{ "cells": [ { "cell_type": "code", "execution_count": 6, "id": "ed7a1260", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: pandas in c:\\programdata\\anaconda3\\lib\\site-packages (1.4.2)\n", "Requirement already satisfied: matplotlib in c:\\programdata\\anaconda3\\lib\\site-packages (3.5.1)\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: 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: pillow>=6.2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (9.0.1)\n", "Requirement already satisfied: fonttools>=4.22.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (4.25.0)\n", "Requirement already satisfied: kiwisolver>=1.0.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (1.3.2)\n", "Requirement already satisfied: pyparsing>=2.2.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (3.0.4)\n", "Requirement already satisfied: cycler>=0.10 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (0.11.0)\n", "Requirement already satisfied: packaging>=20.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (21.3)\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": [ "#任务2.1 jupyter安装软件\n", "!pip install pandas matplotlib" ] }, { "cell_type": "code", "execution_count": 4, "id": "7bb16fb9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple\n", "Collecting selenium\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/74/9e/642a355e43a4ebf68bc4f00dd4ab264f635079c5dc7ed6d9991a0c2be3d7/selenium-4.36.0-py3-none-any.whl (9.6 MB)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "conda-repo-cli 1.0.4 requires pathlib, which is not installed.\n", "anaconda-project 0.10.2 requires ruamel-yaml, which is not installed.\n", "requests 2.27.1 requires urllib3<1.27,>=1.21.1, but you have urllib3 2.6.3 which is incompatible.\n", "jupyter-server 1.13.5 requires pywinpty<2; os_name == \"nt\", but you have pywinpty 2.0.2 which is incompatible.\n", "botocore 1.24.32 requires urllib3<1.27,>=1.25.4, but you have urllib3 2.6.3 which is incompatible.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Collecting certifi>=2025.6.15\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/22/30/7cd8fdcdfbc5b869528b079bfb76dcdf6056b1a2097a662e5e8c04f42965/certifi-2026.4.22-py3-none-any.whl (135 kB)\n", "Collecting typing_extensions<5.0,>=4.14.0\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl (44 kB)\n", "Collecting trio-websocket<1.0,>=0.12.2\n", " Using cached https://pypi.tuna.tsinghua.edu.cn/packages/c7/19/eb640a397bba49ba49ef9dbe2e7e5c04202ba045b6ce2ec36e9cadc51e04/trio_websocket-0.12.2-py3-none-any.whl (21 kB)\n", "Collecting trio<1.0,>=0.30.0\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/31/5b/94237a3485620dbff9741df02ff6d8acaa5fdec67d81ab3f62e4d8511bf7/trio-0.31.0-py3-none-any.whl (512 kB)\n", "Collecting urllib3[socks]<3.0,>=2.5.0\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl (131 kB)\n", "Collecting websocket-client<2.0,>=1.8.0\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/34/db/b10e48aa8fff7407e67470363eac595018441cf32d5e1001567a7aeba5d2/websocket_client-1.9.0-py3-none-any.whl (82 kB)\n", "Collecting attrs>=23.2.0\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/64/b4/17d4b0b2a2dc85a6df63d1157e028ed19f90d4cd97c36717afef2bc2f395/attrs-26.1.0-py3-none-any.whl (67 kB)\n", "Requirement already satisfied: idna in c:\\programdata\\anaconda3\\lib\\site-packages (from trio<1.0,>=0.30.0->selenium) (3.3)\n", "Requirement already satisfied: sortedcontainers in c:\\programdata\\anaconda3\\lib\\site-packages (from trio<1.0,>=0.30.0->selenium) (2.4.0)\n", "Collecting sniffio>=1.3.0\n", " Using cached https://pypi.tuna.tsinghua.edu.cn/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl (10 kB)\n", "Requirement already satisfied: cffi>=1.14 in c:\\programdata\\anaconda3\\lib\\site-packages (from trio<1.0,>=0.30.0->selenium) (1.15.0)\n", "Collecting exceptiongroup\n", " Downloading https://pypi.tuna.tsinghua.edu.cn/packages/8a/0e/97c33bf5009bdbac74fd2beace167cab3f978feb69cc36f1ef79360d6c4e/exceptiongroup-1.3.1-py3-none-any.whl (16 kB)\n", "Collecting outcome\n", " Using cached https://pypi.tuna.tsinghua.edu.cn/packages/55/8b/5ab7257531a5d830fc8000c476e63c935488d74609b50f9384a643ec0a62/outcome-1.3.0.post0-py2.py3-none-any.whl (10 kB)\n", "Requirement already satisfied: pycparser in c:\\programdata\\anaconda3\\lib\\site-packages (from cffi>=1.14->trio<1.0,>=0.30.0->selenium) (2.21)\n", "Collecting wsproto>=0.14\n", " Using cached https://pypi.tuna.tsinghua.edu.cn/packages/78/58/e860788190eba3bcce367f74d29c4675466ce8dddfba85f7827588416f01/wsproto-1.2.0-py3-none-any.whl (24 kB)\n", "Requirement already satisfied: pysocks!=1.5.7,<2.0,>=1.5.6 in c:\\programdata\\anaconda3\\lib\\site-packages (from urllib3[socks]<3.0,>=2.5.0->selenium) (1.7.1)\n", "Collecting h11<1,>=0.9.0\n", " Using cached https://pypi.tuna.tsinghua.edu.cn/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl (37 kB)\n", "Installing collected packages: typing-extensions, attrs, sniffio, outcome, h11, exceptiongroup, wsproto, urllib3, trio, websocket-client, trio-websocket, certifi, selenium\n", " Attempting uninstall: typing-extensions\n", " Found existing installation: typing-extensions 4.1.1\n", " Uninstalling typing-extensions-4.1.1:\n", " Successfully uninstalled typing-extensions-4.1.1\n", " Attempting uninstall: attrs\n", " Found existing installation: attrs 21.4.0\n", " Uninstalling attrs-21.4.0:\n", " Successfully uninstalled attrs-21.4.0\n", " Attempting uninstall: sniffio\n", " Found existing installation: sniffio 1.2.0\n", " Uninstalling sniffio-1.2.0:\n", " Successfully uninstalled sniffio-1.2.0\n", " Attempting uninstall: urllib3\n", " Found existing installation: urllib3 1.26.9\n", " Uninstalling urllib3-1.26.9:\n", " Successfully uninstalled urllib3-1.26.9\n", " Attempting uninstall: websocket-client\n", " Found existing installation: websocket-client 0.58.0\n", " Uninstalling websocket-client-0.58.0:\n", " Successfully uninstalled websocket-client-0.58.0\n", " Attempting uninstall: certifi\n", " Found existing installation: certifi 2021.10.8\n", " Uninstalling certifi-2021.10.8:\n", " Successfully uninstalled certifi-2021.10.8\n", "Successfully installed attrs-26.1.0 certifi-2026.4.22 exceptiongroup-1.3.1 h11-0.16.0 outcome-1.3.0.post0 selenium-4.36.0 sniffio-1.3.1 trio-0.31.0 trio-websocket-0.12.2 typing-extensions-4.15.0 urllib3-2.6.3 websocket-client-1.9.0 wsproto-1.2.0\n" ] } ], "source": [ "#任务2.2 jupyter安装selenium软件\n", "!pip install selenium -i https://pypi.tuna.tsinghua.edu.cn/simple" ] }, { "cell_type": "code", "execution_count": null, "id": "b08b4af2", "metadata": {}, "outputs": [], "source": [ "1+11" ] }, { "cell_type": "code", "execution_count": 5, "id": "12e83309", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "缺失值位置标记：\n", " 语文 数学 英语\n", "0 False False False\n", "1 False False True\n", "2 True False True\n", "3 False False False\n" ] } ], "source": [ "#缺失值\n", "# 导入库\n", "import pandas as pd\n", "import numpy as np\n", "# 自动生成测试成绩表\n", "df = pd.DataFrame({\n", "'语文':[80, 90, None, 70],\n", "'数学':[60, 75, 88, 92],\n", "'英语':[55, np.nan, np.nan, 90]\n", "})\n", "# 检测缺失值：True=缺失，False=正常\n", "print(\"缺失值位置标记：\")\n", "print(pd.isnull(df))" ] }, { "cell_type": "code", "execution_count": 8, "id": "5c247ee7", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 语文 数学 英语\n", "0 False False False\n", "1 False False True\n", "2 True False True\n", "3 False False False\n", "语文 25.0\n", "数学 0.0\n", "英语 50.0\n", "dtype: float64\n" ] } ], "source": [ "#任务3.0 打地基代码\n", "import pandas as pd\n", "import numpy as np\n", "df = pd.DataFrame(\n", "{'语文':[80,90,None,70],\n", " '数学':[60,75,88,92],\n", " '英语':[55,np.NaN,np.NaN,90]\n", "})\n", "##3.1 缺失值显示\n", "print(pd.isnull(df))\n", "##3.2 计算缺失值占比\n", "##先手算缺失值占比为多少？\n", "### 3/12*100%=25%.\n", "print(df.isnull().sum()/len(df)*100)" ] }, { "cell_type": "code", "execution_count": 9, "id": "e0b0c638", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 语文 数学 英语\n", "0 80.0 60 55.0\n", "3 70.0 92 90.0\n" ] } ], "source": [ "## 删除缺失值行\n", "print(df.dropna())" ] }, { "cell_type": "code", "execution_count": 14, "id": "14c25bd5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 语文 数学 英语\n", "0 80.0 60 55.0\n", "1 90.0 75 NaN\n", "2 NaN 88 NaN\n", "3 70.0 92 90.0\n", " 语文 数学 英语\n", "0 80.0 60 55.0\n", "1 90.0 75 66.0\n", "2 66.0 88 66.0\n", "3 70.0 92 90.0\n", " 语文 数学 英语\n", "0 80.0 60 55.0\n", "1 90.0 75 72.5\n", "2 80.0 88 72.5\n", "3 70.0 92 90.0\n", " 语文 数学 英语\n", "0 80.0 60 55.0\n", "1 90.0 75 90.0\n", "2 90.0 88 90.0\n", "3 70.0 92 90.0\n" ] } ], "source": [ "#填充缺失值\n", "print(df)\n", "## 固定为66数字填充\n", "print(df.fillna(66))\n", "## 列平均值填充\n", "print(df.fillna(df.mean()).round(1))\n", "## 思考：用列最大值怎么填充？\n", "print(df.fillna(df.max()))" ] }, { "cell_type": "code", "execution_count": 15, "id": "e0672da1", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0 False\n", "1 False\n", "2 False\n", "3 False\n", "4 True\n", "dtype: bool\n" ] } ], "source": [ "\n", "import pandas as pd\n", "# 学生信息表\n", "df = pd.DataFrame({\n", "'姓名':['张三', '李四', '王五', '赵六', '赵六'],\n", "'年龄':[20,21,22,23,23],\n", "'班级':['1班','1班','2班','2班','2班']\n", "})\n", "## 重复值\n", "print(df.duplicated())" ] }, { "cell_type": "code", "execution_count": 18, "id": "34f4beb5", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 姓名 年龄 班级\n", "0 张三 20 1班\n", "1 李四 21 1班\n", "2 王五 22 2班\n", "3 赵六 23 2班\n" ] } ], "source": [ "##删除重复行\n", "print(df.drop_duplicates(ignore_index=True))" ] }, { "cell_type": "code", "execution_count": null, "id": "9174ebd4", "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 }