Showing
28 changed files
with
597 additions
and
64 deletions
No preview for this file type
This diff is collapsed. Click to expand it.
1 | +{ | ||
2 | + "cells": [ | ||
3 | + { | ||
4 | + "cell_type": "code", | ||
5 | + "execution_count": 3, | ||
6 | + "metadata": {}, | ||
7 | + "outputs": [ | ||
8 | + { | ||
9 | + "data": { | ||
10 | + "text/plain": [ | ||
11 | + "0 37.585736\n", | ||
12 | + "1 37.571817\n", | ||
13 | + "2 37.569003\n", | ||
14 | + "3 37.573001\n", | ||
15 | + "4 37.575743\n", | ||
16 | + " ... \n", | ||
17 | + "11868 37.024922\n", | ||
18 | + "11869 37.246497\n", | ||
19 | + "11870 37.494695\n", | ||
20 | + "11871 37.498222\n", | ||
21 | + "11872 37.497612\n", | ||
22 | + "Name: 위도, Length: 11873, dtype: float64" | ||
23 | + ] | ||
24 | + }, | ||
25 | + "execution_count": 3, | ||
26 | + "metadata": {}, | ||
27 | + "output_type": "execute_result" | ||
28 | + } | ||
29 | + ], | ||
30 | + "source": [ | ||
31 | + "import pandas as pd\n", | ||
32 | + "import numpy as np\n", | ||
33 | + "import pyspark\n", | ||
34 | + "\n", | ||
35 | + "basic_folder = ''\n", | ||
36 | + "file_name = basic_folder + 'elementary_middle_schools_location.csv'\n", | ||
37 | + "df =pd.read_csv(file_name)\n", | ||
38 | + "\n", | ||
39 | + "latitude=df['위도']\n", | ||
40 | + "longitude=df['경도']\n" | ||
41 | + ] | ||
42 | + }, | ||
43 | + { | ||
44 | + "cell_type": "code", | ||
45 | + "execution_count": null, | ||
46 | + "metadata": {}, | ||
47 | + "outputs": [], | ||
48 | + "source": [] | ||
49 | + } | ||
50 | + ], | ||
51 | + "metadata": { | ||
52 | + "kernelspec": { | ||
53 | + "display_name": "Python 3", | ||
54 | + "language": "python", | ||
55 | + "name": "python3" | ||
56 | + }, | ||
57 | + "language_info": { | ||
58 | + "codemirror_mode": { | ||
59 | + "name": "ipython", | ||
60 | + "version": 3 | ||
61 | + }, | ||
62 | + "file_extension": ".py", | ||
63 | + "mimetype": "text/x-python", | ||
64 | + "name": "python", | ||
65 | + "nbconvert_exporter": "python", | ||
66 | + "pygments_lexer": "ipython3", | ||
67 | + "version": "3.7.7" | ||
68 | + } | ||
69 | + }, | ||
70 | + "nbformat": 4, | ||
71 | + "nbformat_minor": 4 | ||
72 | +} |
This diff is collapsed. Click to expand it.
code/dataset/2019_students_num.csv
0 → 100644
This diff could not be displayed because it is too large.
This diff could not be displayed because it is too large.
code/dataset/elementary_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/elementary_school_stu_num.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/elementary_timetable.csv
0 → 100644
code/dataset/final_ele_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/final_high_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/final_middle_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/find_location.ipynb
0 → 100644
1 | +{ | ||
2 | + "cells": [ | ||
3 | + { | ||
4 | + "cell_type": "code", | ||
5 | + "execution_count": 27, | ||
6 | + "metadata": {}, | ||
7 | + "outputs": [ | ||
8 | + { | ||
9 | + "name": "stderr", | ||
10 | + "output_type": "stream", | ||
11 | + "text": [ | ||
12 | + "100%|██████████| 2374/2374 [1:28:59<00:00, 2.25s/it]\n" | ||
13 | + ] | ||
14 | + }, | ||
15 | + { | ||
16 | + "data": { | ||
17 | + "text/html": [ | ||
18 | + "<div>\n", | ||
19 | + "<style scoped>\n", | ||
20 | + " .dataframe tbody tr th:only-of-type {\n", | ||
21 | + " vertical-align: middle;\n", | ||
22 | + " }\n", | ||
23 | + "\n", | ||
24 | + " .dataframe tbody tr th {\n", | ||
25 | + " vertical-align: top;\n", | ||
26 | + " }\n", | ||
27 | + "\n", | ||
28 | + " .dataframe thead th {\n", | ||
29 | + " text-align: right;\n", | ||
30 | + " }\n", | ||
31 | + "</style>\n", | ||
32 | + "<table border=\"1\" class=\"dataframe\">\n", | ||
33 | + " <thead>\n", | ||
34 | + " <tr style=\"text-align: right;\">\n", | ||
35 | + " <th></th>\n", | ||
36 | + " <th>school_name</th>\n", | ||
37 | + " <th>address</th>\n", | ||
38 | + " <th>latitude</th>\n", | ||
39 | + " <th>longitude</th>\n", | ||
40 | + " </tr>\n", | ||
41 | + " </thead>\n", | ||
42 | + " <tbody>\n", | ||
43 | + " <tr>\n", | ||
44 | + " <th>0</th>\n", | ||
45 | + " <td>가락고등학교</td>\n", | ||
46 | + " <td>서울특별시 송파구 송이로 42</td>\n", | ||
47 | + " <td>37.493</td>\n", | ||
48 | + " <td>127.125</td>\n", | ||
49 | + " </tr>\n", | ||
50 | + " <tr>\n", | ||
51 | + " <th>1</th>\n", | ||
52 | + " <td>가재울고등학교</td>\n", | ||
53 | + " <td>서울특별시 서대문구 수색로 100-35</td>\n", | ||
54 | + " <td>37.5773</td>\n", | ||
55 | + " <td>126.903</td>\n", | ||
56 | + " </tr>\n", | ||
57 | + " <tr>\n", | ||
58 | + " <th>2</th>\n", | ||
59 | + " <td>강동고등학교</td>\n", | ||
60 | + " <td>서울특별시 강동구 구천면로 572</td>\n", | ||
61 | + " <td>37.5501</td>\n", | ||
62 | + " <td>127.147</td>\n", | ||
63 | + " </tr>\n", | ||
64 | + " <tr>\n", | ||
65 | + " <th>3</th>\n", | ||
66 | + " <td>강서고등학교</td>\n", | ||
67 | + " <td>서울특별시 양천구 목동중앙남로 27</td>\n", | ||
68 | + " <td>37.5368</td>\n", | ||
69 | + " <td>126.867</td>\n", | ||
70 | + " </tr>\n", | ||
71 | + " <tr>\n", | ||
72 | + " <th>4</th>\n", | ||
73 | + " <td>강서공업고등학교</td>\n", | ||
74 | + " <td>서울특별시 강서구 방화대로47길 9</td>\n", | ||
75 | + " <td>37.5762</td>\n", | ||
76 | + " <td>126.815</td>\n", | ||
77 | + " </tr>\n", | ||
78 | + " <tr>\n", | ||
79 | + " <th>...</th>\n", | ||
80 | + " <td>...</td>\n", | ||
81 | + " <td>...</td>\n", | ||
82 | + " <td>...</td>\n", | ||
83 | + " <td>...</td>\n", | ||
84 | + " </tr>\n", | ||
85 | + " <tr>\n", | ||
86 | + " <th>2369</th>\n", | ||
87 | + " <td>표선고등학교</td>\n", | ||
88 | + " <td>제주특별자치도 서귀포시 표선면 표선중앙로 22-15</td>\n", | ||
89 | + " <td></td>\n", | ||
90 | + " <td></td>\n", | ||
91 | + " </tr>\n", | ||
92 | + " <tr>\n", | ||
93 | + " <th>2370</th>\n", | ||
94 | + " <td>한국뷰티고등학교</td>\n", | ||
95 | + " <td>제주특별자치도 제주시 한경면 용고로 70</td>\n", | ||
96 | + " <td></td>\n", | ||
97 | + " <td></td>\n", | ||
98 | + " </tr>\n", | ||
99 | + " <tr>\n", | ||
100 | + " <th>2371</th>\n", | ||
101 | + " <td>한림고등학교</td>\n", | ||
102 | + " <td>제주특별자치도 제주시 한림읍 월계로 74</td>\n", | ||
103 | + " <td></td>\n", | ||
104 | + " <td></td>\n", | ||
105 | + " </tr>\n", | ||
106 | + " <tr>\n", | ||
107 | + " <th>2372</th>\n", | ||
108 | + " <td>한림공업고등학교</td>\n", | ||
109 | + " <td>제주특별자치도 제주시 한림읍 한림중앙로 87</td>\n", | ||
110 | + " <td></td>\n", | ||
111 | + " <td></td>\n", | ||
112 | + " </tr>\n", | ||
113 | + " <tr>\n", | ||
114 | + " <th>2373</th>\n", | ||
115 | + " <td>함덕고등학교</td>\n", | ||
116 | + " <td>제주특별자치도 제주시 조천읍 신흥로 9</td>\n", | ||
117 | + " <td></td>\n", | ||
118 | + " <td></td>\n", | ||
119 | + " </tr>\n", | ||
120 | + " </tbody>\n", | ||
121 | + "</table>\n", | ||
122 | + "<p>2374 rows × 4 columns</p>\n", | ||
123 | + "</div>" | ||
124 | + ], | ||
125 | + "text/plain": [ | ||
126 | + " school_name address latitude longitude\n", | ||
127 | + "0 가락고등학교 서울특별시 송파구 송이로 42 37.493 127.125\n", | ||
128 | + "1 가재울고등학교 서울특별시 서대문구 수색로 100-35 37.5773 126.903\n", | ||
129 | + "2 강동고등학교 서울특별시 강동구 구천면로 572 37.5501 127.147\n", | ||
130 | + "3 강서고등학교 서울특별시 양천구 목동중앙남로 27 37.5368 126.867\n", | ||
131 | + "4 강서공업고등학교 서울특별시 강서구 방화대로47길 9 37.5762 126.815\n", | ||
132 | + "... ... ... ... ...\n", | ||
133 | + "2369 표선고등학교 제주특별자치도 서귀포시 표선면 표선중앙로 22-15 \n", | ||
134 | + "2370 한국뷰티고등학교 제주특별자치도 제주시 한경면 용고로 70 \n", | ||
135 | + "2371 한림고등학교 제주특별자치도 제주시 한림읍 월계로 74 \n", | ||
136 | + "2372 한림공업고등학교 제주특별자치도 제주시 한림읍 한림중앙로 87 \n", | ||
137 | + "2373 함덕고등학교 제주특별자치도 제주시 조천읍 신흥로 9 \n", | ||
138 | + "\n", | ||
139 | + "[2374 rows x 4 columns]" | ||
140 | + ] | ||
141 | + }, | ||
142 | + "execution_count": 27, | ||
143 | + "metadata": {}, | ||
144 | + "output_type": "execute_result" | ||
145 | + } | ||
146 | + ], | ||
147 | + "source": [ | ||
148 | + "import pandas as pd\n", | ||
149 | + "import numpy as np\n", | ||
150 | + "import pyspark\n", | ||
151 | + "from geopy.geocoders import Nominatim\n", | ||
152 | + "from geopy.extra.rate_limiter import RateLimiter\n", | ||
153 | + "from tqdm import tqdm\n", | ||
154 | + "\n", | ||
155 | + "basic_folder = ''\n", | ||
156 | + "file_name = basic_folder + 'elementary_middle_schools_location.csv'\n", | ||
157 | + "file_name2 = basic_folder + 'school_info.csv'\n", | ||
158 | + "df =pd.read_csv(file_name)\n", | ||
159 | + "df2 =pd.read_csv(file_name2)\n", | ||
160 | + "\n", | ||
161 | + "latitude=df['위도']\n", | ||
162 | + "longitude=df['경도']\n", | ||
163 | + "\n", | ||
164 | + "elementary=[]\n", | ||
165 | + "middle=[]\n", | ||
166 | + "high=[]\n", | ||
167 | + "\n", | ||
168 | + "count_row=df2.shape[0] #number of rows\n", | ||
169 | + "geolocator = Nominatim(user_agent=\"lms\", timeout=10)\n", | ||
170 | + "geocode = RateLimiter(geolocator.geocode, min_delay_seconds=1)\n", | ||
171 | + "\n", | ||
172 | + "def type_of_school():\n", | ||
173 | + " for x in range(count_row):\n", | ||
174 | + " type=df2.loc[x]['학교종류명']\n", | ||
175 | + " if(type=='고등학교'):\n", | ||
176 | + " if(df2.loc[x]['도로명주소']):\n", | ||
177 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['도로명주소'],\"\",\"\"]\n", | ||
178 | + " high.append(row)\n", | ||
179 | + "\n", | ||
180 | + "\n", | ||
181 | + "type_of_school()\n", | ||
182 | + "columns=['school_name','address','latitude','longitude']\n", | ||
183 | + "high_df=pd.DataFrame(high,columns=columns)\n", | ||
184 | + "\n", | ||
185 | + "def find_lat_lon():\n", | ||
186 | + " count_rw=high_df.shape[0]\n", | ||
187 | + " for x in tqdm(range(count_rw)):\n", | ||
188 | + " addr=high_df.loc[x]['address']\n", | ||
189 | + " if geolocator.geocode(addr) is not None:\n", | ||
190 | + " location=geolocator.geocode(addr)\n", | ||
191 | + " high_df.loc[x]['latitude']=location.latitude\n", | ||
192 | + " high_df.loc[x]['longitude']=location.longitude\n", | ||
193 | + "\n", | ||
194 | + "find_lat_lon()\n", | ||
195 | + "high_df.to_csv(r'high_school.csv')\n", | ||
196 | + "high_df" | ||
197 | + ] | ||
198 | + }, | ||
199 | + { | ||
200 | + "cell_type": "code", | ||
201 | + "execution_count": null, | ||
202 | + "metadata": {}, | ||
203 | + "outputs": [], | ||
204 | + "source": [ | ||
205 | + "import pandas as pd\n", | ||
206 | + "import numpy as np\n", | ||
207 | + "import pyspark\n", | ||
208 | + "from geopy.geocoders import Nominatim\n", | ||
209 | + "from geopy.extra.rate_limiter import RateLimiter\n", | ||
210 | + "from tqdm import tqdm\n", | ||
211 | + "\n", | ||
212 | + "basic_folder = ''\n", | ||
213 | + "file_name = basic_folder + 'high_school.csv'\n", | ||
214 | + "\n", | ||
215 | + "df =pd.read_csv(file_name)\n", | ||
216 | + "count_row=df.shape[0]\n", | ||
217 | + "print(count_row)\n", | ||
218 | + "df" | ||
219 | + ] | ||
220 | + } | ||
221 | + ], | ||
222 | + "metadata": { | ||
223 | + "kernelspec": { | ||
224 | + "display_name": "Python 3", | ||
225 | + "language": "python", | ||
226 | + "name": "python3" | ||
227 | + }, | ||
228 | + "language_info": { | ||
229 | + "codemirror_mode": { | ||
230 | + "name": "ipython", | ||
231 | + "version": 3 | ||
232 | + }, | ||
233 | + "file_extension": ".py", | ||
234 | + "mimetype": "text/x-python", | ||
235 | + "name": "python", | ||
236 | + "nbconvert_exporter": "python", | ||
237 | + "pygments_lexer": "ipython3", | ||
238 | + "version": "3.7.7" | ||
239 | + } | ||
240 | + }, | ||
241 | + "nbformat": 4, | ||
242 | + "nbformat_minor": 4 | ||
243 | +} |
code/dataset/high_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/high_school_stu_num.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/high_timetable.csv
0 → 100644
code/dataset/middle_school.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/middle_school_stu_num.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/middle_timetable.csv
0 → 100644
code/dataset/school_info.csv
0 → 100644
This diff could not be displayed because it is too large.
code/dataset/students_num.ipynb
0 → 100644
1 | +{ | ||
2 | + "cells": [ | ||
3 | + { | ||
4 | + "cell_type": "code", | ||
5 | + "execution_count": 4, | ||
6 | + "metadata": {}, | ||
7 | + "outputs": [ | ||
8 | + { | ||
9 | + "name": "stderr", | ||
10 | + "output_type": "stream", | ||
11 | + "text": [ | ||
12 | + "100%|██████████| 21398/21398 [00:16<00:00, 1308.22it/s]\n" | ||
13 | + ] | ||
14 | + } | ||
15 | + ], | ||
16 | + "source": [ | ||
17 | + "import pandas as pd\n", | ||
18 | + "import numpy as np\n", | ||
19 | + "import pyspark\n", | ||
20 | + "from tqdm import tqdm\n", | ||
21 | + "\n", | ||
22 | + "basic_folder = ''\n", | ||
23 | + "file_name2 = basic_folder + '2019_students_num.csv'\n", | ||
24 | + "df2 =pd.read_csv(file_name2)\n", | ||
25 | + "\n", | ||
26 | + "count_row=df2.shape[0] #number of rows\n", | ||
27 | + "elementary=[]\n", | ||
28 | + "middle=[]\n", | ||
29 | + "high=[]\n", | ||
30 | + "\n", | ||
31 | + "def type_of_school():\n", | ||
32 | + " for x in tqdm(range(count_row)):\n", | ||
33 | + " type=df2.loc[x]['학교급']\n", | ||
34 | + " if(type=='고등학교'):\n", | ||
35 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['1학년_학생수_계'],df2.loc[x]['2학년_학생수_계'],df2.loc[x]['3학년_학생수_계']]\n", | ||
36 | + " high.append(row)\n", | ||
37 | + " elif(type=='중학교'):\n", | ||
38 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['1학년_학생수_계'],df2.loc[x]['2학년_학생수_계'],df2.loc[x]['3학년_학생수_계']]\n", | ||
39 | + " middle.append(row)\n", | ||
40 | + " elif(type=='초등학교'):\n", | ||
41 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['1학년_학생수_계'],df2.loc[x]['2학년_학생수_계'],df2.loc[x]['3학년_학생수_계'],df2.loc[x]['4학년_학생수_계'],df2.loc[x]['5학년_학생수_계'],df2.loc[x]['6학년_학생수_계']]\n", | ||
42 | + " elementary.append(row)\n", | ||
43 | + "\n", | ||
44 | + "type_of_school()\n", | ||
45 | + " \n", | ||
46 | + "columns=['school_name','1_stu_num','2_stu_num','3_stu_num']\n", | ||
47 | + "high_df=pd.DataFrame(high,columns=columns)\n", | ||
48 | + "high_df.to_csv(r'high_school_stu_num.csv')\n", | ||
49 | + "\n", | ||
50 | + "middle_df=pd.DataFrame(middle,columns=columns)\n", | ||
51 | + "middle_df.to_csv(r'middle_school_stu_num.csv')\n", | ||
52 | + "\n", | ||
53 | + "columns1=['school_name','1_stu_num','2_stu_num','3_stu_num','4_stu_num','5_stu_num','6_stu_num']\n", | ||
54 | + "ele_df=pd.DataFrame(elementary,columns=columns1)\n", | ||
55 | + "ele_df.to_csv(r'elementary_school_stu_num.csv')" | ||
56 | + ] | ||
57 | + }, | ||
58 | + { | ||
59 | + "cell_type": "code", | ||
60 | + "execution_count": 10, | ||
61 | + "metadata": {}, | ||
62 | + "outputs": [ | ||
63 | + { | ||
64 | + "name": "stderr", | ||
65 | + "output_type": "stream", | ||
66 | + "text": [ | ||
67 | + "100%|██████████| 11873/11873 [00:08<00:00, 1379.25it/s]\n" | ||
68 | + ] | ||
69 | + } | ||
70 | + ], | ||
71 | + "source": [ | ||
72 | + "import pandas as pd\n", | ||
73 | + "import numpy as np\n", | ||
74 | + "import pyspark\n", | ||
75 | + "from tqdm import tqdm\n", | ||
76 | + "\n", | ||
77 | + "basic_folder = ''\n", | ||
78 | + "file_name = basic_folder + 'elementary_middle_schools_location.csv'\n", | ||
79 | + "\n", | ||
80 | + "df2 =pd.read_csv(file_name)\n", | ||
81 | + "count_row=df2.shape[0]\n", | ||
82 | + "\n", | ||
83 | + "elementary=[]\n", | ||
84 | + "middle=[]\n", | ||
85 | + "\n", | ||
86 | + "def type_of_school():\n", | ||
87 | + " for x in tqdm(range(count_row)):\n", | ||
88 | + " type=df2.loc[x]['학교급구분']\n", | ||
89 | + " if(type=='중학교'):\n", | ||
90 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['소재지도로명주소'],df2.loc[x]['위도'],df2.loc[x]['경도']]\n", | ||
91 | + " middle.append(row)\n", | ||
92 | + " elif(type=='초등학교'):\n", | ||
93 | + " row=[df2.loc[x]['학교명'],df2.loc[x]['소재지도로명주소'],df2.loc[x]['위도'],df2.loc[x]['경도']]\n", | ||
94 | + " elementary.append(row)\n", | ||
95 | + "\n", | ||
96 | + "type_of_school()\n", | ||
97 | + "columns=['school_name','school_addr','latitude','longitude']\n", | ||
98 | + "middle_df=pd.DataFrame(middle,columns=columns)\n", | ||
99 | + "middle_df.to_csv(r'middle_school.csv')\n", | ||
100 | + "\n", | ||
101 | + "elem_df=pd.DataFrame(elementary,columns=columns)\n", | ||
102 | + "elem_df.to_csv(r'elementary_school.csv')" | ||
103 | + ] | ||
104 | + }, | ||
105 | + { | ||
106 | + "cell_type": "code", | ||
107 | + "execution_count": 11, | ||
108 | + "metadata": {}, | ||
109 | + "outputs": [ | ||
110 | + { | ||
111 | + "name": "stderr", | ||
112 | + "output_type": "stream", | ||
113 | + "text": [ | ||
114 | + "100%|██████████| 3240/3240 [26:47<00:00, 2.02it/s]\n" | ||
115 | + ] | ||
116 | + } | ||
117 | + ], | ||
118 | + "source": [ | ||
119 | + "import pandas as pd\n", | ||
120 | + "import numpy as np\n", | ||
121 | + "import pyspark\n", | ||
122 | + "from tqdm import tqdm\n", | ||
123 | + "\n", | ||
124 | + "basic_folder = ''\n", | ||
125 | + "file_name = basic_folder + 'middle_school.csv'\n", | ||
126 | + "file_name2 = basic_folder + 'middle_school_stu_num.csv'\n", | ||
127 | + "\n", | ||
128 | + "middle_df =pd.read_csv(file_name)\n", | ||
129 | + "middle_stu_num_df=pd.read_csv(file_name2)\n", | ||
130 | + "\n", | ||
131 | + "count_row=middle_df.shape[0]\n", | ||
132 | + "count_row2=middle_stu_num_df.shape[0]\n", | ||
133 | + "\n", | ||
134 | + "middle_arr=[]\n", | ||
135 | + "\n", | ||
136 | + "def find_middle_student_num():\n", | ||
137 | + " for x in tqdm(range(count_row)):\n", | ||
138 | + " name=middle_df.loc[x]['school_name']\n", | ||
139 | + " for y in range(count_row2):\n", | ||
140 | + " if name == middle_stu_num_df.loc[y]['school_name']:\n", | ||
141 | + " row=[middle_df.loc[x]['school_name'],middle_df.loc[x]['school_addr'],middle_df.loc[x]['latitude'],middle_df.loc[x]['longitude'],\n", | ||
142 | + " middle_stu_num_df.loc[y]['1_stu_num'],middle_stu_num_df.loc[y]['2_stu_num'],middle_stu_num_df.loc[y]['3_stu_num']]\n", | ||
143 | + " middle_arr.append(row)\n", | ||
144 | + " \n", | ||
145 | + "\n", | ||
146 | + "find_middle_student_num()\n", | ||
147 | + "columns=['school_name','school_addr','latitude','longitude','1_stu_num','2_stu_num','3_stu_num']\n", | ||
148 | + "final_middle_df=pd.DataFrame(middle_arr,columns=columns)\n", | ||
149 | + "final_middle_df.to_csv(r'final_middle_school.csv')" | ||
150 | + ] | ||
151 | + }, | ||
152 | + { | ||
153 | + "cell_type": "code", | ||
154 | + "execution_count": 12, | ||
155 | + "metadata": {}, | ||
156 | + "outputs": [ | ||
157 | + { | ||
158 | + "name": "stderr", | ||
159 | + "output_type": "stream", | ||
160 | + "text": [ | ||
161 | + "100%|██████████| 6278/6278 [1:38:36<00:00, 1.06it/s]\n" | ||
162 | + ] | ||
163 | + } | ||
164 | + ], | ||
165 | + "source": [ | ||
166 | + "import pandas as pd\n", | ||
167 | + "import numpy as np\n", | ||
168 | + "import pyspark\n", | ||
169 | + "from tqdm import tqdm\n", | ||
170 | + "\n", | ||
171 | + "basic_folder = ''\n", | ||
172 | + "file_name = basic_folder + 'elementary_school.csv'\n", | ||
173 | + "file_name2 = basic_folder + 'elementary_school_stu_num.csv'\n", | ||
174 | + "\n", | ||
175 | + "ele_df =pd.read_csv(file_name)\n", | ||
176 | + "ele_stu_num_df=pd.read_csv(file_name2)\n", | ||
177 | + "\n", | ||
178 | + "count_row=ele_df.shape[0]\n", | ||
179 | + "count_row2=ele_stu_num_df.shape[0]\n", | ||
180 | + "\n", | ||
181 | + "ele_arr=[]\n", | ||
182 | + "\n", | ||
183 | + "def find_ele_student_num():\n", | ||
184 | + " for x in tqdm(range(count_row)):\n", | ||
185 | + " name=ele_df.loc[x]['school_name']\n", | ||
186 | + " for y in range(count_row2):\n", | ||
187 | + " if name == ele_stu_num_df.loc[y]['school_name']:\n", | ||
188 | + " row=[ele_df.loc[x]['school_name'],ele_df.loc[x]['school_addr'],ele_df.loc[x]['latitude'],ele_df.loc[x]['longitude'],\n", | ||
189 | + " ele_stu_num_df.loc[y]['1_stu_num'],ele_stu_num_df.loc[y]['2_stu_num'],ele_stu_num_df.loc[y]['3_stu_num'],\n", | ||
190 | + " ele_stu_num_df.loc[y]['4_stu_num'],ele_stu_num_df.loc[y]['5_stu_num'],ele_stu_num_df.loc[y]['6_stu_num']]\n", | ||
191 | + " ele_arr.append(row)\n", | ||
192 | + " \n", | ||
193 | + "find_ele_student_num()\n", | ||
194 | + "columns=['school_name','school_addr','latitude','longitude','1_stu_num','2_stu_num','3_stu_num','4_stu_num','5_stu_num','6_stu_num']\n", | ||
195 | + "final_ele_df=pd.DataFrame(ele_arr,columns=columns)\n", | ||
196 | + "final_ele_df.to_csv(r'final_ele_school.csv')" | ||
197 | + ] | ||
198 | + }, | ||
199 | + { | ||
200 | + "cell_type": "code", | ||
201 | + "execution_count": null, | ||
202 | + "metadata": {}, | ||
203 | + "outputs": [], | ||
204 | + "source": [ | ||
205 | + "import pandas as pd\n", | ||
206 | + "import numpy as np\n", | ||
207 | + "import pyspark\n", | ||
208 | + "from tqdm import tqdm\n", | ||
209 | + "\n", | ||
210 | + "basic_folder = ''\n", | ||
211 | + "file_name = basic_folder + 'high_school.csv'\n", | ||
212 | + "file_name2 = basic_folder + 'high_school_stu_num.csv'\n", | ||
213 | + "\n", | ||
214 | + "middle_df =pd.read_csv(file_name)\n", | ||
215 | + "middle_stu_num_df=pd.read_csv(file_name2)\n", | ||
216 | + "\n", | ||
217 | + "count_row=middle_df.shape[0]\n", | ||
218 | + "count_row2=middle_stu_num_df.shape[0]\n", | ||
219 | + "\n", | ||
220 | + "high_arr=[]\n", | ||
221 | + "\n", | ||
222 | + "def find_high_student_num():\n", | ||
223 | + " for x in tqdm(range(count_row)):\n", | ||
224 | + " name=middle_df.loc[x]['school_name']\n", | ||
225 | + " for y in range(count_row2):\n", | ||
226 | + " if name == middle_stu_num_df.loc[y]['school_name']:\n", | ||
227 | + " row=[middle_df.loc[x]['school_name'],middle_df.loc[x]['school_addr'],middle_df.loc[x]['latitude'],middle_df.loc[x]['longitude'],\n", | ||
228 | + " middle_stu_num_df.loc[y]['1_stu_num'],middle_stu_num_df.loc[y]['2_stu_num'],middle_stu_num_df.loc[y]['3_stu_num']]\n", | ||
229 | + " high_arr.append(row)\n", | ||
230 | + " \n", | ||
231 | + "find_high_student_num()\n", | ||
232 | + "columns=['school_name','school_addr','latitude','longitude','1_stu_num','2_stu_num','3_stu_num']\n", | ||
233 | + "final_high_df=pd.DataFrame(middle_arr,columns=columns)\n", | ||
234 | + "final_high_df.to_csv(r'final_high_school.csv')" | ||
235 | + ] | ||
236 | + } | ||
237 | + ], | ||
238 | + "metadata": { | ||
239 | + "kernelspec": { | ||
240 | + "display_name": "Python 3", | ||
241 | + "language": "python", | ||
242 | + "name": "python3" | ||
243 | + }, | ||
244 | + "language_info": { | ||
245 | + "codemirror_mode": { | ||
246 | + "name": "ipython", | ||
247 | + "version": 3 | ||
248 | + }, | ||
249 | + "file_extension": ".py", | ||
250 | + "mimetype": "text/x-python", | ||
251 | + "name": "python", | ||
252 | + "nbconvert_exporter": "python", | ||
253 | + "pygments_lexer": "ipython3", | ||
254 | + "version": "3.7.7" | ||
255 | + } | ||
256 | + }, | ||
257 | + "nbformat": 4, | ||
258 | + "nbformat_minor": 4 | ||
259 | +} |
code/dataset/전국고등학교학교군표준데이터.csv
deleted
100644 → 0
1 | -학구ID,학구명,학구분류,시도코드,시도교육청코드,시도교육청명,교육지원청코드,교육지원청명,생성일자,변경일자,공간객체ID,데이터기준일자,제공기관코드,제공기관명, | ||
2 | -Z000300001,동부학교군,0,11,7010000,서울특별시교육청,7021000,서울특별시동부교육지원청,2016-08-12,2016-08-12,28,2019-09-16,7001220,한국교원대학교, | ||
3 | -Z000300002,서부학교군,0,11,7010000,서울특별시교육청,7031000,서울특별시서부교육지원청,2016-08-12,2016-08-12,9,2019-09-16,7001220,한국교원대학교, | ||
4 | -Z000300003,남부학교군,0,11,7010000,서울특별시교육청,7041000,서울특별시남부교육지원청,2016-08-12,2016-08-12,8,2019-09-16,7001220,한국교원대학교, | ||
5 | -Z000300004,북부학교군,0,11,7010000,서울특별시교육청,7051000,서울특별시북부교육지원청,2016-08-12,2016-08-12,14,2019-09-16,7001220,한국교원대학교, | ||
6 | -Z000300005,중부학교군,0,11,7010000,서울특별시교육청,7061000,서울특별시중부교육지원청,2016-08-12,2016-08-12,10,2019-09-16,7001220,한국교원대학교, | ||
7 | -Z000300006,강동송파학교군,0,11,7010000,서울특별시교육청,7130000,서울특별시강동송파교육지원청,2016-08-12,2016-08-12,15,2019-09-16,7001220,한국교원대학교, | ||
8 | -Z000300007,강서학교군,0,11,7010000,서울특별시교육청,7081300,서울특별시강서양천교육지원청,2016-08-12,2016-08-12,26,2019-09-16,7001220,한국교원대학교, | ||
9 | -Z000300008,강남학교군,0,11,7010000,서울특별시교육청,7091300,서울특별시강남서초교육지원청,2016-08-12,2016-08-12,16,2019-09-16,7001220,한국교원대학교, | ||
10 | -Z000300009,동작관악학교군,0,11,7010000,서울특별시교육청,7132000,서울특별시동작관악교육지원청,2016-08-12,2016-08-12,17,2019-09-16,7001220,한국교원대학교, | ||
11 | -Z000300010,성동광진학교군,0,11,7010000,서울특별시교육청,7134000,서울특별시성동광진교육지원청,2016-08-12,2016-08-12,29,2019-09-16,7001220,한국교원대학교, | ||
12 | -Z000300011,성북학교군,0,11,7010000,서울특별시교육청,7121200,서울특별시성북강북교육지원청,2016-08-12,2016-08-12,13,2019-09-16,7001220,한국교원대학교, | ||
13 | -Z000300012,서부고등학군,0,26,7150000,부산광역시교육청,7171000,부산광역시서부교육지원청,2016-08-12,2016-08-12,53,2019-09-16,7001220,한국교원대학교, | ||
14 | -Z000300013,남부고등학군,0,26,7150000,부산광역시교육청,7181000,부산광역시남부교육지원청,2016-08-12,2016-08-12,23,2019-09-16,7001220,한국교원대학교, | ||
15 | -Z000300014,동래고등학군,0,26,7150000,부산광역시교육청,7191000,부산광역시동래교육지원청,2016-08-12,2016-08-12,54,2019-09-16,7001220,한국교원대학교, | ||
16 | -Z000300015,북부고등학군,0,26,7150000,부산광역시교육청,7201000,부산광역시북부교육지원청,2016-08-12,2016-08-12,21,2019-09-16,7001220,한국교원대학교, | ||
17 | -Z000300016,해운대고등학군,0,26,7150000,부산광역시교육청,7211000,부산광역시해운대교육지원청,2016-08-12,2016-08-12,22,2019-09-16,7001220,한국교원대학교, | ||
18 | -Z000300017,고등학교1학군,0,27,7240000,대구광역시교육청,7251000,대구광역시동부교육지원청,2016-08-12,2016-08-12,25,2019-09-16,7001220,한국교원대학교, | ||
19 | -Z000300018,고등학교2학군,0,27,7240000,대구광역시교육청,7271000,대구광역시남부교육지원청,2016-08-12,2016-08-12,24,2019-09-16,7001220,한국교원대학교, | ||
20 | -Z000300019,1학교군,0,28,7310000,인천광역시교육청,7321000,인천광역시남부교육지원청,2016-08-12,2016-08-12,55,2019-09-16,7001220,한국교원대학교, | ||
21 | -Z000300020,2학교군,0,28,7310000,인천광역시교육청,7331000,인천광역시북부교육지원청,2016-08-12,2016-08-12,30,2019-09-16,7001220,한국교원대학교, | ||
22 | -Z000300021,특수지고등학군,0,28,7310000,인천광역시교육청,7321000,인천광역시남부교육지원청,2016-08-12,2017-02-14,52,2019-09-16,7001220,한국교원대학교, | ||
23 | -Z000300022,3학교군,0,28,7310000,인천광역시교육청,7361000,인천광역시서부교육지원청,2016-08-12,2016-08-12,31,2019-09-16,7001220,한국교원대학교, | ||
24 | -Z000300023,광주광역시단일학교군,0,29,7380000,광주광역시교육청,7391000,광주광역시동부교육지원청,2016-08-12,2017-02-14,18,2019-09-16,7001220,한국교원대학교, | ||
25 | -Z000300024,대전광역시단일학교군,0,30,7430000,대전광역시교육청,7441000,대전광역시동부교육지원청,2016-08-12,2016-08-12,48,2019-09-16,7001220,한국교원대학교, | ||
26 | -Z000300025,동부학교군,0,31,7480000,울산광역시교육청,7491000,울산광역시강북교육지원청,2016-08-12,2016-08-12,20,2019-09-16,7001220,한국교원대학교, | ||
27 | -Z000300026,북부학교군,0,31,7480000,울산광역시교육청,7491000,울산광역시강북교육지원청,2016-08-12,2016-08-12,19,2019-09-16,7001220,한국교원대학교, | ||
28 | -Z000300027,중부학교군,0,31,7480000,울산광역시교육청,7491000,울산광역시강북교육지원청,2018-07-12,2018-07-12,58,2019-09-16,7001220,한국교원대학교, | ||
29 | -Z000300028,남부학교군,0,31,7480000,울산광역시교육청,7501000,울산광역시강남교육지원청,2018-07-12,2018-07-12,59,2019-09-16,7001220,한국교원대학교, | ||
30 | -Z000300029,언양특수학교군,0,31,7480000,울산광역시교육청,7501000,울산광역시강남교육지원청,2016-08-12,2016-08-12,27,2019-09-16,7001220,한국교원대학교, | ||
31 | -Z000300030,수원1구역,0,41,7530000,경기도교육청,7541000,경기도수원교육지원청,2016-08-12,2016-08-12,51,2019-09-16,7001220,한국교원대학교, | ||
32 | -Z000300031,수원2구역,0,41,7530000,경기도교육청,7541000,경기도수원교육지원청,2016-08-12,2016-08-12,50,2019-09-16,7001220,한국교원대학교, | ||
33 | -Z000300032,성남1구역,0,41,7530000,경기도교육청,7551000,경기도성남교육지원청,2016-08-12,2016-08-12,47,2019-09-16,7001220,한국교원대학교, | ||
34 | -Z000300033,성남2구역,0,41,7530000,경기도교육청,7551000,경기도성남교육지원청,2016-08-12,2016-08-12,39,2019-09-16,7001220,한국교원대학교, | ||
35 | -Z000300034,의정부학군,0,41,7530000,경기도교육청,7561000,경기도의정부교육지원청,2016-08-12,2016-08-12,32,2019-09-16,7001220,한국교원대학교, | ||
36 | -Z000300035,안양권1구역,0,41,7530000,경기도교육청,7569000,경기도안양과천교육지원청,2016-08-12,2016-08-12,45,2019-09-16,7001220,한국교원대학교, | ||
37 | -Z000300036,안양권2구역,0,41,7530000,경기도교육청,7569000,경기도안양과천교육지원청,2016-08-12,2016-08-12,49,2019-09-16,7001220,한국교원대학교, | ||
38 | -Z000300037,부천학군,0,41,7530000,경기도교육청,7581000,경기도부천교육지원청,2016-08-12,2016-08-12,34,2019-09-16,7001220,한국교원대학교, | ||
39 | -Z000300038,광명학군,0,41,7530000,경기도교육청,7591000,경기도광명교육지원청,2016-08-12,2016-08-12,33,2019-09-16,7001220,한국교원대학교, | ||
40 | -Z000300039,안산1구역,0,41,7530000,경기도교육청,7611000,경기도안산교육지원청,2016-08-12,2016-08-12,42,2019-09-16,7001220,한국교원대학교, | ||
41 | -Z000300040,안산2구역,0,41,7530000,경기도교육청,7611000,경기도안산교육지원청,2016-08-12,2016-08-12,44,2019-09-16,7001220,한국교원대학교, | ||
42 | -Z000300041,고양1구역,0,41,7530000,경기도교육청,7621000,경기도고양교육지원청,2016-08-12,2016-08-12,41,2019-09-16,7001220,한국교원대학교, | ||
43 | -Z000300042,고양2구역,0,41,7530000,경기도교육청,7621000,경기도고양교육지원청,2016-08-12,2016-08-12,40,2019-09-16,7001220,한국교원대학교, | ||
44 | -Z000300043,안양권3구역,0,41,7530000,경기도교육청,7642000,경기도군포의왕교육지원청,2016-08-12,2016-08-12,35,2019-09-16,7001220,한국교원대학교, | ||
45 | -Z000300044,안양권4구역,0,41,7530000,경기도교육청,7642000,경기도군포의왕교육지원청,2016-08-12,2016-08-12,46,2019-09-16,7001220,한국교원대학교, | ||
46 | -Z000300045,용인1구역,0,41,7530000,경기도교육청,7751000,경기도용인교육지원청,2016-08-12,2016-08-12,43,2019-09-16,7001220,한국교원대학교, | ||
47 | -Z000300046,용인2구역,0,41,7530000,경기도교육청,7751000,경기도용인교육지원청,2016-08-12,2016-08-12,36,2019-09-16,7001220,한국교원대학교, | ||
48 | -Z000300047,용인3구역,0,41,7530000,경기도교육청,7751000,경기도용인교육지원청,2016-08-12,2016-08-12,37,2019-09-16,7001220,한국교원대학교, | ||
49 | -Z000300048,청주시고등학군,0,43,8000000,충청북도교육청,8011000,충청북도청주교육지원청,2016-08-12,2016-08-12,38,2019-09-16,7001220,한국교원대학교, | ||
50 | -Z000300049,천안시학교군,0,44,8140000,충청남도교육청,8151000,충청남도천안교육지원청,2016-08-12,2016-08-12,4,2019-09-16,7001220,한국교원대학교, | ||
51 | -Z000300050,전주시학교군,0,45,8320000,전라북도교육청,8331000,전라북도전주교육지원청,2016-08-12,2017-02-14,1,2019-09-16,7001220,한국교원대학교, | ||
52 | -Z000300051,군산시학교군,0,45,8320000,전라북도교육청,8341000,전라북도군산교육지원청,2016-08-12,2016-08-12,5,2019-09-16,7001220,한국교원대학교, | ||
53 | -Z000300052,익산시학교군,0,45,8320000,전라북도교육청,8351000,전라북도익산교육지원청,2016-08-12,2016-08-12,12,2019-09-16,7001220,한국교원대학교, | ||
54 | -Z000300053,목포시제1학교군,0,46,8490000,전라남도교육청,8501000,전라남도목포교육지원청,2016-08-12,2016-08-12,6,2019-09-16,7001220,한국교원대학교, | ||
55 | -Z000300054,여수시제2학교군,0,46,8490000,전라남도교육청,8511000,전라남도여수교육지원청,2016-08-12,2016-08-12,7,2019-09-16,7001220,한국교원대학교, | ||
56 | -Z000300055,순천시제3학교군,0,46,8490000,전라남도교육청,8521000,전라남도순천교육지원청,2016-08-12,2016-08-12,2,2019-09-16,7001220,한국교원대학교, | ||
57 | -Z000300056,포항시제1학교군,0,47,8750000,경상북도교육청,8761000,경상북도포항교육지원청,2016-08-12,2016-08-12,11,2019-09-16,7001220,한국교원대학교, | ||
58 | -Z000300057,창원시제1학교군,0,48,9010000,경상남도교육청,9022000,경상남도창원교육지원청,2016-08-12,2019-07-16,62,2019-09-16,7001220,한국교원대학교, | ||
59 | -Z000300058,창원시제2학교군,0,48,9010000,경상남도교육청,9022000,경상남도창원교육지원청,2016-08-12,2019-07-16,61,2019-09-16,7001220,한국교원대학교, | ||
60 | -Z000300059,진주시제3학교군,0,48,9010000,경상남도교육청,9051000,경상남도진주교육지원청,2016-08-12,2016-08-12,57,2019-09-16,7001220,한국교원대학교, | ||
61 | -Z000300060,김해시제4학교군,0,48,9010000,경상남도교육청,9091000,경상남도김해교육지원청,2016-08-12,2016-08-12,56,2019-09-16,7001220,한국교원대학교, | ||
62 | -Z000300061,제주시학교군,0,50,9290000,제주특별자치도교육청,9296000,제주특별자치도제주시교육지원청,2016-08-12,2017-02-14,3,2019-09-16,7001220,한국교원대학교, | ||
63 | -Z000300062,세종시고등학군,0,36,9300000,세종특별자치시교육청,9300000,세종특별자치시교육청,2018-11-05,2018-11-06,60,2019-09-16,7001220,한국교원대학교, | ||
64 | -Z000300063,거제시제5학교군,0,48,9010000,경상남도교육청,9111000,경상남도거제교육지원청,2019-07-22,2019-07-22,63,2019-09-16,7001220,한국교원대학교, |
code/dataset/전국초중등학교위치표준데이터.csv
deleted
100644 → 0
This diff could not be displayed because it is too large.
code/dataset/중학교시간표.csv
deleted
100644 → 0
This diff could not be displayed because it is too large.
code/dataset/초등학교시간표_서울시.csv
deleted
100644 → 0
This diff could not be displayed because it is too large.
This diff could not be displayed because it is too large.
code/dataset/학사일정_2020년03월.csv
deleted
100644 → 0
This diff could not be displayed because it is too large.
code/lstm_keras.ipynb
0 → 100644
This diff is collapsed. Click to expand it.
-
Please register or login to post a comment