{"id":3704,"date":"2022-03-18T12:22:20","date_gmt":"2022-03-18T04:22:20","guid":{"rendered":"https:\/\/egonlin.com\/?p=3704"},"modified":"2022-03-18T12:22:20","modified_gmt":"2022-03-18T04:22:20","slug":"%e7%ac%ac%e4%b8%80%e8%8a%82%ef%bc%9a%e6%95%b0%e6%8d%ae%e6%93%8d%e4%bd%9c","status":"publish","type":"post","link":"https:\/\/egonlin.com\/?p=3704","title":{"rendered":"\u7b2c\u4e00\u8282\uff1a\u6570\u636e\u64cd\u4f5c"},"content":{"rendered":"<p>\u672c\u7ae0\u5b66\u4e60\u5185\u5bb9\uff1a<\/p>\n<ul>\n<li>\u6570\u636e\u5bfc\u5165\u3001\u5b58\u50a8<\/li>\n<li>\u6570\u636e\u5904\u7406<\/li>\n<\/ul>\n<p>\u6570\u636e\u64cd\u4f5c\u6700\u91cd\u8981\u7684\u4e00\u6b65\u4e5f\u662f\u7b2c\u4e00\u6b65\u5c31\u662f\u6536\u96c6\u6570\u636e\uff0c\u800c\u6536\u96c6\u6570\u636e\u7684\u65b9\u5f0f\u6709\u5f88\u591a\u79cd\uff0c\u7b2c\u4e00\u79cd\u5c31\u662f\u6211\u4eec\u5df2\u7ecf\u5c06\u6570\u636e\u4e0b\u8f7d\u5230\u4e86\u672c\u5730\uff0c\u5728\u672c\u5730\u901a\u8fc7\u6587\u4ef6\u8fdb\u884c\u8bbf\u95ee\uff0c\u7b2c\u4e8c\u79cd\u5c31\u662f\u9700\u8981\u5230\u7f51\u7ad9\u7684API\u5904\u83b7\u53d6\u6570\u636e\u6216\u8005\u7f51\u9875\u4e0a\u722c\u53d6\u6570\u636e\uff0c\u8fd8\u6709\u4e00\u79cd\u53ef\u80fd\u5c31\u662f\u4f60\u7684\u516c\u53f8\u91cc\u9762\u6709\u81ea\u5df1\u7684\u6570\u636e\u5e93\uff0c\u76f4\u63a5\u8bbf\u95ee\u6570\u636e\u5e93\u91cc\u9762\u7684\u6570\u636e\u8fdb\u884c\u5206\u6790\u3002\u9700\u8981\u6ce8\u610f\u7684\u662f\u6211\u4eec\u4e0d\u4ec5\u9700\u8981\u5c06\u6570\u636e\u6536\u96c6\u8d77\u6765\u8fd8\u8981\u5c06\u4e0d\u540c\u683c\u5f0f\u7684\u6570\u636e\u8fdb\u884c\u6574\u7406\uff0c\u6700\u540e\u518d\u505a\u76f8\u5e94\u7684\u64cd\u4f5c\u3002<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_1.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_1.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h1>1\u3001\u6570\u636e\u5bfc\u5165\u3001\u5b58\u50a8<\/h1>\n<p>\u8bbf\u95ee\u6570\u636e\u662f\u6570\u636e\u5206\u6790\u7684\u6240\u5fc5\u987b\u7684\u7b2c\u4e00\u6b65\uff0c\u53ea\u6709\u8bbf\u95ee\u5230\u6570\u636e\u624d\u53ef\u4ee5\u5bf9\u6570\u636e\u8fdb\u884c\u5206\u6790\u3002<\/p>\n<h2>1.1\u3001\u6587\u672c\u683c\u5f0f<\/h2>\n<p>\u5e38\u7528pandas\u89e3\u6790\u51fd\u6570\uff1a<\/p>\n<p>pandas\u63d0\u4f9b\u4e86\u4e00\u4e9b\u7528\u4e8e\u5c06\u8868\u683c\u578b\u6570\u636e\u8bfb\u53d6\u4e3aDataFrame\u5bf9\u8c61\u7684\u51fd\u6570\u3002\u4ee5\u4e0b<\/p>\n<table>\n<thead>\n<tr>\n<th>\u51fd\u6570<\/th>\n<th style=\"text-align: center;\">\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>read_csv<\/td>\n<td style=\"text-align: center;\">\u4ece\u6587\u4ef6\u3001url\u6216\u8005\u6587\u4ef6\u578b\u5bf9\u8c61\u8bfb\u53d6\u5206\u5272\u597d\u7684\u6570\u636e\uff0c\u9017\u53f7\u662f\u9ed8\u8ba4\u5206\u9694\u7b26<\/td>\n<\/tr>\n<tr>\n<td>read_table<\/td>\n<td style=\"text-align: center;\">\u4ece\u6587\u4ef6\u3001url\u6216\u8005\u6587\u4ef6\u578b\u5bf9\u8c61\u8bfb\u53d6\u5206\u5272\u597d\u7684\u6570\u636e\uff0c\u5236\u8868\u7b26(&#8216;\\t&#8217;)\u662f\u9ed8\u8ba4\u5206\u9694\u7b26<\/td>\n<\/tr>\n<tr>\n<td>read_fwf<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6\u5b9a\u5bbd\u683c\u5f0f\u6570\u636e(\u65e0\u5206\u9694\u7b26)<\/td>\n<\/tr>\n<tr>\n<td>read_clipboard<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6\u526a\u8d34\u677f\u4e2d\u7684\u6570\u636e\uff0c\u53ef\u4ee5\u770b\u505aread_table\u7684\u526a\u8d34\u677f\u3002\u518d\u5c06\u7f51\u9875\u8f6c\u6362\u4e3a\u8868\u683c<\/td>\n<\/tr>\n<tr>\n<td>read_excel<\/td>\n<td style=\"text-align: center;\">\u4eceExcel\u7684XLS\u6216\u8005XLSX\u6587\u4ef6\u4e2d\u8bfb\u53d6\u8868\u683c\u6570\u636e<\/td>\n<\/tr>\n<tr>\n<td>read_hdf<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6pandas\u5199\u7684HDF5\u6587\u4ef6<\/td>\n<\/tr>\n<tr>\n<td>read_html<\/td>\n<td style=\"text-align: center;\">\u4eceHTML\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6240\u6709\u8868\u683c\u6570\u636e<\/td>\n<\/tr>\n<tr>\n<td>read_json<\/td>\n<td style=\"text-align: center;\">\u4ecejson\u5b57\u7b26\u4e32\u4e2d\u8bfb\u53d6\u6570\u636e<\/td>\n<\/tr>\n<tr>\n<td>read_pickle<\/td>\n<td style=\"text-align: center;\">\u4ecePython pickle\u683c\u5f0f\u4e2d\u5b58\u50a8\u7684\u4efb\u610f\u5bf9\u8c61<\/td>\n<\/tr>\n<tr>\n<td>read_msgpack<\/td>\n<td style=\"text-align: center;\">\u4e8c\u8fdb\u5236\u683c\u5f0f\u7f16\u7801\u7684pandas\u6570\u636e<\/td>\n<\/tr>\n<tr>\n<td>read_sas<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6\u5b58\u50a8\u4e8esas\u7cfb\u7edf\u81ea\u5b9a\u4e49\u5b58\u50a8\u683c\u5f0f\u7684SAS\u6570\u636e\u96c6<\/td>\n<\/tr>\n<tr>\n<td>read_stata<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6Stata\u6587\u4ef6\u683c\u5f0f\u7684\u6570\u636e\u96c6<\/td>\n<\/tr>\n<tr>\n<td>read_feather<\/td>\n<td style=\"text-align: center;\">\u8bfb\u53d6Feather\u4e8c\u8fdb\u5236\u6587\u4ef6\u683c\u5f0f<\/td>\n<\/tr>\n<tr>\n<td>read_sql<\/td>\n<td style=\"text-align: center;\">\u5c06SQL\u67e5\u8be2\u7684\u7ed3\u679c\uff08SQLAlchemy\uff09\u8bfb\u53d6\u4e3apandas\u7684DataFrame<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4e0a\u8868\u5bf9\u8fd9\u4e9b\u89e3\u6790\u51fd\u6570\u6709\u4e00\u4e2a\u7b80\u5355\u4e86\u89e3\uff0c\u5176\u4e2dread_csv\u548cread_table\u662f\u4ee5\u540e\u7528\u5f97\u6700\u591a\u7684\u4e24\u4e2a\u65b9\u6cd5\uff0c\u63a5\u4e0b\u6765\u6211\u4eec\u4e3b\u8981\u5c31\u8fd9\u4e24\u4e2a\u65b9\u6cd5\u6d4b\u8bd5\u3002 <\/p>\n<h3>1.1.1\u3001read_csv<\/h3>\n<p>csv\u6587\u4ef6\u5c31\u662f\u4e00\u4e2a\u4ee5\u9017\u53f7\u5206\u9694\u5b57\u6bb5\u7684\u7eaf\u6587\u672c\u6587\u4ef6\uff0c\u7528\u4e8e\u6d4b\u8bd5\u7684\u6587\u4ef6\u662f\u672c\u8eab\u662f\u4e00\u4e2aExcel\u6587\u4ef6\uff0c\u9700\u8981\u4fee\u6539\u4e00\u4e0b\u6269\u5c55\u540d\uff0c\u4f46\u662f\u7b80\u5355\u7684\u4fee\u6539\u540e\u7f00\u540d\u4e0d\u884c\uff0c\u8fd8\u9700\u8981\u5c06\u5b57\u7b26\u7f16\u7801\u6539\u53d8\u4e3a<code>utf-8<\/code>\uff0c\u56e0\u4e3a\u9ed8\u8ba4\u7684\u662f<code>ASCII<\/code>\uff0c\u5426\u5219\u662f\u4f1a\u62a5\u9519\u7684\u3002\u7136\u540e\u5c31\u53ef\u4ee5\u901a\u8fc7<code>read_csv<\/code>\u5c06\u5b83\u8bfb\u5165\u5230\u4e00\u4e2aDataFrame\uff1a<\/p>\n<pre><code class=\"language-python\">import pandas as pd\n\ndf = pd.read_csv(&quot;E:\/Test\/test3.csv&quot;)\ndf\n    name    age sex\n0   \u4f69\u5947  18  \u5973\n1   \u4e54\u6cbb  19  \u7537<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u6570\u636e\u5904\u7406.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u6570\u636e\u5904\u7406.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<div style='color:red'>\u6ce8\u610f:<\/div>\n<p>\u5230\u8fd9\u91cc\u53ef\u80fd\u5c31\u4f1a\u6709\u4e9b\u4eba\u6709\u7591\u95ee\u4e86\uff0c\u4e3a\u4ec0\u4e48\u6211\u7684\u6587\u4ef6\u8def\u5f84\u4e0d\u5bf9\u554a\uff0c\u90a3\u662f\u56e0\u4e3a\u5728\u6211\u4eec\u8fd9\u4e2a\u65b9\u6cd5\u5f53\u4e2d\u7684\u8def\u5f84\u5f53\u5b83\u5f80\u5de6\u659c\u7684\u65f6\u5019\u9700\u8981\u7528\u53cc\u659c\u6760\uff0c\u5426\u5219\u5c31\u8981\u4f7f\u7528\u53f3\u659c\u6760<\/p>\n<h3>1.1.2\u3001read_table<\/h3>\n<p>\u8fd8\u53ef\u4ee5\u4f7f\u7528read_table\uff0c\u5e76\u4e14\u6307\u5b9a\u5206\u9694\u7b26<\/p>\n<pre><code class=\"language-python\">import pandas as pd\ndf = pd.read_csv(&quot;E:\/Test\/test3.csv&quot;)\ndf\n\nname    age sex\n0   \u4f69\u5947  18  \u5973\n1   \u4e54\u6cbb  19  \u7537<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u6570\u636e\u5904\u7406_tabl.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u6570\u636e\u5904\u7406_tabl.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<p>\u5982\u679c\u4e0d\u6307\u5b9a\u5206\u9694\u7b26\uff0c\u5b83\u7684\u6570\u636e\u4e4b\u95f4\u4f1a\u6709\u9017\u53f7\u3002<\/p>\n<p>\u4ee5\u4e0a\u53ea\u662f\u7b80\u5355\u7684\u8bfb\u53d6\u64cd\u4f5c\uff0c<\/p>\n<h3>1.1.3\u3001\u6307\u5b9a\u5217\u540d<\/h3>\n<p>pandas\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u81ea\u52a8\u5206\u914d\u5217\u540d\uff0c\u4e5f\u53ef\u4ee5\u81ea\u5df1\u6307\u5b9a\u5217\u540d<br \/>\n\u9ed8\u8ba4\u5217\u540d<\/p>\n<pre><code class=\"language-python\">import pandas as pd\ndf = pd.read_csv(&quot;E:\/Test\/test.csv&quot;,header=None)\ndf\n    0   1   2   3   4   5\n0   a   b   c   d   e   f\n1   g   h   i   j   k   l\n2   m   n   o   p   q   r<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/recv_table2.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/recv_table2.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<p>\u6307\u5b9a\u5217\u540d <\/p>\n<pre><code class=\"language-python\">import pandas as pd\ndf = pd.read_csv(&quot;E:\/Test\/test.csv&quot;,names=[&#039;\u6570&#039;,&#039;\u636e&#039;,&#039;\u5206&#039;,&#039;\u6790&#039;,&#039;\u771f&#039;,&#039;\u597d&#039;,&#039;\u73a9&#039;])\ndf<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/recv_table3.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/recv_table3.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<p>\u5177\u4f53\u8fd8\u6709\u90a3\u4e9b\u53c2\u6570\uff0c\u901a\u8fc7\u8868\u683c\u5c55\u793a\u4e00\u4e0b\uff0c\u8fd9\u4e9b\u53c2\u6570\u662fread_csv\u548cread_table\u5171\u6709\u7684<\/p>\n<table>\n<thead>\n<tr>\n<th>\u53c2\u6570<\/th>\n<th style=\"text-align: center;\">\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>path<\/td>\n<td style=\"text-align: center;\">\u8868\u660e\u6587\u4ef6\u7cfb\u7edf\u4f4d\u7f6e\u7684\u5b57\u7b26\u4e32\u3001URL\u6216\u8005\u6587\u4ef6\u578b\u5bf9\u8c61<\/td>\n<\/tr>\n<tr>\n<td>sep\u6216delimiter<\/td>\n<td style=\"text-align: center;\">\u7528\u4e8e\u5206\u9694\u6bcf\u884c\u5b57\u6bb5\u7684\u5b57\u7b26\u5e8f\u5217\u6216\u6b63\u5219\u8868\u8fbe\u5f0f<\/td>\n<\/tr>\n<tr>\n<td>header<\/td>\n<td style=\"text-align: center;\">\u7528\u4f5c\u5217\u540d\u7684\u884c\u53f7\uff0c\u9ed8\u8ba4\u662f0\uff08\u7b2c\u4e00\u884c\uff09\uff0c\u5982\u679c\u6ca1\u6709\u4e3aNone<\/td>\n<\/tr>\n<tr>\n<td>names<\/td>\n<td style=\"text-align: center;\">\u7ed3\u679c\u7684\u5217\u540d\u5217\u8868\uff0c\u548cheader=None\u4e00\u8d77\u7528<\/td>\n<\/tr>\n<tr>\n<td>skiprows<\/td>\n<td style=\"text-align: center;\">\u4ece\u6587\u4ef6\u5f00\u5934\u8d77\uff0c\u9700\u8981\u8df3\u8fc7\u7684\u884c\u6570\u6216\u8005\u884c\u53f7\u5217\u8868<\/td>\n<\/tr>\n<tr>\n<td>na_values<\/td>\n<td style=\"text-align: center;\">\u7528NA\u66ff\u6362\u7684\u503c\u5e8f\u5217\uff08\u53ef\u4ee5\u7528\u6765\u5904\u7406\u7f3a\u5931\u503c\uff09<\/td>\n<\/tr>\n<tr>\n<td>data_parser<\/td>\n<td style=\"text-align: center;\">\u7528\u4e8e\u89e3\u6790\u65e5\u671f\u7684\u51fd\u6570<\/td>\n<\/tr>\n<tr>\n<td>nrows<\/td>\n<td style=\"text-align: center;\">\u4ece\u6587\u4ef6\u5f00\u5934\u5904\u8bfb\u53d6\u7684\u884c\u6570<\/td>\n<\/tr>\n<tr>\n<td>chunksize<\/td>\n<td style=\"text-align: center;\">\u7528\u4e8e\u8bbe\u7f6e\u8fed\u4ee3\u7684\u5757\u5927\u5c0f<\/td>\n<\/tr>\n<tr>\n<td>encoding<\/td>\n<td style=\"text-align: center;\">\u8bbe\u7f6e\u6587\u672c\u7f16\u7801<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h3>1.1.4\u3001\u5206\u5757\u8bfb\u53d6\u6587\u4ef6<\/h3>\n<p>\u521a\u624d\u6211\u4eec\u8bfb\u53d6\u6587\u4ef6\u662f\u628a\u6574\u4e2a\u6587\u4ef6\u90fd\u8bfb\u53d6\u51fa\u6765\u4e86\uff0c\u90a3\u63a5\u4e0b\u6765\u6211\u4eec\u5c31\u5c1d\u8bd5\u5206\u5757\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\uff0c\u56e0\u4e3a\u4e0d\u662f\u6240\u6709\u7684\u6587\u4ef6\u5185\u5bb9\u90fd\u53ea\u6709\u8fd9\u4e48\u5c11\uff0c\u6211\u4eec\u5728\u5b9e\u9645\u8fd0\u7528\u5f53\u4e2d\u4f1a\u9700\u8981\u8bfb\u53d6\u6587\u4ef6\u7684\u4e00\u4e2a\u5c0f\u7247\u6bb5\u3002<\/p>\n<p>\u8bfb\u53d6\u5927\u6587\u4ef6\u7684\u65f6\u5019\u53ef\u4ee5\u6dfb\u52a0\u4e00\u4e2a\u53c2\u6570\u4f7f\u5f97\u663e\u793a\u7684\u5185\u5bb9\u66f4\u52a0\u7d27\u51d1<\/p>\n<pre><code class=\"language-python\">import pandas as pd\npd.options.display.max_rows = 3\ndf = pd.read_csv(&quot;E:\/Test\/test.csv&quot;)\ndf<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u5206\u5757\u8bfb\u53d6.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/\u5206\u5757\u8bfb\u53d6.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<p>\u8fd8\u53ef\u4ee5\u901a\u8fc7\u4e0a\u9762\u8868\u683c\u4e2d\u63d0\u5230\u7684 <code>nrows<\/code> \u53c2\u6570\u9009\u62e9\u53ea\u8bfb\u53d6\u5176\u4e2d\u7684\u51e0\u884c<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_2.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_2.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h2>1.2\u3001\u4e8c\u8fdb\u5236<\/h2>\n<h3>1.2.1\u3001pickle<\/h3>\n<p>\u5728Python\u4e2d\u6709\u4e00\u4e2a\u81ea\u5e26\u7684\u5e8f\u5217\u5316\u6a21\u5757<code>pickle<\/code>,\u5b83\u662f\u8fdb\u884c\u4e8c\u8fdb\u5236\u683c\u5f0f\u64cd\u4f5c\u5b58\u50a8\u6570\u636e\u6700\u9ad8\u6548\u3001\u6700\u65b9\u4fbf\u7684\u65b9\u5f0f\u4e4b\u4e00\u3002\u5728pandas\u4e2d\u6709\u4e00\u4e2a<code>to_pickle<\/code>\u65b9\u6cd5\u53ef\u4ee5\u5c06\u6570\u636e\u4ee5<code>pickle<\/code>\u683c\u5f0f\u5199\u5165\u786c\u76d8<\/p>\n<pre><code class=\"language-python\">import pandas as pd\ndf = pd.read_csv(&quot;E:\/Test\/test_j.csv&quot;)\ndf.to_pickle(&quot;E:\/Test\/df_pickle&quot;)<\/code><\/pre>\n<p>\u8fd0\u884c\u5b8c\u4e4b\u540e\u4f1a\u53d1\u73b0\u6ca1\u53cd\u5e94\uff0c\u4f46\u662f\u53ef\u4ee5\u6253\u5f00\u4f60\u5b58\u50a8\u7684\u6587\u4ef6\u5939\u4f1a\u53d1\u73b0\u8fd9\u4e2apickle\u6587\u4ef6\u5df2\u7ecf\u5b58\u5230\u91cc\u9762\u4e86\u3002  <\/p>\n<p>\u867d\u7136\u8bf4\u8fd9\u79cd\u65b9\u5f0f\u975e\u5e38\u65b9\u4fbf\uff0c\u4f46\u662f\u5374\u5f88\u96be\u4fdd\u8bc1\u683c\u5f0f\u7684\u957f\u671f\u6709\u6548\u6027\u3002\u4e00\u4e2a\u4eca\u5929\u88abpickle\u5316\u7684\u5bf9\u8c61\u53ef\u80fd\u660e\u5929\u4f1a\u56e0\u4e3a\u5e93\u7684\u65b0\u7248\u672c\u800c\u65e0\u6cd5\u53cd\u5e8f\u5217\u5316.\u5728pandas\u5f53\u4e2d\u8fd8\u652f\u6301\u5176\u4ed6\u7684\u4e8c\u8fdb\u5236\u683c\u5f0f\u3002\u63a5\u7740\u5f80\u4e0b\u770b<\/p>\n<h3>1.2.2\u3001HDF5<\/h3>\n<p>HDF5\u4e3b\u8981\u7528\u4e8e\u5b58\u50a8\u5927\u91cf\u7684\u79d1\u5b66\u6570\u7ec4\u6570\u636e\u3002\u4ee5C\u5e93\u7684\u5f62\u5f0f\u63d0\u4f9b\uff0c\u5e76\u4e14\u6709\u8bb8\u591a\u5176\u4ed6\u8bed\u8a00\u7684\u63a5\u53e3\uff0c\u4f8b\u5982\uff1aJAVA\u3001Julia\uff0c\u5f53\u7136\u8fd8\u6709\u6211\u4eec\u7684Python\u3002HDF5\u4e2d\u7684<code>HDF<\/code>\u4ee3\u8868\u5206\u5c42\u6570\u636e\u683c\u5f0f\uff0c\u6bcf\u4e2aHDF5\u6587\u4ef6\u53ef\u4ee5\u5b58\u50a8\u591a\u4e2a\u6570\u636e\u96c6\u5e76\u4e14\u652f\u6301\u5143\u6570\u636e<\/p>\n<p>pandas.read_hdf\u51fd\u6570\u662f\u4f7f\u7528HDF5\u683c\u5f0f\u7684\u4e00\u4e2a\u5feb\u6377\u65b9\u6cd5<\/p>\n<pre><code class=\"language-python\">import pandas as pd\nimport numpy as np\nframe = pd.DataFrame({&#039;a&#039;:np.random.randn(100)})\n\nframe.to_hdf(&quot;E:\/Test\/mydata.h5&quot;,&#039;obj3&#039;,format=&#039;table&#039;)\npd.read_hdf(&#039;E:\/Test\/mydata.h5&#039;,&#039;obj3&#039;,where=[&#039;index &lt; 5&#039;])<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/HDF5.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/HDF5.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_3.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_3.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h2>1.3\u3001Web API<\/h2>\n<p>\u73b0\u5728\u5f88\u591a\u7f51\u7ad9\u90fd\u6709\u516c\u5f00\u7684API\uff0c\u901a\u8fc7JSON\u6216\u8005\u5176\u4ed6\u4ec0\u4e48\u683c\u5f0f\u63d0\u4f9b\u6570\u636e\u670d\u52a1\u3002\u90a3\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c31\u901a\u8fc7Python\u7684requests\u6a21\u5757\u8bbf\u95eeWeb API\u3002<\/p>\n<pre><code class=\"language-python\">import requests\nimport pandas as pd\nurl = &quot;https:\/\/api.github.com\/repos\/pandas-dev\/pandas\/issues&quot;\nresp = requests.get(url)\ndata = resp.json()\n# \u56e0\u4e3adata\u4e2d\u7684\u6bcf\u4e2a\u5143\u7d20\u90fd\u662f\u4e00\u4e2a\u5b57\u5178\uff0c\u53ef\u4ee5\u76f4\u63a5\u5c06data\u4f20\u7ed9DataFrame\uff0c\u5e76\u4e14\u5c06\u5176\u4e2d\u81ea\u5df1\u559c\u6b22\u7684\u5b57\u6bb5\u5c55\u793a\u51fa\u6765\nissues = pd.DataFrame(data,columns=[&#039;number&#039;,&#039;title&#039;,&#039;labels&#039;,&#039;state&#039;])\nissues<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/web-API.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/web-API.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_4.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_4.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h2>1.4\u3001\u64cd\u4f5c\u6570\u636e\u5e93<\/h2>\n<p>\u5728\u6570\u636e\u5206\u6790\u7684\u64cd\u4f5c\u5f53\u4e2d\uff0c\u8bfb\u5199\u6570\u636e\u5e93\u4e3b\u8981\u8fd8\u662f\u7531pandas\u6765\u8fdb\u884c\u64cd\u4f5c\u3002\u5728\u5de5\u4f5c\u73af\u5883\u6700\u4e3a\u5e38\u7528\u7684\u5c31\u662fmysql\u6570\u636e\u5e93\uff0c\u6240\u4ee5\u5c31\u4ee5\u64cd\u4f5cmysql\u4f5c\u4e3a\u793a\u4f8b\uff1a<\/p>\n<p>\u4ece\u6570\u636e\u5e93\u5bfc\u51fa\u6570\u636e\uff1a<\/p>\n<pre><code class=\"language-python\">import pandas as pd\nfrom sqlalchemy import create_engine\nimport pymysql\n\n# \u521b\u5efa\u6570\u636e\u5e93\u8fde\u63a5\nconn = create_engine(&quot;mysql+pymysql:\/\/root:123@localhost:3306\/pd_test&quot;)\n\nsql = &quot;select * from emp;&quot;\n# \u901a\u8fc7sql\u8bed\u53e5\u4ee5\u53ca\u8fde\u63a5\u67e5\u8be2\u6570\u636e\u5e93\uff0c\u6700\u7ec8\u8fd4\u56de\u7684\u7ed3\u679c\u662f\u4e00\u4e2aDataFrame\u6570\u7ec4\ndf = pd.read_sql(sql,engine)\ndf<\/code><\/pre>\n<p>\u8fd0\u884c\u7ed3\u679c\uff1a<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/read_sql.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/read_sql.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<p>\u5c06\u6570\u636e\u5bfc\u5165\u6570\u636e\u5e93\uff1a<\/p>\n<p>\u5728pandas\u5f53\u4e2d\u5b58\u5728\u4e00\u4e2ato_sql\u51fd\u6570\uff0c\u53ef\u4ee5\u5c06\u6570\u636e\u5199\u5165\u6570\u636e\u5e93\uff0c\u5b83\u652f\u6301\u4e24\u7c7bmysql\u5f15\u64ce\uff0c\u4e00\u4e2a\u662fsqlalchemy\uff0c\u53e6\u4e00\u4e2a\u662fsqlliet3\uff0c\u4f46\u662f\u7531\u4e8esqlliet3\u5bd2\u5c31\u6ca1\u6709\u66f4\u65b0\uff0c\u6240\u4ee5\u5efa\u8bae\u4f7f\u7528sqlalchemy\u3002<\/p>\n<pre><code class=\"language-python\"># key\u4e3a\u5217\uff0c\u952e\u4e3a\u503c\ndata = pd.DataFrame({&#039;id&#039;:[1,2,3],\n                    &#039;name&#039;:[&#039;\u8d3e\u73b2&#039;,&#039;\u6c88\u817e&#039;,&#039;\u9a6c\u4e3d&#039;],\n                    &#039;password&#039;:[&#039;123&#039;,&#039;456&#039;,&#039;789&#039;]})\n# \u7b2c\u4e00\u4e2a\u53c2\u6570\uff1a\u65b0\u5efa\u7684\u8868\u540d\uff1b\u7b2c\u4e8c\u4e2a\uff1a\u6570\u636e\u5e93\u8fde\u63a5\ndata.to_sql(&#039;pd_test1&#039;,conn,index = True)<\/code><\/pre>\n<p>\u901a\u8fc7\u53ef\u89c6\u5316\u5de5\u5177\u6253\u5f00\u6570\u636e\u5e93\u53ef\u4ee5\u770b\u89c1\uff0c\u4e00\u4e2aDataFrame\u6570\u7ec4\u5c31\u76f4\u63a5\u5b58\u5230\u6570\u636e\u5e93\u91cc\u9762\u4e86<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/to_sql.png'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/to_sql.png\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_5.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_5.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h1>2\u3001\u6570\u636e\u5904\u7406<\/h1>\n<p>\u200b   \u7ecf\u8fc7\u524d\u9762\u7684\u4e86\u89e3\uff0c\u5bf9\u4e8e\u6570\u636e\u7684\u5bfc\u5165\u4ee5\u53ca\u5b58\u50a8\u5df2\u7ecf\u6709\u4e86\u4e00\u4e2a\u7b80\u5355\u7684\u4e86\u89e3\uff0c\u4f46\u662f\u5728\u5b9e\u9645\u7684\u5de5\u4f5c\u60c5\u51b5\u5f53\u4e2d\uff0c\u62ff\u5230\u7684\u6570\u636e\u4e0d\u53ef\u80fd\u90fd\u662f\u9884\u60f3\u7684\u683c\u5f0f\uff0c\u6240\u4ee5\u8bf4\uff0c\u5c31\u9700\u8981\u901a\u8fc7\u4e00\u4e9b\u6587\u672c\u5904\u7406\u5de5\u5177\u5c06\u8fd9\u79cd\u7279\u6b8a\u6570\u636e\u4ece\u4e00\u79cd\u5f62\u5f0f\u8f6c\u6362\u4e3a\u53e6\u4e00\u79cd\u53ef\u4ee5\u63a5\u53d7\u7684\u5f62\u5f0f\uff0c\u6b63\u597d\u5728Python\u7684pandas\u5e93\u5f53\u4e2d\u5c31\u4e3a\u6211\u4eec\u63d0\u4f9b\u4e86\u4e00\u4e2a\u9ad8\u7ea7\u3001\u7075\u6d3b\u548c\u5feb\u901f\u7684\u5de5\u5177\u96c6\uff0c\u5c06\u6570\u636e\u8f6c\u6362\u6210\u60f3\u8981\u7684\u683c\u5f0f\u3002<\/p>\n<p>\u200b   \u4e00\u4e2a\u6ca1\u6709\u5904\u7406\u7684\u6570\u636e\u96c6\u5c31\u548c\u4e00\u4e2a\u6ca1\u6709\u5316\u5986\u7684\u5973\u7f51\u7ea2\u4e00\u6837\uff0c\u6240\u4ee5\u6211\u4eec\u8981\u4e00\u6b65\u4e00\u6b65\u7ed9\u4f60\u7684\u6570\u636e\u5316\u4e0a\u5986\uff0c\u8ba9\u5b83\u4eec\u770b\u8d77\u6765\u66f4\u52a0<strong><code>\u6f02\u4eae<\/code><\/strong>!!!<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_1.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_1.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h2>2.1\u3001\u5904\u7406\u7f3a\u5931\u503c<\/h2>\n<p>\u7f3a\u5931\u6570\u636e\u5728\u6570\u636e\u5206\u6790\u7684\u5e94\u7528\u5f53\u4e2d\u662f\u5f88\u5e38\u89c1\u7684\uff0cpandas\u7684\u76ee\u6807\u4e4b\u4e00\u5c31\u662f\u5c3d\u53ef\u80fd\u7684\u65e0\u5f71\u54cd\u7684\u5904\u7406\u7f3a\u5931\u503c\u3002\u5728pandas\u5f53\u4e2d\u4f7f\u7528\u6d6e\u70b9\u503cNaN(Not a Number\u6765\u8868\u662f\u7f3a\u5931\u503c)\u3002\u5904\u7406\u7f3a\u5931\u503c\u7684\u6700\u5e38\u89c1\u7684\u4e24\u79cd\u7684\u65b9\u6cd5\uff1a\u7b2c\u4e00\u4e2a\u5c31\u662f\u76f4\u63a5\u5c06\u90a3\u4e2a\u503c\u4e22\u5f03\uff0c\u7b2c\u4e8c\u79cd\u65b9\u5f0f\u5c31\u662f\u8865\u5168\u7f3a\u5931\u503c\u3002<\/p>\n<table>\n<thead>\n<tr>\n<th>\u5c5e\u6027<\/th>\n<th style=\"text-align: center;\">\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>dropna<\/td>\n<td style=\"text-align: center;\">\u6839\u636e\u5404\u6807\u7b7e\u7684\u503c\u4e2d\u662f\u5426\u5b58\u5728\u7f3a\u5931\u6570\u636e\u5bf9\u8f74\u6807\u7b7e\u8fdb\u884c\u8fc7\u6ee4\u3002<\/td>\n<\/tr>\n<tr>\n<td>fillna<\/td>\n<td style=\"text-align: center;\">\u7528\u6307\u5b9a\u503c\u6216\u63d2\u503c\u65b9\u6cd5(\u5982ffill\u6216bfill)\u586b\u5145\u7f3a\u5931\u6570\u636e<\/td>\n<\/tr>\n<tr>\n<td>isnull<\/td>\n<td style=\"text-align: center;\">\u8fd4\u56de\u4e00\u4e2a\u542b\u6709\u5e03\u5c14\u503c\u7684\u5bf9\u8c61\uff0c\u8fd9\u4e9b\u5e03\u5c14\u503c\u8868\u793a\u54ea\u4e9b\u503c\u662f\u7f3a\u5931\u503c\/NA<\/td>\n<\/tr>\n<tr>\n<td>notnull<\/td>\n<td style=\"text-align: center;\">isnull\u7684\u5426\u5b9a\u5f0f<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h3>2.1.1\u3001\u8fc7\u6ee4\u7f3a\u5931\u503c<\/h3>\n<pre><code class=\"language-python\">data = pd.Series([&#039;pandas&#039;,&#039;numpy&#039;,np.nan,&#039;matplotlib&#039;])\n-------------------------------------------\ndata.isnull()\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0    False\n1    False\n2     True\n3    False\ndtype: bool    # \u8fd4\u56de\u4e00\u4e2a\u5e03\u5c14\u503c\u6570\u7ec4\n-------------------------------------------\ndata[0] = None  # python\u4e2d\u5185\u7f6e\u7684None\u503c\u5728\u5bf9\u8c61\u6570\u7ec4\u79cd\u4e5f\u53ef\u4ee5\u4f5c\u4e3aNA\ndata.notnull()\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0    False\n1     True\n2    False\n3     True\ndtype: bool\n-------------------------------------------\ndata_1 = pd.Series([1,np.nan,3,np.nan,5.5,9])\ndata_1.dropna()  # \u4e22\u5f03\u4efb\u4f55\u542b\u6709\u7f3a\u5931\u503c\u7684\u884c\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0    1.0\n2    3.0\n4    5.5\n5    9.0\ndtype: float64\n# data_1[data_1.notnull()]\u7b49\u4ef7\u4e8edata_1.dropna()<\/code><\/pre>\n<p>\u4ee5\u4e0a\u90fd\u662f\u5bf9Series\u8fd9\u79cd\u4e00\u7ef4\u6570\u7ec4\u7684\u7f3a\u5931\u503c\u5904\u7406\uff0c\u5982\u679c\u5bf9\u4e8eDataFrame\u8fd9\u79cd\u4e8c\u7ef4\u6570\u7ec4\u7684\u5904\u7406\u5c31\u4f1a\u51fa\u73b0\u4e00\u4e9b\u95ee\u9898\u3002<\/p>\n<pre><code class=\"language-python\">df = pd.DataFrame([[1,3,5,7,9],[2,4,6,np.nan],[1.5,5.,6.3,np.nan],[4.,2.3,np.nan,8,9.],[np.nan,np.nan,np.nan,np.nan,np.nan]])\ndf\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 9.0\n1   2.0 4.0 6.0 NaN NaN\n2   1.5 5.0 6.3 NaN NaN\n3   4.0 2.3 NaN 8.0 9.0\n4   NaN NaN NaN NaN NaN\n-------------------------------------------\ncleaned = df.dropna()\ncleaned\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 9.0\n# \u6240\u6709\u5e26\u6709\u7f3a\u5931\u503c\u7684\u884c\u5168\u88ab\u4e22\u5f03\u4e86<\/code><\/pre>\n<p>\u5bf9\u4e8e\u8fd9\u79cd\u60c5\u51b5\u53ef\u4ee5\u901a\u8fc7\u4f20\u9012\u53c2\u6570\u6765\u89e3\u51b3\uff1a<\/p>\n<pre><code class=\"language-python\">df.dropna(how=&quot;all&quot;)  # \u4e22\u5f03\u5168\u4e3a\u7f3a\u5931\u503c\u7684\u884c\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 9.0\n1   2.0 4.0 6.0 NaN NaN\n2   1.5 5.0 6.3 NaN NaN\n3   4.0 2.3 NaN 8.0 9.0\n-------------------------------------------\ndf[4] = np.nan\ndf.dropna(axis=1,how=&quot;all&quot;) # \u4e22\u5f03\u5168\u4e3a\u7f3a\u5931\u503c\u7684\u5217\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3\n0   1.0 3.0 5.0 7.0\n1   2.0 4.0 6.0 NaN\n2   1.5 5.0 6.3 NaN\n3   4.0 2.3 NaN 8.0\n4   NaN NaN NaN NaN\n-------------------------------------------<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_2.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_2.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.1.2\u3001\u8865\u5168\u7f3a\u5931\u503c<\/h3>\n<p>\u6709\u65f6\u5019\u5728\u64cd\u4f5c\u6570\u636e\u7684\u65f6\u5019\u53ef\u80fd\u4e0d\u60f3\u8fc7\u6ee4\u6389\u7f3a\u5931\u6570\u636e\uff0c\u56e0\u4e3a\u6709\u53ef\u80fd\u4f1a\u4e22\u5f03\u548c\u4ed6\u6709\u5173\u7684\u5176\u4ed6\u6570\u636e\uff0c\u800c\u662f\u5e0c\u671b\u901a\u8fc7\u4e00\u4e9b\u5176\u4ed6\u65b9\u5f0f\u6765\u586b\u8865\u90a3\u4e9b\u7f3a\u5931\u7684\u5730\u65b9\u3002fillna\u65b9\u6cd5\u662f\u5904\u7406\u8fd9\u4e9b\u95ee\u9898\u6700\u4e3b\u8981\u7684\u65b9\u6cd5\u3002<\/p>\n<pre><code class=\"language-python\">df.fillna(0)  # \u66ff\u6362\u7f3a\u5931\u503c\u4e3a0\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 0.0\n1   2.0 4.0 6.0 0.0 0.0\n2   1.5 5.0 6.3 0.0 0.0\n3   4.0 2.3 0.0 8.0 0.0\n4   0.0 0.0 0.0 0.0 0.0\n-------------------------------------------\ndf.fillna({1:0.5,2:0})  # \u5bf9\u4e0d\u540c\u7684\u5217\u586b\u5145\u4e0d\u540c\u7684\u503c\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 NaN\n1   2.0 4.0 6.0 NaN NaN\n2   1.5 5.0 6.3 NaN NaN\n3   4.0 2.3 0.0 8.0 NaN\n4   NaN 0.5 0.0 NaN NaN\n-------------------------------------------\ndf.fillna(0,inplace=True)\ndf\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0   1   2   3   4\n0   1.0 3.0 5.0 7.0 0.0\n1   2.0 4.0 6.0 0.0 0.0\n2   1.5 5.0 6.3 0.0 0.0\n3   4.0 2.3 0.0 8.0 0.0\n4   0.0 0.0 0.0 0.0 0.0<\/code><\/pre>\n<p>\u4f7f\u7528fillna\u8fd8\u53ef\u4ee5\u8fdb\u884c\u63d2\u503c<\/p>\n<pre><code class=\"language-python\">df1 = pd.DataFrame(np.random.randn(6,3))\ndf1\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0           1           2\n0   0.475304    -1.274166   1.467016\n1   -0.113910   0.935197    -1.008954\n2   0.218006    0.209405    0.224217\n3   1.878587    0.492774    -1.391237\n4   -0.702284   0.863064    0.939069\n5   -1.450531   0.994467    0.265843\n# \u4e00\u7ec4\u6570\u636e\u6570\n-------------------------------------------\ndf1.iloc[2:,1] = np.nan  # \u5c06\u7b2c\u4e8c\u5217\u7b2c\u4e09\u884c\u4ee5\u540e\u7684\u6570\u636e\u90fd\u8f6c\u6362\u4e3a\u7f3a\u5931\u503c\ndf1.iloc[4:,2] = np.nan  # \u5c06\u7b2c\u4e09\u5217\u7b2c\u4e94\u884c\u4ee5\u540e\u7684\u6570\u636e\u90fd\u8f6c\u6362\u4e3a\u7f3a\u5931\u503c\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0           1           2\n0   1.073202    0.644249    -0.089127\n1   -0.028500   0.479373    -0.271212\n2   1.575710    NaN         -0.119795\n3   -0.202480   NaN         0.385250\n4   -1.090317   NaN         NaN\n5   0.985767    NaN         NaN\n-------------------------------------------\ndf1.fillna(method=&#039;ffill&#039;)\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    0           1           2\n0   1.073202    0.644249    -0.089127\n1   -0.028500   0.479373    -0.271212\n2   1.575710    0.479373    -0.119795\n3   -0.202480   0.479373    0.385250\n4   -1.090317   0.479373    0.385250\n5   0.985767    0.479373    0.385250\n# \u53c2\u6570limit\u8fd8\u53ef\u4ee5\u8bbe\u7f6e\u66ff\u6362\u7684\u884c<\/code><\/pre>\n<table>\n<thead>\n<tr>\n<th>\u53c2\u6570<\/th>\n<th style=\"text-align: center;\">\u8bf4\u660e<\/th>\n<th><\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>value<\/td>\n<td style=\"text-align: center;\">\u7528\u4e8e\u586b\u5145\u7f3a\u5931\u503c\u7684\u6807\u91cf\u503c\u6216\u5b57\u5178\u5bf9\u8c61<\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>method<\/td>\n<td style=\"text-align: center;\">\u63d2\u503c\u65b9\u5f0f\u3002\u5982\u679c\u51fd\u6570\u8c03\u7528\u65f6\u672a\u6307\u5b9a\u5176\u4ed6\u53c2\u6570\u7684\u8bdd\uff0c\u9ed8\u8ba4\u4e3a&quot;ffill&quot;<\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>axis<\/td>\n<td style=\"text-align: center;\">\u5f85\u586b\u5145\u7684\u8f74\uff0c\u9ed8\u8ba4axis=0<\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>inplace<\/td>\n<td style=\"text-align: center;\">\u4fee\u6539\u8c03\u7528\u8005\u5bf9\u8c61\u800c\u4e0d\u4ea7\u751f\u526f\u672c<\/td>\n<td><\/td>\n<\/tr>\n<tr>\n<td>limit<\/td>\n<td style=\"text-align: center;\">\u53ef\u4ee5\u8fde\u7eed\u586b\u5145\u7684\u6700\u5927\u6570\u91cf<\/td>\n<td><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_3.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_3.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h2>2.2\u3001\u6570\u636e\u8f6c\u6362<\/h2>\n<h3>2.2.1\u3001\u5220\u9664\u91cd\u590d\u503c<\/h3>\n<pre><code class=\"language-python\">data = pd.DataFrame({&quot;k1&quot;:[&#039;one&#039;,&#039;two&#039;] * 3 + [&#039;two&#039;],\n                    &quot;k2&quot;:[1,1,2,3,3,4,4]})   \ndata\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    k1  k2\n0   one 1\n1   two 1\n2   one 2\n3   two 3\n4   one 3\n5   two 4\n6   two 4\n-----------------------------------------------\ndata.duplicated()  # \u8fd4\u56de\u4e00\u4e2a\u5e03\u5c14\u578bSeries\uff0c\u8868\u793a\u5404\u884c\u662f\u5426\u662f\u91cd\u590d\u884c\n0    False\n1    False\n2    False\n3    False\n4    False\n5    False\n6     True\ndtype: bool\n-----------------------------------------------\ndata.drop_duplicates()  # \u8fd4\u56de\u4e00\u4e2aDataFrame\uff0c\u91cd\u590d\u7684\u6570\u7ec4\u4f1a\u6807\u4e3aFalse\n    k1  k2\n0   one 1\n1   two 1\n2   one 2\n3   two 3\n4   one 3\n5   two 4   \n# \u91cd\u590d\u7684\u884c\u88ab\u5220\u9664\u4e86\n-----------------------------------------------<\/code><\/pre>\n<p>\u4ee5\u4e0a\u65b9\u6cd5\u662f\u9488\u5bf9\u5168\u90e8\u5217\uff0c\u8fd8\u53ef\u4ee5\u901a\u8fc7\u4f20\u5165\u53c2\u6570\u5bf9\u90e8\u5206\u6307\u5b9a\u5217\u8fdb\u884c\u91cd\u590d\u9879\u5224\u65ad\u3002<\/p>\n<pre><code class=\"language-python\">data[&#039;v1&#039;] = range(7)  # \u6dfb\u52a0\u4e00\u4e2av1\u5217\ndata.drop_duplicates([&#039;k1&#039;,&#039;k2&#039;])  # \u53ef\u4ee5\u4f20\u5165\u4e00\u4e2a\u5217\u8868\uff0c\u6307\u5b9a\u5217\uff0c\u9ed8\u8ba4\u4fdd\u7559\u7b2c\u4e00\u4e2a\u51fa\u73b0\u7684\u503c\u7ec4\u5408\n    k1  k2  v1\n0   one 1   0\n1   two 1   1\n2   one 2   2\n3   two 3   3\n4   one 3   4\n5   two 4   5\n-----------------------------------------------\ndata.drop_duplicates([&#039;k1&#039;,&#039;k2&#039;],keep=&#039;last&#039;)  # \u4fdd\u7559\u6700\u540e\u4e00\u4e2a\u51fa\u73b0\u7684\u503c\u7ec4\u5408\n    k1  k2  v1\n0   one 1   0\n1   two 1   1\n2   one 2   2\n3   two 3   3\n4   one 3   4\n6   two 4   6<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_4.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_4.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.2.2\u3001\u4f7f\u7528\u51fd\u6570\u6216\u6620\u5c04\u8fdb\u884c\u6570\u636e\u8f6c\u6362<\/h3>\n<pre><code class=\"language-python\">data = pd.DataFrame({&quot;goods&quot;:[&#039;Iphone&#039;,&#039;HUAWEI&#039;,&#039;SAMSUNG&#039;,&#039;MI&#039;,&#039;OPPO&#039;], &quot;price&quot;:[6000,4000,5000,3000,3000]})\ndata\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    goods   price\n0   Iphone  6000\n1   HUAWEI  4000\n2   SAMSUNG 5000\n3   MI      3000\n4   OPPO    3000<\/code><\/pre>\n<p>\u73b0\u5728\u6709\u8fd9\u6837\u4e00\u7ec4\u6570\u636e\uff0c\u5047\u8bbe\u73b0\u5728\u9700\u8981\u52a0\u4e0a\u4e00\u5217\u6570\u636e\u3002\u5c06\u6bcf\u6837\u5546\u54c1\u7684\u51fa\u4ea7\u56fd\u5bb6\u52a0\u4e0a<\/p>\n<pre><code class=\"language-python\"># \u5148\u5b9a\u4e49\u4e00\u4e2a\u4e0d\u540c\u5546\u54c1\u5230\u4ea7\u5730\u7684\u6620\u5c04\nproduce_nation = {\n    &quot;iphone&quot;:&#039;America&#039;,\n    &quot;huawei&quot;:&#039;China&#039;,\n    &quot;samsung&quot;:&#039;Korea&#039;,\n    &quot;mi&quot;:&#039;China&#039;,\n    &quot;oppo&quot;:&#039;China&#039;\n}\n# \u56e0\u4e3a\u5b9a\u4e49\u7684\u5546\u54c1\u5168\u662f\u5927\u5199\uff0c\u9700\u8981\u5168\u90e8\u8f6c\u6362\u4e3a\u5c0f\u5199\nlower_cased = data[&#039;goods&#039;].str.lower()\n\n# \u901a\u8fc7map\u6620\u5c04\u6dfb\u52a0\u4e00\u5217\u51fa\u4ea7\u56fd\u5bb6\u6570\u636e\ndata[&#039;nation&#039;] =  lower_cased.map(produce_nation)\n\u8fd0\u884c\u7ed3\u679c\uff1a\n    goods   price   nation\n0   Iphone  6000    America\n1   HUAWEI  4000    China\n2   SAMSUNG 5000    Korea\n3   MI      3000    China\n4   OPPO    3000    China<\/code><\/pre>\n<p>\u4e5f\u53ef\u4ee5\u901a\u8fc7\u4e00\u4e2a\u51fd\u6570\u5b8c\u6210\u8fd9\u4e9b\u5de5\u4f5c\uff1a<\/p>\n<pre><code class=\"language-python\">data[&#039;goods&#039;].map(lambda x:produce_nation[x.lower()])\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0    America\n1      China\n2      Korea\n3      China\n4      China\nName: goods, dtype: object<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_5.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_5.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.2.3\u3001\u66ff\u6362\u503c<\/h3>\n<p>\u5229\u7528fillna()\u65b9\u6cd5\u586b\u5145\u7f3a\u5931\u6570\u636e\u662f\u503c\u66ff\u6362\u7684\u4e00\u79cd\u7279\u6b8a\u60c5\u51b5\u3002\u63a5\u4e0b\u6765\u53ef\u4ee5\u4f7f\u7528replace\u65b9\u6cd5\u8fdb\u884c\u66ff\u6362\u503c\u64cd\u4f5c\u3002<\/p>\n<pre><code class=\"language-python\">data = pd.Series([1., -999., 2., -999., -1000., 3.])\ndata   # \u751f\u6210\u4e00\u4e2aSeries\u6570\u7ec4\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0       1.0\n1    -999.0\n2       2.0\n3    -999.0\n4   -1000.0\n5       3.0\ndtype: float64\n----------------------------------------------\n# \u5176\u4e2d-999\u53ef\u80fd\u662f\u7f3a\u5931\u503c\u7684\u67d0\u4e00\u6807\u8bc6\uff0c\u9700\u8981\u4f7f\u7528NA\u66ff\u4ee3\u8fd9\u4e9b\u503c\n1\u3001\ndata.replace(-999, np.nan)  # \u901a\u8fc7replace\u4ea7\u751f\u4e00\u4e2a\u65b0\u7684Series\uff0c\u9664\u975e\u4f20\u5165inplace=True\n\u8fd0\u884c\u7ed3\u679c\uff1a\n0       1.0\n1       NaN\n2       2.0\n3       NaN\n4   -1000.0\n5       3.0\ndtype: float64\n2\u3001\ndata.replace([-999, -1000], np.nan)  # \u4e00\u6b21\u6027\u66ff\u6362\u591a\u4e2a\u503c\n3\u3001\ndata.replace([-999, -1000], [np.nan, 0])  # \u66ff\u6362\u4e0d\u540c\u7684\u503c\uff0c\u901a\u8fc7\u5217\u8868\n4\u3001\ndata.replace({-999: np.nan, -1000: 0})  # \u66ff\u6362\u4e0d\u540c\u7684\u503c\uff0c\u901a\u8fc7\u5b57\u5178<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_6.gif'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_6.gif\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.2.4\u3001\u91cd\u547d\u540d\u8f74\u7d22\u5f15<\/h3>\n<pre><code class=\"language-python\">data =  pd.DataFrame(np.arange(12).reshape((3,4)),index=[&#039;a&#039;,&#039;b&#039;,&#039;c&#039;],columns=[&#039;one&#039;,&#039;two&#039;,&#039;three&#039;,&#039;four&#039;])\ndata<\/code><\/pre>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>one<\/th>\n<th>two<\/th>\n<th>three<\/th>\n<th>four<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>a<\/th>\n<td>0<\/td>\n<td>1<\/td>\n<td>2<\/td>\n<td>3<\/td>\n<\/tr>\n<tr>\n<th>b<\/th>\n<td>4<\/td>\n<td>5<\/td>\n<td>6<\/td>\n<td>7<\/td>\n<\/tr>\n<tr>\n<th>c<\/th>\n<td>8<\/td>\n<td>9<\/td>\n<td>10<\/td>\n<td>11<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u60f3\u8981\u7ed9\u6570\u636e\u96c6\u91cd\u65b0\u8f6c\u6362\u6570\u636e\u96c6\u7684\u540d\u79f0\uff0c\u4f46\u662f\u8fd8\u4e0d\u4fee\u6539\u539f\u6709\u6570\u636e\u96c6\uff0c\u5c31\u53ef\u4ee5\u4f7f\u7528\u4e00\u4e2a\u975e\u5e38nb\u7684\u65b9\u6cd5<code>rename<\/code><\/p>\n<pre><code class=\"language-python\">data.rename(index=str.title,columns=str.upper)<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>ONE<\/th>\n<th>TWO<\/th>\n<th>THREE<\/th>\n<th>FOUR<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>A<\/th>\n<td>0<\/td>\n<td>1<\/td>\n<td>2<\/td>\n<td>3<\/td>\n<\/tr>\n<tr>\n<th>B<\/th>\n<td>4<\/td>\n<td>5<\/td>\n<td>6<\/td>\n<td>7<\/td>\n<\/tr>\n<tr>\n<th>C<\/th>\n<td>8<\/td>\n<td>9<\/td>\n<td>10<\/td>\n<td>11<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u4ee5\u4e0a\u53ea\u662f\u5bf9\u8f74\u7d22\u5f15\u7684\u540d\u79f0\u8fdb\u884c\u6574\u5217\u6216\u662f\u6574\u884c\u4fee\u6539\uff0c\u6709\u65f6\u5019\u6211\u4eec\u9700\u8981\u66ff\u6362\u7d22\u5f15\u4e2d\u7684\u90e8\u5206\u503c\uff0c\u8fd9\u5c31\u53ef\u4ee5\u7ed3\u5408\u5b57\u5178\u578b\u5bf9\u8c61\u6765\u4f7f\u7528<\/p>\n<pre><code class=\"language-python\">data.rename(index={&#039;a&#039;:&quot;sean&quot;},\n           columns={&#039;two&#039;:&quot;tank&quot;})<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>one<\/th>\n<th>tank<\/th>\n<th>three<\/th>\n<th>four<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>sean<\/th>\n<td>0<\/td>\n<td>1<\/td>\n<td>2<\/td>\n<td>3<\/td>\n<\/tr>\n<tr>\n<th>b<\/th>\n<td>4<\/td>\n<td>5<\/td>\n<td>6<\/td>\n<td>7<\/td>\n<\/tr>\n<tr>\n<th>c<\/th>\n<td>8<\/td>\n<td>9<\/td>\n<td>10<\/td>\n<td>11<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u8865\u5145\uff1a\u8fd8\u6709\u4e00\u4e2a\u53c2\u6570inplace=True\uff0c\u53ef\u4ee5\u4fee\u6539\u539f\u6709\u7684\u6570\u636e\u96c6<\/p>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_7.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_7.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.2.5\u3001\u79bb\u6563\u5316\u548c\u5206\u7bb1<\/h3>\n<p>\u6211\u4eec\u5728\u8fdb\u884c\u6570\u636e\u5206\u6790\u7684\u65f6\u5019\uff0c\u4e00\u4e9b\u8fde\u7eed\u7684\u6570\u503c\u7ecf\u5e38\u9700\u8981\u8fdb\u884c\u79bb\u6563\u5316\uff0c\u6216\u8005\u9700\u8981\u5206\u79bb\u6210\u4e00\u4e2a\u4e2a&quot;\u5c0f\u5757&quot;\u53ef\u4ee5\u8bf4&quot;\u7bb1\u5b50&quot;\u6765\u8fdb\u884c\u5206\u6790\u3002\u76ee\u524d\u5047\u8bbe\u6211\u4eec\u6709\u67d0\u9879\u7814\u7a76\u7684\u4e00\u7ec4\u4eba\u5458\u7684\u6570\u636e\uff0c\u73b0\u5728\u9700\u8981\u5c06\u4ed6\u4eec\u8fdb\u884c\u5206\u7ec4\uff0c\u653e\u5165\u79bb\u6563\u7684\u5e74\u9f84\u6846\u5f53\u4e2d<\/p>\n<pre><code class=\"language-python\">ages = [19,35,22,20,27,22,30,23,26,31,39,29,66,34,55,45,41,32,25]<\/code><\/pre>\n<p>\u73b0\u5728\u9700\u8981\u5c06\u8fd9\u4e9b\u5e74\u9f84\u5206\u4e3a\uff1a18-25,26-35,36-60\u4ee5\u53ca61\u53ca\u4ee5\u4e0a\u7684\u82e5\u5e72\u6570\u7ec4\u3002<\/p>\n<pre><code class=\"language-python\">bins = [18,25,35,60,100]\ncats = pd.cut(ages,bins)\ncats<\/code><\/pre>\n<pre><code>[(18, 25], (25, 35], (18, 25], (18, 25], (25, 35], ..., (35, 60], (35, 60], (35, 60], (25, 35], (18, 25]]\nLength: 19\nCategories (4, interval[int64]): [(18, 25] &lt; (25, 35] &lt; (35, 60] &lt; (60, 100]]<\/code><\/pre>\n<p>\u4ee5\u4e0a\u662f\u5c06ages\u5217\u8868\u4e2d\u4e0d\u540c\u7684\u6570\u636e\uff0c\u5206\u522b\u653e\u5165\u4e0d\u540c\u7684\u7bb1\u5b50\u5f53\u4e2d\u3002pandas\u8fd4\u56de\u7684\u5bf9\u8c61\u4e5f\u548c\u6211\u4eec\u5e73\u65f6\u6240\u89c1\u7684\u4e0d\u592a\u4e00\u6837\uff0c\u662f\u4e00\u4e2a\u7279\u6b8a\u7684Categorical\u5bf9\u8c61\u3002<\/p>\n<pre><code class=\"language-python\">cats.codes  # \u6307\u660e\u4e86ages\u4e2d\u6807\u7b7e\u5bf9\u5e94\u7684\u6570\u636e\u6240\u5728\u7684`\u7bb1\u5b50`<\/code><\/pre>\n<pre><code>array([0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 2, 1, 3, 1, 2, 2, 2, 1, 0],\n      dtype=int8)<\/code><\/pre>\n<pre><code class=\"language-python\">cats.categories  # \u8fd4\u56de\u6240\u6709\u7684\u7bb1\u5b50<\/code><\/pre>\n<pre><code>IntervalIndex([(18, 25], (25, 35], (35, 60], (60, 100]]\n              closed=&#039;right&#039;,\n              dtype=&#039;interval[int64]&#039;)<\/code><\/pre>\n<pre><code class=\"language-python\">pd.value_counts(cats)  # \u5bf9\u4e0d\u540c\u7bb1\u5b50\u4e2d\u7684\u6570\u636e\u8fdb\u884c\u8ba1\u6570<\/code><\/pre>\n<pre><code>(25, 35]     8\n(18, 25]     6\n(35, 60]     4\n(60, 100]    1\ndtype: int64<\/code><\/pre>\n<p>\u8868\u793a\u7bb1\u5b50\u7684\u7b26\u53f7\u4e0e\u533a\u95f4\u7684\u6570\u5b66\u7b26\u53f7\u662f\u4e00\u81f4\u7684\uff0c\u5c0f\u62ec\u53f7\u8868\u660e\u662f\u5f00\u653e\u7684\uff0c\u4e2d\u62ec\u53f7\u8868\u660e\u4ed6\u662f\u5c01\u95ed\u7684\uff0c\u4e5f\u5c31\u662f\u987e\u5934\u4e0d\u987e\u5c3e\u3002\u53ef\u4ee5\u81ea\u5df1\u6539\u53d8\u53c2\u6570right=False\u6765\u6539\u53d8\u54ea\u4e00\u8fb9\u5c01\u95ed<\/p>\n<pre><code class=\"language-python\">pd.cut(ages,[18,26,36,61,100],right=False)<\/code><\/pre>\n<pre><code>[[18, 26), [26, 36), [18, 26), [18, 26), [26, 36), ..., [36, 61), [36, 61), [36, 61), [26, 36), [18, 26)]\nLength: 19\nCategories (4, interval[int64]): [[18, 26) &lt; [26, 36) &lt; [36, 61) &lt; [61, 100)]<\/code><\/pre>\n<p>\u901a\u8fc7labels\u53c2\u6570\u4f20\u9012\u4e00\u4e2a\u5217\u8868\u6216\u8005\u6570\u7ec4\u6765\u4f20\u5165\u81ea\u5b9a\u4e49\u7684\u7bb1\u540d<\/p>\n<pre><code class=\"language-python\">group_names = [&#039;first&#039;,&quot;second&quot;,&#039;third&#039;,&#039;fourth&#039;]\npd.cut(ages,bins,labels=group_names)<\/code><\/pre>\n<pre><code>[first, second, first, first, second, ..., third, third, third, second, first]\nLength: 19\nCategories (4, object): [first &lt; second &lt; third &lt; fourth]<\/code><\/pre>\n<p>\u5982\u679c\u6211\u4eec\u4f20\u7ed9cut\u4e00\u4e2a\u6574\u6570\u4e2a\u7684\u7bb1\u5b50\u4ee3\u66ff\u663e\u793a\u7684\u7bb1\u8fb9\uff0cpandas\u4f1a\u81ea\u52a8\u6839\u636e\u6570\u636e\u5f53\u4e2d\u7684\u6700\u5927\u503c\u548c\u6700\u5c0f\u503c\u8ba1\u7b97\u51fa\u7b49\u957f\u7684\u7bb1\u5b50\u3002<\/p>\n<pre><code class=\"language-python\">data = np.random.rand(20)\npd.cut(data,4,precision=2)  # precision \u7cbe\u786e\u5ea6\uff0c\u7528\u4e8e\u63a7\u5236\u6570\u4f4d<\/code><\/pre>\n<pre><code>[(0.75, 0.99], (0.27, 0.51], (0.75, 0.99], (0.75, 0.99], (0.27, 0.51], ..., (0.75, 0.99], (0.034, 0.27], (0.034, 0.27], (0.51, 0.75], (0.034, 0.27]]\nLength: 20\nCategories (4, interval[float64]): [(0.034, 0.27] &lt; (0.27, 0.51] &lt; (0.51, 0.75] &lt; (0.75, 0.99]]<\/code><\/pre>\n<p>\u4f7f\u7528cut\u65b9\u6cd5\u901a\u5e38\u4e0d\u4f1a\u4f7f\u6211\u4eec\u6bcf\u4e2a\u7bb1\u5b50\u5177\u6709\u76f8\u540c\u6570\u636e\u91cf\u7684\u6570\u503c\uff0c\u4f46\u662fqcut\uff0c\u5b83\u662f\u57fa\u4e8e\u6837\u672c\u5206\u4e3a\u6570\u8fdb\u884c\u5206\u7bb1\u7684\uff0c\u53ef\u4ee5\u901a\u8fc7qcut\u5f97\u5230\u7b49\u957f\u7684\u7bb1\u5b50\u3002<\/p>\n<pre><code class=\"language-python\">data = np.random.randn(1000)  # \u751f\u4ea7\u6b63\u6001\u5206\u5e03\u7684\u6570\u7ec4\ncats = pd.qcut(data,4)  # \u5207\u6210\u56db\u4efd\npd.value_counts(cats)<\/code><\/pre>\n<pre><code>(0.714, 3.153]      250\n(0.0908, 0.714]     250\n(-0.592, 0.0908]    250\n(-3.242, -0.592]    250\ndtype: int64<\/code><\/pre>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_8.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_8.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n<h3>2.2.6\u3001\u68c0\u6d4b\u548c\u8fc7\u6ee4\u5f02\u5e38\u503c<\/h3>\n<pre><code class=\"language-python\">data = pd.DataFrame(np.random.randn(1000,4))\ndata.describe()<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>0<\/th>\n<th>1<\/th>\n<th>2<\/th>\n<th>3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>count<\/th>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<\/tr>\n<tr>\n<th>mean<\/th>\n<td>0.051415<\/td>\n<td>0.025348<\/td>\n<td>-0.022929<\/td>\n<td>-0.022217<\/td>\n<\/tr>\n<tr>\n<th>std<\/th>\n<td>0.974445<\/td>\n<td>1.001188<\/td>\n<td>0.988803<\/td>\n<td>0.970864<\/td>\n<\/tr>\n<tr>\n<th>min<\/th>\n<td>-2.954484<\/td>\n<td>-3.145678<\/td>\n<td>-2.807353<\/td>\n<td>-3.001159<\/td>\n<\/tr>\n<tr>\n<th>25%<\/th>\n<td>-0.601312<\/td>\n<td>-0.606223<\/td>\n<td>-0.684640<\/td>\n<td>-0.666618<\/td>\n<\/tr>\n<tr>\n<th>50%<\/th>\n<td>0.053944<\/td>\n<td>0.025130<\/td>\n<td>-0.000365<\/td>\n<td>-0.032060<\/td>\n<\/tr>\n<tr>\n<th>75%<\/th>\n<td>0.693812<\/td>\n<td>0.688407<\/td>\n<td>0.658130<\/td>\n<td>0.626298<\/td>\n<\/tr>\n<tr>\n<th>max<\/th>\n<td>2.861130<\/td>\n<td>3.532333<\/td>\n<td>3.326404<\/td>\n<td>3.127593<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u73b0\u5728\u9700\u8981\u627e\u5230\u4e00\u5217\u6570\u636e\u4e2d\u7edd\u5bf9\u503c\u5927\u4e8e\u4e09\u7684\u503c<\/p>\n<pre><code class=\"language-python\">col = data[2]\ncol[np.abs(col) &gt; 3]<\/code><\/pre>\n<pre><code>164    3.027784\n831    3.326404\nName: 2, dtype: float64<\/code><\/pre>\n<p>\u8981\u627e\u51fa\u6240\u6709\u503c\u4e2d\u5927\u4e8e3\u6216\u8005\u5c0f\u4e8e-3\u7684\u884c\uff0c\u53ef\u4ee5\u5bf9\u5e03\u5c14\u503cDataFrame\u4f7f\u7528any\u65b9\u6cd5<\/p>\n<pre><code class=\"language-python\">data[(np.abs(data) &gt; 3).any(1)]<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>0<\/th>\n<th>1<\/th>\n<th>2<\/th>\n<th>3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>164<\/th>\n<td>-1.156633<\/td>\n<td>-1.104849<\/td>\n<td>3.027784<\/td>\n<td>-0.174189<\/td>\n<\/tr>\n<tr>\n<th>624<\/th>\n<td>0.054955<\/td>\n<td>-3.145678<\/td>\n<td>-0.778852<\/td>\n<td>-2.280175<\/td>\n<\/tr>\n<tr>\n<th>664<\/th>\n<td>0.031400<\/td>\n<td>0.274078<\/td>\n<td>-0.924499<\/td>\n<td>-3.001159<\/td>\n<\/tr>\n<tr>\n<th>692<\/th>\n<td>1.397606<\/td>\n<td>3.532333<\/td>\n<td>0.127610<\/td>\n<td>0.816575<\/td>\n<\/tr>\n<tr>\n<th>725<\/th>\n<td>-1.336891<\/td>\n<td>0.206885<\/td>\n<td>0.677548<\/td>\n<td>3.127593<\/td>\n<\/tr>\n<tr>\n<th>831<\/th>\n<td>-0.406038<\/td>\n<td>0.283722<\/td>\n<td>3.326404<\/td>\n<td>-0.907127<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>\u9650\u5236\u503c\u5728-3\u52303\u4e4b\u95f4<\/p>\n<pre><code class=\"language-python\">data[np.abs(data) &gt; 3] = np.sign(data) * 3\ndata.describe()<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>0<\/th>\n<th>1<\/th>\n<th>2<\/th>\n<th>3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>count<\/th>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<td>1000.000000<\/td>\n<\/tr>\n<tr>\n<th>mean<\/th>\n<td>0.051415<\/td>\n<td>0.024962<\/td>\n<td>-0.023283<\/td>\n<td>-0.022344<\/td>\n<\/tr>\n<tr>\n<th>std<\/th>\n<td>0.974445<\/td>\n<td>0.999009<\/td>\n<td>0.987664<\/td>\n<td>0.970454<\/td>\n<\/tr>\n<tr>\n<th>min<\/th>\n<td>-2.954484<\/td>\n<td>-3.000000<\/td>\n<td>-2.807353<\/td>\n<td>-3.000000<\/td>\n<\/tr>\n<tr>\n<th>25%<\/th>\n<td>-0.601312<\/td>\n<td>-0.606223<\/td>\n<td>-0.684640<\/td>\n<td>-0.666618<\/td>\n<\/tr>\n<tr>\n<th>50%<\/th>\n<td>0.053944<\/td>\n<td>0.025130<\/td>\n<td>-0.000365<\/td>\n<td>-0.032060<\/td>\n<\/tr>\n<tr>\n<th>75%<\/th>\n<td>0.693812<\/td>\n<td>0.688407<\/td>\n<td>0.658130<\/td>\n<td>0.626298<\/td>\n<\/tr>\n<tr>\n<th>max<\/th>\n<td>2.861130<\/td>\n<td>3.000000<\/td>\n<td>3.000000<\/td>\n<td>3.000000<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>np.sign(data)\u6839\u636e\u6570\u636e\u4e2d\u7684\u503c\u7684\u6b63\u8d1f\u5206\u522b\u751f\u62101\u548c-1<\/p>\n<pre><code class=\"language-python\">np.sign(data).head()<\/code><\/pre>\n<\/style>\n<table border=\"1\" class=\"dataframe\">\n<thead>\n<tr style=\"text-align: right;\">\n<th><\/th>\n<th>0<\/th>\n<th>1<\/th>\n<th>2<\/th>\n<th>3<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>0<\/th>\n<td>1.0<\/td>\n<td>-1.0<\/td>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<\/tr>\n<tr>\n<th>1<\/th>\n<td>-1.0<\/td>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<\/tr>\n<tr>\n<th>2<\/th>\n<td>1.0<\/td>\n<td>-1.0<\/td>\n<td>-1.0<\/td>\n<td>1.0<\/td>\n<\/tr>\n<tr>\n<th>3<\/th>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<td>-1.0<\/td>\n<\/tr>\n<tr>\n<th>4<\/th>\n<td>1.0<\/td>\n<td>1.0<\/td>\n<td>-1.0<\/td>\n<td>-1.0<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p><div class='fancybox-wrapper lazyload-container-unload' data-fancybox='post-images' href='https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_9.jpg'><img class=\"lazyload lazyload-style-2\" src=\"data:image\/svg+xml;base64,PCEtLUFyZ29uTG9hZGluZy0tPgo8c3ZnIHdpZHRoPSIxIiBoZWlnaHQ9IjEiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgc3Ryb2tlPSIjZmZmZmZmMDAiPjxnPjwvZz4KPC9zdmc+\"  data-original=\"https:\/\/egonlin.com\/wp-content\/uploads\/2022\/03\/data_mp_9.jpg\" src=\"data:image\/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAADsQAAA7EAZUrDhsAAAANSURBVBhXYzh8+PB\/AAffA0nNPuCLAAAAAElFTkSuQmCC\" alt=\"\" \/><\/div><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u672c\u7ae0\u5b66\u4e60\u5185\u5bb9\uff1a \u6570\u636e\u5bfc\u5165\u3001\u5b58\u50a8 \u6570\u636e\u5904\u7406 \u6570\u636e\u64cd\u4f5c\u6700\u91cd\u8981\u7684\u4e00\u6b65\u4e5f\u662f\u7b2c\u4e00\u6b65\u5c31\u662f\u6536\u96c6\u6570\u636e\uff0c\u800c\u6536\u96c6\u6570\u636e\u7684\u65b9\u5f0f\u6709\u5f88\u591a\u79cd [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[316,310],"tags":[],"_links":{"self":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3704"}],"collection":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3704"}],"version-history":[{"count":0,"href":"https:\/\/egonlin.com\/index.php?rest_route=\/wp\/v2\/posts\/3704\/revisions"}],"wp:attachment":[{"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3704"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3704"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/egonlin.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3704"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}