{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "72db5768", "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: numpy>=1.18.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (1.21.5)\n", "Requirement already satisfied: pytz>=2020.1 in c:\\programdata\\anaconda3\\lib\\site-packages (from pandas) (2021.3)\n", "Requirement already satisfied: fonttools>=4.22.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (4.25.0)\n", "Requirement already satisfied: packaging>=20.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (21.3)\n", "Requirement already satisfied: cycler>=0.10 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (0.11.0)\n", "Requirement already satisfied: pillow>=6.2.0 in c:\\programdata\\anaconda3\\lib\\site-packages (from matplotlib) (9.0.1)\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: six>=1.5 in c:\\programdata\\anaconda3\\lib\\site-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n" ] } ], "source": [ "## 第一步安装缺失的组件\n", "!pip install pandas matplotlib" ] }, { "cell_type": "code", "execution_count": 11, "id": "35486f6c", "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 False False False\n", "1 False False True\n", "2 True False True\n", "3 False False False\n" ] }, { "data": { "text/plain": [ "语文 25.0\n", "数学 0.0\n", "英语 50.0\n", "dtype: float64" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "## 缺失值处理\n", "#第一步：打地基\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", "print(df)\n", "\n", "#第二步：查看缺失值\n", "print(df.isnull())\n", "\n", "#第三步：计算缺失值占比\n", "## 方法1：手算：3/12*100 %= 25%\n", "## 方法2：代码：\n", "df.isnull().sum() / len(df) * 100\n", "\n" ] }, { "cell_type": "code", "execution_count": 10, "id": "0543f9fd", "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": [ "#缺失值处理1\n", "print(df.dropna())" ] }, { "cell_type": "code", "execution_count": 12, "id": "ec9b6355", "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 75 656.0\n", "2 656.0 88 656.0\n", "3 70.0 92 90.0\n" ] } ], "source": [ "#缺失值处理2：补上\n", "## 补上方法1：固定值\n", "print(df)\n", "print(df.fillna(656))" ] }, { "cell_type": "code", "execution_count": 14, "id": "d0b73852", "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 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 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 90.0\n", "2 90.0 88 90.0\n", "3 70.0 92 90.0\n" ] } ], "source": [ "#缺失值处理2：补上\n", "## 补上方法2：平均值\n", "print(df)\n", "print(df.fillna(df.mean()))\n", "\n", "## 补上方法3：最大值填充\n", "print(df)\n", "print(df.fillna(df.max()))" ] }, { "cell_type": "code", "execution_count": 17, "id": "d5fcbb6b", "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", "4 赵六 23 2班\n", "0 False\n", "1 False\n", "2 False\n", "3 False\n", "4 True\n", "dtype: bool\n" ] } ], "source": [ "## 重复值\n", "##第一步：打地基\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", "print(df)\n", "## 标记重复行\n", "print(df.duplicated())" ] }, { "cell_type": "code", "execution_count": 18, "id": "060db984", "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())" ] }, { "cell_type": "code", "execution_count": 28, "id": "a3a1edd7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Series([], Name: 数学成绩, dtype: int64)\n" ] } ], "source": [ "## 异常值\n", "df = pd.DataFrame({'数学成绩':[60,75,88,92,10,200,85]})\n", "def 检测异常值(ser):\n", " mean = ser.mean()\n", " std = ser.std()\n", " 条件= (ser mean + 3*std)\n", " return ser[条件]\n", "\n", "print(检测异常值(df['数学成绩']))\n" ] }, { "cell_type": "code", "execution_count": 29, "id": "a7d21f46", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 25968 (\\N{CJK UNIFIED IDEOGRAPH-6570}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 23398 (\\N{CJK UNIFIED IDEOGRAPH-5B66}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 25104 (\\N{CJK UNIFIED IDEOGRAPH-6210}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 32489 (\\N{CJK UNIFIED IDEOGRAPH-7EE9}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 31665 (\\N{CJK UNIFIED IDEOGRAPH-7BB1}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 32447 (\\N{CJK UNIFIED IDEOGRAPH-7EBF}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n", "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\IPython\\core\\pylabtools.py:151: UserWarning: Glyph 22270 (\\N{CJK UNIFIED IDEOGRAPH-56FE}) missing from current font.\n", " fig.canvas.print_figure(bytes_io, **kw)\n" ] }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "## 箱型图\n", "import matplotlib.pyplot as plt\n", "\n", "df.boxplot(column='数学成绩')\n", "plt.title('数学成绩箱线图')\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 32, "id": "ef917abe", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 数学成绩\n", "0 60\n", "1 75\n", "2 88\n", "3 92\n", "4 60\n", "5 92\n", "6 85\n", " 数学成绩\n", "0 60\n", "1 75\n", "2 88\n", "3 92\n", "4 10\n", "5 200\n", "6 85\n", "0 60\n", "1 75\n", "2 88\n", "3 92\n", "4 10\n", "5 200\n", "6 85\n", "Name: 数学成绩, dtype: int64\n" ] } ], "source": [ "#替换异常值\n", "print(df.replace([10,200],[60,92]))\n" ] }, { "cell_type": "code", "execution_count": 35, "id": "bfc33f73", "metadata": { "scrolled": true }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 数学成绩\n", "0 60\n", "1 75\n", "2 88\n", "3 92\n", "4 10\n", "5 200\n", "6 85 \n", "-------\n", "0 60\n", "1 75\n", "2 88\n", "3 92\n", "4 10\n", "5 200\n", "6 85\n", "Name: 数学成绩, dtype: int64\n" ] } ], "source": [ "##如何用最大最小值替换？\n", "print(df,'\\n-------')\n", "print(df['数学成绩'])\n", "#print(df.replace([10,200],[最小值?,df.replace(df['数学成绩'].max(),0)).max()" ] }, { "cell_type": "code", "execution_count": 41, "id": "0d484398", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "object\n", "80907566\n", "int64\n", "311\n" ] } ], "source": [ "#数据类型转换\n", "##转换前--是Object\n", "df = pd.DataFrame({'分数':['80','90','75','66']})\n", "print(df['分数'].dtype)\n", "print(df['分数'].sum())\n", "##转换后--是整数int类型\n", "df['分数'] = df['分数'].astype('int64')\n", "print(df['分数'].dtype)\n", "print(df['分数'].sum())" ] }, { "cell_type": "code", "execution_count": 47, "id": "ba49f1f0", "metadata": { "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 姓名 语文\n", "0 张三 80\n", "1 李四 90\n", " 姓名 语文\n", "0 王五 70\n", "1 赵六 85\n", "纵向拼接结果：\n", " 姓名 语文\n", "0 张三 80\n", "1 李四 90\n", "2 王五 70\n", "3 赵六 85\n" ] } ], "source": [ "##表格合并\n", "import pandas as pd\n", "表1 = pd.DataFrame({'姓名':['张三','李四'], '语文':[80,90]})\n", "表2 = pd.DataFrame({'姓名':['王五','赵六'], '语文':[70,85]})\n", "print(表1)\n", "print(表2)\n", "# 上下合并，重置索引\n", "合并表 = pd.concat([表1, 表2], ignore_index=True)\n", "print(\"纵向拼接结果：\")\n", "print(合并表)" ] }, { "cell_type": "code", "execution_count": 48, "id": "fbd37ecf", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 姓名 语文\n", "0 张三 80\n", "1 李四 90\n", "2 王五 70\n", " 姓名 数学\n", "0 张三 60\n", "1 李四 75\n", "2 赵六 88\n", "主键关联合并：\n", " 姓名 语文 数学\n", "0 张三 80 60.0\n", "1 李四 90 75.0\n", "2 王五 70 NaN\n" ] } ], "source": [ "#左右关联\n", "import pandas as pd\n", "语文表 = pd.DataFrame({'姓名':['张三','李四','王五'], '语文':[80,90,70]})\n", "数学表 = pd.DataFrame({'姓名':['张三','李四','赵六'], '数学':[60,75,88]})\n", "print(语文表)\n", "print(数学表)\n", "# 按姓名字段左连接\n", "合并表 = pd.merge(语文表, 数学表, on='姓名', how='left')\n", "print(\"主键关联合并：\")\n", "print(合并表)" ] }, { "cell_type": "code", "execution_count": 51, "id": "3c5e45fb", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " 日期 商品 销量\n", "0 周一 苹果 10\n", "1 周一 香蕉 20\n", "2 周二 苹果 15\n", "3 周二 香蕉 25\n", "商品销量透视表：\n", "商品 苹果 香蕉\n", "日期 \n", "周一 10 20\n", "周二 15 25\n" ] } ], "source": [ "import pandas as pd\n", "df = pd.DataFrame({\n", "'日期':['周一','周一','周二','周二'],\n", "'商品':['苹果','香蕉','苹果','香蕉'],\n", "'销量':[10,20,15,25]\n", "})\n", "print(df)\n", "# 生成透视表\n", "透视表 = df.pivot(index='日期', columns='商品', values='销量')\n", "print(\"商品销量透视表：\")\n", "print(透视表)" ] }, { "cell_type": "code", "execution_count": null, "id": "69c6b6ee", "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 }