{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "23157c89", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple\n", "Requirement already satisfied: pandas in c:\\programdata\\anaconda3\\lib\\site-packages (1.4.2)\n", "Requirement already satisfied: pymysql in c:\\programdata\\anaconda3\\lib\\site-packages (1.1.2)\n", "Requirement already satisfied: sqlalchemy in c:\\programdata\\anaconda3\\lib\\site-packages (1.4.32)\n", "Requirement already satisfied: pytz>=2020.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2021.3)\n", "Requirement already satisfied: numpy>=1.18.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (1.21.5)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2.8.2)\n", "Requirement already satisfied: greenlet!=0.4.17 in c:\\programdata\\anaconda3\\lib\\site-packages (from sqlalchemy) (1.1.1)\n", "Requirement already satisfied: six>=1.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n" ] } ], "source": [ "!pip install pandas pymysql sqlalchemy -i https://pypi.tuna.tsinghua.edu.cn/simple" ] }, { "cell_type": "code", "execution_count": 4, "id": "67b87f14", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "✅ MySQL数据库连接成功！字符集已修复支持中文\n" ] } ], "source": [ "import pandas as pd\n", "from sqlalchemy import create_engine\n", "\n", "# --------------------------\n", "# 你的MySQL配置（不用改，保持你自己的）\n", "# --------------------------\n", "MYSQL_USER = \"root\" \n", "MYSQL_PASSWORD = \"123456\" \n", "MYSQL_HOST = \"localhost\" \n", "MYSQL_PORT = \"3306\" \n", "MYSQL_DB = \"test_db\" \n", "\n", "# --------------------------\n", "# ✅ 修复：强制指定中文字符集 utf8mb4（关键代码）\n", "# --------------------------\n", "engine = create_engine(\n", " f\"mysql+pymysql://{MYSQL_USER}:{MYSQL_PASSWORD}@{MYSQL_HOST}:{MYSQL_PORT}/{MYSQL_DB}?charset=utf8mb4\",\n", " # 追加字符集初始化，彻底解决中文乱码/写入失败\n", " connect_args={\"init_command\": \"SET NAMES utf8mb4\"}\n", ")\n", "\n", "# 测试连接\n", "try:\n", " with engine.connect():\n", " print(\"✅ MySQL数据库连接成功！字符集已修复支持中文\")\n", "except Exception as e:\n", " print(f\"❌ 连接失败：{e}\")" ] }, { "cell_type": "code", "execution_count": 5, "id": "7f36e3ff", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 课程编号 课程名称 学分 授课教师 上课时间\n", "0 CS001 Python数据分析 4 张老师 周一/周三 第1-2节\n", "1 CS002 数据库原理 3 李老师 周二/周四 第3-4节\n", "2 MA001 高等数学 5 王老师 周一/周五 第5-6节\n", "3 EN001 大学英语 2 刘老师 周三 第7-8节\n", "✅ 任务3.1完成：手动数据已写入MySQL表 course_info_manual\n" ] } ], "source": [ "# 1. 手动构造课程数据（示例）\n", "# --------------------------\n", "data = {\n", " \"课程编号\": [\"CS001\", \"CS002\", \"MA001\", \"EN001\"],\n", " \"课程名称\": [\"Python数据分析\", \"数据库原理\", \"高等数学\", \"大学英语\"],\n", " \"学分\": [4, 3, 5, 2],\n", " \"授课教师\": [\"张老师\", \"李老师\", \"王老师\", \"刘老师\"],\n", " \"上课时间\": [\"周一/周三 第1-2节\", \"周二/周四 第3-4节\", \"周一/周五 第5-6节\", \"周三 第7-8节\"]\n", "}\n", "\n", "# 转为DataFrame\n", "df_manual = pd.DataFrame(data)\n", "print(df_manual)\n", "# --------------------------\n", "# 2. 写入MySQL数据库\n", "# --------------------------\n", "# 参数说明：\n", "# name：要写入的表名（如果不存在会自动创建）\n", "# con：数据库连接引擎\n", "# if_exists：处理表已存在的情况\n", "# - \"replace\"：删除原表，重建新表写入\n", "# - \"append\"：在原表末尾追加数据\n", "# - \"fail\"：如果表存在就报错\n", "# index=False：不把pandas的索引写入数据库\n", "\n", "df_manual.to_sql(\n", " name=\"course_info_manual\", # 自定义表名\n", " con=engine,\n", " if_exists=\"replace\",\n", " index=False\n", ")\n", "\n", "print(\"✅ 任务3.1完成：手动数据已写入MySQL表 course_info_manual\")\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "ea47bd4a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "📊 从MySQL读取的课程表数据：\n", " 课程编号 课程名称 学分 授课教师 上课时间\n", "0 CS001 Python数据分析 4 张老师 周一/周三 第1-2节\n", "1 CS002 数据库原理 3 李老师 周二/周四 第3-4节\n", "2 MA001 高等数学 5 王老师 周一/周五 第5-6节\n", "3 EN001 大学英语 2 刘老师 周三 第7-8节\n" ] } ], "source": [ "df_read = pd.read_sql(\n", " sql=\"SELECT * FROM course_info_manual\", # 读取整张表\n", " con=engine\n", ")\n", "\n", "# 打印读取到的数据\n", "print(\"📊 从MySQL读取的课程表数据：\")\n", "print(df_read)" ] }, { "cell_type": "code", "execution_count": 7, "id": "89eecdba", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "⚠️ 无表格/读取失败，尝试读取网页文字： html5lib not found, please install it\n", "\n", "✅ 网页文字读取成功（前500字）：\n", " 网页文字内容\n", "0 百度一下，你就知道新闻hao123地图视频贴吧登录更多产品关于百度About Baidu©2...\n", "✅ 网页文字已写入MySQL表：web_data_table_text\n", "\n", "🎉 全部完成！\n" ] } ], "source": [ "# 1. 导入所有需要的库\n", "import pandas as pd\n", "from sqlalchemy import create_engine\n", "import requests\n", "from bs4 import BeautifulSoup\n", "\n", "# =====================【只改这里！3个地方】=====================\n", "# 1. 要爬的网页地址\n", "WEB_URL = \"https://www.baidu.com\"\n", "# 2. 你的MySQL数据库名（改成你自己的）\n", "MYSQL_DB = \"test_db\"\n", "# 3. 要写入MySQL的表名\n", "MYSQL_TABLE = \"web_data_table\"\n", "# ==============================================================\n", "\n", "# MySQL固定配置（你刚重置的密码，不用改）\n", "MYSQL_USER = \"root\"\n", "MYSQL_PWD = \"123456\"\n", "MYSQL_HOST = \"localhost\"\n", "\n", "# 创建MySQL连接\n", "engine = create_engine(f\"mysql+pymysql://{MYSQL_USER}:{MYSQL_PWD}@{MYSQL_HOST}:3306/{MYSQL_DB}\")\n", "\n", "# ---------------------- 方式1：读取网页【表格】（最常用）----------------------\n", "try:\n", " # 自动抓取网页所有表格，返回列表，[0]是第一个表格\n", " df_table = pd.read_html(WEB_URL, encoding=\"utf-8\")[0]\n", " print(\"✅ 网页表格读取成功：\")\n", " print(df_table.head())\n", "\n", " # 写入MySQL\n", " df_table.to_sql(\n", " name=MYSQL_TABLE,\n", " con=engine,\n", " if_exists=\"replace\",\n", " index=False\n", " )\n", " print(f\"✅ 网页表格已写入MySQL表：{MYSQL_TABLE}\")\n", "\n", "except Exception as e:\n", " print(\"⚠️ 无表格/读取失败，尝试读取网页文字：\", e)\n", "\n", "# ---------------------- 方式2：读取网页【文字】转DataFrame ----------------------\n", "try:\n", " # 抓取网页文字\n", " resp = requests.get(WEB_URL, timeout=10)\n", " resp.encoding = \"utf-8\"\n", " soup = BeautifulSoup(resp.text, \"html.parser\")\n", " web_text = soup.get_text(strip=True) # 提取纯文字\n", "\n", " # 把文字转成Pandas（1行1列）\n", " df_text = pd.DataFrame({\"网页文字内容\": [web_text[:500]]}) # 取前500字避免太长\n", " print(\"\\n✅ 网页文字读取成功（前500字）：\")\n", " print(df_text)\n", "\n", " # 文字写入MySQL（表名加个后缀区分）\n", " df_text.to_sql(\n", " name=f\"{MYSQL_TABLE}_text\",\n", " con=engine,\n", " if_exists=\"replace\",\n", " index=False\n", " )\n", " print(f\"✅ 网页文字已写入MySQL表：{MYSQL_TABLE}_text\")\n", "\n", "except Exception as e:\n", " print(\"⚠️ 网页文字读取失败：\", e)\n", "\n", "print(\"\\n🎉 全部完成！\")" ] }, { "cell_type": "code", "execution_count": 9, "id": "cc8e34f0", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "✅ 抓取到的天气数据：\n", " 日期/星期 天气状况 最高温度 最低温度 风力\n", "0 今天04/27 小雨 23 16 \n", "1 周二04/28 小雨 17 15 \n", "2 周三04/29 多云转阴 22 14 \n", "3 周四04/30 阴 26 16 \n", "4 周五05/01 小雨 29 17 \n", "5 周六05/02 阴 23 17 \n", "6 周日05/03 小雨 22 17 \n", "7 周一05/04 雨转阴 20 17 \n", "8 周二05/05 阴转多云 23 17 \n", "9 周三05/06 阴转雨 26 20 \n", "10 周四05/07 雨 21 18 \n", "11 周五05/08 雨转阴 21 17 \n", "12 周六05/09 雨 26 19 \n", "13 周日05/10 雨转阴 22 19 \n", "14 周一05/11 雨 30 22 \n", "\n", "📊 从MySQL读回的数据：\n", " 日期/星期 天气状况 最高温度 最低温度 风力\n", "0 今天04/27 小雨 23 16 \n", "1 周二04/28 小雨 17 15 \n", "2 周三04/29 多云转阴 22 14 \n", "3 周四04/30 阴 26 16 \n", "4 周五05/01 小雨 29 17 \n", "5 周六05/02 阴 23 17 \n", "6 周日05/03 小雨 22 17 \n", "7 周一05/04 雨转阴 20 17 \n", "8 周二05/05 阴转多云 23 17 \n", "9 周三05/06 阴转雨 26 20 \n", "10 周四05/07 雨 21 18 \n", "11 周五05/08 雨转阴 21 17 \n", "12 周六05/09 雨 26 19 \n", "13 周日05/10 雨转阴 22 19 \n", "14 周一05/11 雨 30 22 \n", "\n", "🎉 已成功写入MySQL表：jiangjin_weather_15d\n" ] } ], "source": [ "import pandas as pd\n", "import requests\n", "from bs4 import BeautifulSoup\n", "from sqlalchemy import create_engine\n", "\n", "# ===================== MySQL配置（用你之前的账号密码）=====================\n", "engine = create_engine(\"mysql+pymysql://root:123456@localhost:3306/test_db\")\n", "url = \"http://sq.src.weather.com.cn/mweather15d/101040500.shtml\"\n", "table_name = \"jiangjin_weather_15d\"\n", "# ======================================================================\n", "\n", "# 1. 请求网页\n", "headers = {\n", " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36\"\n", "}\n", "response = requests.get(url, headers=headers, timeout=10)\n", "response.encoding = \"utf-8\"\n", "soup = BeautifulSoup(response.text, \"html.parser\")\n", "\n", "# 2. 按你F12的结构定位数据\n", "weather_data = []\n", "\n", "# 找到所有
  • ，对应每一天的数据\n", "items = soup.select(\"ul.list-ul > li.h15li\")\n", "\n", "for item in items:\n", " try:\n", " # ① 日期/星期（在 h15listdaybox 里）\n", " day_box = item.select_one(\".h15listdaybox\")\n", " date_text = day_box.get_text(strip=True) if day_box else \"\"\n", " \n", " # ② 天气状况（在 h15k 里，第二个h15k）\n", " weather_box = item.select(\".h15k\")[1] if len(item.select(\".h15k\")) >= 2 else None\n", " weather = weather_box.get_text(strip=True) if weather_box else \"\"\n", " \n", " # ③ 温度（h15listtem 里的 23/16℃）\n", " temp_box = item.select_one(\".h15listtem\")\n", " temp_text = temp_box.get_text(strip=True) if temp_box else \"\"\n", " high_temp, low_temp = temp_text.split(\"/\") if \"/\" in temp_text else (\"\", \"\")\n", " \n", " # ④ 风力/其他信息（xlt 里）\n", " wind_box = item.select_one(\".xlt\")\n", " wind = wind_box.get_text(strip=True) if wind_box else \"\"\n", "\n", " weather_data.append({\n", " \"日期/星期\": date_text,\n", " \"天气状况\": weather,\n", " \"最高温度\": high_temp.replace(\"℃\", \"\"),\n", " \"最低温度\": low_temp.replace(\"℃\", \"\"),\n", " \"风力\": wind\n", " })\n", " except Exception as e:\n", " print(f\"某条数据抓取失败：{e}\")\n", " continue\n", "\n", "# 3. 转成DataFrame\n", "df = pd.DataFrame(weather_data)\n", "print(\"✅ 抓取到的天气数据：\")\n", "print(df)\n", "\n", "# 4. 写入MySQL\n", "df.to_sql(\n", " name=table_name,\n", " con=engine,\n", " if_exists=\"replace\",\n", " index=False\n", ")\n", "\n", "# 5. 验证读取\n", "df_check = pd.read_sql(f\"SELECT * FROM {table_name}\", engine)\n", "print(\"\\n📊 从MySQL读回的数据：\")\n", "print(df_check)\n", "\n", "print(f\"\\n🎉 已成功写入MySQL表：{table_name}\")" ] }, { "cell_type": "code", "execution_count": 13, "id": "ca698ea4", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "爬取并清洗后的数据预览：\n", " 日期/星期 天气状况 最高温度 最低温度 风力\n", "0 今天04/27 今天 23 16 \n", "1 周二04/28 周二 17 15 \n", "2 周三04/29 周三 22 14 \n", "3 周四04/30 周四 26 16 \n", "4 周五05/01 周五 29 17 \n", "数据已成功写入 MySQL 表 test_db.tianqi！\n" ] } ], "source": [ "import requests\n", "from bs4 import BeautifulSoup\n", "import pandas as pd\n", "from sqlalchemy import create_engine\n", "# 【修复点1】导入SQLAlchemy标准数据类型（必须！）\n", "from sqlalchemy.types import VARCHAR, Integer\n", "\n", "# --------------------------\n", "# 1. 爬取网页数据\n", "# --------------------------\n", "headers = {\n", " \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36\"\n", "}\n", "\n", "url = \"http://sq.src.weather.com.cn/mweather15d/101040500.shtml\"\n", "response = requests.get(url, headers=headers)\n", "response.encoding = \"utf-8\"\n", "soup = BeautifulSoup(response.text, \"html.parser\")\n", "\n", "weather_items = soup.select(\"ul.list-ul li.h15li\")\n", "\n", "# --------------------------\n", "# 2. 解析数据\n", "# --------------------------\n", "data_list = []\n", "for item in weather_items:\n", " date_week = item.select_one(\"div.h15listdaybox\").get_text(strip=True) if item.select_one(\"div.h15listdaybox\") else \"\"\n", " weather_status = item.select_one(\"div.h15k p\").get_text(strip=True) if item.select_one(\"div.h15k p\") else \"\"\n", " temp_text = item.select_one(\"div.h15listtem\").get_text(strip=True) if item.select_one(\"div.h15listtem\") else \"\"\n", " high_temp, low_temp = None, None\n", " if temp_text:\n", " temp_parts = temp_text.replace(\"℃\", \"\").split(\"/\")\n", " if len(temp_parts) == 2:\n", " high_temp = temp_parts[0]\n", " low_temp = temp_parts[1]\n", " wind = item.select_one(\"div.xlt\").get_text(strip=True) if item.select_one(\"div.xlt\") else \"\"\n", "\n", " data_list.append({\n", " \"日期/星期\": date_week,\n", " \"天气状况\": weather_status,\n", " \"最高温度\": high_temp,\n", " \"最低温度\": low_temp,\n", " \"风力\": wind\n", " })\n", "\n", "# --------------------------\n", "# 3. 数据清洗\n", "# --------------------------\n", "df = pd.DataFrame(data_list)\n", "df[\"最高温度\"] = pd.to_numeric(df[\"最高温度\"], errors=\"coerce\")\n", "df[\"最低温度\"] = pd.to_numeric(df[\"最低温度\"], errors=\"coerce\")\n", "\n", "print(\"爬取并清洗后的数据预览：\")\n", "print(df.head())\n", "\n", "# --------------------------\n", "# 4. 写入MySQL（已修复）\n", "# --------------------------\n", "DB_USER = \"root\"\n", "DB_PASSWORD = \"123456\"\n", "DB_HOST = \"localhost\"\n", "DB_NAME = \"test_db\"\n", "TABLE_NAME = \"tianqi\"\n", "\n", "# 【修复点2】编码用utf8mb4，兼容性更强\n", "engine = create_engine(f\"mysql+pymysql://{DB_USER}:{DB_PASSWORD}@{DB_HOST}/{DB_NAME}?charset=utf8mb4\")\n", "\n", "# 【修复点3】dtype使用SQLAlchemy类型对象，不再用字符串！\n", "df.to_sql(\n", " name=TABLE_NAME,\n", " con=engine,\n", " if_exists=\"replace\",\n", " index=False,\n", " dtype={\n", " \"日期/星期\": VARCHAR(50), # 修复\n", " \"天气状况\": VARCHAR(20), # 修复\n", " \"最高温度\": Integer, # 修复\n", " \"最低温度\": Integer, # 修复\n", " \"风力\": VARCHAR(50) # 修复\n", " }\n", ")\n", "\n", "print(f\"数据已成功写入 MySQL 表 {DB_NAME}.{TABLE_NAME}！\")" ] }, { "cell_type": "code", "execution_count": 14, "id": "3e99fb0a", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
    \n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
    Num1Num2Num3Num4
    01.05913.0
    12.061014.0
    266.071166.0
    34.081266.0
    \n", "
    " ], "text/plain": [ " Num1 Num2 Num3 Num4\n", "0 1.0 5 9 13.0\n", "1 2.0 6 10 14.0\n", "2 66.0 7 11 66.0\n", "3 4.0 8 12 66.0" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import pandas as pd\n", "import numpy as np\n", "df_na = pd.DataFrame({'Num1':[1, 2, None, 4],\n", " 'Num2':[5, 6, 7, 8],\n", " 'Num3':[9, 10, 11, 12],\n", " 'Num4':[13, 14, np.NaN, np.NaN]})\n", "df_na.fillna(value=66.0) \n" ] }, { "cell_type": "code", "execution_count": 19, "id": "d17ca47f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "=== 原始数据预览 ===\n", " 区 小区名称 标题 房屋信息 关注 地铁 单价 (元 / 平米) Unnamed: 7 \\\n", "0 锦江 翡翠城四期 翡翠城四期跃 高楼层 (共 29 层) 2009 年建 2 室 1 厅 85.21 平米 东南 \n", "1 锦江 时代豪庭一期 时代豪庭套三 中楼层 (共 38 层) 2009 年建 3 室 1 厅 155.79 平米 东南 \n", "2 锦江 卓锦城六期 卓锦城六期紫 中楼层 (共 31 层) 2014 年建 3 室 1 厅 89.33 平米 西南 \n", "3 锦江 星城银座 春熙路太古里 高楼层 (共 11 层) 2003 年建 1 室 0 厅 51.07 平米 南 \n", "4 锦江 新莲新苑 新莲新苑优质 高楼层 (共 7 层) 2001 年建 3 室 1 厅 77.7 平米 东南 \n", "\n", " Unnamed: 8 Unnamed: 9 Unnamed: 10 \n", "0 331 人关注 / 5 近地铁 176036.0 \n", "1 137 人关注 / 5 NaN 26959.4 \n", "2 36 人关注 / 2 NaN 22612.8 \n", "3 29 人关注 / 5 近地铁 18014.5 \n", "4 14 人关注 / 5 NaN 13513.5 \n", "\n", "=== 数据基本信息 ===\n", "数据总行数：5，总列数：11\n", "\n", "各列缺失值数量：\n", "区 0\n", "小区名称 0\n", "标题 0\n", "房屋信息 0\n", "关注 0\n", "地铁 0\n", "单价 (元 / 平米) 0\n", "Unnamed: 7 0\n", "Unnamed: 8 0\n", "Unnamed: 9 3\n", "Unnamed: 10 0\n", "dtype: int64\n", "\n", "=== 含缺失值的行 ===\n", " 区 小区名称 标题 房屋信息 关注 地铁 单价 (元 / 平米) Unnamed: 7 \\\n", "1 锦江 时代豪庭一期 时代豪庭套三 中楼层 (共 38 层) 2009 年建 3 室 1 厅 155.79 平米 东南 \n", "2 锦江 卓锦城六期 卓锦城六期紫 中楼层 (共 31 层) 2014 年建 3 室 1 厅 89.33 平米 西南 \n", "4 锦江 新莲新苑 新莲新苑优质 高楼层 (共 7 层) 2001 年建 3 室 1 厅 77.7 平米 东南 \n", "\n", " Unnamed: 8 Unnamed: 9 Unnamed: 10 \n", "1 137 人关注 / 5 NaN 26959.4 \n", "2 36 人关注 / 2 NaN 22612.8 \n", "4 14 人关注 / 5 NaN 13513.5 \n" ] } ], "source": [ "import pandas as pd\n", "\n", "# 读取 Excel 文件（注意文件名是 \"secondhandhouse_one.xlsx.xlsx\"，需匹配实际文件名）\n", "file_path = r\"C:\\Users\\Administrator\\Desktop\\secondhandhouse_one.xlsx\" # 路径根据你的文件位置调整\n", "df = pd.read_excel(file_path)\n", "\n", "# 1. 查看数据原始形态（前5行）\n", "print(\"=== 原始数据预览 ===\")\n", "print(df.head())\n", "\n", "# 2. 查看数据基本信息（行数、列数、数据类型、缺失值数量）\n", "print(\"\\n=== 数据基本信息 ===\")\n", "print(f\"数据总行数：{len(df)}，总列数：{len(df.columns)}\")\n", "print(\"\\n各列缺失值数量：\")\n", "print(df.isnull().sum()) # isnull() 标记缺失值，sum() 统计每列缺失值个数\n", "\n", "# 3. 查看含缺失值的行（定位具体哪些行有缺失）\n", "print(\"\\n=== 含缺失值的行 ===\")\n", "missing_rows = df[df.isnull().any(axis=1)] # any(axis=1) 表示行内有任一缺失值\n", "print(missing_rows)" ] }, { "cell_type": "code", "execution_count": null, "id": "c0f8b184", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.9.12" } }, "nbformat": 4, "nbformat_minor": 5 }