\n",
-      "총 거주인원: 3820791.0 ,  20/50/60대 거주인원: 424653.0 \n",
-      "\n",
-      "지역명: 대전광역시 서구\n",
-      "관련 행정동코드:  [3017000000, 3017051000, 3017052000, 3017053000, 3017053500, 3017054000, 3017055000, 3017055500, 3017056000, 3017057000, 3017057500, 3017058100, 3017058200, 3017058600, 3017058700, 3017058800, 3017059000, 3017059300, 3017059600, 3017059700, 3017060000, 3017063000, 3017064000, 3017065000, 3017066000]\n",
-      "총 거주인원: 5536840.0 ,  20/50/60대 거주인원: 674439.0 \n",
-      "\n",
-      "지역명: 대전광역시 대덕구\n",
-      "관련 행정동코드:  [3023000000, 3023051000, 3023052000, 3023052500, 3023053300, 3023054300, 3023054600, 3023055000, 3023056000, 3023057000, 3023058000, 3023060000, 3023061000]\n",
-      "총 거주인원: 2377042.0 ,  20/50/60대 거주인원: 306052.0 \n",
-      "\n",
-      "지역명: 대전광역시 중구\n",
-      "관련 행정동코드:  [3014000000, 3014053500, 3014055000, 3014056000, 3014057500, 3014060500, 3014062000, 3014063000, 3014064000, 3014065500, 3014067000, 3014068000, 3014069000, 3014070000, 3014071000, 3014072000, 3014073000, 3014074000]\n",
-      "총 거주인원: 2922017.0 ,  20/50/60대 거주인원: 354956.0 \n",
-      "\n",
-      "지역명: 충청남도 금산군\n",
-      "관련 행정동코드:  [4471000000, 4471025000, 4471031000, 4471032000, 4471033000, 4471034000, 4471035000, 4471036000, 4471037000, 4471038000, 4471039000]\n",
-      "총 거주인원: 554830.0 ,  20/50/60대 거주인원: 76765.0 \n",
-      "\n",
-      "지역명: 충청북도 영동군\n",
-      "관련 행정동코드:  [4374000000, 4374025000, 4374031000, 4374032000, 4374033500, 4374034000, 4374035000, 4374036000, 4374037000, 4374038000, 4374039000, 4374040000]\n",
-      "총 거주인원: 450046.0 ,  20/50/60대 거주인원: 61760.0 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 거주인원: 211731.0 ,  20/50/60대 거주인원: 26123.0 \n",
-      "\n",
-      "지역명: 세종특별자치시\n",
-      "관련 행정동코드:  [3600000000, 3611000000, 3611025000, 3611031000, 3611032000, 3611033000, 3611034000, 3611035000, 3611036000, 3611037000, 3611038000, 3611039000, 3611051000, 3611051500, 3611051800, 3611052000, 3611052300, 3611052500, 3611053000, 3611054000, 3611055000, 3611055500, 3611055600, 3611056000, 3611057000, 3611058000]\n",
-      "총 방문객 수: 758 ,  20/50/60대 방문객 수: 41 \n",
-      "\n",
-      "지역명: 대전광역시 유성구\n",
-      "관련 행정동코드:  [3020000000, 3020052000, 3020052600, 3020052700, 3020053000, 3020054000, 3020054600, 3020054700, 3020054800, 3020055000, 3020057000, 3020058000, 3020060000, 3020061000]\n",
-      "총 방문객 수: 895 ,  20/50/60대 방문객 수: 189 \n",
-      "\n",
-      "지역명: 대전광역시 서구\n",
-      "관련 행정동코드:  [3017000000, 3017051000, 3017052000, 3017053000, 3017053500, 3017054000, 3017055000, 3017055500, 3017056000, 3017057000, 3017057500, 3017058100, 3017058200, 3017058600, 3017058700, 3017058800, 3017059000, 3017059300, 3017059600, 3017059700, 3017060000, 3017063000, 3017064000, 3017065000, 3017066000]\n",
-      "총 방문객 수: 1182 ,  20/50/60대 방문객 수: 304 \n",
-      "\n",
-      "지역명: 대전광역시 대덕구\n",
-      "관련 행정동코드:  [3023000000, 3023051000, 3023052000, 3023052500, 3023053300, 3023054300, 3023054600, 3023055000, 3023056000, 3023057000, 3023058000, 3023060000, 3023061000]\n",
-      "총 방문객 수: 375 ,  20/50/60대 방문객 수: 60 \n",
-      "\n",
-      "지역명: 대전광역시 중구\n",
-      "관련 행정동코드:  [3014000000, 3014053500, 3014055000, 3014056000, 3014057500, 3014060500, 3014062000, 3014063000, 3014064000, 3014065500, 3014067000, 3014068000, 3014069000, 3014070000, 3014071000, 3014072000, 3014073000, 3014074000]\n",
-      "총 방문객 수: 602 ,  20/50/60대 방문객 수: 109 \n",
-      "\n",
-      "지역명: 충청남도 금산군\n",
-      "관련 행정동코드:  [4471000000, 4471025000, 4471031000, 4471032000, 4471033000, 4471034000, 4471035000, 4471036000, 4471037000, 4471038000, 4471039000]\n",
-      "총 방문객 수: 538 ,  20/50/60대 방문객 수: 92 \n",
-      "\n",
-      "지역명: 충청북도 영동군\n",
-      "관련 행정동코드:  [4374000000, 4374025000, 4374031000, 4374032000, 4374033500, 4374034000, 4374035000, 4374036000, 4374037000, 4374038000, 4374039000, 4374040000]\n",
-      "총 방문객 수: 618 ,  20/50/60대 방문객 수: 129 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 방문객 수: 24957 ,  20/50/60대 방문객 수: 4768 \n",
-      "\n",
-      "{'세종특별자치시': 0.0690751357958365, '대전광역시 유성구': 0.21970336845100272, '대전광역시 서구': 0.23004991987725867, '대전광역시 대덕구': 0.07679235776727512, '대전광역시 중구': 0.07842699953443562, '충청남도 금산군': 0.07764202535394257, '충청북도 영동군': 0.21916897136041014, '전라북도 무주군': 0.029141221859838744}\n",
-      "대전지역 최적의 셔틀 노선\n",
-      "최적의 셔틀 노선: ['대전광역시 중구', '대전광역시 대덕구', '대전광역시 서구', '전라북도 무주군'] | 총 거리: 75.06 km | 총 시간: 1.0시간 24분 | 총 가중치: 0.3068422776445338 | threshold: 1.40\n",
-      "최적의 셔틀 노선: ['대전광역시 유성구', '대전광역시 서구', '대전광역시 대덕구', '전라북도 무주군'] | 총 거리: 71.59 km | 총 시간: 1.0시간 17분 | 총 가중치: 0.3068422776445338 | threshold: 1.50\n",
-      "최적의 셔틀 노선: ['대전광역시 유성구', '대전광역시 서구', '대전광역시 중구', '전라북도 무주군'] | 총 거리: 64.15 km | 총 시간: 1.0시간 21분 | 총 가중치: 0.3084769194116943 | threshold: 1.50\n",
-      "최적의 셔틀 노선: ['대전광역시 유성구', '대전광역시 대덕구', '대전광역시 중구', '전라북도 무주군'] | 총 거리: 65.30 km | 총 시간: 1.0시간 19분 | 총 가중치: 0.15521935730171074 | threshold: 1.50\n"
-     ]
-    }
-   ],
-   "source": [
-    "search(daejun, daejun_weights, \"대전\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 78,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "지역명: 전라북도 군산시\n",
-      "관련 행정동코드:  [4513000000, 4513025000, 4513031000, 4513032000, 4513033000, 4513034000, 4513035000, 4513036000, 4513037000, 4513038000, 4513039000, 4513040000, 4513051500, 4513053000, 4513055000, 4513056000, 4513060500, 4513064000, 4513065000, 4513066000, 4513067000, 4513068000, 4513069000, 4513070100, 4513070200, 4513070300, 4513071000, 4513072000]\n",
-      "총 거주인원: 3132379.0 ,  20/50/60대 거주인원: 378252.0 \n",
-      "\n",
-      "지역명: 전라북도 익산시\n",
-      "관련 행정동코드:  [4514000000, 4514025000, 4514031000, 4514032000, 4514033000, 4514034000, 4514035000, 4514036000, 4514037000, 4514038000, 4514039000, 4514040000, 4514041000, 4514042000, 4514043000, 4514044000, 4514052000, 4514053000, 4514056000, 4514057000, 4514058000, 4514059500, 4514061000, 4514062000, 4514064600, 4514064700, 4514065200, 4514065600, 4514067000, 4514069000]\n",
-      "총 거주인원: 3328022.0 ,  20/50/60대 거주인원: 420440.0 \n",
-      "\n",
-      "지역명: 전라북도 전주시 완산구\n",
-      "관련 행정동코드:  [4511100000, 4511151000, 4511153000, 4511160500, 4511163500, 4511165000, 4511166000, 4511167100, 4511167200, 4511168000, 4511169100, 4511169200, 4511170100, 4511170200, 4511170300, 4511171100, 4511171200, 4511171300, 4511171400, 4511173000]\n",
-      "총 거주인원: 4116105.0 ,  20/50/60대 거주인원: 486210.0 \n",
-      "\n",
-      "지역명: 전라북도 전주시 덕진구\n",
-      "관련 행정동코드:  [4511300000, 4511352500, 4511354000, 4511355000, 4511356000, 4511357000, 4511358000, 4511359000, 4511360000, 4511361100, 4511361200, 4511362000, 4511364100, 4511364200, 4511365000, 4511366500, 4511367000]\n",
-      "총 거주인원: 3377434.0 ,  20/50/60대 거주인원: 400961.0 \n",
-      "\n",
-      "지역명: 전라북도 진안군\n",
-      "관련 행정동코드:  [4572000000, 4572025000, 4572031000, 4572032000, 4572033000, 4572034000, 4572035000, 4572036000, 4572037000, 4572038000, 4572039000, 4572040000]\n",
-      "총 거주인원: 179814.0 ,  20/50/60대 거주인원: 24852.0 \n",
-      "\n",
-      "지역명: 전라북도 장수군\n",
-      "관련 행정동코드:  [4574000000, 4574025000, 4574031000, 4574032000, 4574033500, 4574034000, 4574035000, 4574036000]\n",
-      "총 거주인원: 201626.0 ,  20/50/60대 거주인원: 26141.0 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 거주인원: 211731.0 ,  20/50/60대 거주인원: 26123.0 \n",
-      "\n",
-      "지역명: 전라북도 군산시\n",
-      "관련 행정동코드:  [4513000000, 4513025000, 4513031000, 4513032000, 4513033000, 4513034000, 4513035000, 4513036000, 4513037000, 4513038000, 4513039000, 4513040000, 4513051500, 4513053000, 4513055000, 4513056000, 4513060500, 4513064000, 4513065000, 4513066000, 4513067000, 4513068000, 4513069000, 4513070100, 4513070200, 4513070300, 4513071000, 4513072000]\n",
-      "총 방문객 수: 14 ,  20/50/60대 방문객 수: 14 \n",
-      "\n",
-      "지역명: 전라북도 익산시\n",
-      "관련 행정동코드:  [4514000000, 4514025000, 4514031000, 4514032000, 4514033000, 4514034000, 4514035000, 4514036000, 4514037000, 4514038000, 4514039000, 4514040000, 4514041000, 4514042000, 4514043000, 4514044000, 4514052000, 4514053000, 4514056000, 4514057000, 4514058000, 4514059500, 4514061000, 4514062000, 4514064600, 4514064700, 4514065200, 4514065600, 4514067000, 4514069000]\n",
-      "총 방문객 수: 21 ,  20/50/60대 방문객 수: 7 \n",
-      "\n",
-      "지역명: 전라북도 전주시 완산구\n",
-      "관련 행정동코드:  [4511100000, 4511151000, 4511153000, 4511160500, 4511163500, 4511165000, 4511166000, 4511167100, 4511167200, 4511168000, 4511169100, 4511169200, 4511170100, 4511170200, 4511170300, 4511171100, 4511171200, 4511171300, 4511171400, 4511173000]\n",
-      "총 방문객 수: 96 ,  20/50/60대 방문객 수: 10 \n",
-      "\n",
-      "지역명: 전라북도 전주시 덕진구\n",
-      "관련 행정동코드:  [4511300000, 4511352500, 4511354000, 4511355000, 4511356000, 4511357000, 4511358000, 4511359000, 4511360000, 4511361100, 4511361200, 4511362000, 4511364100, 4511364200, 4511365000, 4511366500, 4511367000]\n",
-      "총 방문객 수: 127 ,  20/50/60대 방문객 수: 47 \n",
-      "\n",
-      "지역명: 전라북도 진안군\n",
-      "관련 행정동코드:  [4572000000, 4572025000, 4572031000, 4572032000, 4572033000, 4572034000, 4572035000, 4572036000, 4572037000, 4572038000, 4572039000, 4572040000]\n",
-      "총 방문객 수: 277 ,  20/50/60대 방문객 수: 62 \n",
-      "\n",
-      "지역명: 전라북도 장수군\n",
-      "관련 행정동코드:  [4574000000, 4574025000, 4574031000, 4574032000, 4574033500, 4574034000, 4574035000, 4574036000]\n",
-      "총 방문객 수: 436 ,  20/50/60대 방문객 수: 160 \n",
-      "\n",
-      "지역명: 전라북도 무주군\n",
-      "관련 행정동코드:  [4573000000, 4573025000, 4573031000, 4573032000, 4573033000, 4573034000, 4573035000]\n",
-      "총 방문객 수: 24957 ,  20/50/60대 방문객 수: 4768 \n",
-      "\n",
-      "{'전라북도 군산시': 0.16290893515183477, '전라북도 익산시': 0.08364023615032236, '전라북도 전주시 완산구': 0.18079395836979623, '전라북도 전주시 덕진구': 0.23586747596828486, '전라북도 진안군': 0.0749647557263006, '전라북도 장수군': 0.23513594628281875, '전라북도 무주군': 0.026688692350642314}\n",
-      "전북지역 최적의 셔틀 노선\n",
-      "최적의 셔틀 노선: ['전라북도 전주시 완산구', '전라북도 전주시 덕진구', '전라북도 무주군'] | 총 거리: 75.56 km | 총 시간: 1.0시간 32분 | 총 가중치: 0.23586747596828486 | threshold: 1.20\n",
-      "최적의 셔틀 노선: ['전라북도 군산시', '전라북도 익산시', '전라북도 무주군'] | 총 거리: 118.16 km | 총 시간: 2.0시간 4분 | 총 가중치: 0.08364023615032236 | threshold: 1.30\n",
-      "최적의 셔틀 노선: ['전라북도 전주시 덕진구', '전라북도 군산시', '전라북도 무주군'] | 총 거리: 153.42 km | 총 시간: 2.0시간 22분 | 총 가중치: 0.16290893515183477 | threshold: 1.40\n",
-      "최적의 셔틀 노선: ['전라북도 전주시 덕진구', '전라북도 익산시', '전라북도 무주군'] | 총 거리: 118.14 km | 총 시간: 2.0시간 10분 | 총 가중치: 0.08364023615032236 | threshold: 1.40\n",
-      "최적의 셔틀 노선: ['전라북도 익산시', '전라북도 전주시 완산구', '전라북도 무주군'] | 총 거리: 104.53 km | 총 시간: 2.0시간 2분 | 총 가중치: 0.18079395836979623 | threshold: 1.50\n",
-      "최적의 셔틀 노선: ['전라북도 전주시 완산구', '전라북도 군산시', '전라북도 무주군'] | 총 거리: 163.53 km | 총 시간: 2.0시간 29분 | 총 가중치: 0.16290893515183477 | threshold: 1.50\n"
-     ]
-    }
-   ],
-   "source": [
-    "search(jeonbuk, jeonbuk_weights, \"전북\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "base",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/dataloader/dataloader.py b/dataloader/dataloader.py
index 6c0b054..7f1f4ec 100644
--- a/dataloader/dataloader.py
+++ b/dataloader/dataloader.py
@@ -4,34 +4,21 @@
 import json
  
 sys.path.append(os.path.dirname(os.path.abspath(os.path.dirname(__file__))))
-from preprocess.dataload_preprocess import preprocess_od, preprocess_stay
+from preprocess.dataload_preprocess import preprocess_od, preprocess_stay, preprocess_address, preprocess_visitor_city
 
 # paths 파일 불러오기
 with open('config.json', 'r', encoding='utf-8') as f:
     paths = json.load(f)
 
-
-# 'data/raw_data' 경로 설정
-root_dir = paths['root_dir']
-visitor_city = pd.read_csv(os.path.join(root_dir, "city_of_festival_visitors.csv"))  # 무주축제 방문객 top 18 지역들 (시군구명,od_cnts,시도명,행정동코드,위도,경도)
-address = pd.read_csv(os.path.join(root_dir, "address_with_lon_lat_final.csv"))  # 행정동코드 + 위도경도 (행정동코드,시도명,시군구명,읍면동명,동리명,위도,경도)
-mooju = set(list(address[address['시군구명'] == '무주군']['행정동코드']))  # 무주군 행정동코드
-other_city = list(address.merge(visitor_city, on=['시도명', '시군구명'])['행정동코드_x'])  # 다른 지역들 행정동코드 모음
-
-visitor_city['시도 시군구'] = visitor_city['시도명'].fillna('') + ' ' + visitor_city['시군구명'].fillna('')
-visitor_city['시도 시군구'] = visitor_city['시도 시군구'].str.strip() # 양쪽 값이 모두 null인 경우 빈 문자열 처리
-
-address['시도 시군구'] = address['시도명'].fillna('') + ' ' + address['시군구명'].fillna('')
-address['시도 시군구'] = address['시도 시군구'].str.strip() # 양쪽 값이 모두 null인 경우 빈 문자열 처리
-
-# raw_data 경로 설정
-od_dir = paths['od_dir']
-stay_dir = paths['stay_dir']
-
-
-# festival od data load
+# 축제기간의 od 데이터 로드 함수
 def load_od():
     df_od = pd.DataFrame()
+    od_dir = paths['od_dir']
+
+    address_df = load_address()
+    # 무주군의 행정동코드 추출
+    mooju = set(address_df[address_df['시군구명'] == '무주군']['행정동코드'])
+    
     for dirpath, dirnames, filenames in os.walk(od_dir):
         for filename in tqdm(filenames, desc="load od data", unit="file"):
             if filename.endswith('.csv'):
@@ -55,9 +42,10 @@ def load_od():
                     df_od = pd.concat([df_od, globals()[f'df_{mmdd_str}']])
     return df_od
 
-# festival stay data load
+# stay 데이터 로드 함수
 def load_stay():
     df_stay = pd.DataFrame()
+    stay_dir = paths['stay_dir']
     for dirpath, dirnames, filenames in os.walk(stay_dir):
         for filename in tqdm(filenames, desc="load stay data", unit="file"):
             if filename.endswith('.csv'):
@@ -79,4 +67,24 @@ def load_stay():
                     # 동적으로 변수 생성 (예: df_0902)
                     globals()[f'df_{mmdd_str}'] = filtered_data
                     df_stay = pd.concat([df_stay, globals()[f'df_{mmdd_str}']])
-        return df_stay
\ No newline at end of file
+        return df_stay
+    
+# address 데이터 로드 함수
+def load_address():
+    address_path = os.path.join(paths['root_dir'], "address_with_lon_lat_final.csv")
+    address_df = pd.read_csv(address_path)
+
+    address_df = preprocess_address(address_df)
+     
+    return address_df
+
+
+
+# visitor_city 데이터 로드 함수
+def load_visitor_city():
+    visitor_city_path = os.path.join(paths['root_dir'], "city_of_festival_visitors.csv")
+    visitor_city_df = pd.read_csv(visitor_city_path)
+    
+    visitor_city_df = preprocess_visitor_city(visitor_city_df)
+    
+    return visitor_city_df
\ No newline at end of file
diff --git a/func/weight_by_region.py b/func/weight_by_region.py
index 30b71bf..14d6c1e 100644
--- a/func/weight_by_region.py
+++ b/func/weight_by_region.py
@@ -5,44 +5,42 @@
  
 sys.path.append(os.path.dirname(os.path.abspath(os.path.dirname(__file__))))
 
-from dataloader.dataloader import load_od, load_stay
+from dataloader.dataloader import load_od, load_stay, load_address
 
-# 'data/raw_data' 경로 설정
-with open('config.json', 'r', encoding='utf-8') as f:
-    paths = json.load(f)
-
-root_dir = paths['root_dir']
-address = pd.read_csv(os.path.join(root_dir, "address_with_lon_lat_final.csv"))  # 행정동코드 + 위도경도 (행정동코드,시도명,시군구명,읍면동명,동리명,위도,경도)
-address['시도 시군구'] = address['시도명'].fillna('') + ' ' + address['시군구명'].fillna('')
-address['시도 시군구'] = address['시도 시군구'].str.strip() # 양쪽 값이 모두 null인 경우 빈 문자열 처리
-
-
-####
-df_od = load_od()
-df_stay = load_stay()
+def total_number_of_residents_by_region():
+    df_stay = load_stay()
+    
+    # 지역별 전체 거주민 수
+    df_stay_all = df_stay.groupby(['hdong_cd', 'date'])['stay_cnts'].sum().reset_index()  # 날짜별 거주인구 합산
+    avg_stay_cnts_all = round(df_stay_all.groupby('hdong_cd')['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 거주인구
 
-# 지역별 전체 거주민 수
-df_stay_all = df_stay.groupby(['hdong_cd', 'date'])['stay_cnts'].sum().reset_index()  # 날짜별 거주인구 합산
-avg_stay_cnts_all = round(df_stay_all.groupby('hdong_cd')['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 거주인구
+    # 지역별 20대,50대,60대 거주민 수
+    df_stay_age = df_stay[df_stay['age'].isin([2,5,6])]  # 날짜별 20대 거주인구
+    avg_stay_cnts_age = round(df_stay_age.groupby(['hdong_cd'])['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 20대 거주인구
 
-# 지역별 20대,50대,60대 거주민 수
-df_stay_age = df_stay[df_stay['age'].isin([2,5,6])]  # 날짜별 20대 거주인구
-avg_stay_cnts_age = round(df_stay_age.groupby(['hdong_cd'])['stay_cnts'].mean().reset_index(), 0)  # 하루 평균 20대 거주인구
+    return avg_stay_cnts_all, avg_stay_cnts_age
 
-# 지역별 무주축제 방문객 인원수
-df_od_group = df_od.groupby(['origin_hdong_cd', 'date', 'age'])['od_cnts'].sum().reset_index()
-df_od_all = df_od_group.groupby(['origin_hdong_cd', 'date'])['od_cnts'].sum().reset_index()  # 날짜별 방문객수 합산
-sum_od_cnts_all = round(df_od_all.groupby(['origin_hdong_cd'])['od_cnts'].sum().reset_index(), 0)  # 해당 지역에서 온 전체 방문객수
+def number_of_visitors_to_Muju_by_region():
+    df_od = load_od()
+    
+    # 지역별 무주축제 방문객 인원수
+    df_od_group = df_od.groupby(['origin_hdong_cd', 'date', 'age'])['od_cnts'].sum().reset_index()
+    df_od_all = df_od_group.groupby(['origin_hdong_cd', 'date'])['od_cnts'].sum().reset_index()  # 날짜별 방문객수 합산
+    sum_od_cnts_all = round(df_od_all.groupby(['origin_hdong_cd'])['od_cnts'].sum().reset_index(), 0)  # 해당 지역에서 온 전체 방문객수
 
-# 지역별 20대,50대,60대 무주축제방문객 수
-df_od_age = df_od_group[df_od_group['age'].isin([2,5,6])]
-sum_od_cnts_age = round(df_od_age.groupby('origin_hdong_cd')['od_cnts'].sum().reset_index(), 0)
+    # 지역별 20대,50대,60대 무주축제방문객 수
+    df_od_age = df_od_group[df_od_group['age'].isin([2,5,6])]
+    sum_od_cnts_age = round(df_od_age.groupby('origin_hdong_cd')['od_cnts'].sum().reset_index(), 0)
 
+    return sum_od_cnts_all, sum_od_cnts_age
 
 # 각 지역 거주인원
 def get_residents_num(lst):
+    address = load_address()
+    avg_stay_cnts_all, avg_stay_cnts_age = total_number_of_residents_by_region()
     residents_num = []
     residents_num_256 = []
+
     for name in lst:
         #print("지역명:", name)
         codes = address[address['시도 시군구'] == name]['행정동코드'].unique().tolist()
@@ -64,8 +62,11 @@ def get_residents_num(lst):
 
 # 각 지역 방문객
 def get_visitors_num(lst):
+    address = load_address()
+    sum_od_cnts_all, sum_od_cnts_age = number_of_visitors_to_Muju_by_region()
     visitors_num = []
     visitors_num_256 = []
+
     for name in lst:
         #print("지역명:", name)
         codes = address[address['시도 시군구'] == name]['행정동코드'].unique().tolist()
@@ -114,8 +115,5 @@ def get_weights(nodes, weights):
     
     stations = {nodes: weight for nodes, weight in zip(nodes, softmax_weights)}
     stations['전라북도 무주군'] = 0 # 무주군은 목적지이므로 가중치 0 으로 설정  
-    
-    #print("정류장 가중치")
-    #print(stations)
 
     return stations
\ No newline at end of file
diff --git a/preprocess/dataload_preprocess.py b/preprocess/dataload_preprocess.py
index 321254d..14dd01f 100644
--- a/preprocess/dataload_preprocess.py
+++ b/preprocess/dataload_preprocess.py
@@ -29,4 +29,21 @@ def preprocess_stay(df):
     filtered_df = df[(df['purpose'] == 0)]
     grouped_residents = filtered_df.groupby(['hdong_cd', 'date', 'age'])['stay_cnts'].sum().reset_index()
 
-    return grouped_residents
\ No newline at end of file
+    return grouped_residents
+
+
+def preprocess_address(df):
+
+    # 전처리: 시도명과 시군구명 결합 및 null 값 처리
+    df['시도 시군구'] = df['시도명'].fillna('') + ' ' + df['시군구명'].fillna('')
+    df['시도 시군구'] = df['시도 시군구'].str.strip()  # 양쪽 값이 모두 null인 경우 빈 문자열 처리
+
+    return df
+
+def preprocess_visitor_city(df):
+
+    # 전처리: 시도명과 시군구명 결합 및 null 값 처리
+    df['시도 시군구'] = df['시도명'].fillna('') + ' ' + df['시군구명'].fillna('')
+    df['시도 시군구'] = df['시도 시군구'].str.strip()  # 양쪽 값이 모두 null인 경우 빈 문자열 처리
+
+    return df
\ No newline at end of file
diff --git a/visualization/chanwoong.ipynb b/visualization/chanwoong.ipynb
deleted file mode 100644
index 2fe3e8d..0000000
--- a/visualization/chanwoong.ipynb
+++ /dev/null
@@ -1,946 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 내/외부인 비율 파이차트"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 축제 방문객 내/외부인 분포 파악"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "데이터프레임 df_0901가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0902가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0903가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0904가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0905가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0906가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0907가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0908가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0909가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0910가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0911가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0912가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0913가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0914가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0915가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0916가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0917가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0918가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0919가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0920가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0921가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0922가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0923가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0924가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0925가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0926가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0927가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0928가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0929가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_0930가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1001가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1002가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1003가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1004가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1005가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1006가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1007가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1008가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1009가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1010가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1011가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1012가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1013가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1014가 생성되었고, 기존데이터프레임에 포함합니다.\n",
-      "데이터프레임 df_1015가 생성되었고, 기존데이터프레임에 포함합니다.\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "import pandas as pd\n",
-    "\n",
-    "# 'data/raw_data' 경로 설정\n",
-    "root_dir = '../data/raw_data'\n",
-    "df = pd.DataFrame()\n",
-    "address = pd.read_csv(\"../data/address_with_lon_lat_final.csv\")\n",
-    "mooju = set(list(address[address['시군구명'] == '무주군']['행정동코드']))\n",
-    "\n",
-    "# 전처리코드는 모두 여기에\n",
-    "def preprocess(df):\n",
-    "    # dest_hdong_cd 값이 축제가 열리는 곳인 무주군 데이터만 필터링\n",
-    "    filtered_df = df[df['dest_hdong_cd'].isin(mooju)]\n",
-    "\n",
-    "    #filtered_df = df[df['dest_hdong_cd'] == 4573025000]\n",
-    "    \"\"\"#filtered_df = df[df['dest_hdong_cd'] == 4573025000]\n",
-    "    df = pd.merge(df, address[['행정동코드', '시도명', '시군구명']], \n",
-    "                     left_on='dest_hdong_cd', right_on='행정동코드', how='left')\n",
-    "\n",
-    "    # 병합 후 불필요한 '행정동코드' 컬럼 제거 (필요에 따라)\n",
-    "    df = df.drop(columns=['행정동코드'])\n",
-    "\n",
-    "    filtered_df = df[df['시군구명'] == '무주군']\n",
-    "\n",
-    "    filtered_df = filtered_df.drop(columns=['시도명', '시군구명'])\"\"\"\n",
-    "\n",
-    "    # 타 지역에서 온 데이터만 필터링\n",
-    "    #filtered_df = filtered_df[filtered_df['origin_hdong_cd'] != filtered_df['dest_hdong_cd']]\n",
-    "    #filtered_df = filtered_df[~filtered_df['origin_hdong_cd'].isin(mooju)]\n",
-    "\n",
-    "    # 체류목적이 3(쇼핑여가), 4(기타), 5(여행) 인경우만 \n",
-    "    filtered_df = filtered_df[(filtered_df['dest_purpose'] == 3) | \n",
-    "                          (filtered_df['dest_purpose'] == 4) | \n",
-    "                          (filtered_df['dest_purpose'] == 5)]\n",
-    "\n",
-    "    return filtered_df\n",
-    "\n",
-    "# 'od'로 시작하는 폴더 내의 모든 CSV 파일 처리\n",
-    "for dirpath, dirnames, filenames in os.walk(root_dir):\n",
-    "    if os.path.basename(dirpath).startswith('od'):\n",
-    "        for filename in filenames:\n",
-    "            if filename.endswith('.csv'):\n",
-    "                # 파일 이름에서 날짜 추출\n",
-    "                date_str = filename.split('_')[1]\n",
-    "                \n",
-    "                # 파일 경로 설정 및 CSV 읽기\n",
-    "                file_path = os.path.join(dirpath, filename)\n",
-    "                csv_data = pd.read_csv(file_path)\n",
-    "                \n",
-    "                # 전처리\n",
-    "                filtered_data = preprocess(csv_data)\n",
-    "\n",
-    "                # 날짜에서 월일(MMDD) 부분 추출\n",
-    "                mmdd_str = date_str[4:]  # 'YYYYMMDD'에서 마지막 네 자리 'MMDD' 추출\n",
-    "                \n",
-    "                # 동적으로 변수 생성 (예: df_0901)\n",
-    "                globals()[f'df_{mmdd_str}'] = filtered_data\n",
-    "                \n",
-    "                # 데이터프레임 이름 출력 (예: df_0901)\n",
-    "                print(f\"데이터프레임 df_{mmdd_str}가 생성되었고, 기존데이터프레임에 포함합니다.\")\n",
-    "                df = pd.concat([df, globals()[f'df_{mmdd_str}']])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 74,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "festival_df = df[(df['date'] >= 20230902) & (df['date'] <= 20230910)]\n",
-    "festival_df_grouped = festival_df.groupby('date')['od_cnts'].sum().reset_index()\n",
-    "\n",
-    "# 'date'와 'origin_hdong_cd'을 기준으로 'od_cnts'를 집계\n",
-    "festival_df_grouped_2 = festival_df.groupby(['origin_hdong_cd'])['od_cnts'].sum().reset_index()\n",
-    "\n",
-    "# df_1의 'origin_hdong_cd'와 df_2의 '행정동코드'를 기준으로 병합\n",
-    "festival_df_grouped_2 = pd.merge(festival_df_grouped_2, address[['행정동코드', '시도명', '시군구명']], \n",
-    "                     left_on='origin_hdong_cd', right_on='행정동코드', how='left')\n",
-    "\n",
-    "# 병합 후 불필요한 '행정동코드' 컬럼 제거 (필요에 따라)\n",
-    "festival_df_grouped_2 = festival_df_grouped_2.drop(columns=['행정동코드'])\n",
-    "\n",
-    "festival_df_grouped_2.drop_duplicates(inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 75,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# '시도명'별로 'od_cnts' 합계를 구한 후 'od_cnts' 기준으로 정렬\n",
-    "festival_df_grouped_sido = festival_df_grouped_2.groupby('시도명')['od_cnts'].sum().reset_index()\n",
-    "\n",
-    "# 'od_cnts' 기준으로 내림차순 정렬\n",
-    "festival_df_grouped_sido = festival_df_grouped_sido.sort_values(by='od_cnts', ascending=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 76,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# '시도명'별로 'od_cnts' 합계를 구한 후 'od_cnts' 기준으로 정렬\n",
-    "junbok_filtered = festival_df_grouped_2[festival_df_grouped_2['시도명'] == '전라북도']\n",
-    "festival_df_grouped_junbok = junbok_filtered.groupby('시군구명')['od_cnts'].sum().reset_index()\n",
-    "\n",
-    "# 'od_cnts' 기준으로 내림차순 정렬\n",
-    "festival_df_grouped_junbok = festival_df_grouped_junbok.sort_values(by='od_cnts', ascending=False)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>내/외부인</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>외부인</td>\n",
-       "      <td>35542</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>내부인</td>\n",
-       "      <td>8863</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "  내/외부인  od_cnts\n",
-       "0   외부인    35542\n",
-       "1   내부인     8863"
-      ]
-     },
-     "execution_count": 77,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 내부인(첫 번째 행)과 외부인(나머지 행)의 데이터프레임 생성\n",
-    "internal_df = festival_df_grouped_junbok.iloc[[0]].copy()  # .copy() 사용하여 SettingWithCopyWarning 방지\n",
-    "internal_df['시군구명'] = '외부인'\n",
-    "\n",
-    "external_sum = festival_df_grouped_junbok.iloc[1:]['od_cnts'].sum()\n",
-    "external_df = pd.DataFrame([['내부인', external_sum]], columns=['시군구명', 'od_cnts'])\n",
-    "\n",
-    "# 최종 데이터프레임 합치기\n",
-    "in_out_df = pd.concat([internal_df, external_df]).reset_index(drop=True)\n",
-    "in_out_df.columns = ['내/외부인', 'od_cnts']\n",
-    "\n",
-    "in_out_df"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 외부인 세부분포 파악"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 78,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#festival_df_grouped_sido = festival_df_grouped_sido[1:]\n",
-    "festival_df_grouped_junbok = festival_df_grouped_junbok.iloc[1:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 79,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "전라북도\n",
-      "       시군구명  od_cnts   시도명\n",
-      "4       무주군    35542  전라북도\n",
-      "11  전주시 덕진구     2834  전라북도\n",
-      "12  전주시 완산구     1561  전라북도\n",
-      "10      장수군     1139  전라북도\n",
-      "8       익산시      772  전라북도\n",
-      "14      진안군      704  전라북도\n",
-      "1       군산시      592  전라북도\n",
-      "7       완주군      488  전라북도\n",
-      "3       남원시      259  전라북도\n",
-      "2       김제시      141  전라북도\n",
-      "13      정읍시      123  전라북도\n",
-      "9       임실군      109  전라북도\n",
-      "6       순창군       66  전라북도\n",
-      "0       고창군       54  전라북도\n",
-      "5       부안군       21  전라북도\n",
-      "\n",
-      "대전광역시\n",
-      "  시군구명  od_cnts    시도명\n",
-      "2   서구     1813  대전광역시\n",
-      "3  유성구     1379  대전광역시\n",
-      "1   동구     1207  대전광역시\n",
-      "4   중구      776  대전광역시\n",
-      "0  대덕구      562  대전광역시\n",
-      "\n",
-      "경상남도\n",
-      "         시군구명  od_cnts   시도명\n",
-      "1         거창군      658  경상남도\n",
-      "9         진주시      560  경상남도\n",
-      "16        통영시      384  경상남도\n",
-      "0         거제시      374  경상남도\n",
-      "19        함양군      323  경상남도\n",
-      "3         김해시      179  경상남도\n",
-      "5         사천시      131  경상남도\n",
-      "6         산청군      121  경상남도\n",
-      "14    창원시 의창구      115  경상남도\n",
-      "13    창원시 성산구       81  경상남도\n",
-      "11  창원시 마산합포구       70  경상남도\n",
-      "20        합천군       49  경상남도\n",
-      "18        함안군       43  경상남도\n",
-      "4         남해군       35  경상남도\n",
-      "12  창원시 마산회원구       31  경상남도\n",
-      "7         양산시       27  경상남도\n",
-      "17        하동군       15  경상남도\n",
-      "10        창녕군       14  경상남도\n",
-      "2         고성군       13  경상남도\n",
-      "15    창원시 진해구        7  경상남도\n",
-      "8         의령군        5  경상남도\n",
-      "\n",
-      "충청남도\n",
-      "       시군구명  od_cnts   시도명\n",
-      "2       금산군      882  충청남도\n",
-      "11  천안시 동남구      310  충청남도\n",
-      "12  천안시 서북구      265  충청남도\n",
-      "1       공주시      170  충청남도\n",
-      "10      예산군      153  충청남도\n",
-      "3       논산시      148  충청남도\n",
-      "9       아산시      142  충청남도\n",
-      "0       계룡시      125  충청남도\n",
-      "13      홍성군       52  충청남도\n",
-      "7       서산시       47  충청남도\n",
-      "6       부여군       41  충청남도\n",
-      "4       당진시       40  충청남도\n",
-      "5       보령시       32  충청남도\n",
-      "8       서천군        6  충청남도\n",
-      "\n",
-      "충청북도\n",
-      "       시군구명  od_cnts   시도명\n",
-      "3       영동군     1084  충청북도\n",
-      "10  청주시 흥덕구      230  충청북도\n",
-      "8   청주시 서원구      217  충청북도\n",
-      "4       옥천군      211  충청북도\n",
-      "7   청주시 상당구      194  충청북도\n",
-      "9   청주시 청원구      185  충청북도\n",
-      "5       음성군       60  충청북도\n",
-      "6       진천군       55  충청북도\n",
-      "2       보은군       53  충청북도\n",
-      "11      충주시       12  충청북도\n",
-      "1       단양군        7  충청북도\n",
-      "0       괴산군        6  충청북도\n",
-      "\n",
-      "경기도\n",
-      "       시군구명  od_cnts  시도명\n",
-      "34      화성시      202  경기도\n",
-      "30      이천시      133  경기도\n",
-      "31      평택시      132  경기도\n",
-      "26  용인시 기흥구      126  경기도\n",
-      "7      남양주시      123  경기도\n",
-      "33      하남시       99  경기도\n",
-      "10  성남시 분당구       84  경기도\n",
-      "0   고양시 덕양구       71  경기도\n",
-      "28  용인시 처인구       66  경기도\n",
-      "4       구리시       63  경기도\n",
-      "9       부천시       57  경기도\n",
-      "20      안성시       56  경기도\n",
-      "2       광명시       49  경기도\n",
-      "19  안산시 상록구       49  경기도\n",
-      "3       광주시       48  경기도\n",
-      "14  수원시 영통구       48  경기도\n",
-      "24      여주시       46  경기도\n",
-      "13  수원시 권선구       45  경기도\n",
-      "15  수원시 장안구       40  경기도\n",
-      "17      시흥시       38  경기도\n",
-      "25      오산시       37  경기도\n",
-      "5       군포시       33  경기도\n",
-      "27  용인시 수지구       31  경기도\n",
-      "12  성남시 중원구       20  경기도\n",
-      "23      양주시       19  경기도\n",
-      "29     의정부시       18  경기도\n",
-      "1       과천시       18  경기도\n",
-      "18  안산시 단원구       16  경기도\n",
-      "21  안양시 동안구       12  경기도\n",
-      "22  안양시 만안구       12  경기도\n",
-      "16  수원시 팔달구       12  경기도\n",
-      "6       김포시       12  경기도\n",
-      "11  성남시 수정구        6  경기도\n",
-      "32      포천시        6  경기도\n",
-      "8      동두천시        5  경기도\n",
-      "\n",
-      "대구광역시\n",
-      "  시군구명  od_cnts    시도명\n",
-      "1  달서구      656  대구광역시\n",
-      "2  달성군      335  대구광역시\n",
-      "4   북구      285  대구광역시\n",
-      "6  수성구      163  대구광역시\n",
-      "3   동구      126  대구광역시\n",
-      "5   서구       82  대구광역시\n",
-      "7   중구       27  대구광역시\n",
-      "0   남구       12  대구광역시\n",
-      "\n",
-      "경상북도\n",
-      "      시군구명  od_cnts   시도명\n",
-      "4      김천시      568  경상북도\n",
-      "3      구미시      393  경상북도\n",
-      "15  포항시 북구      146  경상북도\n",
-      "0      경산시      133  경상북도\n",
-      "13     칠곡군      117  경상북도\n",
-      "1      경주시       94  경상북도\n",
-      "7      안동시       46  경상북도\n",
-      "6      성주군       39  경상북도\n",
-      "8      영양군       29  경상북도\n",
-      "14  포항시 남구       28  경상북도\n",
-      "2      고령군       19  경상북도\n",
-      "10     예천군       14  경상북도\n",
-      "11     의성군       12  경상북도\n",
-      "12     청도군       12  경상북도\n",
-      "9      영천시       11  경상북도\n",
-      "5      상주시        5  경상북도\n",
-      "\n",
-      "광주광역시\n",
-      "  시군구명  od_cnts    시도명\n",
-      "0  광산구      477  광주광역시\n",
-      "4   서구      245  광주광역시\n",
-      "3   북구      223  광주광역시\n",
-      "1   남구      138  광주광역시\n",
-      "2   동구        9  광주광역시\n",
-      "\n",
-      "세종특별자치시\n",
-      "       시도명  od_cnts\n",
-      "0  세종특별자치시      999\n",
-      "\n",
-      "전라남도\n",
-      "   시군구명  od_cnts   시도명\n",
-      "11  여수시      142  전라남도\n",
-      "3   광양시      111  전라남도\n",
-      "10  순천시      103  전라남도\n",
-      "7   목포시       61  전라남도\n",
-      "5   나주시       54  전라남도\n",
-      "8   무안군       44  전라남도\n",
-      "6   담양군       24  전라남도\n",
-      "9   보성군       19  전라남도\n",
-      "13  장성군       18  전라남도\n",
-      "1   고흥군       14  전라남도\n",
-      "14  화순군       12  전라남도\n",
-      "0   강진군       11  전라남도\n",
-      "12  영광군       10  전라남도\n",
-      "2   곡성군        7  전라남도\n",
-      "4   구례군        5  전라남도\n",
-      "\n",
-      "서울특별시\n",
-      "    시군구명  od_cnts    시도명\n",
-      "16   송파구      116  서울특별시\n",
-      "8    노원구       70  서울특별시\n",
-      "17  영등포구       42  서울특별시\n",
-      "4    관악구       37  서울특별시\n",
-      "6    구로구       33  서울특별시\n",
-      "10   동작구       32  서울특별시\n",
-      "7    금천구       29  서울특별시\n",
-      "13   서초구       27  서울특별시\n",
-      "12  서대문구       26  서울특별시\n",
-      "1    강동구       26  서울특별시\n",
-      "0    강남구       23  서울특별시\n",
-      "3    강서구       21  서울특별시\n",
-      "11   마포구       19  서울특별시\n",
-      "15   성북구       18  서울특별시\n",
-      "18   용산구       12  서울특별시\n",
-      "20   종로구       10  서울특별시\n",
-      "5    광진구        9  서울특별시\n",
-      "9    도봉구        6  서울특별시\n",
-      "14   성동구        6  서울특별시\n",
-      "2    강북구        5  서울특별시\n",
-      "19   은평구        5  서울특별시\n",
-      "21    중구        5  서울특별시\n",
-      "\n",
-      "부산광역시\n",
-      "    시군구명  od_cnts    시도명\n",
-      "9     중구       64  부산광역시\n",
-      "5   부산진구       62  부산광역시\n",
-      "2    기장군       58  부산광역시\n",
-      "10  해운대구       42  부산광역시\n",
-      "0    강서구       40  부산광역시\n",
-      "4    동래구       40  부산광역시\n",
-      "7    사하구       24  부산광역시\n",
-      "1    금정구       14  부산광역시\n",
-      "3     남구       12  부산광역시\n",
-      "8    영도구        9  부산광역시\n",
-      "6    사상구        6  부산광역시\n",
-      "\n",
-      "인천광역시\n",
-      "   시군구명  od_cnts    시도명\n",
-      "4    서구      132  인천광역시\n",
-      "1   남동구       72  인천광역시\n",
-      "5   연수구       24  인천광역시\n",
-      "6    중구       15  인천광역시\n",
-      "0   계양구       12  인천광역시\n",
-      "3   부평구       11  인천광역시\n",
-      "2  미추홀구       10  인천광역시\n",
-      "\n",
-      "강원특별자치도\n",
-      "  시군구명  od_cnts      시도명\n",
-      "0  원주시       92  강원특별자치도\n",
-      "1  인제군       50  강원특별자치도\n",
-      "\n",
-      "울산광역시\n",
-      "  시군구명  od_cnts    시도명\n",
-      "2   북구       50  울산광역시\n",
-      "0   남구       25  울산광역시\n",
-      "3   중구       21  울산광역시\n",
-      "1   동구       20  울산광역시\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "map_filtered = pd.DataFrame()\n",
-    "for i in festival_df_grouped_sido['시도명']:\n",
-    "    # '시도명'별로 'od_cnts' 합계를 구한 후 'od_cnts' 기준으로 정렬\n",
-    "    junbok_filtered = festival_df_grouped_2[festival_df_grouped_2['시도명'] == i]\n",
-    "    if i == '세종특별자치시':\n",
-    "        festival_df_grouped_junbok = junbok_filtered.groupby('시도명')['od_cnts'].sum().reset_index()\n",
-    "    else:\n",
-    "        festival_df_grouped_junbok = junbok_filtered.groupby('시군구명')['od_cnts'].sum().reset_index()\n",
-    "    festival_df_grouped_junbok['시도명'] = i\n",
-    "    # 'od_cnts' 기준으로 내림차순 정렬\n",
-    "    festival_df_grouped_junbok = festival_df_grouped_junbok.sort_values(by='od_cnts', ascending=False)\n",
-    "\n",
-    "    map_filtered = pd.concat([map_filtered, festival_df_grouped_junbok])\n",
-    "    # 결과 출력\n",
-    "    print(i)\n",
-    "    print(festival_df_grouped_junbok)\n",
-    "    print()\n",
-    "\n",
-    "#map_filtered.drop(columns=['시도명'], inplace=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 80,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>시도명</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>전라북도</td>\n",
-       "      <td>44405</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>대전광역시</td>\n",
-       "      <td>5737</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>경상남도</td>\n",
-       "      <td>3235</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>충청남도</td>\n",
-       "      <td>2413</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15</th>\n",
-       "      <td>충청북도</td>\n",
-       "      <td>2314</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>경기도</td>\n",
-       "      <td>1832</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>대구광역시</td>\n",
-       "      <td>1686</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>경상북도</td>\n",
-       "      <td>1666</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>광주광역시</td>\n",
-       "      <td>1092</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>세종특별자치시</td>\n",
-       "      <td>999</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>전라남도</td>\n",
-       "      <td>635</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>서울특별시</td>\n",
-       "      <td>577</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>부산광역시</td>\n",
-       "      <td>371</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>인천광역시</td>\n",
-       "      <td>276</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>강원특별자치도</td>\n",
-       "      <td>142</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>울산광역시</td>\n",
-       "      <td>116</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "        시도명  od_cnts\n",
-       "13     전라북도    44405\n",
-       "6     대전광역시     5737\n",
-       "2      경상남도     3235\n",
-       "14     충청남도     2413\n",
-       "15     충청북도     2314\n",
-       "1       경기도     1832\n",
-       "5     대구광역시     1686\n",
-       "3      경상북도     1666\n",
-       "4     광주광역시     1092\n",
-       "9   세종특별자치시      999\n",
-       "12     전라남도      635\n",
-       "8     서울특별시      577\n",
-       "7     부산광역시      371\n",
-       "11    인천광역시      276\n",
-       "0   강원특별자치도      142\n",
-       "10    울산광역시      116"
-      ]
-     },
-     "execution_count": 80,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "od_cnts_sum_by_sido = map_filtered.groupby('시도명')['od_cnts'].sum().reset_index().sort_values(by='od_cnts', ascending=False)\n",
-    "\n",
-    "od_cnts_sum_by_sido"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 91,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>시도명</th>\n",
-       "      <th>od_cnts</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>전라북도</td>\n",
-       "      <td>44405</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>충남/대전 지역</td>\n",
-       "      <td>9149</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>전라북도 무주군 (개최지)</td>\n",
-       "      <td>8863</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>기타</td>\n",
-       "      <td>8393</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>경상남도</td>\n",
-       "      <td>3235</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>충청북도</td>\n",
-       "      <td>2314</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "              시도명  od_cnts\n",
-       "2            전라북도    44405\n",
-       "3        충남/대전 지역     9149\n",
-       "0  전라북도 무주군 (개최지)     8863\n",
-       "1              기타     8393\n",
-       "0            경상남도     3235\n",
-       "4            충청북도     2314"
-      ]
-     },
-     "execution_count": 91,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# 대전광역시, 충청남도, 세종특별자치시를 '충남/대전 지역'으로 묶기\n",
-    "od_cnts_sum_by_sido['시도명'] = od_cnts_sum_by_sido['시도명'].replace({\n",
-    "    '대전광역시': '충남/대전 지역', \n",
-    "    '충청남도': '충남/대전 지역', \n",
-    "    '세종특별자치시': '충남/대전 지역'\n",
-    "})\n",
-    "\n",
-    "# 시도명별 od_cnts 합계 계산\n",
-    "od_cnts_sum_grouped = od_cnts_sum_by_sido.groupby('시도명')['od_cnts'].sum().reset_index()\n",
-    "\n",
-    "# od_cnts 값이 2000 미만인 항목을 '기타'로 묶기\n",
-    "od_cnts_sum_grouped['시도명'] = od_cnts_sum_grouped['시도명'].where(od_cnts_sum_grouped['od_cnts'] >= 2000, '기타')\n",
-    "\n",
-    "\n",
-    "# 시도명별 od_cnts 합계 계산\n",
-    "od_cnts_sum_grouped = od_cnts_sum_grouped.groupby('시도명')['od_cnts'].sum().reset_index()\n",
-    "new_data = pd.DataFrame({'시도명': ['전라북도 무주군 (개최지)'], 'od_cnts': [8863]})\n",
-    "od_cnts_sum_grouped = pd.concat([od_cnts_sum_grouped, new_data]).sort_values(by='od_cnts', ascending=False)\n",
-    "od_cnts_sum_grouped"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 내/외부인 비율 시각화"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 92,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 2 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "import pandas as pd\n",
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "\n",
-    "plt.rcParams['font.family'] ='Malgun Gothic'\n",
-    "plt.rcParams['axes.unicode_minus'] =False\n",
-    "\n",
-    "# 서브플롯 생성\n",
-    "fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6))\n",
-    "\n",
-    "# 왼쪽 그래프: in_out_df (30도 회전)\n",
-    "ax1.pie(in_out_df['od_cnts'], \n",
-    "        labels=in_out_df['내/외부인'], \n",
-    "        autopct='%1.1f%%', \n",
-    "        startangle=210, \n",
-    "        colors=['#ff7f0e', '#1f77b4'])  # 내부인: 주황색, 외부인: 파란색\n",
-    "ax1.set_title('내/외부인 비율')\n",
-    "\n",
-    "# 오른쪽 그래프: od_cnts_sum_grouped\n",
-    "ax2.pie(od_cnts_sum_grouped['od_cnts'], labels=od_cnts_sum_grouped['시도명'], autopct='%1.1f%%', startangle=90, colors=plt.cm.tab20.colors)\n",
-    "ax2.set_title('시도별 세부 비율')\n",
-    "\n",
-    "\n",
-    "# 그래프 표시\n",
-    "plt.tight_layout()\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "map_filtered = pd.DataFrame()\n",
-    "for i in festival_df_grouped_sido['시도명']:\n",
-    "    # '시도명'별로 'od_cnts' 합계를 구한 후 'od_cnts' 기준으로 정렬\n",
-    "    junbok_filtered = festival_df_grouped_2[festival_df_grouped_2['시도명'] == i]\n",
-    "    if i == '세종특별자치시':\n",
-    "        festival_df_grouped_junbok = junbok_filtered.groupby('시도명')['od_cnts'].sum().reset_index()\n",
-    "    else:\n",
-    "        festival_df_grouped_junbok = junbok_filtered.groupby('시군구명')['od_cnts'].sum().reset_index()\n",
-    "    festival_df_grouped_junbok['시도명'] = i\n",
-    "    # 'od_cnts' 기준으로 내림차순 정렬\n",
-    "    festival_df_grouped_junbok = festival_df_grouped_junbok.sort_values(by='od_cnts', ascending=False)\n",
-    "\n",
-    "    map_filtered = pd.concat([map_filtered, festival_df_grouped_junbok[festival_df_grouped_junbok['od_cnts'] >= 500]])\n",
-    "    # 결과 출력\n",
-    "    print(i)\n",
-    "    print(festival_df_grouped_junbok[festival_df_grouped_junbok['od_cnts'] >= 500])\n",
-    "    print()\n",
-    "\n",
-    "#map_filtered.drop(columns=['시도명'], inplace=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}