mirror of
https://github.com/BlackWallTeam/ML.git
synced 2025-02-18 20:50:36 +03:00
1 line
11 KiB
Plaintext
1 line
11 KiB
Plaintext
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"mount_file_id":"11qi0Zs-HQZhJFvclA7OVLT8cqojQf2aI","authorship_tag":"ABX9TyNkG4DRTbevw8ODM0d/AIu/"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"}},"cells":[{"cell_type":"code","source":["import pandas as pd\n","import numpy as np"],"metadata":{"id":"1wCgQ3uby0j8","executionInfo":{"status":"ok","timestamp":1676663619141,"user_tz":480,"elapsed":787,"user":{"displayName":"Радмир Зосимов","userId":"04742503366191314986"}}},"execution_count":1,"outputs":[]},{"cell_type":"code","source":["df = pd.read_excel('/content/krasnodar_hack_data.xlsx')\n","df['date'] = df['date'].apply(lambda x: x[1:-1])\n","df['date'] = pd.to_datetime(df['date'])\n","df['floor'] = df['floor'].apply(lambda x: str(x).replace('--', '-'))\n","df['liter_num'] = df['liter_num'].apply(lambda x: str(x).replace('--', '-'))\n","df['price_per_m'] = df['price_per_m'].apply(lambda x: x.replace('\\xa0', '').replace(' ', '')).astype(int)\n","df['num_beds'] = df['num_beds'].astype(int)\n","df['area'] = df['area'].apply(lambda x: str(x).replace(',', '.')).astype(float)\n","df"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"zYk8ByTx8DXL","executionInfo":{"status":"ok","timestamp":1676664071326,"user_tz":480,"elapsed":424,"user":{"displayName":"Радмир Зосимов","userId":"04742503366191314986"}},"outputId":"909d53dd-a9a5-4185-dda0-49fd511f3055"},"execution_count":22,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" community liter_num done_date developer floor \\\n","0 ЖК «Смородина» 1-5 1 квартал 2023 ООО «АЛЬФА» 1-4 \n","1 ЖК «Смородина» 1-5 1 квартал 2023 ООО «АЛЬФА» 5-8 \n","2 ЖК «Смородина» 1-5 1 квартал 2023 ООО «АЛЬФА» 9-12 \n","3 ЖК «Смородина» 1-5 1 квартал 2023 ООО «АЛЬФА» 13-16 \n","4 ЖК «Смородина» 1-5 1 квартал 2023 ООО «АЛЬФА» 1-4 \n","... ... ... ... ... ... \n","1284 ЖК «Role Clef» nan 2 полугодие 2021 ООО «Уютный дом» 2-12 \n","1285 ЖК «Role Clef» nan 2 полугодие 2021 ООО «Уютный дом» 2-12 \n","1286 ЖК «Role Clef» nan 2 полугодие 2021 ООО «Уютный дом» 2-12 \n","1287 ЖК «Мелодия» nan дом сдан NaN 5 \n","1288 ЖК «Мелодия» nan дом сдан NaN 11 \n","\n"," area num_beds price_per_m date \n","0 32.95 1 118000 2022-01-25 \n","1 32.95 1 119000 2022-01-25 \n","2 32.95 1 120000 2022-01-25 \n","3 32.95 1 121000 2022-01-25 \n","4 35.20 1 117000 2022-01-25 \n","... ... ... ... ... \n","1284 NaN 1 586000 2023-02-15 \n","1285 NaN 2 400000 2023-02-15 \n","1286 NaN 3 395000 2023-02-15 \n","1287 NaN 2 94000 2023-02-15 \n","1288 NaN 2 94000 2023-02-15 \n","\n","[1289 rows x 9 columns]"],"text/html":["\n"," <div id=\"df-51bcb803-24d8-4839-9267-3795b41713f9\">\n"," <div class=\"colab-df-container\">\n"," <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>community</th>\n"," <th>liter_num</th>\n"," <th>done_date</th>\n"," <th>developer</th>\n"," <th>floor</th>\n"," <th>area</th>\n"," <th>num_beds</th>\n"," <th>price_per_m</th>\n"," <th>date</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>ЖК «Смородина»</td>\n"," <td>1-5</td>\n"," <td>1 квартал 2023</td>\n"," <td>ООО «АЛЬФА»</td>\n"," <td>1-4</td>\n"," <td>32.95</td>\n"," <td>1</td>\n"," <td>118000</td>\n"," <td>2022-01-25</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>ЖК «Смородина»</td>\n"," <td>1-5</td>\n"," <td>1 квартал 2023</td>\n"," <td>ООО «АЛЬФА»</td>\n"," <td>5-8</td>\n"," <td>32.95</td>\n"," <td>1</td>\n"," <td>119000</td>\n"," <td>2022-01-25</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>ЖК «Смородина»</td>\n"," <td>1-5</td>\n"," <td>1 квартал 2023</td>\n"," <td>ООО «АЛЬФА»</td>\n"," <td>9-12</td>\n"," <td>32.95</td>\n"," <td>1</td>\n"," <td>120000</td>\n"," <td>2022-01-25</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>ЖК «Смородина»</td>\n"," <td>1-5</td>\n"," <td>1 квартал 2023</td>\n"," <td>ООО «АЛЬФА»</td>\n"," <td>13-16</td>\n"," <td>32.95</td>\n"," <td>1</td>\n"," <td>121000</td>\n"," <td>2022-01-25</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>ЖК «Смородина»</td>\n"," <td>1-5</td>\n"," <td>1 квартал 2023</td>\n"," <td>ООО «АЛЬФА»</td>\n"," <td>1-4</td>\n"," <td>35.20</td>\n"," <td>1</td>\n"," <td>117000</td>\n"," <td>2022-01-25</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"," </tr>\n"," <tr>\n"," <th>1284</th>\n"," <td>ЖК «Role Clef»</td>\n"," <td>nan</td>\n"," <td>2 полугодие 2021</td>\n"," <td>ООО «Уютный дом»</td>\n"," <td>2-12</td>\n"," <td>NaN</td>\n"," <td>1</td>\n"," <td>586000</td>\n"," <td>2023-02-15</td>\n"," </tr>\n"," <tr>\n"," <th>1285</th>\n"," <td>ЖК «Role Clef»</td>\n"," <td>nan</td>\n"," <td>2 полугодие 2021</td>\n"," <td>ООО «Уютный дом»</td>\n"," <td>2-12</td>\n"," <td>NaN</td>\n"," <td>2</td>\n"," <td>400000</td>\n"," <td>2023-02-15</td>\n"," </tr>\n"," <tr>\n"," <th>1286</th>\n"," <td>ЖК «Role Clef»</td>\n"," <td>nan</td>\n"," <td>2 полугодие 2021</td>\n"," <td>ООО «Уютный дом»</td>\n"," <td>2-12</td>\n"," <td>NaN</td>\n"," <td>3</td>\n"," <td>395000</td>\n"," <td>2023-02-15</td>\n"," </tr>\n"," <tr>\n"," <th>1287</th>\n"," <td>ЖК «Мелодия»</td>\n"," <td>nan</td>\n"," <td>дом сдан</td>\n"," <td>NaN</td>\n"," <td>5</td>\n"," <td>NaN</td>\n"," <td>2</td>\n"," <td>94000</td>\n"," <td>2023-02-15</td>\n"," </tr>\n"," <tr>\n"," <th>1288</th>\n"," <td>ЖК «Мелодия»</td>\n"," <td>nan</td>\n"," <td>дом сдан</td>\n"," <td>NaN</td>\n"," <td>11</td>\n"," <td>NaN</td>\n"," <td>2</td>\n"," <td>94000</td>\n"," <td>2023-02-15</td>\n"," </tr>\n"," </tbody>\n","</table>\n","<p>1289 rows × 9 columns</p>\n","</div>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-51bcb803-24d8-4839-9267-3795b41713f9')\"\n"," title=\"Convert this dataframe to an interactive table.\"\n"," style=\"display:none;\">\n"," \n"," <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n"," width=\"24px\">\n"," <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n"," <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n"," </svg>\n"," </button>\n"," \n"," <style>\n"," .colab-df-container {\n"," display:flex;\n"," flex-wrap:wrap;\n"," gap: 12px;\n"," }\n","\n"," .colab-df-convert {\n"," background-color: #E8F0FE;\n"," border: none;\n"," border-radius: 50%;\n"," cursor: pointer;\n"," display: none;\n"," fill: #1967D2;\n"," height: 32px;\n"," padding: 0 0 0 0;\n"," width: 32px;\n"," }\n","\n"," .colab-df-convert:hover {\n"," background-color: #E2EBFA;\n"," box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n"," fill: #174EA6;\n"," }\n","\n"," [theme=dark] .colab-df-convert {\n"," background-color: #3B4455;\n"," fill: #D2E3FC;\n"," }\n","\n"," [theme=dark] .colab-df-convert:hover {\n"," background-color: #434B5C;\n"," box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n"," filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n"," fill: #FFFFFF;\n"," }\n"," </style>\n","\n"," <script>\n"," const buttonEl =\n"," document.querySelector('#df-51bcb803-24d8-4839-9267-3795b41713f9 button.colab-df-convert');\n"," buttonEl.style.display =\n"," google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n"," async function convertToInteractive(key) {\n"," const element = document.querySelector('#df-51bcb803-24d8-4839-9267-3795b41713f9');\n"," const dataTable =\n"," await google.colab.kernel.invokeFunction('convertToInteractive',\n"," [key], {});\n"," if (!dataTable) return;\n","\n"," const docLinkHtml = 'Like what you see? Visit the ' +\n"," '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n"," + ' to learn more about interactive tables.';\n"," element.innerHTML = '';\n"," dataTable['output_type'] = 'display_data';\n"," await google.colab.output.renderOutput(dataTable, element);\n"," const docLink = document.createElement('div');\n"," docLink.innerHTML = docLinkHtml;\n"," element.appendChild(docLink);\n"," }\n"," </script>\n"," </div>\n"," </div>\n"," "]},"metadata":{},"execution_count":22}]},{"cell_type":"code","source":["df.to_csv('krasnodar_data_final.csv', index=False)"],"metadata":{"id":"v7B0OICi8LOx","executionInfo":{"status":"ok","timestamp":1676664099279,"user_tz":480,"elapsed":119,"user":{"displayName":"Радмир Зосимов","userId":"04742503366191314986"}}},"execution_count":23,"outputs":[]},{"cell_type":"code","source":[],"metadata":{"id":"UNgPSTGM8Ypj"},"execution_count":null,"outputs":[]}]} |