diff --git "a/Day31-35/31-35.\347\216\251\350\275\254Linux\346\223\215\344\275\234\347\263\273\347\273\237.md" "b/Day31-35/31-35.\347\216\251\350\275\254Linux\346\223\215\344\275\234\347\263\273\347\273\237.md" index 2bcc59878018d4d5ab64045b7a888a40c487e164..93103633dca334437e7362db7eaf5bf4ad3967a2 100644 --- "a/Day31-35/31-35.\347\216\251\350\275\254Linux\346\223\215\344\275\234\347\263\273\347\273\237.md" +++ "b/Day31-35/31-35.\347\216\251\350\275\254Linux\346\223\215\344\275\234\347\263\273\347\273\237.md" @@ -230,7 +230,7 @@ Linux系统的命令通常都是如下所示的格式： [root@iZwz97tbgo9lkabnat2lo8Z ~]# !454 ``` - > 说明：查看到历史命令之后，可以用`!历史命令编号`来重新执行该命令；通过`history -c`可以清除历史命令。 + > **说明**：查看到历史命令之后，可以用`!历史命令编号`来重新执行该命令；通过`history -c`可以清除历史命令。 ### 实用程序 @@ -308,7 +308,7 @@ Linux系统的命令通常都是如下所示的格式： ... ``` - > 说明：上面用到了一个名为`wget`的命令，它是一个网络下载器程序，可以从指定的URL下载资源。 + > **说明**：上面用到了一个名为`wget`的命令，它是一个网络下载器程序，可以从指定的URL下载资源。 6. 拷贝/移动文件 - **cp** / **mv**。 @@ -350,7 +350,7 @@ Linux系统的命令通常都是如下所示的格式： 52: ... ``` - > 说明：`grep`在搜索字符串时可以使用正则表达式，如果需要使用正则表达式可以用`grep -E`或者直接使用`egrep`。 + > **说明**：`grep`在搜索字符串时可以使用正则表达式，如果需要使用正则表达式可以用`grep -E`或者直接使用`egrep`。 9. 创建链接和查看链接 - **ln** / **readlink**。 @@ -372,7 +372,7 @@ Linux系统的命令通常都是如下所示的格式： CentOS Linux release 7.4.1708 (Core) ``` - > 说明：链接可以分为硬链接和软链接（符号链接）。硬链接可以认为是一个指向文件数据的指针，就像Python中对象的引用计数，每添加一个硬链接，文件的对应链接数就增加1，只有当文件的链接数为0时，文件所对应的存储空间才有可能被其他文件覆盖。我们平常删除文件时其实并没有删除硬盘上的数据，我们删除的只是一个指针，或者说是数据的一条使用记录，所以类似于“文件粉碎机”之类的软件在“粉碎”文件时除了删除文件指针，还会在文件对应的存储区域填入数据来保证文件无法再恢复。软链接类似于Windows系统下的快捷方式，当软链接链接的文件被删除时，软链接也就失效了。 + > **说明**：链接可以分为硬链接和软链接（符号链接）。硬链接可以认为是一个指向文件数据的指针，就像Python中对象的引用计数，每添加一个硬链接，文件的对应链接数就增加1，只有当文件的链接数为0时，文件所对应的存储空间才有可能被其他文件覆盖。我们平常删除文件时其实并没有删除硬盘上的数据，我们删除的只是一个指针，或者说是数据的一条使用记录，所以类似于“文件粉碎机”之类的软件在“粉碎”文件时除了删除文件指针，还会在文件对应的存储区域填入数据来保证文件无法再恢复。软链接类似于Windows系统下的快捷方式，当软链接链接的文件被删除时，软链接也就失效了。 10. 压缩/解压缩和归档/解归档 - **gzip** / **gunzip** / **xz**。 @@ -429,7 +429,7 @@ Linux系统的命令通常都是如下所示的格式： [root@iZwz97tbgo9lkabnat2lo8Z ~]# xargs < a.txt > b.txt ``` - > 说明：这个命令就像上面演示的那样常在管道（实现进程间通信的一种方式）和重定向（重新指定输入输出的位置）操作中用到，后面的内容中会讲到管道操作和输入输出重定向操作。 + > **说明**：这个命令就像上面演示的那样常在管道（实现进程间通信的一种方式）和重定向（重新指定输入输出的位置）操作中用到，后面的内容中会讲到管道操作和输入输出重定向操作。 13. 显示文件或目录 - **basename** / **dirname**。 diff --git "a/Day41-55/48.\345\211\215\345\220\216\347\253\257\345\210\206\347\246\273\345\274\200\345\217\221\345\205\245\351\227\250.md" "b/Day41-55/48.\345\211\215\345\220\216\347\253\257\345\210\206\347\246\273\345\274\200\345\217\221\345\205\245\351\227\250.md" index 974a9cc4743eed84f041a79cfa8dd5d5fb0610a4..0675a7558ae80ff6cba919bf8e7ef8bf1f512532 100644 --- "a/Day41-55/48.\345\211\215\345\220\216\347\253\257\345\210\206\347\246\273\345\274\200\345\217\221\345\205\245\351\227\250.md" +++ "b/Day41-55/48.\345\211\215\345\220\216\347\253\257\345\210\206\347\246\273\345\274\200\345\217\221\345\205\245\351\227\250.md" @@ -133,21 +133,7 @@ class SubjectMapper(ModelMapper): 学科信息 @@ -157,7 +143,9 @@ class SubjectMapper(ModelMapper):
- {{ subject.name }} + + {{ subject.name }} +
{{ subject.intro }}
diff --git "a/Day41-55/49.RESTful\346\236\266\346\236\204\345\222\214DRF\345\205\245\351\227\250.md" "b/Day41-55/49.RESTful\346\236\266\346\236\204\345\222\214DRF\345\205\245\351\227\250.md" index 0004429fc02e5b41fc518dcec83fd13bb58bdf70..04eb692adbbb7c7d69f913efc3eaf683856ed09e 100644 --- "a/Day41-55/49.RESTful\346\236\266\346\236\204\345\222\214DRF\345\205\245\351\227\250.md" +++ "b/Day41-55/49.RESTful\346\236\266\346\236\204\345\222\214DRF\345\205\245\351\227\250.md" @@ -156,48 +156,14 @@ urlpatterns = [ 通过Vue.js渲染页面。 -```Python +```HTML 老师信息 @@ -217,9 +183,11 @@ urlpatterns = [
{{ teacher.intro }}
- 好评  ({{ teacher.good_count }}) + 好评   + ({{ teacher.good_count }})      - 差评  ({{ teacher.bad_count }}) + 差评   + ({{ teacher.bad_count }})
@@ -355,7 +323,7 @@ JSON Web Token通常简称为JWT，它是一种开放标准（RFC 7519）。随 2. 在令牌过期之前，无法作废已经颁发的令牌，要解决这个问题，还需要额外的中间层和代码来辅助。 3. JWT是用户的身份令牌，一旦泄露，任何人都可以获得该用户的所有权限。为了降低令牌被盗用后产生的风险，JWT的有效期应该设置得比较短。对于一些比较重要的权限，使用时应通过其他方式再次对用户进行认证，例如短信验证码等。 -#### 使用PyJWT生成和验证令牌 +#### 使用PyJWT 在Python代码中，可以使用三方库`PyJWT`生成和验证JWT，下面是安装`PyJWT`的命令。 diff --git "a/Day76-90/code/.ipynb_checkpoints/1-pandas\345\205\245\351\227\250-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/1-pandas\345\205\245\351\227\250-checkpoint.ipynb" index b5b3acc8b66de0cdcc01778d81d566fdc93bed4e..d10293f1ebd3368cbce772d721e9bfd85f58d6d0 100644 --- "a/Day76-90/code/.ipynb_checkpoints/1-pandas\345\205\245\351\227\250-checkpoint.ipynb" +++ "b/Day76-90/code/.ipynb_checkpoints/1-pandas\345\205\245\351\227\250-checkpoint.ipynb" @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -13,7 +13,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -22,14 +22,7 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "metadata": { "scrolled": false }, @@ -44,7 +37,7 @@ "dtype: int64" ] }, - "execution_count": 4, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -52,13 +45,13 @@ "source": [ "# 创建\n", "# Series是一维的数据\n", - "s = Series(data = [120,136,128,99],index = ['Math','Python','En','Chinese'])\n", + "s = Series(data=[120,136,128,99], index=['Math','Python','En','Chinese'])\n", "s" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -67,7 +60,7 @@ "(4,)" ] }, - "execution_count": 5, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -78,16 +71,16 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "array([120, 136, 128, 99], dtype=int64)" + "array([120, 136, 128, 99])" ] }, - "execution_count": 6, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -99,7 +92,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -108,7 +101,7 @@ "numpy.ndarray" ] }, - "execution_count": 7, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -119,7 +112,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -128,7 +121,7 @@ "120.75" ] }, - "execution_count": 8, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -139,7 +132,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -148,7 +141,7 @@ "136" ] }, - "execution_count": 9, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -159,7 +152,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -168,7 +161,7 @@ "15.903353943953666" ] }, - "execution_count": 10, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -179,36 +172,33 @@ }, { "cell_type": "code", - "execution_count": 11, - "metadata": { - "collapsed": true - }, + "execution_count": 20, + "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "Math 14400\n", - "Python 18496\n", - "En 16384\n", - "Chinese 9801\n", + "Math 122\n", + "Python 138\n", + "En 130\n", + "Chinese 101\n", "dtype: int64" ] }, - "execution_count": 11, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "s.pow(2)" + "s.add(1)\n", + "s" ] }, { "cell_type": "code", - "execution_count": 12, - "metadata": { - "collapsed": true - }, + "execution_count": 21, + "metadata": {}, "outputs": [ { "data": { @@ -238,64 +228,64 @@ " \n", " \n", " \n", - " a\n", - " 113\n", - " 116\n", - " 75\n", + " a\n", + " 109\n", + " 120\n", + " 23\n", " \n", " \n", - " b\n", - " 19\n", - " 145\n", - " 23\n", + " b\n", + " 54\n", + " 39\n", + " 54\n", " \n", " \n", - " c\n", - " 57\n", - " 107\n", - " 113\n", + " c\n", + " 97\n", + " 22\n", + " 106\n", " \n", " \n", - " d\n", - " 95\n", + " d\n", + " 21\n", + " 96\n", " 3\n", - " 66\n", " \n", " \n", - " e\n", - " 28\n", - " 121\n", - " 120\n", + " e\n", + " 23\n", + " 145\n", + " 147\n", " \n", " \n", - " f\n", - " 141\n", - " 85\n", - " 132\n", + " f\n", + " 80\n", + " 62\n", + " 83\n", " \n", " \n", - " h\n", - " 124\n", - " 39\n", - " 10\n", + " h\n", + " 70\n", + " 31\n", + " 134\n", " \n", " \n", - " i\n", - " 80\n", - " 35\n", - " 17\n", + " i\n", + " 132\n", + " 51\n", + " 115\n", " \n", " \n", - " j\n", - " 68\n", - " 99\n", - " 31\n", + " j\n", + " 95\n", + " 143\n", + " 111\n", " \n", " \n", - " k\n", - " 74\n", - " 12\n", - " 11\n", + " k\n", + " 66\n", + " 94\n", + " 7\n", " \n", " \n", "\n", @@ -303,19 +293,19 @@ ], "text/plain": [ " Python En Math\n", - "a 113 116 75\n", - "b 19 145 23\n", - "c 57 107 113\n", - "d 95 3 66\n", - "e 28 121 120\n", - "f 141 85 132\n", - "h 124 39 10\n", - "i 80 35 17\n", - "j 68 99 31\n", - "k 74 12 11" + "a 109 120 23\n", + "b 54 39 54\n", + "c 97 22 106\n", + "d 21 96 3\n", + "e 23 145 147\n", + "f 80 62 83\n", + "h 70 31 134\n", + "i 132 51 115\n", + "j 95 143 111\n", + "k 66 94 7" ] }, - "execution_count": 12, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } @@ -324,7 +314,7 @@ "# DataFrame是二维的数据\n", "# excel就非常相似\n", "# 所有进行数据分析，数据挖掘的工具最基础的结果：行和列，行表示样本，列表示的是属性\n", - "df = DataFrame(data = np.random.randint(0,150,size = (10,3)),index = list('abcdefhijk'),columns=['Python','En','Math'])\n", + "df = DataFrame(data=np.random.randint(0, 150, size=(10, 3)), index=list('abcdefhijk'), columns=['Python', 'En', 'Math'])\n", "df" ] }, @@ -553,7 +543,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 22, "metadata": { "scrolled": true }, @@ -561,50 +551,57 @@ { "data": { "text/plain": [ - "Python 79.9\n", - "En 76.2\n", - "Math 59.8\n", + "Python 74.7\n", + "En 80.3\n", + "Math 78.3\n", "dtype: float64" ] }, - "execution_count": 19, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.mean(axis = 0)" + "df.mean(axis=0)" ] }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "a 101.333333\n", - "b 62.333333\n", - "c 92.333333\n", - "d 54.666667\n", - "e 89.666667\n", - "f 119.333333\n", - "h 57.666667\n", - "i 44.000000\n", - "j 66.000000\n", - "k 32.333333\n", + "a 84.000000\n", + "b 49.000000\n", + "c 75.000000\n", + "d 40.000000\n", + "e 105.000000\n", + "f 75.000000\n", + "h 78.333333\n", + "i 99.333333\n", + "j 116.333333\n", + "k 55.666667\n", "dtype: float64" ] }, - "execution_count": 20, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.mean(axis = 1)" + "df.mean(axis=1)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -623,7 +620,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/.ipynb_checkpoints/2-pandas-\347\264\242\345\274\225-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/2-pandas-\347\264\242\345\274\225-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..98c1704a55e4b859e0acab107b952edcd499cae7 --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/2-pandas-\347\264\242\345\274\225-checkpoint.ipynb" @@ -0,0 +1,372 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "\n", + "from pandas import Series, DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s = Series(np.random.randint(0,150,size = 100),index = np.arange(10,110),dtype=np.int16,name = 'Python')\n", + "s" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s[10]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s[[10,20]]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 切片操作\n", + "s[10:20]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s[::2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s[::-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 可以使用pandas为开发者提供方法，去进行检索\n", + "s.loc[10]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "s.loc[[10,20]]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.loc[10:20]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.loc[::2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.loc[::-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.index" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# iloc 索引从0开始，数字化自然索引\n", + "s.iloc[0]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.iloc[[0,10]]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.iloc[0:20]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "s.iloc[::-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# DataFrame是二维，索引大同小异，\n", + "df = DataFrame(data = np.random.randint(0,150,size= (10,3)),index=list('ABCDEFHIJK'),columns=['Python','En','Math'])\n", + "\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df['A']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df['Python']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df[['Python','En']]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "df['Python':'Math']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df['A':'D']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.loc['Python']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "df.loc['A']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.loc[['A','H']]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.loc['A':'E']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.loc[::2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.loc[::-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.iloc['A']" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.iloc[0]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "df.iloc[[0,5]]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.iloc[0:5]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "df.iloc[::-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.iloc[::2,1:]" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..17346ba230f606d3a7742ffb5729959ac8160a38 --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256-checkpoint.ipynb" @@ -0,0 +1,5834 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMathPhysicChem
100455079129
101728257138111
10254115818151
10313805412940
10411391393498
..................
1951351041027640
1967572283931
197136261236281
1985048103606
199771391145147
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 4 55 0 79 129\n", + "101 72 82 57 138 111\n", + "102 54 115 81 81 51\n", + "103 13 80 54 129 40\n", + "104 113 91 39 34 98\n", + ".. ... ... ... ... ...\n", + "195 135 104 102 76 40\n", + "196 75 72 28 39 31\n", + "197 136 26 123 62 81\n", + "198 50 48 103 60 6\n", + "199 77 13 91 145 147\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = DataFrame(np.random.randint(0,150,size = (100,5)),index = np.arange(100,200),columns=['Python','En','Math','Physic','Chem'])\n", + "df\n", + "df[100]['Python']" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python False\n", + "En False\n", + "Math False\n", + "Physic False\n", + "Chem False\n", + "dtype: bool" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 判断DataFrame是否存在空数据\n", + "df.isnull().any()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python True\n", + "En True\n", + "Math True\n", + "Physic True\n", + "Chem True\n", + "dtype: bool" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.notnull().all()" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "500" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "100*5" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": {}, + "outputs": [], + "source": [ + "for i in range(50):\n", + " # 行索引\n", + " index = np.random.randint(100,200,size =1)[0]\n", + "\n", + " cols = df.columns\n", + "\n", + " # 列索引\n", + " col = np.random.choice(cols)\n", + "\n", + " df.loc[index,col] = None" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "for i in range(20):\n", + " # 行索引\n", + " index = np.random.randint(100,200,size =1)[0]\n", + "\n", + " cols = df.columns\n", + "\n", + " # 列索引\n", + " col = np.random.choice(cols)\n", + "\n", + "# not a number 不是一个数\n", + " df.loc[index,col] = np.NAN" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 122.0 10.0 5.0 28.0 57.0\n", + "101 NaN 129.0 16.0 114.0 26.0\n", + "102 97.0 121.0 122.0 29.0 65.0\n", + "103 141.0 73.0 120.0 147.0 1.0\n", + "104 126.0 NaN 86.0 116.0 17.0\n", + "105 85.0 NaN 42.0 121.0 66.0\n", + "106 142.0 65.0 1.0 124.0 83.0\n", + "107 136.0 141.0 NaN 86.0 113.0\n", + "108 15.0 37.0 124.0 110.0 102.0\n", + "109 63.0 30.0 NaN 69.0 58.0\n", + "110 NaN NaN 113.0 109.0 16.0\n", + "111 5.0 51.0 87.0 58.0 126.0\n", + "112 53.0 97.0 76.0 37.0 45.0\n", + "113 42.0 148.0 NaN 97.0 NaN\n", + "114 70.0 138.0 69.0 68.0 134.0\n", + "115 NaN 136.0 113.0 22.0 94.0\n", + "116 31.0 137.0 6.0 20.0 28.0\n", + "117 148.0 74.0 134.0 4.0 124.0\n", + "118 102.0 81.0 138.0 128.0 32.0\n", + "119 27.0 111.0 13.0 NaN 22.0\n", + "120 28.0 93.0 121.0 NaN 4.0\n", + "121 136.0 NaN 25.0 97.0 19.0\n", + "122 111.0 70.0 12.0 38.0 58.0\n", + "123 NaN 103.0 147.0 86.0 8.0\n", + "124 10.0 10.0 46.0 63.0 149.0\n", + "125 7.0 75.0 97.0 108.0 31.0\n", + "126 88.0 6.0 NaN NaN 55.0\n", + "127 33.0 74.0 106.0 50.0 46.0\n", + "128 74.0 28.0 26.0 100.0 76.0\n", + "129 76.0 18.0 101.0 NaN NaN\n", + ".. ... ... ... ... ...\n", + "170 144.0 124.0 77.0 92.0 82.0\n", + "171 36.0 98.0 NaN 43.0 80.0\n", + "172 51.0 NaN 68.0 34.0 74.0\n", + "173 149.0 NaN 18.0 141.0 NaN\n", + "174 8.0 139.0 146.0 112.0 NaN\n", + "175 115.0 NaN 64.0 62.0 9.0\n", + "176 NaN 7.0 140.0 45.0 148.0\n", + "177 NaN 43.0 68.0 109.0 18.0\n", + "178 31.0 100.0 NaN 49.0 123.0\n", + "179 29.0 46.0 69.0 57.0 90.0\n", + "180 146.0 86.0 18.0 22.0 46.0\n", + "181 71.0 50.0 40.0 NaN 140.0\n", + "182 4.0 100.0 147.0 116.0 110.0\n", + "183 55.0 87.0 93.0 NaN 34.0\n", + "184 NaN 109.0 124.0 87.0 82.0\n", + "185 10.0 118.0 139.0 50.0 51.0\n", + "186 32.0 12.0 71.0 36.0 NaN\n", + "187 94.0 NaN 138.0 13.0 149.0\n", + "188 65.0 101.0 123.0 128.0 86.0\n", + "189 43.0 94.0 NaN 29.0 132.0\n", + "190 68.0 135.0 94.0 28.0 125.0\n", + "191 30.0 60.0 98.0 NaN 15.0\n", + "192 89.0 16.0 10.0 135.0 4.0\n", + "193 104.0 139.0 97.0 29.0 17.0\n", + "194 5.0 29.0 41.0 99.0 NaN\n", + "195 19.0 102.0 135.0 41.0 40.0\n", + "196 58.0 NaN 70.0 82.0 64.0\n", + "197 NaN 97.0 129.0 76.0 13.0\n", + "198 131.0 15.0 NaN 44.0 114.0\n", + "199 79.0 NaN 95.0 128.0 NaN\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python True\n", + "En True\n", + "Math True\n", + "Physic True\n", + "Chem True\n", + "dtype: bool" + ] + }, + "execution_count": 18, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.isnull().any()" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 14\n", + "En 14\n", + "Math 15\n", + "Physic 11\n", + "Chem 13\n", + "dtype: int64" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [], + "source": [ + "df2 = df.copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 14\n", + "En 14\n", + "Math 15\n", + "Physic 11\n", + "Chem 13\n", + "dtype: int64" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101100.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0100.086.0116.017.0
10585.0100.042.0121.066.0
106142.065.01.0124.083.0
107136.0141.0100.086.0113.0
10815.037.0124.0110.0102.0
10963.030.0100.069.058.0
110100.0100.0113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0100.097.0100.0
11470.0138.069.068.0134.0
115100.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0100.022.0
12028.093.0121.0100.04.0
121136.0100.025.097.019.0
122111.070.012.038.058.0
123100.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0100.0100.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0100.0100.0
..................
170144.0124.077.092.082.0
17136.098.0100.043.080.0
17251.0100.068.034.074.0
173149.0100.018.0141.0100.0
1748.0139.0146.0112.0100.0
175115.0100.064.062.09.0
176100.07.0140.045.0148.0
177100.043.068.0109.018.0
17831.0100.0100.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0100.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.0100.034.0
184100.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0100.0
18794.0100.0138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0100.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.0100.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0100.0
19519.0102.0135.041.040.0
19658.0100.070.082.064.0
197100.097.0129.076.013.0
198131.015.0100.044.0114.0
19979.0100.095.0128.0100.0
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 122.0 10.0 5.0 28.0 57.0\n", + "101 100.0 129.0 16.0 114.0 26.0\n", + "102 97.0 121.0 122.0 29.0 65.0\n", + "103 141.0 73.0 120.0 147.0 1.0\n", + "104 126.0 100.0 86.0 116.0 17.0\n", + "105 85.0 100.0 42.0 121.0 66.0\n", + "106 142.0 65.0 1.0 124.0 83.0\n", + "107 136.0 141.0 100.0 86.0 113.0\n", + "108 15.0 37.0 124.0 110.0 102.0\n", + "109 63.0 30.0 100.0 69.0 58.0\n", + "110 100.0 100.0 113.0 109.0 16.0\n", + "111 5.0 51.0 87.0 58.0 126.0\n", + "112 53.0 97.0 76.0 37.0 45.0\n", + "113 42.0 148.0 100.0 97.0 100.0\n", + "114 70.0 138.0 69.0 68.0 134.0\n", + "115 100.0 136.0 113.0 22.0 94.0\n", + "116 31.0 137.0 6.0 20.0 28.0\n", + "117 148.0 74.0 134.0 4.0 124.0\n", + "118 102.0 81.0 138.0 128.0 32.0\n", + "119 27.0 111.0 13.0 100.0 22.0\n", + "120 28.0 93.0 121.0 100.0 4.0\n", + "121 136.0 100.0 25.0 97.0 19.0\n", + "122 111.0 70.0 12.0 38.0 58.0\n", + "123 100.0 103.0 147.0 86.0 8.0\n", + "124 10.0 10.0 46.0 63.0 149.0\n", + "125 7.0 75.0 97.0 108.0 31.0\n", + "126 88.0 6.0 100.0 100.0 55.0\n", + "127 33.0 74.0 106.0 50.0 46.0\n", + "128 74.0 28.0 26.0 100.0 76.0\n", + "129 76.0 18.0 101.0 100.0 100.0\n", + ".. ... ... ... ... ...\n", + "170 144.0 124.0 77.0 92.0 82.0\n", + "171 36.0 98.0 100.0 43.0 80.0\n", + "172 51.0 100.0 68.0 34.0 74.0\n", + "173 149.0 100.0 18.0 141.0 100.0\n", + "174 8.0 139.0 146.0 112.0 100.0\n", + "175 115.0 100.0 64.0 62.0 9.0\n", + "176 100.0 7.0 140.0 45.0 148.0\n", + "177 100.0 43.0 68.0 109.0 18.0\n", + "178 31.0 100.0 100.0 49.0 123.0\n", + "179 29.0 46.0 69.0 57.0 90.0\n", + "180 146.0 86.0 18.0 22.0 46.0\n", + "181 71.0 50.0 40.0 100.0 140.0\n", + "182 4.0 100.0 147.0 116.0 110.0\n", + "183 55.0 87.0 93.0 100.0 34.0\n", + "184 100.0 109.0 124.0 87.0 82.0\n", + "185 10.0 118.0 139.0 50.0 51.0\n", + "186 32.0 12.0 71.0 36.0 100.0\n", + "187 94.0 100.0 138.0 13.0 149.0\n", + "188 65.0 101.0 123.0 128.0 86.0\n", + "189 43.0 94.0 100.0 29.0 132.0\n", + "190 68.0 135.0 94.0 28.0 125.0\n", + "191 30.0 60.0 98.0 100.0 15.0\n", + "192 89.0 16.0 10.0 135.0 4.0\n", + "193 104.0 139.0 97.0 29.0 17.0\n", + "194 5.0 29.0 41.0 99.0 100.0\n", + "195 19.0 102.0 135.0 41.0 40.0\n", + "196 58.0 100.0 70.0 82.0 64.0\n", + "197 100.0 97.0 129.0 76.0 13.0\n", + "198 131.0 15.0 100.0 44.0 114.0\n", + "199 79.0 100.0 95.0 128.0 100.0\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 固定值填充\n", + "df2.fillna(value=100)" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 71.662791\n", + "En 75.627907\n", + "Math 77.929412\n", + "Physic 73.471910\n", + "Chem 69.080460\n", + "dtype: float64" + ] + }, + "execution_count": 27, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.mean()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
1001221052857
101711291611426
102971211222965
103141731201471
104126758611617
10585754212166
10614265112483
1071361417786113
1081537124110102
1096330776958
110717511310916
1115518758126
1125397763745
11342148779769
114701386968134
115711361132294
1163113762028
117148741344124
1181028113812832
11927111137322
1202893121734
12113675259719
12211170123858
12371103147868
12410104663149
1257759710831
126886777355
12733741065046
12874282610076
12976181017369
..................
170144124779282
1713698774380
1725175683474
173149751814169
174813914611269
1751157564629
17671714045148
17771436810918
178311007749123
1792946695790
18014686182246
18171504073140
1824100147116110
1835587937334
184711091248782
185101181395051
1863212713669
187947513813149
1886510112312886
18943947729132
190681359428125
1913060987315
1928916101354
193104139972917
194529419969
195191021354140
1965875708264
19771971297613
198131157744114
19979759512869
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 122 10 5 28 57\n", + "101 71 129 16 114 26\n", + "102 97 121 122 29 65\n", + "103 141 73 120 147 1\n", + "104 126 75 86 116 17\n", + "105 85 75 42 121 66\n", + "106 142 65 1 124 83\n", + "107 136 141 77 86 113\n", + "108 15 37 124 110 102\n", + "109 63 30 77 69 58\n", + "110 71 75 113 109 16\n", + "111 5 51 87 58 126\n", + "112 53 97 76 37 45\n", + "113 42 148 77 97 69\n", + "114 70 138 69 68 134\n", + "115 71 136 113 22 94\n", + "116 31 137 6 20 28\n", + "117 148 74 134 4 124\n", + "118 102 81 138 128 32\n", + "119 27 111 13 73 22\n", + "120 28 93 121 73 4\n", + "121 136 75 25 97 19\n", + "122 111 70 12 38 58\n", + "123 71 103 147 86 8\n", + "124 10 10 46 63 149\n", + "125 7 75 97 108 31\n", + "126 88 6 77 73 55\n", + "127 33 74 106 50 46\n", + "128 74 28 26 100 76\n", + "129 76 18 101 73 69\n", + ".. ... ... ... ... ...\n", + "170 144 124 77 92 82\n", + "171 36 98 77 43 80\n", + "172 51 75 68 34 74\n", + "173 149 75 18 141 69\n", + "174 8 139 146 112 69\n", + "175 115 75 64 62 9\n", + "176 71 7 140 45 148\n", + "177 71 43 68 109 18\n", + "178 31 100 77 49 123\n", + "179 29 46 69 57 90\n", + "180 146 86 18 22 46\n", + "181 71 50 40 73 140\n", + "182 4 100 147 116 110\n", + "183 55 87 93 73 34\n", + "184 71 109 124 87 82\n", + "185 10 118 139 50 51\n", + "186 32 12 71 36 69\n", + "187 94 75 138 13 149\n", + "188 65 101 123 128 86\n", + "189 43 94 77 29 132\n", + "190 68 135 94 28 125\n", + "191 30 60 98 73 15\n", + "192 89 16 10 135 4\n", + "193 104 139 97 29 17\n", + "194 5 29 41 99 69\n", + "195 19 102 135 41 40\n", + "196 58 75 70 82 64\n", + "197 71 97 129 76 13\n", + "198 131 15 77 44 114\n", + "199 79 75 95 128 69\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 均值\n", + "df3 = df2.fillna(value=df2.mean())\n", + "df3.astype(np.int16)" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 6, 18, 1, 17, 19, 5, 17, 16, 13, 3])" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "nd = np.random.randint(0,20,size = 10)\n", + "nd" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 1, 3, 5, 6, 13, 16, 17, 17, 18, 19])" + ] + }, + "execution_count": 33, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "nd.sort()\n", + "nd" + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "14.5" + ] + }, + "execution_count": 34, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "(13 + 16)/2" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "14.5" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "np.median(nd)" + ] + }, + { + "cell_type": "code", + "execution_count": 36, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
100122.010.05.028.057.0
10168.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.082.586.0116.017.0
10585.082.542.0121.066.0
106142.065.01.0124.083.0
107136.0141.086.086.0113.0
10815.037.0124.0110.0102.0
10963.030.086.069.058.0
11068.082.5113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.086.097.065.0
11470.0138.069.068.0134.0
11568.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.069.022.0
12028.093.0121.069.04.0
121136.082.525.097.019.0
122111.070.012.038.058.0
12368.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.086.069.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.069.065.0
..................
170144.0124.077.092.082.0
17136.098.086.043.080.0
17251.082.568.034.074.0
173149.082.518.0141.065.0
1748.0139.0146.0112.065.0
175115.082.564.062.09.0
17668.07.0140.045.0148.0
17768.043.068.0109.018.0
17831.0100.086.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.069.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.069.034.0
18468.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.065.0
18794.082.5138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.086.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.069.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.065.0
19519.0102.0135.041.040.0
19658.082.570.082.064.0
19768.097.0129.076.013.0
198131.015.086.044.0114.0
19979.082.595.0128.065.0
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 122.0 10.0 5.0 28.0 57.0\n", + "101 68.0 129.0 16.0 114.0 26.0\n", + "102 97.0 121.0 122.0 29.0 65.0\n", + "103 141.0 73.0 120.0 147.0 1.0\n", + "104 126.0 82.5 86.0 116.0 17.0\n", + "105 85.0 82.5 42.0 121.0 66.0\n", + "106 142.0 65.0 1.0 124.0 83.0\n", + "107 136.0 141.0 86.0 86.0 113.0\n", + "108 15.0 37.0 124.0 110.0 102.0\n", + "109 63.0 30.0 86.0 69.0 58.0\n", + "110 68.0 82.5 113.0 109.0 16.0\n", + "111 5.0 51.0 87.0 58.0 126.0\n", + "112 53.0 97.0 76.0 37.0 45.0\n", + "113 42.0 148.0 86.0 97.0 65.0\n", + "114 70.0 138.0 69.0 68.0 134.0\n", + "115 68.0 136.0 113.0 22.0 94.0\n", + "116 31.0 137.0 6.0 20.0 28.0\n", + "117 148.0 74.0 134.0 4.0 124.0\n", + "118 102.0 81.0 138.0 128.0 32.0\n", + "119 27.0 111.0 13.0 69.0 22.0\n", + "120 28.0 93.0 121.0 69.0 4.0\n", + "121 136.0 82.5 25.0 97.0 19.0\n", + "122 111.0 70.0 12.0 38.0 58.0\n", + "123 68.0 103.0 147.0 86.0 8.0\n", + "124 10.0 10.0 46.0 63.0 149.0\n", + "125 7.0 75.0 97.0 108.0 31.0\n", + "126 88.0 6.0 86.0 69.0 55.0\n", + "127 33.0 74.0 106.0 50.0 46.0\n", + "128 74.0 28.0 26.0 100.0 76.0\n", + "129 76.0 18.0 101.0 69.0 65.0\n", + ".. ... ... ... ... ...\n", + "170 144.0 124.0 77.0 92.0 82.0\n", + "171 36.0 98.0 86.0 43.0 80.0\n", + "172 51.0 82.5 68.0 34.0 74.0\n", + "173 149.0 82.5 18.0 141.0 65.0\n", + "174 8.0 139.0 146.0 112.0 65.0\n", + "175 115.0 82.5 64.0 62.0 9.0\n", + "176 68.0 7.0 140.0 45.0 148.0\n", + "177 68.0 43.0 68.0 109.0 18.0\n", + "178 31.0 100.0 86.0 49.0 123.0\n", + "179 29.0 46.0 69.0 57.0 90.0\n", + "180 146.0 86.0 18.0 22.0 46.0\n", + "181 71.0 50.0 40.0 69.0 140.0\n", + "182 4.0 100.0 147.0 116.0 110.0\n", + "183 55.0 87.0 93.0 69.0 34.0\n", + "184 68.0 109.0 124.0 87.0 82.0\n", + "185 10.0 118.0 139.0 50.0 51.0\n", + "186 32.0 12.0 71.0 36.0 65.0\n", + "187 94.0 82.5 138.0 13.0 149.0\n", + "188 65.0 101.0 123.0 128.0 86.0\n", + "189 43.0 94.0 86.0 29.0 132.0\n", + "190 68.0 135.0 94.0 28.0 125.0\n", + "191 30.0 60.0 98.0 69.0 15.0\n", + "192 89.0 16.0 10.0 135.0 4.0\n", + "193 104.0 139.0 97.0 29.0 17.0\n", + "194 5.0 29.0 41.0 99.0 65.0\n", + "195 19.0 102.0 135.0 41.0 40.0\n", + "196 58.0 82.5 70.0 82.0 64.0\n", + "197 68.0 97.0 129.0 76.0 13.0\n", + "198 131.0 15.0 86.0 44.0 114.0\n", + "199 79.0 82.5 95.0 128.0 65.0\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 36, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 中位数填充\n", + "df2.median()\n", + "df4 = df2.fillna(df2.median())\n", + "df4" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", + "

100 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 122.0 10.0 5.0 28.0 57.0\n", + "101 NaN 129.0 16.0 114.0 26.0\n", + "102 97.0 121.0 122.0 29.0 65.0\n", + "103 141.0 73.0 120.0 147.0 1.0\n", + "104 126.0 NaN 86.0 116.0 17.0\n", + "105 85.0 NaN 42.0 121.0 66.0\n", + "106 142.0 65.0 1.0 124.0 83.0\n", + "107 136.0 141.0 NaN 86.0 113.0\n", + "108 15.0 37.0 124.0 110.0 102.0\n", + "109 63.0 30.0 NaN 69.0 58.0\n", + "110 NaN NaN 113.0 109.0 16.0\n", + "111 5.0 51.0 87.0 58.0 126.0\n", + "112 53.0 97.0 76.0 37.0 45.0\n", + "113 42.0 148.0 NaN 97.0 NaN\n", + "114 70.0 138.0 69.0 68.0 134.0\n", + "115 NaN 136.0 113.0 22.0 94.0\n", + "116 31.0 137.0 6.0 20.0 28.0\n", + "117 148.0 74.0 134.0 4.0 124.0\n", + "118 102.0 81.0 138.0 128.0 32.0\n", + "119 27.0 111.0 13.0 NaN 22.0\n", + "120 28.0 93.0 121.0 NaN 4.0\n", + "121 136.0 NaN 25.0 97.0 19.0\n", + "122 111.0 70.0 12.0 38.0 58.0\n", + "123 NaN 103.0 147.0 86.0 8.0\n", + "124 10.0 10.0 46.0 63.0 149.0\n", + "125 7.0 75.0 97.0 108.0 31.0\n", + "126 88.0 6.0 NaN NaN 55.0\n", + "127 33.0 74.0 106.0 50.0 46.0\n", + "128 74.0 28.0 26.0 100.0 76.0\n", + "129 76.0 18.0 101.0 NaN NaN\n", + ".. ... ... ... ... ...\n", + "170 144.0 124.0 77.0 92.0 82.0\n", + "171 36.0 98.0 NaN 43.0 80.0\n", + "172 51.0 NaN 68.0 34.0 74.0\n", + "173 149.0 NaN 18.0 141.0 NaN\n", + "174 8.0 139.0 146.0 112.0 NaN\n", + "175 115.0 NaN 64.0 62.0 9.0\n", + "176 NaN 7.0 140.0 45.0 148.0\n", + "177 NaN 43.0 68.0 109.0 18.0\n", + "178 31.0 100.0 NaN 49.0 123.0\n", + "179 29.0 46.0 69.0 57.0 90.0\n", + "180 146.0 86.0 18.0 22.0 46.0\n", + "181 71.0 50.0 40.0 NaN 140.0\n", + "182 4.0 100.0 147.0 116.0 110.0\n", + "183 55.0 87.0 93.0 NaN 34.0\n", + "184 NaN 109.0 124.0 87.0 82.0\n", + "185 10.0 118.0 139.0 50.0 51.0\n", + "186 32.0 12.0 71.0 36.0 NaN\n", + "187 94.0 NaN 138.0 13.0 149.0\n", + "188 65.0 101.0 123.0 128.0 86.0\n", + "189 43.0 94.0 NaN 29.0 132.0\n", + "190 68.0 135.0 94.0 28.0 125.0\n", + "191 30.0 60.0 98.0 NaN 15.0\n", + "192 89.0 16.0 10.0 135.0 4.0\n", + "193 104.0 139.0 97.0 29.0 17.0\n", + "194 5.0 29.0 41.0 99.0 NaN\n", + "195 19.0 102.0 135.0 41.0 40.0\n", + "196 58.0 NaN 70.0 82.0 64.0\n", + "197 NaN 97.0 129.0 76.0 13.0\n", + "198 131.0 15.0 NaN 44.0 114.0\n", + "199 79.0 NaN 95.0 128.0 NaN\n", + "\n", + "[100 rows x 5 columns]" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 众数填充，数量最多的那个数\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 42, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
100828999101125
101431109325
10256103566190
1034710014713899
1043846827544
10518111223126
106562610614139
10731377567144
10835471026063
109861265788149
11019140303533
11176151133
11231549111969
1136437502321
11472571381521
115551201043225
11696248922146
11763086489
11828461258274
119853970132111
12010990447439
121214810311465
12211029998057
123109888113571
12470103134121121
12551921172743
1266929759105
12765905214822
12841291711913
1292410010728139
..................
207012777241631
2071936192822
20721166154861
207347214011234
2074261081233233
207546130135124113
207633181363820
20771071112954119
207884551293787
20799550451984
2080124746514053
20812635149145127
20821921101389
20838410131714
208428741056889
20852393849788
2086861332612513
208721124401155
20882015353137
208996123123564
20902243927860
20911631176058
20926518131334
209369491094058
2094128461082111
20952659854149
209611147909266
209759773140104
2098102675119
209997197714348
\n", + "

2000 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 82 89 99 101 125\n", + "101 4 31 109 32 5\n", + "102 56 103 56 61 90\n", + "103 47 100 147 138 99\n", + "104 38 46 82 75 44\n", + "105 18 11 122 3 126\n", + "106 56 26 106 14 139\n", + "107 3 137 75 67 144\n", + "108 35 47 102 60 63\n", + "109 86 126 57 88 149\n", + "110 19 140 30 35 33\n", + "111 76 1 5 11 33\n", + "112 31 54 91 119 69\n", + "113 64 37 50 23 21\n", + "114 72 57 138 15 21\n", + "115 55 120 104 32 25\n", + "116 96 24 89 22 146\n", + "117 63 0 8 64 89\n", + "118 28 46 125 82 74\n", + "119 85 39 70 132 111\n", + "120 109 90 44 74 39\n", + "121 2 148 103 114 65\n", + "122 110 29 99 80 57\n", + "123 109 88 81 135 71\n", + "124 70 103 134 121 121\n", + "125 51 92 117 27 43\n", + "126 6 92 97 59 105\n", + "127 65 90 52 148 22\n", + "128 4 129 17 119 13\n", + "129 24 100 107 28 139\n", + "... ... ... ... ... ...\n", + "2070 127 77 24 16 31\n", + "2071 93 61 9 28 22\n", + "2072 116 61 54 8 61\n", + "2073 4 72 140 112 34\n", + "2074 26 108 123 32 33\n", + "2075 46 130 135 124 113\n", + "2076 33 18 136 38 20\n", + "2077 107 11 129 54 119\n", + "2078 84 55 129 37 87\n", + "2079 95 50 45 19 84\n", + "2080 124 74 65 140 53\n", + "2081 26 35 149 145 127\n", + "2082 19 21 101 3 89\n", + "2083 84 10 131 71 4\n", + "2084 28 74 105 68 89\n", + "2085 23 93 84 97 88\n", + "2086 86 133 26 125 13\n", + "2087 21 124 40 115 5\n", + "2088 20 15 35 31 37\n", + "2089 96 123 123 5 64\n", + "2090 22 43 92 78 60\n", + "2091 16 31 17 60 58\n", + "2092 65 18 13 13 34\n", + "2093 69 49 109 40 58\n", + "2094 128 46 10 82 111\n", + "2095 26 59 8 54 149\n", + "2096 111 47 90 92 66\n", + "2097 5 97 73 140 104\n", + "2098 102 6 7 5 119\n", + "2099 97 19 77 143 48\n", + "\n", + "[2000 rows x 5 columns]" + ] + }, + "execution_count": 42, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = DataFrame(np.random.randint(0,150,size = (2000,5)),index = np.arange(100,2100),columns=['Python','En','Math','Physic','Chem'])\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 43, + "metadata": {}, + "outputs": [], + "source": [ + "for i in range(1000):\n", + " # 行索引\n", + " index = np.random.randint(100,2100,size =1)[0]\n", + "\n", + " cols = df.columns\n", + "\n", + " # 列索引\n", + " col = np.random.choice(cols)\n", + "\n", + " df.loc[index,col] = None" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 190\n", + "En 200\n", + "Math 194\n", + "Physic 189\n", + "Chem 181\n", + "dtype: int64" + ] + }, + "execution_count": 44, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 45, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 82.0 89.0 99.0 101.0 125.0\n", + "101 4.0 31.0 109.0 32.0 5.0\n", + "102 56.0 103.0 56.0 NaN 90.0\n", + "103 47.0 100.0 147.0 138.0 99.0\n", + "104 38.0 46.0 NaN 75.0 44.0" + ] + }, + "execution_count": 45, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.head()" + ] + }, + { + "cell_type": "code", + "execution_count": 46, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMathPhysicChem
209526.059.08.054.0149.0
2096NaN47.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.0NaN48.0
\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "2095 26.0 59.0 8.0 54.0 149.0\n", + "2096 NaN 47.0 90.0 92.0 66.0\n", + "2097 5.0 97.0 73.0 140.0 104.0\n", + "2098 102.0 6.0 7.0 5.0 119.0\n", + "2099 97.0 19.0 77.0 NaN 48.0" + ] + }, + "execution_count": 46, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.tail()" + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([ 82., 4., 56., 47., 38., 18., 3., 35., 86., 19., 76.,\n", + " 31., 64., 72., 55., 96., 63., 28., 85., 109., 2., 110.,\n", + " 70., 51., 6., 65., 24., 48., 44., 11., 114., 129., 87.,\n", + " 108., 125., nan, 140., 132., 91., 34., 54., 30., 12., 98.,\n", + " 142., 79., 13., 77., 40., 139., 39., 81., 112., 36., 22.,\n", + " 5., 120., 17., 127., 119., 59., 146., 89., 103., 8., 97.,\n", + " 130., 73., 83., 122., 95., 100., 41., 21., 136., 80., 101.,\n", + " 50., 27., 71., 16., 141., 126., 102., 145., 15., 52., 94.,\n", + " 10., 33., 137., 9., 128., 88., 26., 84., 93., 1., 7.,\n", + " 131., 107., 148., 0., 105., 66., 32., 115., 118., 58., 53.,\n", + " 29., 42., 57., 62., 25., 60., 69., 133., 68., 20., 106.,\n", + " 147., 78., 90., 124., 149., 92., 75., 117., 143., 99., 37.,\n", + " 123., 45., 61., 121., 135., 138., 116., 14., 104., 74., 46.,\n", + " 111., 23., 43., 49., 144., 113., 67., 134.])" + ] + }, + "execution_count": 48, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 去重之后的数据\n", + "df['Python'].unique()" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "143.0 20\n", + "136.0 20\n", + "102.0 19\n", + "105.0 19\n", + "26.0 19\n", + "69.0 19\n", + "31.0 18\n", + "148.0 18\n", + "75.0 18\n", + "139.0 18\n", + "1.0 18\n", + "35.0 17\n", + "140.0 17\n", + "110.0 17\n", + "125.0 17\n", + "146.0 17\n", + "141.0 17\n", + "64.0 16\n", + "30.0 16\n", + "79.0 16\n", + "73.0 16\n", + "40.0 16\n", + "10.0 15\n", + "6.0 15\n", + "65.0 15\n", + "81.0 15\n", + "28.0 15\n", + "48.0 15\n", + "92.0 15\n", + "103.0 15\n", + " ..\n", + "104.0 9\n", + "12.0 9\n", + "116.0 9\n", + "13.0 9\n", + "59.0 9\n", + "93.0 9\n", + "124.0 9\n", + "85.0 8\n", + "135.0 8\n", + "131.0 8\n", + "68.0 8\n", + "66.0 8\n", + "62.0 8\n", + "120.0 8\n", + "17.0 8\n", + "25.0 8\n", + "145.0 7\n", + "58.0 7\n", + "134.0 7\n", + "113.0 7\n", + "123.0 7\n", + "39.0 7\n", + "34.0 7\n", + "43.0 7\n", + "74.0 6\n", + "144.0 6\n", + "132.0 6\n", + "142.0 5\n", + "67.0 5\n", + "49.0 5\n", + "Name: Python, Length: 150, dtype: int64" + ] + }, + "execution_count": 49, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['Python'].value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "8.0 21\n", + "96.0 19\n", + "118.0 19\n", + "24.0 19\n", + "43.0 19\n", + "27.0 19\n", + "19.0 19\n", + "41.0 18\n", + "0.0 18\n", + "3.0 18\n", + "52.0 18\n", + "4.0 17\n", + "137.0 17\n", + "1.0 17\n", + "101.0 17\n", + "51.0 17\n", + "39.0 17\n", + "100.0 17\n", + "127.0 17\n", + "115.0 16\n", + "33.0 16\n", + "112.0 16\n", + "92.0 16\n", + "126.0 16\n", + "133.0 15\n", + "32.0 15\n", + "89.0 15\n", + "95.0 15\n", + "36.0 15\n", + "93.0 15\n", + " ..\n", + "12.0 9\n", + "28.0 9\n", + "106.0 9\n", + "45.0 9\n", + "80.0 9\n", + "84.0 9\n", + "58.0 9\n", + "79.0 9\n", + "71.0 9\n", + "83.0 9\n", + "142.0 9\n", + "7.0 9\n", + "6.0 8\n", + "61.0 8\n", + "149.0 8\n", + "34.0 8\n", + "20.0 8\n", + "38.0 8\n", + "130.0 8\n", + "104.0 7\n", + "120.0 7\n", + "56.0 7\n", + "146.0 7\n", + "98.0 7\n", + "134.0 6\n", + "123.0 6\n", + "35.0 6\n", + "87.0 5\n", + "42.0 5\n", + "119.0 4\n", + "Name: En, Length: 150, dtype: int64" + ] + }, + "execution_count": 53, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "en = df['En'].value_counts()\n", + "en" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "8.0" + ] + }, + "execution_count": 54, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "en.index[0]" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Python 75.0\n", + "En 74.0\n", + "Math 77.5\n", + "Physic 73.0\n", + "Chem 72.0\n", + "dtype: float64 \n" + ] + } + ], + "source": [ + "s = df.median()\n", + "print(s,type(s))" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": {}, + "outputs": [], + "source": [ + "zhongshu = []\n", + "for col in df.columns:\n", + " zhongshu.append(df[col].value_counts().index[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 143.0\n", + "En 8.0\n", + "Math 80.0\n", + "Physic 31.0\n", + "Chem 125.0\n", + "dtype: float64" + ] + }, + "execution_count": 57, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s = Series(zhongshu,index = df.columns)\n", + "s" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + " \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", + "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.031.090.0
10347.0100.0147.0138.099.0
10438.046.080.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.080.088.0149.0
11019.0140.080.035.033.0
11176.08.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.031.0146.0
11763.08.08.064.089.0
11828.08.0125.082.074.0
11985.039.070.0132.0111.0
120109.090.080.074.039.0
1212.08.0103.0114.065.0
122110.029.099.080.057.0
123109.088.081.0135.071.0
12470.0103.0134.0121.0121.0
12551.092.0117.031.043.0
1266.092.097.059.0105.0
12765.090.052.0148.022.0
1284.0129.017.0119.013.0
12924.0100.0107.028.0139.0
..................
2070127.077.024.016.0125.0
207193.061.09.028.022.0
2072116.061.054.08.061.0
20734.072.0140.031.034.0
2074143.0108.0123.032.033.0
207546.08.0135.0124.0113.0
2076143.018.0136.038.0125.0
2077143.011.0129.054.0119.0
207884.055.0129.037.087.0
207995.050.045.019.084.0
2080124.074.065.031.053.0
208126.035.0149.0145.0127.0
208219.021.0101.03.089.0
208384.08.0131.071.04.0
208428.074.0105.068.089.0
208523.093.084.097.088.0
208686.0133.026.0125.013.0
208721.0124.040.031.05.0
208820.015.035.031.037.0
208996.0123.0123.05.064.0
209022.043.092.078.060.0
209116.031.017.060.058.0
209265.018.013.013.034.0
209369.049.0109.040.058.0
2094128.046.010.082.0111.0
209526.059.08.054.0149.0
2096143.047.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.031.048.0
\n", + "

2000 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 82.0 89.0 99.0 101.0 125.0\n", + "101 4.0 31.0 109.0 32.0 5.0\n", + "102 56.0 103.0 56.0 31.0 90.0\n", + "103 47.0 100.0 147.0 138.0 99.0\n", + "104 38.0 46.0 80.0 75.0 44.0\n", + "105 18.0 11.0 122.0 3.0 126.0\n", + "106 56.0 26.0 106.0 14.0 139.0\n", + "107 3.0 137.0 75.0 67.0 144.0\n", + "108 35.0 47.0 102.0 60.0 63.0\n", + "109 86.0 126.0 80.0 88.0 149.0\n", + "110 19.0 140.0 80.0 35.0 33.0\n", + "111 76.0 8.0 5.0 11.0 33.0\n", + "112 31.0 54.0 91.0 119.0 69.0\n", + "113 64.0 37.0 50.0 23.0 21.0\n", + "114 72.0 57.0 138.0 15.0 21.0\n", + "115 55.0 120.0 104.0 32.0 25.0\n", + "116 96.0 24.0 89.0 31.0 146.0\n", + "117 63.0 8.0 8.0 64.0 89.0\n", + "118 28.0 8.0 125.0 82.0 74.0\n", + "119 85.0 39.0 70.0 132.0 111.0\n", + "120 109.0 90.0 80.0 74.0 39.0\n", + "121 2.0 8.0 103.0 114.0 65.0\n", + "122 110.0 29.0 99.0 80.0 57.0\n", + "123 109.0 88.0 81.0 135.0 71.0\n", + "124 70.0 103.0 134.0 121.0 121.0\n", + "125 51.0 92.0 117.0 31.0 43.0\n", + "126 6.0 92.0 97.0 59.0 105.0\n", + "127 65.0 90.0 52.0 148.0 22.0\n", + "128 4.0 129.0 17.0 119.0 13.0\n", + "129 24.0 100.0 107.0 28.0 139.0\n", + "... ... ... ... ... ...\n", + "2070 127.0 77.0 24.0 16.0 125.0\n", + "2071 93.0 61.0 9.0 28.0 22.0\n", + "2072 116.0 61.0 54.0 8.0 61.0\n", + "2073 4.0 72.0 140.0 31.0 34.0\n", + "2074 143.0 108.0 123.0 32.0 33.0\n", + "2075 46.0 8.0 135.0 124.0 113.0\n", + "2076 143.0 18.0 136.0 38.0 125.0\n", + "2077 143.0 11.0 129.0 54.0 119.0\n", + "2078 84.0 55.0 129.0 37.0 87.0\n", + "2079 95.0 50.0 45.0 19.0 84.0\n", + "2080 124.0 74.0 65.0 31.0 53.0\n", + "2081 26.0 35.0 149.0 145.0 127.0\n", + "2082 19.0 21.0 101.0 3.0 89.0\n", + "2083 84.0 8.0 131.0 71.0 4.0\n", + "2084 28.0 74.0 105.0 68.0 89.0\n", + "2085 23.0 93.0 84.0 97.0 88.0\n", + "2086 86.0 133.0 26.0 125.0 13.0\n", + "2087 21.0 124.0 40.0 31.0 5.0\n", + "2088 20.0 15.0 35.0 31.0 37.0\n", + "2089 96.0 123.0 123.0 5.0 64.0\n", + "2090 22.0 43.0 92.0 78.0 60.0\n", + "2091 16.0 31.0 17.0 60.0 58.0\n", + "2092 65.0 18.0 13.0 13.0 34.0\n", + "2093 69.0 49.0 109.0 40.0 58.0\n", + "2094 128.0 46.0 10.0 82.0 111.0\n", + "2095 26.0 59.0 8.0 54.0 149.0\n", + "2096 143.0 47.0 90.0 92.0 66.0\n", + "2097 5.0 97.0 73.0 140.0 104.0\n", + "2098 102.0 6.0 7.0 5.0 119.0\n", + "2099 97.0 19.0 77.0 31.0 48.0\n", + "\n", + "[2000 rows x 5 columns]" + ] + }, + "execution_count": 60, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2 = df.fillna(s)\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 61, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 0\n", + "En 0\n", + "Math 0\n", + "Physic 0\n", + "Chem 0\n", + "dtype: int64" + ] + }, + "execution_count": 61, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 62, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 190\n", + "En 200\n", + "Math 194\n", + "Physic 189\n", + "Chem 181\n", + "dtype: int64" + ] + }, + "execution_count": 62, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.isnull().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.0NaN88.0149.0
11019.0140.0NaN35.033.0
11176.0NaN5.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0NaN146.0
11763.0NaN8.064.089.0
11828.0NaN125.082.074.0
11985.039.070.0132.0111.0
\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 82.0 89.0 99.0 101.0 125.0\n", + "101 4.0 31.0 109.0 32.0 5.0\n", + "102 56.0 103.0 56.0 NaN 90.0\n", + "103 47.0 100.0 147.0 138.0 99.0\n", + "104 38.0 46.0 NaN 75.0 44.0\n", + "105 18.0 11.0 122.0 3.0 126.0\n", + "106 56.0 26.0 106.0 14.0 139.0\n", + "107 3.0 137.0 75.0 67.0 144.0\n", + "108 35.0 47.0 102.0 60.0 63.0\n", + "109 86.0 126.0 NaN 88.0 149.0\n", + "110 19.0 140.0 NaN 35.0 33.0\n", + "111 76.0 NaN 5.0 11.0 33.0\n", + "112 31.0 54.0 91.0 119.0 69.0\n", + "113 64.0 37.0 50.0 23.0 21.0\n", + "114 72.0 57.0 138.0 15.0 21.0\n", + "115 55.0 120.0 104.0 32.0 25.0\n", + "116 96.0 24.0 89.0 NaN 146.0\n", + "117 63.0 NaN 8.0 64.0 89.0\n", + "118 28.0 NaN 125.0 82.0 74.0\n", + "119 85.0 39.0 70.0 132.0 111.0" + ] + }, + "execution_count": 65, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3 = df.iloc[:20]\n", + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.090.090.0
10347.0100.0147.0138.099.0
10438.046.075.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.088.088.0149.0
11019.0140.035.035.033.0
11176.05.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0146.0146.0
11763.08.08.064.089.0
11828.0125.0125.082.074.0
11985.039.070.0132.0111.0
\n", + "
" + ], + "text/plain": [ + " Python En Math Physic Chem\n", + "100 82.0 89.0 99.0 101.0 125.0\n", + "101 4.0 31.0 109.0 32.0 5.0\n", + "102 56.0 103.0 56.0 90.0 90.0\n", + "103 47.0 100.0 147.0 138.0 99.0\n", + "104 38.0 46.0 75.0 75.0 44.0\n", + "105 18.0 11.0 122.0 3.0 126.0\n", + "106 56.0 26.0 106.0 14.0 139.0\n", + "107 3.0 137.0 75.0 67.0 144.0\n", + "108 35.0 47.0 102.0 60.0 63.0\n", + "109 86.0 126.0 88.0 88.0 149.0\n", + "110 19.0 140.0 35.0 35.0 33.0\n", + "111 76.0 5.0 5.0 11.0 33.0\n", + "112 31.0 54.0 91.0 119.0 69.0\n", + "113 64.0 37.0 50.0 23.0 21.0\n", + "114 72.0 57.0 138.0 15.0 21.0\n", + "115 55.0 120.0 104.0 32.0 25.0\n", + "116 96.0 24.0 89.0 146.0 146.0\n", + "117 63.0 8.0 8.0 64.0 89.0\n", + "118 28.0 125.0 125.0 82.0 74.0\n", + "119 85.0 39.0 70.0 132.0 111.0" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "'''method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None\n", + " Method to use for filling holes in reindexed Series\n", + " pad / ffill: propagate last valid observation forward to next valid\n", + " backfill / bfill: use NEXT valid observation to fill gap'''\n", + "df3.fillna(method='bfill',axis = 1)" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(2000, 5)" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#数据量足够大，空数据比较少，直接删除\n", + "df.shape" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "df.dro" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..d8e0d1ee9084e4b818e547d0c2eb48d301335d72 --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225-checkpoint.ipynb" @@ -0,0 +1,494 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "# 数据分析BI-------->人工智能AI\n", + "# 数据分析和数据挖掘一个意思，\n", + "# 工具和软件：Excel 免费版\n", + "# SPSS（一人一年10000）、SAS（一人一年5000）、Matlab 收费\n", + "# R、Python（全方位语言，流行） 免费\n", + "# Python + numpy + scipy + pandas + matplotlib + seaborn + pyEcharts + sklearn + kereas（Tensorflow）+…… \n", + "# 代码，自动化（数据输入----输出结果）\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "a 63\n", + "b 107\n", + "c 16\n", + "d 35\n", + "e 140\n", + "f 83\n", + "dtype: int32" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 多层索引，行列\n", + "# 单层索引\n", + "s = Series(np.random.randint(0,150,size = 6),index=list('abcdef'))\n", + "s" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "张三 期中 114\n", + " 期末 131\n", + "李四 期中 3\n", + " 期末 63\n", + "王五 期中 107\n", + " 期末 34\n", + "dtype: int32" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 多层索引，两层，三层以上（规则一样）\n", + "s2 = Series(np.random.randint(0,150,size = 6),index = pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末']]))\n", + "s2" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'DataFrame' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m150\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Python'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'En'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'Math'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMultiIndex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_product\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'张三'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'李四'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'王五'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'期中'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'期末'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNameError\u001b[0m: name 'DataFrame' is not defined" + ] + } + ], + "source": [ + "df = DataFrame(np.random.randint(0,150,size = (6,3)),columns=['Python','En','Math'],index =pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末']]) )\n", + "\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMath
张三期中A153117
B8256123
期末A14278
B695017
李四期中A9187143
B12011839
期末A567655
B11105121
王五期中A147781
B128126146
期末A4945114
B1212677
\n", + "
" + ], + "text/plain": [ + " Python En Math\n", + "张三 期中 A 15 31 17\n", + " B 82 56 123\n", + " 期末 A 14 2 78\n", + " B 69 50 17\n", + "李四 期中 A 91 87 143\n", + " B 120 118 39\n", + " 期末 A 56 76 55\n", + " B 11 105 121\n", + "王五 期中 A 147 78 1\n", + " B 128 126 146\n", + " 期末 A 49 45 114\n", + " B 121 26 77" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 三层索引\n", + "df3 = DataFrame(np.random.randint(0,150,size = (12,3)),columns=['Python','En','Math'],index =pd.MultiIndex.from_product([['张三','李四','王五'],['期中','期末'],['A','B']]) )\n", + "\n", + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "73" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 先获取列后获取行\n", + "df['Python']['张三']['期中']" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "df2 = df.copy()" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMath
张三期中73525
期末373656
李四期中14981142
期末711380
王五期中1194103
期末2512183
\n", + "
" + ], + "text/plain": [ + " Python En Math\n", + "张三 期中 73 5 25\n", + " 期末 37 36 56\n", + "李四 期中 149 81 142\n", + " 期末 71 138 0\n", + "王五 期中 11 94 103\n", + " 期末 25 121 83" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.sort_index()" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "73" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 先获取行，后获取列\n", + "df.loc['张三'].loc['期中']['Python']" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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", + "
PythonEnMath
张三期中73525
期末373656
\n", + "
" + ], + "text/plain": [ + " Python En Math\n", + "张三 期中 73 5 25\n", + " 期末 37 36 56" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.iloc[[0,1]]" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..4bcaad27c2d0841f35580bb30c254b0d580eb095 --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227-checkpoint.ipynb" @@ -0,0 +1,1000 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "scrolled": true + }, + "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", + " \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", + "
PythonEnMath
期中期末期中期末期中期末
A1311011731517
B6234531012457
C247636117123105
D11246794246122
E661131044510108
F11110844113221
\n", + "
" + ], + "text/plain": [ + " Python En Math \n", + " 期中 期末 期中 期末 期中 期末\n", + "A 131 101 1 73 15 17\n", + "B 62 34 53 101 24 57\n", + "C 24 76 36 117 123 105\n", + "D 112 46 79 42 46 122\n", + "E 66 113 104 45 10 108\n", + "F 111 108 4 41 132 21" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 多层列索引\n", + "df = DataFrame(np.random.randint(0,150,size = (6,6)),index = list('ABCDEF'),\n", + " columns=pd.MultiIndex.from_product([['Python','En','Math'],['期中','期末']]))\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "scrolled": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 期中 84.3\n", + " 期末 79.7\n", + "En 期中 46.2\n", + " 期末 69.8\n", + "Math 期中 58.3\n", + " 期末 71.7\n", + "dtype: float64" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# round保留2位小数\n", + "df.mean().round(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "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", + " \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", + "
PythonEnMath
期中期末期中期末期中期末
A1311011731517
B6234531012457
C247636117123105
D11246794246122
E661131044510108
F11110844113221
\n", + "
" + ], + "text/plain": [ + " Python En Math \n", + " 期中 期末 期中 期末 期中 期末\n", + "A 131 101 1 73 15 17\n", + "B 62 34 53 101 24 57\n", + "C 24 76 36 117 123 105\n", + "D 112 46 79 42 46 122\n", + "E 66 113 104 45 10 108\n", + "F 111 108 4 41 132 21" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "scrolled": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonEnMath
A116.037.016.0
B48.077.040.5
C50.076.5114.0
D79.060.584.0
E89.574.559.0
F109.522.576.5
\n", + "
" + ], + "text/plain": [ + " Python En Math\n", + "A 116.0 37.0 16.0\n", + "B 48.0 77.0 40.5\n", + "C 50.0 76.5 114.0\n", + "D 79.0 60.5 84.0\n", + "E 89.5 74.5 59.0\n", + "F 109.5 22.5 76.5" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# axis = 0代表行\n", + "# axis = 1代表列\n", + "df.mean(axis = 1,level = 0)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 15, + "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", + "
期中期末
A49.063.7
B46.364.0
C61.099.3
D79.070.0
E60.088.7
F82.356.7
\n", + "
" + ], + "text/plain": [ + " 期中 期末\n", + "A 49.0 63.7\n", + "B 46.3 64.0\n", + "C 61.0 99.3\n", + "D 79.0 70.0\n", + "E 60.0 88.7\n", + "F 82.3 56.7" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.mean(axis = 1,level = 1).round(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "scrolled": true + }, + "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", + " \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", + "
PythonEnMath
期中期末期中期末期中期末
A1311011731517
B6234531012457
C247636117123105
D11246794246122
E661131044510108
F11110844113221
\n", + "
" + ], + "text/plain": [ + " Python En Math \n", + " 期中 期末 期中 期末 期中 期末\n", + "A 131 101 1 73 15 17\n", + "B 62 34 53 101 24 57\n", + "C 24 76 36 117 123 105\n", + "D 112 46 79 42 46 122\n", + "E 66 113 104 45 10 108\n", + "F 111 108 4 41 132 21" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
EnMathPython
A期中115131
期末7317101
B期中532462
期末1015734
C期中3612324
期末11710576
D期中7946112
期末4212246
E期中1041066
期末45108113
F期中4132111
期末4121108
\n", + "
" + ], + "text/plain": [ + " En Math Python\n", + "A 期中 1 15 131\n", + " 期末 73 17 101\n", + "B 期中 53 24 62\n", + " 期末 101 57 34\n", + "C 期中 36 123 24\n", + " 期末 117 105 76\n", + "D 期中 79 46 112\n", + " 期末 42 122 46\n", + "E 期中 104 10 66\n", + " 期末 45 108 113\n", + "F 期中 4 132 111\n", + " 期末 41 21 108" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 行和列的多层索引，进行转换\n", + "# Stack the prescribed level(s) from columns to index.\n", + "# 从列变成行\n", + "df2 = df.stack(level = 1)\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "scrolled": true + }, + "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", + " \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", + "
EnMathPython
ABCDEFABCDEFABCDEF
期中1533679104415241234610132131622411266111
期末73101117424541175710512210821101347646113108
\n", + "
" + ], + "text/plain": [ + " En Math Python \n", + " A B C D E F A B C D E F A B C D E F\n", + "期中 1 53 36 79 104 4 15 24 123 46 10 132 131 62 24 112 66 111\n", + "期末 73 101 117 42 45 41 17 57 105 122 108 21 101 34 76 46 113 108" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 从行变成列\n", + "df2.unstack(level= 0 )" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "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", + " \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", + "
EnMathPython
期中期末期中期末期中期末
A1731517131101
B5310124576234
C361171231052476
D79424612211246
E104451010866113
F44113221111108
\n", + "
" + ], + "text/plain": [ + " En Math Python \n", + " 期中 期末 期中 期末 期中 期末\n", + "A 1 73 15 17 131 101\n", + "B 53 101 24 57 62 34\n", + "C 36 117 123 105 24 76\n", + "D 79 42 46 122 112 46\n", + "E 104 45 10 108 66 113\n", + "F 4 41 132 21 111 108" + ] + }, + "execution_count": 22, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2.unstack(level = 1)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..7df4f33a7af910d51f07f2f7ee5bd1fbf36adc8b --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220-checkpoint.ipynb" @@ -0,0 +1,1209 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 数据分析数据挖掘\n", + "# 有数据情况下：\n", + "# 数据预处理\n", + "# 数据清洗（空数据，异常值）\n", + "# 数据集成（多个数据合并到一起，级联）数据可能存放在多个表中\n", + "# 数据转化\n", + "# 数据规约（属性减少（不重要的属性删除），数据减少去重操作）" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 5, 12, 67, 29, 46, 103, 53, 53, 139, 87],\n", + " [126, 33, 55, 104, 45, 70, 96, 133, 116, 43],\n", + " [ 84, 45, 17, 42, 19, 11, 125, 43, 54, 39],\n", + " [ 97, 68, 99, 90, 28, 60, 135, 84, 111, 63],\n", + " [114, 56, 30, 81, 48, 73, 119, 65, 20, 22]])" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "array([[115, 128, 122, 127, 4, 135, 26, 25, 131, 139],\n", + " [ 66, 119, 37, 136, 101, 40, 102, 127, 148, 127],\n", + " [ 89, 80, 140, 133, 51, 142, 47, 27, 54, 23],\n", + " [ 64, 127, 33, 128, 60, 106, 67, 94, 110, 76],\n", + " [ 6, 21, 23, 96, 10, 62, 26, 79, 149, 43],\n", + " [116, 143, 132, 118, 68, 21, 57, 133, 124, 124]])" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# 首先看numpy数组的集成\n", + "nd1 = np.random.randint(0,150,size = (5,10))\n", + "\n", + "nd2 = np.random.randint(0,150,size = (6,10))\n", + "display(nd1,nd2)" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[ 5, 12, 67, 29, 46, 103, 53, 53, 139, 87],\n", + " [126, 33, 55, 104, 45, 70, 96, 133, 116, 43],\n", + " [ 84, 45, 17, 42, 19, 11, 125, 43, 54, 39],\n", + " [ 97, 68, 99, 90, 28, 60, 135, 84, 111, 63],\n", + " [114, 56, 30, 81, 48, 73, 119, 65, 20, 22],\n", + " [115, 128, 122, 127, 4, 135, 26, 25, 131, 139],\n", + " [ 66, 119, 37, 136, 101, 40, 102, 127, 148, 127],\n", + " [ 89, 80, 140, 133, 51, 142, 47, 27, 54, 23],\n", + " [ 64, 127, 33, 128, 60, 106, 67, 94, 110, 76],\n", + " [ 6, 21, 23, 96, 10, 62, 26, 79, 149, 43],\n", + " [116, 143, 132, 118, 68, 21, 57, 133, 124, 124]])" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 原来数据一个5行，一个是6行，级联之后变成了11行\n", + "nd3 = np.concatenate([nd1,nd2],axis = 0)\n", + "nd3" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[110, 38, 144, 92, 38, 2, 67, 2, 103, 81],\n", + " [ 56, 61, 61, 22, 108, 145, 95, 44, 40, 100],\n", + " [ 65, 74, 85, 123, 47, 117, 35, 55, 120, 20],\n", + " [ 15, 9, 4, 84, 71, 133, 140, 13, 71, 91],\n", + " [ 94, 31, 41, 5, 7, 32, 50, 24, 18, 120]])" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/plain": [ + "array([[ 65, 149, 86, 138, 98],\n", + " [136, 49, 102, 45, 140],\n", + " [ 13, 124, 94, 81, 73],\n", + " [ 82, 38, 0, 75, 94],\n", + " [146, 28, 143, 61, 49]])" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "nd1 = np.random.randint(0,150,size = (5,10))\n", + "\n", + "nd2 = np.random.randint(0,150,size = (5,5))\n", + "display(nd1,nd2)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "array([[110, 38, 144, 92, 38, 2, 67, 2, 103, 81, 65, 149, 86,\n", + " 138, 98],\n", + " [ 56, 61, 61, 22, 108, 145, 95, 44, 40, 100, 136, 49, 102,\n", + " 45, 140],\n", + " [ 65, 74, 85, 123, 47, 117, 35, 55, 120, 20, 13, 124, 94,\n", + " 81, 73],\n", + " [ 15, 9, 4, 84, 71, 133, 140, 13, 71, 91, 82, 38, 0,\n", + " 75, 94],\n", + " [ 94, 31, 41, 5, 7, 32, 50, 24, 18, 120, 146, 28, 143,\n", + " 61, 49]])" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# axis = 0行级联（第一维度的级联），axis = 1（第二个维度的级联，列的级联）\n", + "np.concatenate((nd1,nd2),axis = 1)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# pandas级联操作，pandas基于numpy\n", + "# pandas的级联类似" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": true + }, + "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", + "
PythonMathEn
A1135380
B1354052
C1441864
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 113 53 80\n", + "B 135 40 52\n", + "C 144 18 64" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
D126118146
E1478127
F87631
G359533
H13011791
I12498122
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "D 126 118 146\n", + "E 147 81 27\n", + "F 87 63 1\n", + "G 35 95 33\n", + "H 130 117 91\n", + "I 124 98 122" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "df1 = DataFrame(np.random.randint(0,150,size = (3,3)),index = list('ABC'),columns=['Python','Math','En'])\n", + "\n", + "df2 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('DEFGHI'),columns=['Python','Math','En'])\n", + "\n", + "display(df1,df2)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "collapsed": true + }, + "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", + " \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", + "
PythonMathEn
A1135380
B1354052
C1441864
D126118146
E1478127
F87631
G359533
H13011791
I12498122
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 113 53 80\n", + "B 135 40 52\n", + "C 144 18 64\n", + "D 126 118 146\n", + "E 147 81 27\n", + "F 87 63 1\n", + "G 35 95 33\n", + "H 130 117 91\n", + "I 124 98 122" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# pandas汇总数据，数据集成\n", + "df1.append(df2)" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "collapsed": true + }, + "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", + " \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", + "
PythonMathEn
A1135380
B1354052
C1441864
D126118146
E1478127
F87631
G359533
H13011791
I12498122
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 113 53 80\n", + "B 135 40 52\n", + "C 144 18 64\n", + "D 126 118 146\n", + "E 147 81 27\n", + "F 87 63 1\n", + "G 35 95 33\n", + "H 130 117 91\n", + "I 124 98 122" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([df1,df2])" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "d:\\python36\\lib\\site-packages\\ipykernel_launcher.py:1: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n", + "of pandas will change to not sort by default.\n", + "\n", + "To accept the future behavior, pass 'sort=False'.\n", + "\n", + "To retain the current behavior and silence the warning, pass 'sort=True'.\n", + "\n", + " \"\"\"Entry point for launching an IPython kernel.\n" + ] + }, + { + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEnPythonMathEn
A113.053.080.0NaNNaNNaN
B135.040.052.0NaNNaNNaN
C144.018.064.0NaNNaNNaN
DNaNNaNNaN126.0118.0146.0
ENaNNaNNaN147.081.027.0
FNaNNaNNaN87.063.01.0
GNaNNaNNaN35.095.033.0
HNaNNaNNaN130.0117.091.0
INaNNaNNaN124.098.0122.0
\n", + "
" + ], + "text/plain": [ + " Python Math En Python Math En\n", + "A 113.0 53.0 80.0 NaN NaN NaN\n", + "B 135.0 40.0 52.0 NaN NaN NaN\n", + "C 144.0 18.0 64.0 NaN NaN NaN\n", + "D NaN NaN NaN 126.0 118.0 146.0\n", + "E NaN NaN NaN 147.0 81.0 27.0\n", + "F NaN NaN NaN 87.0 63.0 1.0\n", + "G NaN NaN NaN 35.0 95.0 33.0\n", + "H NaN NaN NaN 130.0 117.0 91.0\n", + "I NaN NaN NaN 124.0 98.0 122.0" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([df1,df2],axis = 1,ignore_index = False)" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
A225813
B995735
C512824
E560111
F13723121
G4978115
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 22 58 13\n", + "B 99 57 35\n", + "C 51 28 24\n", + "E 5 60 111\n", + "F 137 23 121\n", + "G 49 78 115" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
A11811381
B5122126
C0115128
E10013094
F4993140
G705994
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 118 113 81\n", + "B 51 22 126\n", + "C 0 115 128\n", + "E 100 130 94\n", + "F 49 93 140\n", + "G 70 59 94" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# 期中\n", + "df1 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCEFG'),columns=['Python','Math','En'])\n", + "\n", + "# 期末\n", + "df2 = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCEFG'),columns=['Python','Math','En'])\n", + "\n", + "display(df1,df2)" + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
期中A225813
B995735
C512824
E560111
F13723121
G4978115
期末A11811381
B5122126
C0115128
E10013094
F4993140
G705994
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "期中 A 22 58 13\n", + " B 99 57 35\n", + " C 51 28 24\n", + " E 5 60 111\n", + " F 137 23 121\n", + " G 49 78 115\n", + "期末 A 118 113 81\n", + " B 51 22 126\n", + " C 0 115 128\n", + " E 100 130 94\n", + " F 49 93 140\n", + " G 70 59 94" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3 = pd.concat([df1,df2],axis = 0,keys = ['期中','期末'])\n", + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
A期中225813
期末11811381
B期中995735
期末5122126
C期中512824
期末0115128
E期中560111
期末10013094
F期中13723121
期末4993140
G期中4978115
期末705994
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 期中 22 58 13\n", + " 期末 118 113 81\n", + "B 期中 99 57 35\n", + " 期末 51 22 126\n", + "C 期中 51 28 24\n", + " 期末 0 115 128\n", + "E 期中 5 60 111\n", + " 期末 100 130 94\n", + "F 期中 137 23 121\n", + " 期末 49 93 140\n", + "G 期中 49 78 115\n", + " 期末 70 59 94" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3.unstack(level = 0).stack()" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..06fd9f690e58d7c15f7d600789c6e1230af4b21e --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge-checkpoint.ipynb" @@ -0,0 +1,1272 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 上一讲，append，concat数据集成方法\n", + "# merge融合，根据某一共同属性进行级联，高级用法" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
namesexid
0A男1
1B女2
2C女3
3D女4
4E男5
5F男6
\n", + "
" + ], + "text/plain": [ + " name sex id\n", + "0 A 男 1\n", + "1 B 女 2\n", + "2 C 女 3\n", + "3 D 女 4\n", + "4 E 男 5\n", + "5 F 男 6" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1 = DataFrame({'name':['A','B','C','D','E','F'],\n", + " 'sex':['男','女','女','女','男','男'],\n", + " 'id':[1,2,3,4,5,6]})\n", + "df1" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
agesalaryid
022120001
125150002
227200003
321300004
418100005
52980007
\n", + "
" + ], + "text/plain": [ + " age salary id\n", + "0 22 12000 1\n", + "1 25 15000 2\n", + "2 27 20000 3\n", + "3 21 30000 4\n", + "4 18 10000 5\n", + "5 29 8000 7" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2 = DataFrame({'age':[22,25,27,21,18,29],'salary':[12000,15000,20000,30000,10000,8000],'id':[1,2,3,4,5,7]})\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "collapsed": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "d:\\python36\\lib\\site-packages\\pandas\\core\\frame.py:6692: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version\n", + "of pandas will change to not sort by default.\n", + "\n", + "To accept the future behavior, pass 'sort=False'.\n", + "\n", + "To retain the current behavior and silence the warning, pass 'sort=True'.\n", + "\n", + " sort=sort)\n" + ] + }, + { + "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", + " \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", + " \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", + "
ageidnamesalarysex
0NaN1ANaN男
1NaN2BNaN女
2NaN3CNaN女
3NaN4DNaN女
4NaN5ENaN男
5NaN6FNaN男
022.01NaN12000.0NaN
125.02NaN15000.0NaN
227.03NaN20000.0NaN
321.04NaN30000.0NaN
418.05NaN10000.0NaN
529.07NaN8000.0NaN
\n", + "
" + ], + "text/plain": [ + " age id name salary sex\n", + "0 NaN 1 A NaN 男\n", + "1 NaN 2 B NaN 女\n", + "2 NaN 3 C NaN 女\n", + "3 NaN 4 D NaN 女\n", + "4 NaN 5 E NaN 男\n", + "5 NaN 6 F NaN 男\n", + "0 22.0 1 NaN 12000.0 NaN\n", + "1 25.0 2 NaN 15000.0 NaN\n", + "2 27.0 3 NaN 20000.0 NaN\n", + "3 21.0 4 NaN 30000.0 NaN\n", + "4 18.0 5 NaN 10000.0 NaN\n", + "5 29.0 7 NaN 8000.0 NaN" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1.append(df2)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "scrolled": true + }, + "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", + " \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", + "
namesexidagesalaryid
0A男122120001
1B女225150002
2C女327200003
3D女421300004
4E男518100005
5F男62980007
\n", + "
" + ], + "text/plain": [ + " name sex id age salary id\n", + "0 A 男 1 22 12000 1\n", + "1 B 女 2 25 15000 2\n", + "2 C 女 3 27 20000 3\n", + "3 D 女 4 21 30000 4\n", + "4 E 男 5 18 10000 5\n", + "5 F 男 6 29 8000 7" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pd.concat([df1,df2],axis = 1)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
namesexidagesalary
0A男12212000
1B女22515000
2C女32720000
3D女42130000
4E男51810000
\n", + "
" + ], + "text/plain": [ + " name sex id age salary\n", + "0 A 男 1 22 12000\n", + "1 B 女 2 25 15000\n", + "2 C 女 3 27 20000\n", + "3 D 女 4 21 30000\n", + "4 E 男 5 18 10000" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1.merge(df2)" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "collapsed": true + }, + "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", + " \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", + "
namesexidagesalary
0A男122.012000.0
1B女225.015000.0
2C女327.020000.0
3D女421.030000.0
4E男518.010000.0
5F男6NaNNaN
6NaNNaN729.08000.0
\n", + "
" + ], + "text/plain": [ + " name sex id age salary\n", + "0 A 男 1 22.0 12000.0\n", + "1 B 女 2 25.0 15000.0\n", + "2 C 女 3 27.0 20000.0\n", + "3 D 女 4 21.0 30000.0\n", + "4 E 男 5 18.0 10000.0\n", + "5 F 男 6 NaN NaN\n", + "6 NaN NaN 7 29.0 8000.0" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df1.merge(df2,how = 'outer')" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "scrolled": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
A401590
B595283
C14138137
D897853
E811013
F757986
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 40 15 90\n", + "B 59 52 83\n", + "C 14 138 137\n", + "D 89 78 53\n", + "E 81 101 3\n", + "F 75 79 86" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = DataFrame(np.random.randint(0,150,size = (6,3)),index = list('ABCDEF'),columns=['Python','Math','En'])\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "scrolled": false + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Python 59.7\n", + "Math 77.2\n", + "En 75.3\n", + "dtype: float64" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "s = df.mean().round(1)\n", + "s" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "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", + "
score_mean
Python59.7
Math77.2
En75.3
\n", + "
" + ], + "text/plain": [ + " score_mean\n", + "Python 59.7\n", + "Math 77.2\n", + "En 75.3" + ] + }, + "execution_count": 20, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2 = DataFrame(s)\n", + "df2.columns = ['score_mean']\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
score_mean59.777.275.3
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "score_mean 59.7 77.2 75.3" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3 = df2.T\n", + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "scrolled": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEn
A40.015.090.0
B59.052.083.0
C14.0138.0137.0
D89.078.053.0
E81.0101.03.0
F75.079.086.0
score_mean59.777.275.3
\n", + "
" + ], + "text/plain": [ + " Python Math En\n", + "A 40.0 15.0 90.0\n", + "B 59.0 52.0 83.0\n", + "C 14.0 138.0 137.0\n", + "D 89.0 78.0 53.0\n", + "E 81.0 101.0 3.0\n", + "F 75.0 79.0 86.0\n", + "score_mean 59.7 77.2 75.3" + ] + }, + "execution_count": 32, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df4 = df.append(df3)\n", + "df4" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "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", + "
score_mean
A48.3
B64.7
C96.3
D73.3
E61.7
F80.0
score_mean70.7
\n", + "
" + ], + "text/plain": [ + " score_mean\n", + "A 48.3\n", + "B 64.7\n", + "C 96.3\n", + "D 73.3\n", + "E 61.7\n", + "F 80.0\n", + "score_mean 70.7" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df5 = DataFrame(df4.mean(axis = 1).round(1))\n", + "df5.columns = ['score_mean']\n", + "df5" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
PythonMathEnscore_mean
A40.015.090.048.3
B59.052.083.064.7
C14.0138.0137.096.3
D89.078.053.073.3
E81.0101.03.061.7
F75.079.086.080.0
score_mean59.777.275.370.7
\n", + "
" + ], + "text/plain": [ + " Python Math En score_mean\n", + "A 40.0 15.0 90.0 48.3\n", + "B 59.0 52.0 83.0 64.7\n", + "C 14.0 138.0 137.0 96.3\n", + "D 89.0 78.0 53.0 73.3\n", + "E 81.0 101.0 3.0 61.7\n", + "F 75.0 79.0 86.0 80.0\n", + "score_mean 59.7 77.2 75.3 70.7" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df4.merge(df5,left_index=True,right_index=True)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/.ipynb_checkpoints/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234-checkpoint.ipynb" "b/Day76-90/code/.ipynb_checkpoints/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234-checkpoint.ipynb" new file mode 100644 index 0000000000000000000000000000000000000000..e9dddcc7ec29237094648b99c04a984bb9d28bd6 --- /dev/null +++ "b/Day76-90/code/.ipynb_checkpoints/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234-checkpoint.ipynb" @@ -0,0 +1,877 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [], + "source": [ + "# 分组聚合透视\n", + "# 很多时候属性是相似的\n", + "\n", + "import numpy as np\n", + "\n", + "import pandas as pd\n", + "\n", + "from pandas import Series,DataFrame" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "scrolled": true + }, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
HandSmokesexweightIQ
0rightyesmale80100
1leftyesfemale50120
2leftnofemale4890
3rightnomale75130
4rightyesmale68140
5rightnomale10080
6rightnofemale4094
7rightnofemale90110
8leftnomale88100
9rightyesfemale76160
\n", + "
" + ], + "text/plain": [ + " Hand Smoke sex weight IQ\n", + "0 right yes male 80 100\n", + "1 left yes female 50 120\n", + "2 left no female 48 90\n", + "3 right no male 75 130\n", + "4 right yes male 68 140\n", + "5 right no male 100 80\n", + "6 right no female 40 94\n", + "7 right no female 90 110\n", + "8 left no male 88 100\n", + "9 right yes female 76 160" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# 走右手习惯，是否抽烟，性别，对体重，智商，有一定影响\n", + "\n", + "df = DataFrame({'Hand':['right','left','left','right','right','right','right','right','left','right'],\n", + " 'Smoke':['yes','yes','no','no','yes','no','no','no','no','yes'],\n", + " 'sex':['male','female','female','male','male','male','female','female','male','female'],\n", + " 'weight':[80,50,48,75,68,100,40,90,88,76],\n", + " 'IQ':[100,120,90,130,140,80,94,110,100,160]})\n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# 分组聚合查看规律，某一条件下规律" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "scrolled": true + }, + "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", + "
weightIQ
Hand
left62.0103.3
right75.6116.3
\n", + "
" + ], + "text/plain": [ + " weight IQ\n", + "Hand \n", + "left 62.0 103.3\n", + "right 75.6 116.3" + ] + }, + "execution_count": 7, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = df.groupby(by = ['Hand'])[['weight','IQ']].mean().round(1)\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "scrolled": true + }, + "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", + "
weight
Hand
left62.0
right75.6
\n", + "
" + ], + "text/plain": [ + " weight\n", + "Hand \n", + "left 62.0\n", + "right 75.6" + ] + }, + "execution_count": 11, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.groupby(by = ['Hand'])[['weight']].apply(np.mean).round(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": {}, + "outputs": [], + "source": [ + "df2 = df.groupby(by = ['Hand'])[['weight']].transform(np.mean).round(1)\n" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "collapsed": true + }, + "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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
weight_mean
075.6
162.0
262.0
375.6
475.6
575.6
675.6
775.6
862.0
975.6
\n", + "
" + ], + "text/plain": [ + " weight_mean\n", + "0 75.6\n", + "1 62.0\n", + "2 62.0\n", + "3 75.6\n", + "4 75.6\n", + "5 75.6\n", + "6 75.6\n", + "7 75.6\n", + "8 62.0\n", + "9 75.6" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df2 = df2.add_suffix('_mean')\n", + "df2" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "collapsed": true + }, + "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", + " \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", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
HandSmokesexweightIQweight_mean
0rightyesmale8010075.6
1leftyesfemale5012062.0
2leftnofemale489062.0
3rightnomale7513075.6
4rightyesmale6814075.6
5rightnomale1008075.6
6rightnofemale409475.6
7rightnofemale9011075.6
8leftnomale8810062.0
9rightyesfemale7616075.6
\n", + "
" + ], + "text/plain": [ + " Hand Smoke sex weight IQ weight_mean\n", + "0 right yes male 80 100 75.6\n", + "1 left yes female 50 120 62.0\n", + "2 left no female 48 90 62.0\n", + "3 right no male 75 130 75.6\n", + "4 right yes male 68 140 75.6\n", + "5 right no male 100 80 75.6\n", + "6 right no female 40 94 75.6\n", + "7 right no female 90 110 75.6\n", + "8 left no male 88 100 62.0\n", + "9 right yes female 76 160 75.6" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df3 = df.merge(df2,left_index=True,right_index=True)\n", + "df3" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "Hand\n", + "left ([3, 3], [62.0, 103.3])\n", + "right ([7, 7], [75.6, 116.3])\n", + "dtype: object" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "def count(x):\n", + " \n", + " return (x.count(),x.mean().round(1))\n", + "\n", + "df.groupby(by = ['Hand'])[['weight','IQ']].apply(count)" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "scrolled": true + }, + "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", + "
IQ
Handsex
leftfemale120
male100
rightfemale160
male140
\n", + "
" + ], + "text/plain": [ + " IQ\n", + "Hand sex \n", + "left female 120\n", + " male 100\n", + "right female 160\n", + " male 140" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df.groupby(by = ['Hand','sex'])[['IQ']].max()" + ] + }, + { + "cell_type": "code", + "execution_count": 29, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 29, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data = df.groupby(by = ['Hand'])['IQ','weight']\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "scrolled": true + }, + "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", + "
IQweight
maxmeanmaxmean
Hand
left120103.38862.0
right160116.310075.6
\n", + "
" + ], + "text/plain": [ + " IQ weight \n", + " max mean max mean\n", + "Hand \n", + "left 120 103.3 88 62.0\n", + "right 160 116.3 100 75.6" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.agg(['max','mean']).round(1)" + ] + }, + { + "cell_type": "code", + "execution_count": 35, + "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", + "
IQweight
Hand
left12062.0
right16075.6
\n", + "
" + ], + "text/plain": [ + " IQ weight\n", + "Hand \n", + "left 120 62.0\n", + "right 160 75.6" + ] + }, + "execution_count": 35, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "data.agg({'IQ':'max','weight':'mean'}).round(1)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.7.7" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Day76-90/code/1-pandas\345\205\245\351\227\250.ipynb" "b/Day76-90/code/1-pandas\345\205\245\351\227\250.ipynb" index b5b3acc8b66de0cdcc01778d81d566fdc93bed4e..d10293f1ebd3368cbce772d721e9bfd85f58d6d0 100644 --- "a/Day76-90/code/1-pandas\345\205\245\351\227\250.ipynb" +++ "b/Day76-90/code/1-pandas\345\205\245\351\227\250.ipynb" @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "metadata": {}, "outputs": [], "source": [ @@ -13,7 +13,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -22,14 +22,7 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "metadata": { "scrolled": false }, @@ -44,7 +37,7 @@ "dtype: int64" ] }, - "execution_count": 4, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -52,13 +45,13 @@ "source": [ "# 创建\n", "# Series是一维的数据\n", - "s = Series(data = [120,136,128,99],index = ['Math','Python','En','Chinese'])\n", + "s = Series(data=[120,136,128,99], index=['Math','Python','En','Chinese'])\n", "s" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -67,7 +60,7 @@ "(4,)" ] }, - "execution_count": 5, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -78,16 +71,16 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "array([120, 136, 128, 99], dtype=int64)" + "array([120, 136, 128, 99])" ] }, - "execution_count": 6, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -99,7 +92,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -108,7 +101,7 @@ "numpy.ndarray" ] }, - "execution_count": 7, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -119,7 +112,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -128,7 +121,7 @@ "120.75" ] }, - "execution_count": 8, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -139,7 +132,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -148,7 +141,7 @@ "136" ] }, - "execution_count": 9, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -159,7 +152,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 11, "metadata": {}, "outputs": [ { @@ -168,7 +161,7 @@ "15.903353943953666" ] }, - "execution_count": 10, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -179,36 +172,33 @@ }, { "cell_type": "code", - "execution_count": 11, - "metadata": { - "collapsed": true - }, + "execution_count": 20, + "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "Math 14400\n", - "Python 18496\n", - "En 16384\n", - "Chinese 9801\n", + "Math 122\n", + "Python 138\n", + "En 130\n", + "Chinese 101\n", "dtype: int64" ] }, - "execution_count": 11, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "s.pow(2)" + "s.add(1)\n", + "s" ] }, { "cell_type": "code", - "execution_count": 12, - "metadata": { - "collapsed": true - }, + "execution_count": 21, + "metadata": {}, "outputs": [ { "data": { @@ -238,64 +228,64 @@ " \n", " \n", " \n", - " a\n", - " 113\n", - " 116\n", - " 75\n", + " a\n", + " 109\n", + " 120\n", + " 23\n", " \n", " \n", - " b\n", - " 19\n", - " 145\n", - " 23\n", + " b\n", + " 54\n", + " 39\n", + " 54\n", " \n", " \n", - " c\n", - " 57\n", - " 107\n", - " 113\n", + " c\n", + " 97\n", + " 22\n", + " 106\n", " \n", " \n", - " d\n", - " 95\n", + " d\n", + " 21\n", + " 96\n", " 3\n", - " 66\n", " \n", " \n", - " e\n", - " 28\n", - " 121\n", - " 120\n", + " e\n", + " 23\n", + " 145\n", + " 147\n", " \n", " \n", - " f\n", - " 141\n", - " 85\n", - " 132\n", + " f\n", + " 80\n", + " 62\n", + " 83\n", " \n", " \n", - " h\n", - " 124\n", - " 39\n", - " 10\n", + " h\n", + " 70\n", + " 31\n", + " 134\n", " \n", " \n", - " i\n", - " 80\n", - " 35\n", - " 17\n", + " i\n", + " 132\n", + " 51\n", + " 115\n", " \n", " \n", - " j\n", - " 68\n", - " 99\n", - " 31\n", + " j\n", + " 95\n", + " 143\n", + " 111\n", " \n", " \n", - " k\n", - " 74\n", - " 12\n", - " 11\n", + " k\n", + " 66\n", + " 94\n", + " 7\n", " \n", " \n", "\n", @@ -303,19 +293,19 @@ ], "text/plain": [ " Python En Math\n", - "a 113 116 75\n", - "b 19 145 23\n", - "c 57 107 113\n", - "d 95 3 66\n", - "e 28 121 120\n", - "f 141 85 132\n", - "h 124 39 10\n", - "i 80 35 17\n", - "j 68 99 31\n", - "k 74 12 11" + "a 109 120 23\n", + "b 54 39 54\n", + "c 97 22 106\n", + "d 21 96 3\n", + "e 23 145 147\n", + "f 80 62 83\n", + "h 70 31 134\n", + "i 132 51 115\n", + "j 95 143 111\n", + "k 66 94 7" ] }, - "execution_count": 12, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } @@ -324,7 +314,7 @@ "# DataFrame是二维的数据\n", "# excel就非常相似\n", "# 所有进行数据分析，数据挖掘的工具最基础的结果：行和列，行表示样本，列表示的是属性\n", - "df = DataFrame(data = np.random.randint(0,150,size = (10,3)),index = list('abcdefhijk'),columns=['Python','En','Math'])\n", + "df = DataFrame(data=np.random.randint(0, 150, size=(10, 3)), index=list('abcdefhijk'), columns=['Python', 'En', 'Math'])\n", "df" ] }, @@ -553,7 +543,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 22, "metadata": { "scrolled": true }, @@ -561,50 +551,57 @@ { "data": { "text/plain": [ - "Python 79.9\n", - "En 76.2\n", - "Math 59.8\n", + "Python 74.7\n", + "En 80.3\n", + "Math 78.3\n", "dtype: float64" ] }, - "execution_count": 19, + "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.mean(axis = 0)" + "df.mean(axis=0)" ] }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "a 101.333333\n", - "b 62.333333\n", - "c 92.333333\n", - "d 54.666667\n", - "e 89.666667\n", - "f 119.333333\n", - "h 57.666667\n", - "i 44.000000\n", - "j 66.000000\n", - "k 32.333333\n", + "a 84.000000\n", + "b 49.000000\n", + "c 75.000000\n", + "d 40.000000\n", + "e 105.000000\n", + "f 75.000000\n", + "h 78.333333\n", + "i 99.333333\n", + "j 116.333333\n", + "k 55.666667\n", "dtype: float64" ] }, - "execution_count": 20, + "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "df.mean(axis = 1)" + "df.mean(axis=1)" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -623,7 +620,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.3" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/2-pandas-\347\264\242\345\274\225.ipynb" "b/Day76-90/code/2-pandas-\347\264\242\345\274\225.ipynb" index ddbde0ae5bd30888fb4d542ac391c6bea89e8ca1..98c1704a55e4b859e0acab107b952edcd499cae7 100644 --- "a/Day76-90/code/2-pandas-\347\264\242\345\274\225.ipynb" +++ "b/Day76-90/code/2-pandas-\347\264\242\345\274\225.ipynb" @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -10,88 +10,14 @@ "\n", "import pandas as pd\n", "\n", - "from pandas import Series,DataFrame" + "from pandas import Series, DataFrame" ] }, { "cell_type": "code", - "execution_count": 3, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "11 111\n", - "12 113\n", - "13 103\n", - "14 147\n", - "15 63\n", - "16 11\n", - "17 130\n", - "18 38\n", - "19 17\n", - "20 32\n", - "21 112\n", - "22 75\n", - "23 68\n", - "24 124\n", - "25 138\n", - "26 56\n", - "27 1\n", - "28 88\n", - "29 113\n", - "30 63\n", - "31 42\n", - "32 65\n", - "33 104\n", - "34 105\n", - "35 0\n", - "36 95\n", - "37 119\n", - "38 86\n", - "39 124\n", - " ... \n", - "80 127\n", - "81 139\n", - "82 110\n", - "83 65\n", - "84 127\n", - "85 108\n", - "86 33\n", - "87 91\n", - "88 134\n", - "89 65\n", - "90 110\n", - "91 144\n", - "92 40\n", - "93 3\n", - "94 3\n", - "95 59\n", - "96 97\n", - "97 64\n", - "98 126\n", - "99 94\n", - "100 20\n", - "101 107\n", - "102 59\n", - "103 146\n", - "104 83\n", - "105 59\n", - "106 25\n", - "107 0\n", - "108 78\n", - "109 93\n", - "Name: Python, Length: 100, dtype: int16" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s = Series(np.random.randint(0,150,size = 100),index = np.arange(10,110),dtype=np.int16,name = 'Python')\n", "s" @@ -99,107 +25,27 @@ }, { "cell_type": "code", - "execution_count": 4, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "ename": "KeyError", - "evalue": "0", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;31m# 索引操作\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0ms\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 866\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 867\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 868\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 869\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 870\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_value\u001b[1;34m(self, series, key)\u001b[0m\n\u001b[0;32m 4373\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4374\u001b[0m return self._engine.get_value(s, k,\n\u001b[1;32m-> 4375\u001b[1;33m tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[0;32m 4376\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4377\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m0\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mholds_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_boolean\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.Int64HashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.Int64HashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;31mKeyError\u001b[0m: 0" - ] - } - ], - "source": [ - "# 索引操作\n", - "s[0]" - ] - }, - { - "cell_type": "code", - "execution_count": 5, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "34" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "s[10]" ] }, { "cell_type": "code", - "execution_count": 6, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "20 32\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 6, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s[[10,20]]" ] }, { "cell_type": "code", - "execution_count": 7, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "20 32\n", - "21 112\n", - "22 75\n", - "23 68\n", - "24 124\n", - "25 138\n", - "26 56\n", - "27 1\n", - "28 88\n", - "29 113\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 7, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 切片操作\n", "s[10:20]" @@ -207,164 +53,27 @@ }, { "cell_type": "code", - "execution_count": 8, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "12 113\n", - "14 147\n", - "16 11\n", - "18 38\n", - "20 32\n", - "22 75\n", - "24 124\n", - "26 56\n", - "28 88\n", - "30 63\n", - "32 65\n", - "34 105\n", - "36 95\n", - "38 86\n", - "40 6\n", - "42 57\n", - "44 72\n", - "46 43\n", - "48 87\n", - "50 83\n", - "52 99\n", - "54 132\n", - "56 17\n", - "58 116\n", - "60 33\n", - "62 51\n", - "64 80\n", - "66 121\n", - "68 81\n", - "70 0\n", - "72 50\n", - "74 31\n", - "76 114\n", - "78 60\n", - "80 127\n", - "82 110\n", - "84 127\n", - "86 33\n", - "88 134\n", - "90 110\n", - "92 40\n", - "94 3\n", - "96 97\n", - "98 126\n", - "100 20\n", - "102 59\n", - "104 83\n", - "106 25\n", - "108 78\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s[::2]" ] }, { "cell_type": "code", - "execution_count": 9, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "109 93\n", - "107 0\n", - "105 59\n", - "103 146\n", - "101 107\n", - "99 94\n", - "97 64\n", - "95 59\n", - "93 3\n", - "91 144\n", - "89 65\n", - "87 91\n", - "85 108\n", - "83 65\n", - "81 139\n", - "79 14\n", - "77 96\n", - "75 76\n", - "73 29\n", - "71 68\n", - "69 4\n", - "67 57\n", - "65 58\n", - "63 106\n", - "61 42\n", - "59 135\n", - "57 56\n", - "55 12\n", - "53 135\n", - "51 74\n", - "49 129\n", - "47 110\n", - "45 1\n", - "43 90\n", - "41 120\n", - "39 124\n", - "37 119\n", - "35 0\n", - "33 104\n", - "31 42\n", - "29 113\n", - "27 1\n", - "25 138\n", - "23 68\n", - "21 112\n", - "19 17\n", - "17 130\n", - "15 63\n", - "13 103\n", - "11 111\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 9, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s[::-2]" ] }, { "cell_type": "code", - "execution_count": 10, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "34" - ] - }, - "execution_count": 10, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# 可以使用pandas为开发者提供方法，去进行检索\n", "s.loc[10]" @@ -372,249 +81,56 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "20 32\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 11, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "s.loc[[10,20]]" ] }, { "cell_type": "code", - "execution_count": 12, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "11 111\n", - "12 113\n", - "13 103\n", - "14 147\n", - "15 63\n", - "16 11\n", - "17 130\n", - "18 38\n", - "19 17\n", - "20 32\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 12, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s.loc[10:20]" ] }, { "cell_type": "code", - "execution_count": 13, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "12 113\n", - "14 147\n", - "16 11\n", - "18 38\n", - "20 32\n", - "22 75\n", - "24 124\n", - "26 56\n", - "28 88\n", - "30 63\n", - "32 65\n", - "34 105\n", - "36 95\n", - "38 86\n", - "40 6\n", - "42 57\n", - "44 72\n", - "46 43\n", - "48 87\n", - "50 83\n", - "52 99\n", - "54 132\n", - "56 17\n", - "58 116\n", - "60 33\n", - "62 51\n", - "64 80\n", - "66 121\n", - "68 81\n", - "70 0\n", - "72 50\n", - "74 31\n", - "76 114\n", - "78 60\n", - "80 127\n", - "82 110\n", - "84 127\n", - "86 33\n", - "88 134\n", - "90 110\n", - "92 40\n", - "94 3\n", - "96 97\n", - "98 126\n", - "100 20\n", - "102 59\n", - "104 83\n", - "106 25\n", - "108 78\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 13, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s.loc[::2]" ] }, { "cell_type": "code", - "execution_count": 14, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "109 93\n", - "107 0\n", - "105 59\n", - "103 146\n", - "101 107\n", - "99 94\n", - "97 64\n", - "95 59\n", - "93 3\n", - "91 144\n", - "89 65\n", - "87 91\n", - "85 108\n", - "83 65\n", - "81 139\n", - "79 14\n", - "77 96\n", - "75 76\n", - "73 29\n", - "71 68\n", - "69 4\n", - "67 57\n", - "65 58\n", - "63 106\n", - "61 42\n", - "59 135\n", - "57 56\n", - "55 12\n", - "53 135\n", - "51 74\n", - "49 129\n", - "47 110\n", - "45 1\n", - "43 90\n", - "41 120\n", - "39 124\n", - "37 119\n", - "35 0\n", - "33 104\n", - "31 42\n", - "29 113\n", - "27 1\n", - "25 138\n", - "23 68\n", - "21 112\n", - "19 17\n", - "17 130\n", - "15 63\n", - "13 103\n", - "11 111\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 14, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s.loc[::-2]" ] }, { "cell_type": "code", - "execution_count": 16, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "Int64Index([ 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22,\n", - " 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35,\n", - " 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48,\n", - " 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61,\n", - " 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74,\n", - " 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87,\n", - " 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100,\n", - " 101, 102, 103, 104, 105, 106, 107, 108, 109],\n", - " dtype='int64')" - ] - }, - "execution_count": 16, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "s.index" ] }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "34" - ] - }, - "execution_count": 15, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# iloc 索引从0开始，数字化自然索引\n", "s.iloc[0]" @@ -622,257 +138,36 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "20 32\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 17, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "s.iloc[[0,10]]" ] }, { "cell_type": "code", - "execution_count": 18, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "10 34\n", - "11 111\n", - "12 113\n", - "13 103\n", - "14 147\n", - "15 63\n", - "16 11\n", - "17 130\n", - "18 38\n", - "19 17\n", - "20 32\n", - "21 112\n", - "22 75\n", - "23 68\n", - "24 124\n", - "25 138\n", - "26 56\n", - "27 1\n", - "28 88\n", - "29 113\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s.iloc[0:20]" ] }, { "cell_type": "code", - "execution_count": 20, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "109 93\n", - "107 0\n", - "105 59\n", - "103 146\n", - "101 107\n", - "99 94\n", - "97 64\n", - "95 59\n", - "93 3\n", - "91 144\n", - "89 65\n", - "87 91\n", - "85 108\n", - "83 65\n", - "81 139\n", - "79 14\n", - "77 96\n", - "75 76\n", - "73 29\n", - "71 68\n", - "69 4\n", - "67 57\n", - "65 58\n", - "63 106\n", - "61 42\n", - "59 135\n", - "57 56\n", - "55 12\n", - "53 135\n", - "51 74\n", - "49 129\n", - "47 110\n", - "45 1\n", - "43 90\n", - "41 120\n", - "39 124\n", - "37 119\n", - "35 0\n", - "33 104\n", - "31 42\n", - "29 113\n", - "27 1\n", - "25 138\n", - "23 68\n", - "21 112\n", - "19 17\n", - "17 130\n", - "15 63\n", - "13 103\n", - "11 111\n", - "Name: Python, dtype: int16" - ] - }, - "execution_count": 20, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "s.iloc[::-2]" ] }, { "cell_type": "code", - "execution_count": 21, - "metadata": { - "collapsed": true - }, - "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", - " \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", - "
PythonEnMath
A1035698
B13565135
C1379146
D4724145
E899716
F6426109
H4846111
I164997
J122126100
K6013662
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "B 135 65 135\n", - "C 13 79 146\n", - "D 47 24 145\n", - "E 89 97 16\n", - "F 64 26 109\n", - "H 48 46 111\n", - "I 16 49 97\n", - "J 122 126 100\n", - "K 60 136 62" - ] - }, - "execution_count": 21, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# DataFrame是二维，索引大同小异，\n", "df = DataFrame(data = np.random.randint(0,150,size= (10,3)),index=list('ABCDEFHIJK'),columns=['Python','En','Math'])\n", @@ -882,1177 +177,172 @@ }, { "cell_type": "code", - "execution_count": 22, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "ename": "KeyError", - "evalue": "'A'", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2656\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2657\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;31mKeyError\u001b[0m: 'A'", - "\nDuring handling of the above exception, another exception occurred:\n", - "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'A'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 2925\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnlevels\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2926\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_multilevel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2927\u001b[1;33m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2928\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2929\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mindexer\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2657\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2659\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2660\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2661\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msize\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;31mKeyError\u001b[0m: 'A'" - ] - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df['A']" ] }, { "cell_type": "code", - "execution_count": 23, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "A 103\n", - "B 135\n", - "C 13\n", - "D 47\n", - "E 89\n", - "F 64\n", - "H 48\n", - "I 16\n", - "J 122\n", - "K 60\n", - "Name: Python, dtype: int32" - ] - }, - "execution_count": 23, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df['Python']" ] }, { "cell_type": "code", - "execution_count": 24, - "metadata": { - "collapsed": true - }, - "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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEn
A10356
B13565
C1379
D4724
E8997
F6426
H4846
I1649
J122126
K60136
\n", - "
" - ], - "text/plain": [ - " Python En\n", - "A 103 56\n", - "B 135 65\n", - "C 13 79\n", - "D 47 24\n", - "E 89 97\n", - "F 64 26\n", - "H 48 46\n", - "I 16 49\n", - "J 122 126\n", - "K 60 136" - ] - }, - "execution_count": 24, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df[['Python','En']]" ] }, { "cell_type": "code", - "execution_count": 25, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMath
\n", - "
" - ], - "text/plain": [ - "Empty DataFrame\n", - "Columns: [Python, En, Math]\n", - "Index: []" - ] - }, - "execution_count": 25, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df['Python':'Math']" ] }, { "cell_type": "code", - "execution_count": 26, - "metadata": { - "collapsed": true - }, - "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", - "
PythonEnMath
A1035698
B13565135
C1379146
D4724145
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "B 135 65 135\n", - "C 13 79 146\n", - "D 47 24 145" - ] - }, - "execution_count": 26, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df['A':'D']" ] }, { "cell_type": "code", - "execution_count": 27, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "ename": "KeyError", - "evalue": "'Python'", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2656\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2657\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;31mKeyError\u001b[0m: 'Python'", - "\nDuring handling of the above exception, another exception occurred:\n", - "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Python'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1498\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1499\u001b[0m \u001b[0mmaybe_callable\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1500\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmaybe_callable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1501\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1502\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_is_scalar_access\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_getitem_axis\u001b[1;34m(self, key, axis)\u001b[0m\n\u001b[0;32m 1911\u001b[0m \u001b[1;31m# fall thru to straight lookup\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1912\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_validate_key\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1913\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_get_label\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1914\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1915\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_get_label\u001b[1;34m(self, label, axis)\u001b[0m\n\u001b[0;32m 139\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mIndexingError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'no slices here, handle elsewhere'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 140\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 141\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_xs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 142\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 143\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_get_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36mxs\u001b[1;34m(self, key, axis, level, drop_level)\u001b[0m\n\u001b[0;32m 3583\u001b[0m drop_level=drop_level)\n\u001b[0;32m 3584\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3585\u001b[1;33m \u001b[0mloc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3586\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3587\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexes\\base.py\u001b[0m in \u001b[0;36mget_loc\u001b[1;34m(self, key, method, tolerance)\u001b[0m\n\u001b[0;32m 2657\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2658\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2659\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2660\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2661\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m \u001b[1;32mor\u001b[0m \u001b[0mindexer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msize\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;32mpandas\\_libs\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[1;34m()\u001b[0m\n", - "\u001b[1;31mKeyError\u001b[0m: 'Python'" - ] - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.loc['Python']" ] }, { "cell_type": "code", - "execution_count": 28, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 103\n", - "En 56\n", - "Math 98\n", - "Name: A, dtype: int32" - ] - }, - "execution_count": 28, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.loc['A']" ] }, { "cell_type": "code", - "execution_count": 29, + "execution_count": null, "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", - "
PythonEnMath
A1035698
H4846111
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "H 48 46 111" - ] - }, - "execution_count": 29, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.loc[['A','H']]" ] }, { "cell_type": "code", - "execution_count": 30, + "execution_count": null, "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", - " \n", - "
PythonEnMath
A1035698
B13565135
C1379146
D4724145
E899716
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "B 135 65 135\n", - "C 13 79 146\n", - "D 47 24 145\n", - "E 89 97 16" - ] - }, - "execution_count": 30, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.loc['A':'E']" ] }, { "cell_type": "code", - "execution_count": 31, + "execution_count": null, "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", - " \n", - "
PythonEnMath
A1035698
C1379146
E899716
H4846111
J122126100
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "C 13 79 146\n", - "E 89 97 16\n", - "H 48 46 111\n", - "J 122 126 100" - ] - }, - "execution_count": 31, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.loc[::2]" ] }, { "cell_type": "code", - "execution_count": 32, - "metadata": { - "collapsed": true - }, - "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", - " \n", - "
PythonEnMath
K6013662
I164997
F6426109
D4724145
B13565135
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "K 60 136 62\n", - "I 16 49 97\n", - "F 64 26 109\n", - "D 47 24 145\n", - "B 135 65 135" - ] - }, - "execution_count": 32, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.loc[::-2]" ] }, { "cell_type": "code", - "execution_count": 33, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "ename": "TypeError", - "evalue": "Cannot index by location index with a non-integer key", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0miloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'A'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1498\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1499\u001b[0m \u001b[0mmaybe_callable\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1500\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmaybe_callable\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 1501\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1502\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_is_scalar_access\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32md:\\python36\\lib\\site-packages\\pandas\\core\\indexing.py\u001b[0m in \u001b[0;36m_getitem_axis\u001b[1;34m(self, key, axis)\u001b[0m\n\u001b[0;32m 2224\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2225\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_integer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2226\u001b[1;33m raise TypeError(\"Cannot index by location index with a \"\n\u001b[0m\u001b[0;32m 2227\u001b[0m \"non-integer key\")\n\u001b[0;32m 2228\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mTypeError\u001b[0m: Cannot index by location index with a non-integer key" - ] - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.iloc['A']" ] }, { "cell_type": "code", - "execution_count": 34, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 103\n", - "En 56\n", - "Math 98\n", - "Name: A, dtype: int32" - ] - }, - "execution_count": 34, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.iloc[0]" ] }, { "cell_type": "code", - "execution_count": 35, + "execution_count": null, "metadata": { "scrolled": true }, - "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", - "
PythonEnMath
A1035698
F6426109
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "F 64 26 109" - ] - }, - "execution_count": 35, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.iloc[[0,5]]" ] }, { "cell_type": "code", - "execution_count": 36, - "metadata": { - "collapsed": true - }, - "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", - " \n", - "
PythonEnMath
A1035698
B13565135
C1379146
D4724145
E899716
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "B 135 65 135\n", - "C 13 79 146\n", - "D 47 24 145\n", - "E 89 97 16" - ] - }, - "execution_count": 36, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.iloc[0:5]" ] }, { "cell_type": "code", - "execution_count": 38, + "execution_count": null, "metadata": { "scrolled": true }, - "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", - " \n", - "
PythonEnMath
K6013662
I164997
F6426109
D4724145
B13565135
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "K 60 136 62\n", - "I 16 49 97\n", - "F 64 26 109\n", - "D 47 24 145\n", - "B 135 65 135" - ] - }, - "execution_count": 38, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.iloc[::-2]" ] }, { "cell_type": "code", - "execution_count": 39, + "execution_count": null, "metadata": { "scrolled": true }, - "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", - " \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", - "
PythonEnMath
A1035698
B13565135
C1379146
D4724145
E899716
F6426109
H4846111
I164997
J122126100
K6013662
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "A 103 56 98\n", - "B 135 65 135\n", - "C 13 79 146\n", - "D 47 24 145\n", - "E 89 97 16\n", - "F 64 26 109\n", - "H 48 46 111\n", - "I 16 49 97\n", - "J 122 126 100\n", - "K 60 136 62" - ] - }, - "execution_count": 39, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df" ] }, { "cell_type": "code", - "execution_count": 40, + "execution_count": null, "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", - "
EnMath
A5698
C79146
E9716
H46111
J126100
\n", - "
" - ], - "text/plain": [ - " En Math\n", - "A 56 98\n", - "C 79 146\n", - "E 97 16\n", - "H 46 111\n", - "J 126 100" - ] - }, - "execution_count": 40, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.iloc[::2,1:]" ] @@ -2074,7 +364,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256.ipynb" "b/Day76-90/code/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256.ipynb" index dde9ec651078ec3ce2f605925eee9f3c19b3ed01..2c6fb401848582e3e812a13f5de0243d08deddb9 100644 --- "a/Day76-90/code/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256.ipynb" +++ "b/Day76-90/code/3-pandas\346\225\260\346\215\256\346\270\205\346\264\227\344\271\213\347\251\272\346\225\260\346\215\256.ipynb" @@ -2,7 +2,7 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -15,633 +15,21 @@ }, { "cell_type": "code", - "execution_count": 2, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
1001221052857
101741291611426
102971211222965
103141731201471
1041261328611617
1058534212166
10614265112483
10713614112286113
1081537124110102
1096330446958
110593811310916
1115518758126
1125397763745
1134214810797143
114701386968134
115471361132294
1163113762028
117148741344124
1181028113812832
11927111137022
1202893121684
12113643259719
12211170123858
12396103147868
12410104663149
1257759710831
12688614511655
12733741065046
12874282610076
1297618101126133
..................
170144124779282
1713698484380
17251143683474
17314911718141120
1748139146112122
17511510164629
17610714045148
17765436810918
1783110011049123
1792946695790
18014686182246
18171504090140
1824100147116110
1835587937834
18451091248782
185101181395051
18632127136124
187941613813149
1886510112312886
18943941029132
190681359428125
1913060982715
1928916101354
193104139972917
194529419991
195191021354140
19658100708264
19784971297613
19813115744114
199793795128116
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122 10 5 28 57\n", - "101 74 129 16 114 26\n", - "102 97 121 122 29 65\n", - "103 141 73 120 147 1\n", - "104 126 132 86 116 17\n", - "105 85 3 42 121 66\n", - "106 142 65 1 124 83\n", - "107 136 141 122 86 113\n", - "108 15 37 124 110 102\n", - "109 63 30 44 69 58\n", - "110 59 38 113 109 16\n", - "111 5 51 87 58 126\n", - "112 53 97 76 37 45\n", - "113 42 148 107 97 143\n", - "114 70 138 69 68 134\n", - "115 47 136 113 22 94\n", - "116 31 137 6 20 28\n", - "117 148 74 134 4 124\n", - "118 102 81 138 128 32\n", - "119 27 111 13 70 22\n", - "120 28 93 121 68 4\n", - "121 136 43 25 97 19\n", - "122 111 70 12 38 58\n", - "123 96 103 147 86 8\n", - "124 10 10 46 63 149\n", - "125 7 75 97 108 31\n", - "126 88 6 145 116 55\n", - "127 33 74 106 50 46\n", - "128 74 28 26 100 76\n", - "129 76 18 101 126 133\n", - ".. ... ... ... ... ...\n", - "170 144 124 77 92 82\n", - "171 36 98 48 43 80\n", - "172 51 143 68 34 74\n", - "173 149 117 18 141 120\n", - "174 8 139 146 112 122\n", - "175 115 101 64 62 9\n", - "176 10 7 140 45 148\n", - "177 65 43 68 109 18\n", - "178 31 100 110 49 123\n", - "179 29 46 69 57 90\n", - "180 146 86 18 22 46\n", - "181 71 50 40 90 140\n", - "182 4 100 147 116 110\n", - "183 55 87 93 78 34\n", - "184 5 109 124 87 82\n", - "185 10 118 139 50 51\n", - "186 32 12 71 36 124\n", - "187 94 16 138 13 149\n", - "188 65 101 123 128 86\n", - "189 43 94 10 29 132\n", - "190 68 135 94 28 125\n", - "191 30 60 98 27 15\n", - "192 89 16 10 135 4\n", - "193 104 139 97 29 17\n", - "194 5 29 41 99 91\n", - "195 19 102 135 41 40\n", - "196 58 100 70 82 64\n", - "197 84 97 129 76 13\n", - "198 131 15 7 44 114\n", - "199 79 37 95 128 116\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 2, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df = DataFrame(np.random.randint(0,150,size = (100,5)),index = np.arange(100,200),columns=['Python','En','Math','Physic','Chem'])\n", - "df" + "df.loc[100, 'En'] = None" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python False\n", - "En False\n", - "Math False\n", - "Physic False\n", - "Chem False\n", - "dtype: bool" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "# 判断DataFrame是否存在空数据\n", "df.isnull().any()" @@ -649,54 +37,18 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python True\n", - "En True\n", - "Math True\n", - "Physic True\n", - "Chem True\n", - "dtype: bool" - ] - }, - "execution_count": 6, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.notnull().all()" ] }, { "cell_type": "code", - "execution_count": 12, - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "500" - ] - }, - "execution_count": 12, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "100*5" - ] - }, - { - "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -714,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -733,666 +85,38 @@ }, { "cell_type": "code", - "execution_count": 16, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122.0 10.0 5.0 28.0 57.0\n", - "101 NaN 129.0 16.0 114.0 26.0\n", - "102 97.0 121.0 122.0 29.0 65.0\n", - "103 141.0 73.0 120.0 147.0 1.0\n", - "104 126.0 NaN 86.0 116.0 17.0\n", - "105 85.0 NaN 42.0 121.0 66.0\n", - "106 142.0 65.0 1.0 124.0 83.0\n", - "107 136.0 141.0 NaN 86.0 113.0\n", - "108 15.0 37.0 124.0 110.0 102.0\n", - "109 63.0 30.0 NaN 69.0 58.0\n", - "110 NaN NaN 113.0 109.0 16.0\n", - "111 5.0 51.0 87.0 58.0 126.0\n", - "112 53.0 97.0 76.0 37.0 45.0\n", - "113 42.0 148.0 NaN 97.0 NaN\n", - "114 70.0 138.0 69.0 68.0 134.0\n", - "115 NaN 136.0 113.0 22.0 94.0\n", - "116 31.0 137.0 6.0 20.0 28.0\n", - "117 148.0 74.0 134.0 4.0 124.0\n", - "118 102.0 81.0 138.0 128.0 32.0\n", - "119 27.0 111.0 13.0 NaN 22.0\n", - "120 28.0 93.0 121.0 NaN 4.0\n", - "121 136.0 NaN 25.0 97.0 19.0\n", - "122 111.0 70.0 12.0 38.0 58.0\n", - "123 NaN 103.0 147.0 86.0 8.0\n", - "124 10.0 10.0 46.0 63.0 149.0\n", - "125 7.0 75.0 97.0 108.0 31.0\n", - "126 88.0 6.0 NaN NaN 55.0\n", - "127 33.0 74.0 106.0 50.0 46.0\n", - "128 74.0 28.0 26.0 100.0 76.0\n", - "129 76.0 18.0 101.0 NaN NaN\n", - ".. ... ... ... ... ...\n", - "170 144.0 124.0 77.0 92.0 82.0\n", - "171 36.0 98.0 NaN 43.0 80.0\n", - "172 51.0 NaN 68.0 34.0 74.0\n", - "173 149.0 NaN 18.0 141.0 NaN\n", - "174 8.0 139.0 146.0 112.0 NaN\n", - "175 115.0 NaN 64.0 62.0 9.0\n", - "176 NaN 7.0 140.0 45.0 148.0\n", - "177 NaN 43.0 68.0 109.0 18.0\n", - "178 31.0 100.0 NaN 49.0 123.0\n", - "179 29.0 46.0 69.0 57.0 90.0\n", - "180 146.0 86.0 18.0 22.0 46.0\n", - "181 71.0 50.0 40.0 NaN 140.0\n", - "182 4.0 100.0 147.0 116.0 110.0\n", - "183 55.0 87.0 93.0 NaN 34.0\n", - "184 NaN 109.0 124.0 87.0 82.0\n", - "185 10.0 118.0 139.0 50.0 51.0\n", - "186 32.0 12.0 71.0 36.0 NaN\n", - "187 94.0 NaN 138.0 13.0 149.0\n", - "188 65.0 101.0 123.0 128.0 86.0\n", - "189 43.0 94.0 NaN 29.0 132.0\n", - "190 68.0 135.0 94.0 28.0 125.0\n", - "191 30.0 60.0 98.0 NaN 15.0\n", - "192 89.0 16.0 10.0 135.0 4.0\n", - "193 104.0 139.0 97.0 29.0 17.0\n", - "194 5.0 29.0 41.0 99.0 NaN\n", - "195 19.0 102.0 135.0 41.0 40.0\n", - "196 58.0 NaN 70.0 82.0 64.0\n", - "197 NaN 97.0 129.0 76.0 13.0\n", - "198 131.0 15.0 NaN 44.0 114.0\n", - "199 79.0 NaN 95.0 128.0 NaN\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 16, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df" ] }, { "cell_type": "code", - "execution_count": 18, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python True\n", - "En True\n", - "Math True\n", - "Physic True\n", - "Chem True\n", - "dtype: bool" - ] - }, - "execution_count": 18, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.isnull().any()" ] }, { "cell_type": "code", - "execution_count": 22, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 14\n", - "En 14\n", - "Math 15\n", - "Physic 11\n", - "Chem 13\n", - "dtype: int64" - ] - }, - "execution_count": 22, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", - "execution_count": 23, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -1401,658 +125,28 @@ }, { "cell_type": "code", - "execution_count": 24, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 14\n", - "En 14\n", - "Math 15\n", - "Physic 11\n", - "Chem 13\n", - "dtype: int64" - ] - }, - "execution_count": 24, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df2.isnull().sum()" ] }, { "cell_type": "code", - "execution_count": 26, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101100.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0100.086.0116.017.0
10585.0100.042.0121.066.0
106142.065.01.0124.083.0
107136.0141.0100.086.0113.0
10815.037.0124.0110.0102.0
10963.030.0100.069.058.0
110100.0100.0113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0100.097.0100.0
11470.0138.069.068.0134.0
115100.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0100.022.0
12028.093.0121.0100.04.0
121136.0100.025.097.019.0
122111.070.012.038.058.0
123100.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0100.0100.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0100.0100.0
..................
170144.0124.077.092.082.0
17136.098.0100.043.080.0
17251.0100.068.034.074.0
173149.0100.018.0141.0100.0
1748.0139.0146.0112.0100.0
175115.0100.064.062.09.0
176100.07.0140.045.0148.0
177100.043.068.0109.018.0
17831.0100.0100.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0100.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.0100.034.0
184100.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0100.0
18794.0100.0138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0100.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.0100.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0100.0
19519.0102.0135.041.040.0
19658.0100.070.082.064.0
197100.097.0129.076.013.0
198131.015.0100.044.0114.0
19979.0100.095.0128.0100.0
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122.0 10.0 5.0 28.0 57.0\n", - "101 100.0 129.0 16.0 114.0 26.0\n", - "102 97.0 121.0 122.0 29.0 65.0\n", - "103 141.0 73.0 120.0 147.0 1.0\n", - "104 126.0 100.0 86.0 116.0 17.0\n", - "105 85.0 100.0 42.0 121.0 66.0\n", - "106 142.0 65.0 1.0 124.0 83.0\n", - "107 136.0 141.0 100.0 86.0 113.0\n", - "108 15.0 37.0 124.0 110.0 102.0\n", - "109 63.0 30.0 100.0 69.0 58.0\n", - "110 100.0 100.0 113.0 109.0 16.0\n", - "111 5.0 51.0 87.0 58.0 126.0\n", - "112 53.0 97.0 76.0 37.0 45.0\n", - "113 42.0 148.0 100.0 97.0 100.0\n", - "114 70.0 138.0 69.0 68.0 134.0\n", - "115 100.0 136.0 113.0 22.0 94.0\n", - "116 31.0 137.0 6.0 20.0 28.0\n", - "117 148.0 74.0 134.0 4.0 124.0\n", - "118 102.0 81.0 138.0 128.0 32.0\n", - "119 27.0 111.0 13.0 100.0 22.0\n", - "120 28.0 93.0 121.0 100.0 4.0\n", - "121 136.0 100.0 25.0 97.0 19.0\n", - "122 111.0 70.0 12.0 38.0 58.0\n", - "123 100.0 103.0 147.0 86.0 8.0\n", - "124 10.0 10.0 46.0 63.0 149.0\n", - "125 7.0 75.0 97.0 108.0 31.0\n", - "126 88.0 6.0 100.0 100.0 55.0\n", - "127 33.0 74.0 106.0 50.0 46.0\n", - "128 74.0 28.0 26.0 100.0 76.0\n", - "129 76.0 18.0 101.0 100.0 100.0\n", - ".. ... ... ... ... ...\n", - "170 144.0 124.0 77.0 92.0 82.0\n", - "171 36.0 98.0 100.0 43.0 80.0\n", - "172 51.0 100.0 68.0 34.0 74.0\n", - "173 149.0 100.0 18.0 141.0 100.0\n", - "174 8.0 139.0 146.0 112.0 100.0\n", - "175 115.0 100.0 64.0 62.0 9.0\n", - "176 100.0 7.0 140.0 45.0 148.0\n", - "177 100.0 43.0 68.0 109.0 18.0\n", - "178 31.0 100.0 100.0 49.0 123.0\n", - "179 29.0 46.0 69.0 57.0 90.0\n", - "180 146.0 86.0 18.0 22.0 46.0\n", - "181 71.0 50.0 40.0 100.0 140.0\n", - "182 4.0 100.0 147.0 116.0 110.0\n", - "183 55.0 87.0 93.0 100.0 34.0\n", - "184 100.0 109.0 124.0 87.0 82.0\n", - "185 10.0 118.0 139.0 50.0 51.0\n", - "186 32.0 12.0 71.0 36.0 100.0\n", - "187 94.0 100.0 138.0 13.0 149.0\n", - "188 65.0 101.0 123.0 128.0 86.0\n", - "189 43.0 94.0 100.0 29.0 132.0\n", - "190 68.0 135.0 94.0 28.0 125.0\n", - "191 30.0 60.0 98.0 100.0 15.0\n", - "192 89.0 16.0 10.0 135.0 4.0\n", - "193 104.0 139.0 97.0 29.0 17.0\n", - "194 5.0 29.0 41.0 99.0 100.0\n", - "195 19.0 102.0 135.0 41.0 40.0\n", - "196 58.0 100.0 70.0 82.0 64.0\n", - "197 100.0 97.0 129.0 76.0 13.0\n", - "198 131.0 15.0 100.0 44.0 114.0\n", - "199 79.0 100.0 95.0 128.0 100.0\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 26, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 固定值填充\n", - "df2.fillna(value=100)" + "df.fillna(value=100)" ] }, { "cell_type": "code", - "execution_count": 27, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 71.662791\n", - "En 75.627907\n", - "Math 77.929412\n", - "Physic 73.471910\n", - "Chem 69.080460\n", - "dtype: float64" - ] - }, - "execution_count": 27, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df2.mean()" ] @@ -2066,605 +160,9 @@ }, { "cell_type": "code", - "execution_count": 29, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
1001221052857
101711291611426
102971211222965
103141731201471
104126758611617
10585754212166
10614265112483
1071361417786113
1081537124110102
1096330776958
110717511310916
1115518758126
1125397763745
11342148779769
114701386968134
115711361132294
1163113762028
117148741344124
1181028113812832
11927111137322
1202893121734
12113675259719
12211170123858
12371103147868
12410104663149
1257759710831
126886777355
12733741065046
12874282610076
12976181017369
..................
170144124779282
1713698774380
1725175683474
173149751814169
174813914611269
1751157564629
17671714045148
17771436810918
178311007749123
1792946695790
18014686182246
18171504073140
1824100147116110
1835587937334
184711091248782
185101181395051
1863212713669
187947513813149
1886510112312886
18943947729132
190681359428125
1913060987315
1928916101354
193104139972917
194529419969
195191021354140
1965875708264
19771971297613
198131157744114
19979759512869
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122 10 5 28 57\n", - "101 71 129 16 114 26\n", - "102 97 121 122 29 65\n", - "103 141 73 120 147 1\n", - "104 126 75 86 116 17\n", - "105 85 75 42 121 66\n", - "106 142 65 1 124 83\n", - "107 136 141 77 86 113\n", - "108 15 37 124 110 102\n", - "109 63 30 77 69 58\n", - "110 71 75 113 109 16\n", - "111 5 51 87 58 126\n", - "112 53 97 76 37 45\n", - "113 42 148 77 97 69\n", - "114 70 138 69 68 134\n", - "115 71 136 113 22 94\n", - "116 31 137 6 20 28\n", - "117 148 74 134 4 124\n", - "118 102 81 138 128 32\n", - "119 27 111 13 73 22\n", - "120 28 93 121 73 4\n", - "121 136 75 25 97 19\n", - "122 111 70 12 38 58\n", - "123 71 103 147 86 8\n", - "124 10 10 46 63 149\n", - "125 7 75 97 108 31\n", - "126 88 6 77 73 55\n", - "127 33 74 106 50 46\n", - "128 74 28 26 100 76\n", - "129 76 18 101 73 69\n", - ".. ... ... ... ... ...\n", - "170 144 124 77 92 82\n", - "171 36 98 77 43 80\n", - "172 51 75 68 34 74\n", - "173 149 75 18 141 69\n", - "174 8 139 146 112 69\n", - "175 115 75 64 62 9\n", - "176 71 7 140 45 148\n", - "177 71 43 68 109 18\n", - "178 31 100 77 49 123\n", - "179 29 46 69 57 90\n", - "180 146 86 18 22 46\n", - "181 71 50 40 73 140\n", - "182 4 100 147 116 110\n", - "183 55 87 93 73 34\n", - "184 71 109 124 87 82\n", - "185 10 118 139 50 51\n", - "186 32 12 71 36 69\n", - "187 94 75 138 13 149\n", - "188 65 101 123 128 86\n", - "189 43 94 77 29 132\n", - "190 68 135 94 28 125\n", - "191 30 60 98 73 15\n", - "192 89 16 10 135 4\n", - "193 104 139 97 29 17\n", - "194 5 29 41 99 69\n", - "195 19 102 135 41 40\n", - "196 58 75 70 82 64\n", - "197 71 97 129 76 13\n", - "198 131 15 77 44 114\n", - "199 79 75 95 128 69\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 29, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 均值\n", "df3 = df2.fillna(value=df2.mean())\n", @@ -2673,22 +171,11 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "data": { - "text/plain": [ - "array([ 6, 18, 1, 17, 19, 5, 17, 16, 13, 3])" - ] - }, - "execution_count": 31, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "nd = np.random.randint(0,20,size = 10)\n", "nd" @@ -2696,20 +183,9 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "array([ 1, 3, 5, 6, 13, 16, 17, 17, 18, 19])" - ] - }, - "execution_count": 33, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "nd.sort()\n", "nd" @@ -2717,645 +193,27 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "14.5" - ] - }, - "execution_count": 34, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "(13 + 16)/2" ] }, { "cell_type": "code", - "execution_count": 35, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "14.5" - ] - }, - "execution_count": 35, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "np.median(nd)" ] }, { "cell_type": "code", - "execution_count": 36, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
100122.010.05.028.057.0
10168.0129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.082.586.0116.017.0
10585.082.542.0121.066.0
106142.065.01.0124.083.0
107136.0141.086.086.0113.0
10815.037.0124.0110.0102.0
10963.030.086.069.058.0
11068.082.5113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.086.097.065.0
11470.0138.069.068.0134.0
11568.0136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.069.022.0
12028.093.0121.069.04.0
121136.082.525.097.019.0
122111.070.012.038.058.0
12368.0103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.086.069.055.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.069.065.0
..................
170144.0124.077.092.082.0
17136.098.086.043.080.0
17251.082.568.034.074.0
173149.082.518.0141.065.0
1748.0139.0146.0112.065.0
175115.082.564.062.09.0
17668.07.0140.045.0148.0
17768.043.068.0109.018.0
17831.0100.086.049.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.069.0140.0
1824.0100.0147.0116.0110.0
18355.087.093.069.034.0
18468.0109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.065.0
18794.082.5138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.086.029.0132.0
19068.0135.094.028.0125.0
19130.060.098.069.015.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.065.0
19519.0102.0135.041.040.0
19658.082.570.082.064.0
19768.097.0129.076.013.0
198131.015.086.044.0114.0
19979.082.595.0128.065.0
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122.0 10.0 5.0 28.0 57.0\n", - "101 68.0 129.0 16.0 114.0 26.0\n", - "102 97.0 121.0 122.0 29.0 65.0\n", - "103 141.0 73.0 120.0 147.0 1.0\n", - "104 126.0 82.5 86.0 116.0 17.0\n", - "105 85.0 82.5 42.0 121.0 66.0\n", - "106 142.0 65.0 1.0 124.0 83.0\n", - "107 136.0 141.0 86.0 86.0 113.0\n", - "108 15.0 37.0 124.0 110.0 102.0\n", - "109 63.0 30.0 86.0 69.0 58.0\n", - "110 68.0 82.5 113.0 109.0 16.0\n", - "111 5.0 51.0 87.0 58.0 126.0\n", - "112 53.0 97.0 76.0 37.0 45.0\n", - "113 42.0 148.0 86.0 97.0 65.0\n", - "114 70.0 138.0 69.0 68.0 134.0\n", - "115 68.0 136.0 113.0 22.0 94.0\n", - "116 31.0 137.0 6.0 20.0 28.0\n", - "117 148.0 74.0 134.0 4.0 124.0\n", - "118 102.0 81.0 138.0 128.0 32.0\n", - "119 27.0 111.0 13.0 69.0 22.0\n", - "120 28.0 93.0 121.0 69.0 4.0\n", - "121 136.0 82.5 25.0 97.0 19.0\n", - "122 111.0 70.0 12.0 38.0 58.0\n", - "123 68.0 103.0 147.0 86.0 8.0\n", - "124 10.0 10.0 46.0 63.0 149.0\n", - "125 7.0 75.0 97.0 108.0 31.0\n", - "126 88.0 6.0 86.0 69.0 55.0\n", - "127 33.0 74.0 106.0 50.0 46.0\n", - "128 74.0 28.0 26.0 100.0 76.0\n", - "129 76.0 18.0 101.0 69.0 65.0\n", - ".. ... ... ... ... ...\n", - "170 144.0 124.0 77.0 92.0 82.0\n", - "171 36.0 98.0 86.0 43.0 80.0\n", - "172 51.0 82.5 68.0 34.0 74.0\n", - "173 149.0 82.5 18.0 141.0 65.0\n", - "174 8.0 139.0 146.0 112.0 65.0\n", - "175 115.0 82.5 64.0 62.0 9.0\n", - "176 68.0 7.0 140.0 45.0 148.0\n", - "177 68.0 43.0 68.0 109.0 18.0\n", - "178 31.0 100.0 86.0 49.0 123.0\n", - "179 29.0 46.0 69.0 57.0 90.0\n", - "180 146.0 86.0 18.0 22.0 46.0\n", - "181 71.0 50.0 40.0 69.0 140.0\n", - "182 4.0 100.0 147.0 116.0 110.0\n", - "183 55.0 87.0 93.0 69.0 34.0\n", - "184 68.0 109.0 124.0 87.0 82.0\n", - "185 10.0 118.0 139.0 50.0 51.0\n", - "186 32.0 12.0 71.0 36.0 65.0\n", - "187 94.0 82.5 138.0 13.0 149.0\n", - "188 65.0 101.0 123.0 128.0 86.0\n", - "189 43.0 94.0 86.0 29.0 132.0\n", - "190 68.0 135.0 94.0 28.0 125.0\n", - "191 30.0 60.0 98.0 69.0 15.0\n", - "192 89.0 16.0 10.0 135.0 4.0\n", - "193 104.0 139.0 97.0 29.0 17.0\n", - "194 5.0 29.0 41.0 99.0 65.0\n", - "195 19.0 102.0 135.0 41.0 40.0\n", - "196 58.0 82.5 70.0 82.0 64.0\n", - "197 68.0 97.0 129.0 76.0 13.0\n", - "198 131.0 15.0 86.0 44.0 114.0\n", - "199 79.0 82.5 95.0 128.0 65.0\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 36, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 中位数填充\n", "df2.median()\n", @@ -3365,605 +223,9 @@ }, { "cell_type": "code", - "execution_count": 37, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
100122.010.05.028.057.0
101NaN129.016.0114.026.0
10297.0121.0122.029.065.0
103141.073.0120.0147.01.0
104126.0NaN86.0116.017.0
10585.0NaN42.0121.066.0
106142.065.01.0124.083.0
107136.0141.0NaN86.0113.0
10815.037.0124.0110.0102.0
10963.030.0NaN69.058.0
110NaNNaN113.0109.016.0
1115.051.087.058.0126.0
11253.097.076.037.045.0
11342.0148.0NaN97.0NaN
11470.0138.069.068.0134.0
115NaN136.0113.022.094.0
11631.0137.06.020.028.0
117148.074.0134.04.0124.0
118102.081.0138.0128.032.0
11927.0111.013.0NaN22.0
12028.093.0121.0NaN4.0
121136.0NaN25.097.019.0
122111.070.012.038.058.0
123NaN103.0147.086.08.0
12410.010.046.063.0149.0
1257.075.097.0108.031.0
12688.06.0NaNNaN55.0
12733.074.0106.050.046.0
12874.028.026.0100.076.0
12976.018.0101.0NaNNaN
..................
170144.0124.077.092.082.0
17136.098.0NaN43.080.0
17251.0NaN68.034.074.0
173149.0NaN18.0141.0NaN
1748.0139.0146.0112.0NaN
175115.0NaN64.062.09.0
176NaN7.0140.045.0148.0
177NaN43.068.0109.018.0
17831.0100.0NaN49.0123.0
17929.046.069.057.090.0
180146.086.018.022.046.0
18171.050.040.0NaN140.0
1824.0100.0147.0116.0110.0
18355.087.093.0NaN34.0
184NaN109.0124.087.082.0
18510.0118.0139.050.051.0
18632.012.071.036.0NaN
18794.0NaN138.013.0149.0
18865.0101.0123.0128.086.0
18943.094.0NaN29.0132.0
19068.0135.094.028.0125.0
19130.060.098.0NaN15.0
19289.016.010.0135.04.0
193104.0139.097.029.017.0
1945.029.041.099.0NaN
19519.0102.0135.041.040.0
19658.0NaN70.082.064.0
197NaN97.0129.076.013.0
198131.015.0NaN44.0114.0
19979.0NaN95.0128.0NaN
\n", - "

100 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 122.0 10.0 5.0 28.0 57.0\n", - "101 NaN 129.0 16.0 114.0 26.0\n", - "102 97.0 121.0 122.0 29.0 65.0\n", - "103 141.0 73.0 120.0 147.0 1.0\n", - "104 126.0 NaN 86.0 116.0 17.0\n", - "105 85.0 NaN 42.0 121.0 66.0\n", - "106 142.0 65.0 1.0 124.0 83.0\n", - "107 136.0 141.0 NaN 86.0 113.0\n", - "108 15.0 37.0 124.0 110.0 102.0\n", - "109 63.0 30.0 NaN 69.0 58.0\n", - "110 NaN NaN 113.0 109.0 16.0\n", - "111 5.0 51.0 87.0 58.0 126.0\n", - "112 53.0 97.0 76.0 37.0 45.0\n", - "113 42.0 148.0 NaN 97.0 NaN\n", - "114 70.0 138.0 69.0 68.0 134.0\n", - "115 NaN 136.0 113.0 22.0 94.0\n", - "116 31.0 137.0 6.0 20.0 28.0\n", - "117 148.0 74.0 134.0 4.0 124.0\n", - "118 102.0 81.0 138.0 128.0 32.0\n", - "119 27.0 111.0 13.0 NaN 22.0\n", - "120 28.0 93.0 121.0 NaN 4.0\n", - "121 136.0 NaN 25.0 97.0 19.0\n", - "122 111.0 70.0 12.0 38.0 58.0\n", - "123 NaN 103.0 147.0 86.0 8.0\n", - "124 10.0 10.0 46.0 63.0 149.0\n", - "125 7.0 75.0 97.0 108.0 31.0\n", - "126 88.0 6.0 NaN NaN 55.0\n", - "127 33.0 74.0 106.0 50.0 46.0\n", - "128 74.0 28.0 26.0 100.0 76.0\n", - "129 76.0 18.0 101.0 NaN NaN\n", - ".. ... ... ... ... ...\n", - "170 144.0 124.0 77.0 92.0 82.0\n", - "171 36.0 98.0 NaN 43.0 80.0\n", - "172 51.0 NaN 68.0 34.0 74.0\n", - "173 149.0 NaN 18.0 141.0 NaN\n", - "174 8.0 139.0 146.0 112.0 NaN\n", - "175 115.0 NaN 64.0 62.0 9.0\n", - "176 NaN 7.0 140.0 45.0 148.0\n", - "177 NaN 43.0 68.0 109.0 18.0\n", - "178 31.0 100.0 NaN 49.0 123.0\n", - "179 29.0 46.0 69.0 57.0 90.0\n", - "180 146.0 86.0 18.0 22.0 46.0\n", - "181 71.0 50.0 40.0 NaN 140.0\n", - "182 4.0 100.0 147.0 116.0 110.0\n", - "183 55.0 87.0 93.0 NaN 34.0\n", - "184 NaN 109.0 124.0 87.0 82.0\n", - "185 10.0 118.0 139.0 50.0 51.0\n", - "186 32.0 12.0 71.0 36.0 NaN\n", - "187 94.0 NaN 138.0 13.0 149.0\n", - "188 65.0 101.0 123.0 128.0 86.0\n", - "189 43.0 94.0 NaN 29.0 132.0\n", - "190 68.0 135.0 94.0 28.0 125.0\n", - "191 30.0 60.0 98.0 NaN 15.0\n", - "192 89.0 16.0 10.0 135.0 4.0\n", - "193 104.0 139.0 97.0 29.0 17.0\n", - "194 5.0 29.0 41.0 99.0 NaN\n", - "195 19.0 102.0 135.0 41.0 40.0\n", - "196 58.0 NaN 70.0 82.0 64.0\n", - "197 NaN 97.0 129.0 76.0 13.0\n", - "198 131.0 15.0 NaN 44.0 114.0\n", - "199 79.0 NaN 95.0 128.0 NaN\n", - "\n", - "[100 rows x 5 columns]" - ] - }, - "execution_count": 37, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 众数填充，数量最多的那个数\n", "df2" @@ -3971,605 +233,9 @@ }, { "cell_type": "code", - "execution_count": 42, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
100828999101125
101431109325
10256103566190
1034710014713899
1043846827544
10518111223126
106562610614139
10731377567144
10835471026063
109861265788149
11019140303533
11176151133
11231549111969
1136437502321
11472571381521
115551201043225
11696248922146
11763086489
11828461258274
119853970132111
12010990447439
121214810311465
12211029998057
123109888113571
12470103134121121
12551921172743
1266929759105
12765905214822
12841291711913
1292410010728139
..................
207012777241631
2071936192822
20721166154861
207347214011234
2074261081233233
207546130135124113
207633181363820
20771071112954119
207884551293787
20799550451984
2080124746514053
20812635149145127
20821921101389
20838410131714
208428741056889
20852393849788
2086861332612513
208721124401155
20882015353137
208996123123564
20902243927860
20911631176058
20926518131334
209369491094058
2094128461082111
20952659854149
209611147909266
209759773140104
2098102675119
209997197714348
\n", - "

2000 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 82 89 99 101 125\n", - "101 4 31 109 32 5\n", - "102 56 103 56 61 90\n", - "103 47 100 147 138 99\n", - "104 38 46 82 75 44\n", - "105 18 11 122 3 126\n", - "106 56 26 106 14 139\n", - "107 3 137 75 67 144\n", - "108 35 47 102 60 63\n", - "109 86 126 57 88 149\n", - "110 19 140 30 35 33\n", - "111 76 1 5 11 33\n", - "112 31 54 91 119 69\n", - "113 64 37 50 23 21\n", - "114 72 57 138 15 21\n", - "115 55 120 104 32 25\n", - "116 96 24 89 22 146\n", - "117 63 0 8 64 89\n", - "118 28 46 125 82 74\n", - "119 85 39 70 132 111\n", - "120 109 90 44 74 39\n", - "121 2 148 103 114 65\n", - "122 110 29 99 80 57\n", - "123 109 88 81 135 71\n", - "124 70 103 134 121 121\n", - "125 51 92 117 27 43\n", - "126 6 92 97 59 105\n", - "127 65 90 52 148 22\n", - "128 4 129 17 119 13\n", - "129 24 100 107 28 139\n", - "... ... ... ... ... ...\n", - "2070 127 77 24 16 31\n", - "2071 93 61 9 28 22\n", - "2072 116 61 54 8 61\n", - "2073 4 72 140 112 34\n", - "2074 26 108 123 32 33\n", - "2075 46 130 135 124 113\n", - "2076 33 18 136 38 20\n", - "2077 107 11 129 54 119\n", - "2078 84 55 129 37 87\n", - "2079 95 50 45 19 84\n", - "2080 124 74 65 140 53\n", - "2081 26 35 149 145 127\n", - "2082 19 21 101 3 89\n", - "2083 84 10 131 71 4\n", - "2084 28 74 105 68 89\n", - "2085 23 93 84 97 88\n", - "2086 86 133 26 125 13\n", - "2087 21 124 40 115 5\n", - "2088 20 15 35 31 37\n", - "2089 96 123 123 5 64\n", - "2090 22 43 92 78 60\n", - "2091 16 31 17 60 58\n", - "2092 65 18 13 13 34\n", - "2093 69 49 109 40 58\n", - "2094 128 46 10 82 111\n", - "2095 26 59 8 54 149\n", - "2096 111 47 90 92 66\n", - "2097 5 97 73 140 104\n", - "2098 102 6 7 5 119\n", - "2099 97 19 77 143 48\n", - "\n", - "[2000 rows x 5 columns]" - ] - }, - "execution_count": 42, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df = DataFrame(np.random.randint(0,150,size = (2000,5)),index = np.arange(100,2100),columns=['Python','En','Math','Physic','Chem'])\n", "df" @@ -4577,7 +243,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -4595,258 +261,36 @@ }, { "cell_type": "code", - "execution_count": 44, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 190\n", - "En 200\n", - "Math 194\n", - "Physic 189\n", - "Chem 181\n", - "dtype: int64" - ] - }, - "execution_count": 44, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", - "execution_count": 45, - "metadata": { - "collapsed": true - }, - "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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 82.0 89.0 99.0 101.0 125.0\n", - "101 4.0 31.0 109.0 32.0 5.0\n", - "102 56.0 103.0 56.0 NaN 90.0\n", - "103 47.0 100.0 147.0 138.0 99.0\n", - "104 38.0 46.0 NaN 75.0 44.0" - ] - }, - "execution_count": 45, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.head()" ] }, { "cell_type": "code", - "execution_count": 46, - "metadata": { - "collapsed": true - }, - "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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMathPhysicChem
209526.059.08.054.0149.0
2096NaN47.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.0NaN48.0
\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "2095 26.0 59.0 8.0 54.0 149.0\n", - "2096 NaN 47.0 90.0 92.0 66.0\n", - "2097 5.0 97.0 73.0 140.0 104.0\n", - "2098 102.0 6.0 7.0 5.0 119.0\n", - "2099 97.0 19.0 77.0 NaN 48.0" - ] - }, - "execution_count": 46, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.tail()" ] }, { "cell_type": "code", - "execution_count": 48, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "array([ 82., 4., 56., 47., 38., 18., 3., 35., 86., 19., 76.,\n", - " 31., 64., 72., 55., 96., 63., 28., 85., 109., 2., 110.,\n", - " 70., 51., 6., 65., 24., 48., 44., 11., 114., 129., 87.,\n", - " 108., 125., nan, 140., 132., 91., 34., 54., 30., 12., 98.,\n", - " 142., 79., 13., 77., 40., 139., 39., 81., 112., 36., 22.,\n", - " 5., 120., 17., 127., 119., 59., 146., 89., 103., 8., 97.,\n", - " 130., 73., 83., 122., 95., 100., 41., 21., 136., 80., 101.,\n", - " 50., 27., 71., 16., 141., 126., 102., 145., 15., 52., 94.,\n", - " 10., 33., 137., 9., 128., 88., 26., 84., 93., 1., 7.,\n", - " 131., 107., 148., 0., 105., 66., 32., 115., 118., 58., 53.,\n", - " 29., 42., 57., 62., 25., 60., 69., 133., 68., 20., 106.,\n", - " 147., 78., 90., 124., 149., 92., 75., 117., 143., 99., 37.,\n", - " 123., 45., 61., 121., 135., 138., 116., 14., 104., 74., 46.,\n", - " 111., 23., 43., 49., 144., 113., 67., 134.])" - ] - }, - "execution_count": 48, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "# 去重之后的数据\n", "df['Python'].unique()" @@ -4854,166 +298,18 @@ }, { "cell_type": "code", - "execution_count": 49, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "143.0 20\n", - "136.0 20\n", - "102.0 19\n", - "105.0 19\n", - "26.0 19\n", - "69.0 19\n", - "31.0 18\n", - "148.0 18\n", - "75.0 18\n", - "139.0 18\n", - "1.0 18\n", - "35.0 17\n", - "140.0 17\n", - "110.0 17\n", - "125.0 17\n", - "146.0 17\n", - "141.0 17\n", - "64.0 16\n", - "30.0 16\n", - "79.0 16\n", - "73.0 16\n", - "40.0 16\n", - "10.0 15\n", - "6.0 15\n", - "65.0 15\n", - "81.0 15\n", - "28.0 15\n", - "48.0 15\n", - "92.0 15\n", - "103.0 15\n", - " ..\n", - "104.0 9\n", - "12.0 9\n", - "116.0 9\n", - "13.0 9\n", - "59.0 9\n", - "93.0 9\n", - "124.0 9\n", - "85.0 8\n", - "135.0 8\n", - "131.0 8\n", - "68.0 8\n", - "66.0 8\n", - "62.0 8\n", - "120.0 8\n", - "17.0 8\n", - "25.0 8\n", - "145.0 7\n", - "58.0 7\n", - "134.0 7\n", - "113.0 7\n", - "123.0 7\n", - "39.0 7\n", - "34.0 7\n", - "43.0 7\n", - "74.0 6\n", - "144.0 6\n", - "132.0 6\n", - "142.0 5\n", - "67.0 5\n", - "49.0 5\n", - "Name: Python, Length: 150, dtype: int64" - ] - }, - "execution_count": 49, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df['Python'].value_counts()" ] }, { "cell_type": "code", - "execution_count": 53, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "8.0 21\n", - "96.0 19\n", - "118.0 19\n", - "24.0 19\n", - "43.0 19\n", - "27.0 19\n", - "19.0 19\n", - "41.0 18\n", - "0.0 18\n", - "3.0 18\n", - "52.0 18\n", - "4.0 17\n", - "137.0 17\n", - "1.0 17\n", - "101.0 17\n", - "51.0 17\n", - "39.0 17\n", - "100.0 17\n", - "127.0 17\n", - "115.0 16\n", - "33.0 16\n", - "112.0 16\n", - "92.0 16\n", - "126.0 16\n", - "133.0 15\n", - "32.0 15\n", - "89.0 15\n", - "95.0 15\n", - "36.0 15\n", - "93.0 15\n", - " ..\n", - "12.0 9\n", - "28.0 9\n", - "106.0 9\n", - "45.0 9\n", - "80.0 9\n", - "84.0 9\n", - "58.0 9\n", - "79.0 9\n", - "71.0 9\n", - "83.0 9\n", - "142.0 9\n", - "7.0 9\n", - "6.0 8\n", - "61.0 8\n", - "149.0 8\n", - "34.0 8\n", - "20.0 8\n", - "38.0 8\n", - "130.0 8\n", - "104.0 7\n", - "120.0 7\n", - "56.0 7\n", - "146.0 7\n", - "98.0 7\n", - "134.0 6\n", - "123.0 6\n", - "35.0 6\n", - "87.0 5\n", - "42.0 5\n", - "119.0 4\n", - "Name: En, Length: 150, dtype: int64" - ] - }, - "execution_count": 53, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "en = df['En'].value_counts()\n", "en" @@ -5021,44 +317,20 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "8.0" - ] - }, - "execution_count": 54, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "en.index[0]" ] }, { "cell_type": "code", - "execution_count": 52, + "execution_count": null, "metadata": { "scrolled": true }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Python 75.0\n", - "En 74.0\n", - "Math 77.5\n", - "Physic 73.0\n", - "Chem 72.0\n", - "dtype: float64 \n" - ] - } - ], + "outputs": [], "source": [ "s = df.median()\n", "print(s,type(s))" @@ -5066,7 +338,7 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": null, "metadata": {}, "outputs": [], "source": [ @@ -5077,25 +349,9 @@ }, { "cell_type": "code", - "execution_count": 57, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 143.0\n", - "En 8.0\n", - "Math 80.0\n", - "Physic 31.0\n", - "Chem 125.0\n", - "dtype: float64" - ] - }, - "execution_count": 57, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "s = Series(zhongshu,index = df.columns)\n", "s" @@ -5103,605 +359,9 @@ }, { "cell_type": "code", - "execution_count": 60, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - " \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", - "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.031.090.0
10347.0100.0147.0138.099.0
10438.046.080.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.080.088.0149.0
11019.0140.080.035.033.0
11176.08.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.031.0146.0
11763.08.08.064.089.0
11828.08.0125.082.074.0
11985.039.070.0132.0111.0
120109.090.080.074.039.0
1212.08.0103.0114.065.0
122110.029.099.080.057.0
123109.088.081.0135.071.0
12470.0103.0134.0121.0121.0
12551.092.0117.031.043.0
1266.092.097.059.0105.0
12765.090.052.0148.022.0
1284.0129.017.0119.013.0
12924.0100.0107.028.0139.0
..................
2070127.077.024.016.0125.0
207193.061.09.028.022.0
2072116.061.054.08.061.0
20734.072.0140.031.034.0
2074143.0108.0123.032.033.0
207546.08.0135.0124.0113.0
2076143.018.0136.038.0125.0
2077143.011.0129.054.0119.0
207884.055.0129.037.087.0
207995.050.045.019.084.0
2080124.074.065.031.053.0
208126.035.0149.0145.0127.0
208219.021.0101.03.089.0
208384.08.0131.071.04.0
208428.074.0105.068.089.0
208523.093.084.097.088.0
208686.0133.026.0125.013.0
208721.0124.040.031.05.0
208820.015.035.031.037.0
208996.0123.0123.05.064.0
209022.043.092.078.060.0
209116.031.017.060.058.0
209265.018.013.013.034.0
209369.049.0109.040.058.0
2094128.046.010.082.0111.0
209526.059.08.054.0149.0
2096143.047.090.092.066.0
20975.097.073.0140.0104.0
2098102.06.07.05.0119.0
209997.019.077.031.048.0
\n", - "

2000 rows × 5 columns

\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 82.0 89.0 99.0 101.0 125.0\n", - "101 4.0 31.0 109.0 32.0 5.0\n", - "102 56.0 103.0 56.0 31.0 90.0\n", - "103 47.0 100.0 147.0 138.0 99.0\n", - "104 38.0 46.0 80.0 75.0 44.0\n", - "105 18.0 11.0 122.0 3.0 126.0\n", - "106 56.0 26.0 106.0 14.0 139.0\n", - "107 3.0 137.0 75.0 67.0 144.0\n", - "108 35.0 47.0 102.0 60.0 63.0\n", - "109 86.0 126.0 80.0 88.0 149.0\n", - "110 19.0 140.0 80.0 35.0 33.0\n", - "111 76.0 8.0 5.0 11.0 33.0\n", - "112 31.0 54.0 91.0 119.0 69.0\n", - "113 64.0 37.0 50.0 23.0 21.0\n", - "114 72.0 57.0 138.0 15.0 21.0\n", - "115 55.0 120.0 104.0 32.0 25.0\n", - "116 96.0 24.0 89.0 31.0 146.0\n", - "117 63.0 8.0 8.0 64.0 89.0\n", - "118 28.0 8.0 125.0 82.0 74.0\n", - "119 85.0 39.0 70.0 132.0 111.0\n", - "120 109.0 90.0 80.0 74.0 39.0\n", - "121 2.0 8.0 103.0 114.0 65.0\n", - "122 110.0 29.0 99.0 80.0 57.0\n", - "123 109.0 88.0 81.0 135.0 71.0\n", - "124 70.0 103.0 134.0 121.0 121.0\n", - "125 51.0 92.0 117.0 31.0 43.0\n", - "126 6.0 92.0 97.0 59.0 105.0\n", - "127 65.0 90.0 52.0 148.0 22.0\n", - "128 4.0 129.0 17.0 119.0 13.0\n", - "129 24.0 100.0 107.0 28.0 139.0\n", - "... ... ... ... ... ...\n", - "2070 127.0 77.0 24.0 16.0 125.0\n", - "2071 93.0 61.0 9.0 28.0 22.0\n", - "2072 116.0 61.0 54.0 8.0 61.0\n", - "2073 4.0 72.0 140.0 31.0 34.0\n", - "2074 143.0 108.0 123.0 32.0 33.0\n", - "2075 46.0 8.0 135.0 124.0 113.0\n", - "2076 143.0 18.0 136.0 38.0 125.0\n", - "2077 143.0 11.0 129.0 54.0 119.0\n", - "2078 84.0 55.0 129.0 37.0 87.0\n", - "2079 95.0 50.0 45.0 19.0 84.0\n", - "2080 124.0 74.0 65.0 31.0 53.0\n", - "2081 26.0 35.0 149.0 145.0 127.0\n", - "2082 19.0 21.0 101.0 3.0 89.0\n", - "2083 84.0 8.0 131.0 71.0 4.0\n", - "2084 28.0 74.0 105.0 68.0 89.0\n", - "2085 23.0 93.0 84.0 97.0 88.0\n", - "2086 86.0 133.0 26.0 125.0 13.0\n", - "2087 21.0 124.0 40.0 31.0 5.0\n", - "2088 20.0 15.0 35.0 31.0 37.0\n", - "2089 96.0 123.0 123.0 5.0 64.0\n", - "2090 22.0 43.0 92.0 78.0 60.0\n", - "2091 16.0 31.0 17.0 60.0 58.0\n", - "2092 65.0 18.0 13.0 13.0 34.0\n", - "2093 69.0 49.0 109.0 40.0 58.0\n", - "2094 128.0 46.0 10.0 82.0 111.0\n", - "2095 26.0 59.0 8.0 54.0 149.0\n", - "2096 143.0 47.0 90.0 92.0 66.0\n", - "2097 5.0 97.0 73.0 140.0 104.0\n", - "2098 102.0 6.0 7.0 5.0 119.0\n", - "2099 97.0 19.0 77.0 31.0 48.0\n", - "\n", - "[2000 rows x 5 columns]" - ] - }, - "execution_count": 60, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df2 = df.fillna(s)\n", "df2" @@ -5709,285 +369,27 @@ }, { "cell_type": "code", - "execution_count": 61, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 0\n", - "En 0\n", - "Math 0\n", - "Physic 0\n", - "Chem 0\n", - "dtype: int64" - ] - }, - "execution_count": 61, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df2.isnull().sum()" ] }, { "cell_type": "code", - "execution_count": 62, - "metadata": { - "collapsed": true - }, - "outputs": [ - { - "data": { - "text/plain": [ - "Python 190\n", - "En 200\n", - "Math 194\n", - "Physic 189\n", - "Chem 181\n", - "dtype: int64" - ] - }, - "execution_count": 62, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "df.isnull().sum()" ] }, { "cell_type": "code", - "execution_count": 65, + "execution_count": null, "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", - " \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", - " \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", - " \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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.0NaN90.0
10347.0100.0147.0138.099.0
10438.046.0NaN75.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.0NaN88.0149.0
11019.0140.0NaN35.033.0
11176.0NaN5.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0NaN146.0
11763.0NaN8.064.089.0
11828.0NaN125.082.074.0
11985.039.070.0132.0111.0
\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 82.0 89.0 99.0 101.0 125.0\n", - "101 4.0 31.0 109.0 32.0 5.0\n", - "102 56.0 103.0 56.0 NaN 90.0\n", - "103 47.0 100.0 147.0 138.0 99.0\n", - "104 38.0 46.0 NaN 75.0 44.0\n", - "105 18.0 11.0 122.0 3.0 126.0\n", - "106 56.0 26.0 106.0 14.0 139.0\n", - "107 3.0 137.0 75.0 67.0 144.0\n", - "108 35.0 47.0 102.0 60.0 63.0\n", - "109 86.0 126.0 NaN 88.0 149.0\n", - "110 19.0 140.0 NaN 35.0 33.0\n", - "111 76.0 NaN 5.0 11.0 33.0\n", - "112 31.0 54.0 91.0 119.0 69.0\n", - "113 64.0 37.0 50.0 23.0 21.0\n", - "114 72.0 57.0 138.0 15.0 21.0\n", - "115 55.0 120.0 104.0 32.0 25.0\n", - "116 96.0 24.0 89.0 NaN 146.0\n", - "117 63.0 NaN 8.0 64.0 89.0\n", - "118 28.0 NaN 125.0 82.0 74.0\n", - "119 85.0 39.0 70.0 132.0 111.0" - ] - }, - "execution_count": 65, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "df3 = df.iloc[:20]\n", "df3" @@ -5995,233 +397,9 @@ }, { "cell_type": "code", - "execution_count": 70, - "metadata": { - "collapsed": true - }, - "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", - " \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", - " \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", - " \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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMathPhysicChem
10082.089.099.0101.0125.0
1014.031.0109.032.05.0
10256.0103.056.090.090.0
10347.0100.0147.0138.099.0
10438.046.075.075.044.0
10518.011.0122.03.0126.0
10656.026.0106.014.0139.0
1073.0137.075.067.0144.0
10835.047.0102.060.063.0
10986.0126.088.088.0149.0
11019.0140.035.035.033.0
11176.05.05.011.033.0
11231.054.091.0119.069.0
11364.037.050.023.021.0
11472.057.0138.015.021.0
11555.0120.0104.032.025.0
11696.024.089.0146.0146.0
11763.08.08.064.089.0
11828.0125.0125.082.074.0
11985.039.070.0132.0111.0
\n", - "
" - ], - "text/plain": [ - " Python En Math Physic Chem\n", - "100 82.0 89.0 99.0 101.0 125.0\n", - "101 4.0 31.0 109.0 32.0 5.0\n", - "102 56.0 103.0 56.0 90.0 90.0\n", - "103 47.0 100.0 147.0 138.0 99.0\n", - "104 38.0 46.0 75.0 75.0 44.0\n", - "105 18.0 11.0 122.0 3.0 126.0\n", - "106 56.0 26.0 106.0 14.0 139.0\n", - "107 3.0 137.0 75.0 67.0 144.0\n", - "108 35.0 47.0 102.0 60.0 63.0\n", - "109 86.0 126.0 88.0 88.0 149.0\n", - "110 19.0 140.0 35.0 35.0 33.0\n", - "111 76.0 5.0 5.0 11.0 33.0\n", - "112 31.0 54.0 91.0 119.0 69.0\n", - "113 64.0 37.0 50.0 23.0 21.0\n", - "114 72.0 57.0 138.0 15.0 21.0\n", - "115 55.0 120.0 104.0 32.0 25.0\n", - "116 96.0 24.0 89.0 146.0 146.0\n", - "117 63.0 8.0 8.0 64.0 89.0\n", - "118 28.0 125.0 125.0 82.0 74.0\n", - "119 85.0 39.0 70.0 132.0 111.0" - ] - }, - "execution_count": 70, - "metadata": {}, - "output_type": "execute_result" - } - ], + "execution_count": null, + "metadata": {}, + "outputs": [], "source": [ "'''method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None\n", " Method to use for filling holes in reindexed Series\n", @@ -6232,20 +410,9 @@ }, { "cell_type": "code", - "execution_count": 71, + "execution_count": null, "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "(2000, 5)" - ] - }, - "execution_count": 71, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ "#数据量足够大，空数据比较少，直接删除\n", "df.shape" @@ -6277,7 +444,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225.ipynb" "b/Day76-90/code/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225.ipynb" index 01f9dd637139844815f5e8fe2c58ddc461418ca9..d8e0d1ee9084e4b818e547d0c2eb48d301335d72 100644 --- "a/Day76-90/code/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225.ipynb" +++ "b/Day76-90/code/4-pandas\345\244\232\345\261\202\347\264\242\345\274\225.ipynb" @@ -82,95 +82,21 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 1, "metadata": { "scrolled": true }, "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", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
PythonEnMath
张三期中73525
期末373656
李四期中14981142
期末711380
王五期中1194103
期末2512183
\n", - "
" - ], - "text/plain": [ - " Python En Math\n", - "张三 期中 73 5 25\n", - " 期末 37 36 56\n", - "李四 期中 149 81 142\n", - " 期末 71 138 0\n", - "王五 期中 11 94 103\n", - " 期末 25 121 83" - ] - }, - "execution_count": 4, - "metadata": {}, - "output_type": "execute_result" + "ename": "NameError", + "evalue": "name 'DataFrame' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mDataFrame\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m150\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Python'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'En'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'Math'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mindex\u001b[0m \u001b[0;34m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mMultiIndex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_product\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'张三'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'李四'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'王五'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'期中'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'期末'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", + "\u001b[0;31mNameError\u001b[0m: name 'DataFrame' is not defined" + ] } ], "source": [ @@ -560,7 +486,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227.ipynb" "b/Day76-90/code/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227.ipynb" index 22e1c8e38f0fe0e7c8d6fb02b30836c845f77a31..4bcaad27c2d0841f35580bb30c254b0d580eb095 100644 --- "a/Day76-90/code/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227.ipynb" +++ "b/Day76-90/code/5-pandas\345\244\232\345\261\202\347\264\242\345\274\225\350\256\241\347\256\227.ipynb" @@ -992,7 +992,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220.ipynb" "b/Day76-90/code/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220.ipynb" index e128ee4a1c53f7cefc6dc3156bc8f68a2858f283..7df4f33a7af910d51f07f2f7ee5bd1fbf36adc8b 100644 --- "a/Day76-90/code/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220.ipynb" +++ "b/Day76-90/code/6-pandas\346\225\260\346\215\256\351\233\206\346\210\220.ipynb" @@ -1201,7 +1201,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge.ipynb" "b/Day76-90/code/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge.ipynb" index 8b2eefcef74a3bf1b678d1313e98d7303015e131..06fd9f690e58d7c15f7d600789c6e1230af4b21e 100644 --- "a/Day76-90/code/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge.ipynb" +++ "b/Day76-90/code/7-pandas\346\225\260\346\215\256\351\233\206\346\210\220merge.ipynb" @@ -1264,7 +1264,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4, diff --git "a/Day76-90/code/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234.ipynb" "b/Day76-90/code/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234.ipynb" index 7c16aff829f8955703c002534dbf4afe84a3c7ba..e9dddcc7ec29237094648b99c04a984bb9d28bd6 100644 --- "a/Day76-90/code/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234.ipynb" +++ "b/Day76-90/code/8-pandas\345\210\206\347\273\204\350\201\232\345\220\210\346\223\215\344\275\234.ipynb" @@ -869,7 +869,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.6.5" + "version": "3.7.7" } }, "nbformat": 4,