Skip to content

Commit

Permalink
fix/ imports and geocoder
Browse files Browse the repository at this point in the history
GeorgeKontsevik committed Jun 9, 2024
1 parent 030768d commit f237471
Showing 8 changed files with 1,725 additions and 1,630 deletions.
Binary file modified .DS_Store
Binary file not shown.
200 changes: 198 additions & 2 deletions examples/city_services_example.ipynb
Original file line number Diff line number Diff line change
@@ -23,7 +23,25 @@
"name": "stdout",
"output_type": "stream",
"text": [
"2024-04-25 10:08:13,127 SequenceTagger predicts: Dictionary with 7 tags: O, S-Service, B-Service, E-Service, I-Service, <START>, <STOP>\n"
"INFO: Pandarallel will run on -1 workers.\n",
"INFO: Pandarallel will use standard multiprocessing data transfer (pipe) to transfer data between the main process and workers.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[nltk_data] Downloading package stopwords to /Users/test/nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n",
"[nltk_data] Downloading package stopwords to /Users/test/nltk_data...\n",
"[nltk_data] Package stopwords is already up-to-date!\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"2024-06-09 13:02:33,176 SequenceTagger predicts: Dictionary with 7 tags: O, S-Service, B-Service, E-Service, I-Service, <START>, <STOP>\n"
]
}
],
@@ -159,6 +177,184 @@
"result = City_services().run(df, text_column='Текст комментария')"
]
},
{
"cell_type": "code",
"execution_count": 6,
"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>message_id</th>\n",
" <th>Дата и время</th>\n",
" <th>Текст комментария</th>\n",
" <th>City_services_extraced</th>\n",
" <th>City_services</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>2023.01.26 16:32</td>\n",
" <td>Здравствуйте! В Санкт-Петербурге нет Генеральн...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>2023.01.26 11:55</td>\n",
" <td>[club143265175|Центральный район Санкт-Петербу...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>2023.01.28 12:39</td>\n",
" <td>1) Фурштатская, 19 Отслоение штукатурного слоя...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>2023.01.28 12:42</td>\n",
" <td>2) Фурштатская, 17 Здесь прямо-таки умоляю обр...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>2023.01.28 12:45</td>\n",
" <td>3) Фурштатская, 13 Отслоение штукатурного слоя...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>195</th>\n",
" <td>195</td>\n",
" <td>2022.10.24 14:02</td>\n",
" <td>На Чайковского 63 тоже идет кап.ремонт. В квар...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>196</th>\n",
" <td>196</td>\n",
" <td>2022.10.21 22:22</td>\n",
" <td>Вся улица Жуковского и Восстания заклеена рекл...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>197</th>\n",
" <td>197</td>\n",
" <td>2022.10.26 12:57</td>\n",
" <td>О каком благоустройстве идёт речь. Стремянная...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>198</th>\n",
" <td>198</td>\n",
" <td>2022.10.20 22:08</td>\n",
" <td>🤣🤣🤣🤣 угол 1й советской и Суворовского Клюваты...</td>\n",
" <td>[]</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>199</th>\n",
" <td>199</td>\n",
" <td>2022.10.18 19:24</td>\n",
" <td>Искренне благодарю за участие в решении многих...</td>\n",
" <td>[Фонтанке]</td>\n",
" <td>[Фонтан]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>200 rows × 5 columns</p>\n",
"</div>"
],
"text/plain": [
" message_id Дата и время \\\n",
"0 0 2023.01.26 16:32 \n",
"1 1 2023.01.26 11:55 \n",
"2 2 2023.01.28 12:39 \n",
"3 3 2023.01.28 12:42 \n",
"4 4 2023.01.28 12:45 \n",
".. ... ... \n",
"195 195 2022.10.24 14:02 \n",
"196 196 2022.10.21 22:22 \n",
"197 197 2022.10.26 12:57 \n",
"198 198 2022.10.20 22:08 \n",
"199 199 2022.10.18 19:24 \n",
"\n",
" Текст комментария City_services_extraced \\\n",
"0 Здравствуйте! В Санкт-Петербурге нет Генеральн... [] \n",
"1 [club143265175|Центральный район Санкт-Петербу... [] \n",
"2 1) Фурштатская, 19 Отслоение штукатурного слоя... [] \n",
"3 2) Фурштатская, 17 Здесь прямо-таки умоляю обр... [] \n",
"4 3) Фурштатская, 13 Отслоение штукатурного слоя... [] \n",
".. ... ... \n",
"195 На Чайковского 63 тоже идет кап.ремонт. В квар... [] \n",
"196 Вся улица Жуковского и Восстания заклеена рекл... [] \n",
"197 О каком благоустройстве идёт речь. Стремянная... [] \n",
"198 🤣🤣🤣🤣 угол 1й советской и Суворовского Клюваты... [] \n",
"199 Искренне благодарю за участие в решении многих... [Фонтанке] \n",
"\n",
" City_services \n",
"0 [] \n",
"1 [] \n",
"2 [] \n",
"3 [] \n",
"4 [] \n",
".. ... \n",
"195 [] \n",
"196 [] \n",
"197 [] \n",
"198 [] \n",
"199 [Фонтан] \n",
"\n",
"[200 rows x 5 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"display(result)"
]
},
{
"cell_type": "code",
"execution_count": 4,
@@ -676,7 +872,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.8"
"version": "3.11.9"
}
},
"nbformat": 4,
Loading

0 comments on commit f237471

Please sign in to comment.