feat: 新增Vol13章节示例源码及样例数据

code/13/reshape_data.ipynb

@@ -0,0 +1,215 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  id  1992  1993  1994\n",
+      "0  a     1     3     5\n",
+      "1  b     2     4     6\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "wide = pd.DataFrame(\n",
+    "    {\n",
+    "        \"id\": [\"a\", \"b\"],\n",
+    "        \"1992\": [1, 2],\n",
+    "        \"1993\": [3, 4],\n",
+    "        \"1994\": [5, 6],\n",
+    "    }\n",
+    ")\n",
+    "print(wide)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  id  year  value\n",
+      "0  a  1992      1\n",
+      "1  b  1992      2\n",
+      "2  a  1993      3\n",
+      "3  b  1993      4\n",
+      "4  a  1994      5\n",
+      "5  b  1994      6\n"
+     ]
+    }
+   ],
+   "source": [
+    "melted = wide.melt(\n",
+    "    id_vars=[\"id\"],\n",
+    "    value_vars=[\"1992\", \"1993\", \"1994\"],\n",
+    "    var_name=\"year\",\n",
+    "    value_name=\"value\",\n",
+    ")\n",
+    "print(melted)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "year  1992  1993  1994\nid                    \na        1     3     5\nb        2     4     6",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th>year</th>\n      <th>1992</th>\n      <th>1993</th>\n      <th>1994</th>\n    </tr>\n    <tr>\n      <th>id</th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>a</th>\n      <td>1</td>\n      <td>3</td>\n      <td>5</td>\n    </tr>\n    <tr>\n      <th>b</th>\n      <td>2</td>\n      <td>4</td>\n      <td>6</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "melted.pivot(index=\"id\", columns=\"year\", values=\"value\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   platforms      apps  user_views\n",
+      "0    Windows     Weibo       77769\n",
+      "1    Windows        QQ       72028\n",
+      "2    Windows    Wechat       21587\n",
+      "3    Windows  Facebook       61832\n",
+      "4    Windows   Twitter       99428\n",
+      "5      MacOS     Weibo       40012\n",
+      "6      MacOS        QQ       38287\n",
+      "7      MacOS    Wechat       91048\n",
+      "8      MacOS  Facebook       45890\n",
+      "9      MacOS   Twitter       25002\n",
+      "10       iOS     Weibo       81961\n",
+      "11       iOS        QQ       91249\n",
+      "12       iOS    Wechat       83411\n",
+      "13       iOS  Facebook       94873\n",
+      "14       iOS   Twitter       42350\n",
+      "15   Android     Weibo        4867\n",
+      "16   Android        QQ       60387\n",
+      "17   Android    Wechat       22915\n",
+      "18   Android  Facebook       62127\n",
+      "19   Android   Twitter        8725\n",
+      "20       Web     Weibo       44557\n",
+      "21       Web        QQ       63616\n",
+      "22       Web    Wechat       23107\n",
+      "23       Web  Facebook       58033\n",
+      "24       Web   Twitter       70295\n"
+     ]
+    }
+   ],
+   "source": [
+    "import random\n",
+    "from itertools import product\n",
+    "\n",
+    "import pandas as pd\n",
+    "\n",
+    "random.seed(3.14)\n",
+    "\n",
+    "platforms = [\"Windows\", \"MacOS\", \"iOS\", \"Android\", \"Web\"]\n",
+    "apps = [\"Weibo\", \"QQ\", \"Wechat\", \"Facebook\", \"Twitter\"]\n",
+    "\n",
+    "data = pd.DataFrame(list(product(platforms, apps)), columns=[\"platforms\", \"apps\"])\n",
+    "data[\"user_views\"] = random.choices(range(1000, 100000), k=data.shape[0])\n",
+    "print(data)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "apps       Facebook     QQ  Twitter  Wechat  Weibo\nplatforms                                         \nAndroid       62127  60387     8725   22915   4867\nMacOS         45890  38287    25002   91048  40012\nWeb           58033  63616    70295   23107  44557\nWindows       61832  72028    99428   21587  77769\niOS           94873  91249    42350   83411  81961",
+      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th>apps</th>\n      <th>Facebook</th>\n      <th>QQ</th>\n      <th>Twitter</th>\n      <th>Wechat</th>\n      <th>Weibo</th>\n    </tr>\n    <tr>\n      <th>platforms</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Android</th>\n      <td>62127</td>\n      <td>60387</td>\n      <td>8725</td>\n      <td>22915</td>\n      <td>4867</td>\n    </tr>\n    <tr>\n      <th>MacOS</th>\n      <td>45890</td>\n      <td>38287</td>\n      <td>25002</td>\n      <td>91048</td>\n      <td>40012</td>\n    </tr>\n    <tr>\n      <th>Web</th>\n      <td>58033</td>\n      <td>63616</td>\n      <td>70295</td>\n      <td>23107</td>\n      <td>44557</td>\n    </tr>\n    <tr>\n      <th>Windows</th>\n      <td>61832</td>\n      <td>72028</td>\n      <td>99428</td>\n      <td>21587</td>\n      <td>77769</td>\n    </tr>\n    <tr>\n      <th>iOS</th>\n      <td>94873</td>\n      <td>91249</td>\n      <td>42350</td>\n      <td>83411</td>\n      <td>81961</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.pivot_table(\n",
+    "    index=\"platforms\",\n",
+    "    columns=\"apps\",\n",
+    "    values=\"user_views\",\n",
+    "    aggfunc=sum,\n",
+    "    fill_value=0,\n",
+    ")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}