{"id":1066718,"date":"2024-12-31T16:28:53","date_gmt":"2024-12-31T08:28:53","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1066718.html"},"modified":"2024-12-31T16:28:56","modified_gmt":"2024-12-31T08:28:56","slug":"python%e5%a6%82%e4%bd%95%e5%b0%86excel%e4%b8%ad%e6%96%87%e4%bb%b6%e5%90%88%e5%b9%b6","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1066718.html","title":{"rendered":"python\u5982\u4f55\u5c06Excel\u4e2d\u6587\u4ef6\u5408\u5e76"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-docs.pingcode.com\/wp-content\/uploads\/2024\/12\/4017c962-93f8-4687-8946-dafd2522da49.webp?x-oss-process=image\/auto-orient,1\/format,webp\" alt=\"python\u5982\u4f55\u5c06Excel\u4e2d\u6587\u4ef6\u5408\u5e76\" \/><\/p>\n<p><p> <strong>Python\u5c06Excel\u6587\u4ef6\u5408\u5e76\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528pandas\u5e93\u3001openpyxl\u5e93\u3001xlrd\u5e93\u7b49\uff0c\u5176\u4e2dpandas\u5e93\u6700\u4e3a\u5e38\u7528\u3001\u7b80\u5355\u6613\u7528\u3001\u529f\u80fd\u5f3a\u5927\u3002<\/strong>pandas\u5e93\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u51fd\u6570\u548c\u65b9\u6cd5\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8bfb\u53d6\u3001\u5904\u7406\u3001\u5408\u5e76\u548c\u4fdd\u5b58Excel\u6587\u4ef6\u3002\u63a5\u4e0b\u6765\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528pandas\u5e93\u6765\u5408\u5e76Excel\u6587\u4ef6\u3002<\/p>\n<\/p>\n<p><h2>\u4e00\u3001\u5b89\u88c5\u548c\u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h2>\n<\/p>\n<p><p>\u5728\u5f00\u59cb\u4e4b\u524d\uff0c\u9996\u5148\u9700\u8981\u786e\u4fdd\u5df2\u7ecf\u5b89\u88c5\u4e86pandas\u5e93\u3002\u5982\u679c\u6ca1\u6709\u5b89\u88c5\uff0c\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u8fdb\u884c\u5b89\u88c5\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">pip install pandas<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u5b89\u88c5\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u5728Python\u811a\u672c\u4e2d\u5bfc\u5165pandas\u5e93\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u4e8c\u3001\u8bfb\u53d6Excel\u6587\u4ef6<\/h2>\n<\/p>\n<p><p>pandas\u63d0\u4f9b\u4e86<code>pd.read_excel()<\/code>\u51fd\u6570\u6765\u8bfb\u53d6Excel\u6587\u4ef6\u3002\u5047\u8bbe\u6211\u4eec\u6709\u591a\u4e2aExcel\u6587\u4ef6\uff0c\u6bcf\u4e2a\u6587\u4ef6\u5305\u542b\u4e00\u4e2a\u6216\u591a\u4e2a\u5de5\u4f5c\u8868\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u8be5\u51fd\u6570\u5c06\u8fd9\u4e9b\u6587\u4ef6\u8bfb\u53d6\u5230DataFrame\u4e2d\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8bfb\u53d6\u5355\u4e2aExcel\u6587\u4ef6<\/p>\n<p>df1 = pd.read_excel(&#39;file1.xlsx&#39;)<\/p>\n<h2><strong>\u8bfb\u53d6\u591a\u4e2aExcel\u6587\u4ef6<\/strong><\/h2>\n<p>df2 = pd.read_excel(&#39;file2.xlsx&#39;)<\/p>\n<p>df3 = pd.read_excel(&#39;file3.xlsx&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u4e09\u3001\u5408\u5e76\u591a\u4e2aExcel\u6587\u4ef6<\/h2>\n<\/p>\n<p><p>\u5408\u5e76Excel\u6587\u4ef6\u7684\u65b9\u5f0f\u6709\u591a\u79cd\uff0c\u5177\u4f53\u53d6\u51b3\u4e8e\u5b9e\u9645\u9700\u6c42\u3002\u5e38\u89c1\u7684\u5408\u5e76\u65b9\u5f0f\u5305\u62ec\u7eb5\u5411\u5408\u5e76\uff08\u6309\u884c\u5408\u5e76\uff09\u548c\u6a2a\u5411\u5408\u5e76\uff08\u6309\u5217\u5408\u5e76\uff09\u3002<\/p>\n<\/p>\n<p><h3>1. \u7eb5\u5411\u5408\u5e76\uff08\u6309\u884c\u5408\u5e76\uff09<\/h3>\n<\/p>\n<p><p>\u7eb5\u5411\u5408\u5e76\u662f\u5c06\u591a\u4e2aDataFrame\u6309\u884c\u5806\u53e0\u5728\u4e00\u8d77\uff0c\u9002\u7528\u4e8e\u591a\u4e2aExcel\u6587\u4ef6\u5177\u6709\u76f8\u540c\u7684\u5217\u7ed3\u6784\u7684\u60c5\u51b5\u3002\u53ef\u4ee5\u4f7f\u7528<code>pd.concat()<\/code>\u51fd\u6570\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8bfb\u53d6\u591a\u4e2aExcel\u6587\u4ef6\u5230DataFrame\u5217\u8868\u4e2d<\/p>\n<p>df_list = [pd.read_excel(f&#39;file{i}.xlsx&#39;) for i in range(1, 4)]<\/p>\n<h2><strong>\u7eb5\u5411\u5408\u5e76DataFrame<\/strong><\/h2>\n<p>merged_df = pd.concat(df_list, axis=0, ignore_index=True)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>2. \u6a2a\u5411\u5408\u5e76\uff08\u6309\u5217\u5408\u5e76\uff09<\/h3>\n<\/p>\n<p><p>\u6a2a\u5411\u5408\u5e76\u662f\u5c06\u591a\u4e2aDataFrame\u6309\u5217\u62fc\u63a5\u5728\u4e00\u8d77\uff0c\u9002\u7528\u4e8e\u591a\u4e2aExcel\u6587\u4ef6\u5177\u6709\u76f8\u540c\u7684\u884c\u7ed3\u6784\u7684\u60c5\u51b5\u3002\u53ef\u4ee5\u4f7f\u7528<code>pd.concat()<\/code>\u51fd\u6570\u5e76\u6307\u5b9a<code>axis=1<\/code>\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8bfb\u53d6\u591a\u4e2aExcel\u6587\u4ef6\u5230DataFrame\u5217\u8868\u4e2d<\/p>\n<p>df_list = [pd.read_excel(f&#39;file{i}.xlsx&#39;) for i in range(1, 4)]<\/p>\n<h2><strong>\u6a2a\u5411\u5408\u5e76DataFrame<\/strong><\/h2>\n<p>merged_df = pd.concat(df_list, axis=1)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u56db\u3001\u5904\u7406\u91cd\u590d\u6570\u636e\u548c\u7f3a\u5931\u503c<\/h2>\n<\/p>\n<p><p>\u5728\u5408\u5e76\u591a\u4e2aExcel\u6587\u4ef6\u540e\uff0c\u53ef\u80fd\u4f1a\u51fa\u73b0\u91cd\u590d\u6570\u636e\u548c\u7f3a\u5931\u503c\u3002pandas\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u65b9\u6cd5\u6765\u5904\u7406\u8fd9\u4e9b\u95ee\u9898\u3002<\/p>\n<\/p>\n<p><h3>1. \u5904\u7406\u91cd\u590d\u6570\u636e<\/h3>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528<code>drop_duplicates()<\/code>\u51fd\u6570\u6765\u5220\u9664\u91cd\u590d\u7684\u884c\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u5220\u9664\u91cd\u590d\u884c<\/p>\n<p>merged_df.drop_duplicates(inplace=True)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>2. \u5904\u7406\u7f3a\u5931\u503c<\/h3>\n<\/p>\n<p><p>\u53ef\u4ee5\u4f7f\u7528<code>fillna()<\/code>\u51fd\u6570\u6765\u586b\u5145\u7f3a\u5931\u503c\uff0c\u6216\u4f7f\u7528<code>dropna()<\/code>\u51fd\u6570\u6765\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c\u6216\u5217\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u586b\u5145\u7f3a\u5931\u503c<\/p>\n<p>merged_df.fillna(value=0, inplace=True)<\/p>\n<h2><strong>\u5220\u9664\u5305\u542b\u7f3a\u5931\u503c\u7684\u884c<\/strong><\/h2>\n<p>merged_df.dropna(inplace=True)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u4e94\u3001\u4fdd\u5b58\u5408\u5e76\u540e\u7684Excel\u6587\u4ef6<\/h2>\n<\/p>\n<p><p>\u5408\u5e76\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>to_excel()<\/code>\u51fd\u6570\u5c06\u5408\u5e76\u540e\u7684DataFrame\u4fdd\u5b58\u5230\u65b0\u7684Excel\u6587\u4ef6\u4e2d\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u4fdd\u5b58\u5408\u5e76\u540e\u7684DataFrame\u5230Excel\u6587\u4ef6<\/p>\n<p>merged_df.to_excel(&#39;merged_file.xlsx&#39;, index=False)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u516d\u3001\u5904\u7406\u591a\u4e2a\u5de5\u4f5c\u8868<\/h2>\n<\/p>\n<p><p>\u5982\u679c\u6bcf\u4e2aExcel\u6587\u4ef6\u4e2d\u5305\u542b\u591a\u4e2a\u5de5\u4f5c\u8868\uff0c\u53ef\u4ee5\u4f7f\u7528<code>pd.ExcelFile()<\/code>\u51fd\u6570\u6765\u8bfb\u53d6\u5de5\u4f5c\u8868\u540d\u79f0\uff0c\u5e76\u4f7f\u7528\u5faa\u73af\u6765\u8bfb\u53d6\u548c\u5408\u5e76\u6bcf\u4e2a\u5de5\u4f5c\u8868\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8bfb\u53d6Excel\u6587\u4ef6<\/p>\n<p>xls = pd.ExcelFile(&#39;file1.xlsx&#39;)<\/p>\n<h2><strong>\u8bfb\u53d6\u6240\u6709\u5de5\u4f5c\u8868\u540d\u79f0<\/strong><\/h2>\n<p>sheet_names = xls.sheet_names<\/p>\n<h2><strong>\u8bfb\u53d6\u6240\u6709\u5de5\u4f5c\u8868\u5e76\u5408\u5e76<\/strong><\/h2>\n<p>df_list = [pd.read_excel(xls, sheet_name=sheet) for sheet in sheet_names]<\/p>\n<p>merged_df = pd.concat(df_list, axis=0, ignore_index=True)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h2>\u4e03\u3001\u66f4\u591a\u9ad8\u7ea7\u64cd\u4f5c<\/h2>\n<\/p>\n<p><p>pandas\u5e93\u63d0\u4f9b\u4e86\u8bb8\u591a\u9ad8\u7ea7\u64cd\u4f5c\uff0c\u80fd\u591f\u6ee1\u8db3\u66f4\u52a0\u590d\u6742\u7684\u9700\u6c42\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528<code>merge()<\/code>\u51fd\u6570\u8fdb\u884c\u6570\u636e\u8868\u7684\u5408\u5e76\u64cd\u4f5c\uff0c\u7c7b\u4f3c\u4e8eSQL\u4e2d\u7684JOIN\u64cd\u4f5c\u3002<\/p>\n<\/p>\n<p><p>\u793a\u4f8b\u5982\u4e0b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\"># \u8bfb\u53d6\u4e24\u4e2aExcel\u6587\u4ef6<\/p>\n<p>df1 = pd.read_excel(&#39;file1.xlsx&#39;)<\/p>\n<p>df2 = pd.read_excel(&#39;file2.xlsx&#39;)<\/p>\n<h2><strong>\u6309\u7167\u6307\u5b9a\u5217\u8fdb\u884c\u5408\u5e76<\/strong><\/h2>\n<p>merged_df = pd.merge(df1, df2, on=&#39;key_column&#39;, how=&#39;inner&#39;)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528Python\u4e2d\u7684pandas\u5e93\u8f7b\u677e\u5b9e\u73b0Excel\u6587\u4ef6\u7684\u5408\u5e76\u64cd\u4f5c\u3002\u6839\u636e\u5b9e\u9645\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5408\u5e76\u65b9\u5f0f\u548c\u5904\u7406\u65b9\u6cd5\uff0c\u53ef\u4ee5\u9ad8\u6548\u5730\u5904\u7406\u548c\u5206\u6790\u6570\u636e\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u4e2d\u8bfb\u53d6\u591a\u4e2aExcel\u6587\u4ef6\uff1f<\/strong><br \/>\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528<code>pandas<\/code>\u5e93\u6765\u8bfb\u53d6\u591a\u4e2aExcel\u6587\u4ef6\u3002\u9996\u5148\uff0c\u786e\u4fdd\u5b89\u88c5\u4e86<code>pandas<\/code>\u548c<code>openpyxl<\/code>\u5e93\u3002\u4f7f\u7528<code>pd.read_excel()<\/code>\u51fd\u6570\u53ef\u4ee5\u8bfb\u53d6\u5355\u4e2aExcel\u6587\u4ef6\uff0c\u800c\u8981\u8bfb\u53d6\u591a\u4e2a\u6587\u4ef6\uff0c\u53ef\u4ee5\u4f7f\u7528\u5faa\u73af\u6216\u5217\u8868\u63a8\u5bfc\u5f0f\u5c06\u6240\u6709\u6587\u4ef6\u8bfb\u5165\u4e00\u4e2aDataFrame\u4e2d\u3002\u4f8b\u5982\uff0c\u53ef\u4ee5\u4f7f\u7528<code>glob<\/code>\u6a21\u5757\u6765\u83b7\u53d6\u6240\u6709Excel\u6587\u4ef6\u8def\u5f84\uff0c\u5e76\u9010\u4e2a\u8bfb\u53d6\u5b83\u4eec\u3002<\/p>\n<p><strong>\u5408\u5e76Excel\u6587\u4ef6\u65f6\uff0c\u5982\u4f55\u5904\u7406\u4e0d\u540c\u683c\u5f0f\u7684\u6570\u636e\uff1f<\/strong><br \/>\u5728\u5408\u5e76\u591a\u4e2aExcel\u6587\u4ef6\u65f6\uff0c\u786e\u4fdd\u5404\u6587\u4ef6\u7684\u6570\u636e\u683c\u5f0f\u4e00\u81f4\u662f\u975e\u5e38\u91cd\u8981\u7684\u3002\u5982\u679c\u67d0\u4e9b\u6587\u4ef6\u7684\u5217\u540d\u4e0d\u540c\u6216\u6570\u636e\u7c7b\u578b\u4e0d\u4e00\u81f4\uff0c\u53ef\u4ee5\u5728\u5408\u5e76\u4e4b\u524d\u5bf9\u5b83\u4eec\u8fdb\u884c\u6807\u51c6\u5316\u5904\u7406\u3002\u901a\u8fc7<code>pandas<\/code>\u4e2d\u7684<code>rename()<\/code>\u548c<code>astype()<\/code>\u65b9\u6cd5\uff0c\u53ef\u4ee5\u4fee\u6539\u5217\u540d\u548c\u6570\u636e\u7c7b\u578b\uff0c\u4f7f\u6240\u6709\u6570\u636e\u5728\u5408\u5e76\u65f6\u80fd\u591f\u987a\u5229\u5bf9\u9f50\u3002<\/p>\n<p><strong>\u5408\u5e76\u540e\u7684Excel\u6587\u4ef6\u53ef\u4ee5\u5982\u4f55\u4fdd\u5b58\uff1f<\/strong><br \/>\u5408\u5e76\u5b8c\u6210\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>pandas<\/code>\u7684<code>to_excel()<\/code>\u51fd\u6570\u5c06\u7ed3\u679c\u4fdd\u5b58\u4e3a\u65b0\u7684Excel\u6587\u4ef6\u3002\u53ef\u4ee5\u6307\u5b9a\u6587\u4ef6\u540d\u548c\u4fdd\u5b58\u8def\u5f84\uff0c\u5e76\u8bbe\u7f6e<code>index=False<\/code>\u4ee5\u907f\u514d\u5c06\u7d22\u5f15\u5199\u5165\u6587\u4ef6\u3002\u5982\u679c\u9700\u8981\u5c06\u6570\u636e\u4fdd\u5b58\u4e3a\u591a\u4e2a\u5de5\u4f5c\u8868\uff0c\u53ef\u4ee5\u4f7f\u7528<code>ExcelWriter<\/code>\u7c7b\u6765\u5b9e\u73b0\u3002\u8fd9\u6837\uff0c\u60a8\u53ef\u4ee5\u5c06\u4e0d\u540c\u7684\u6570\u636e\u96c6\u5199\u5165\u540c\u4e00\u4e2aExcel\u6587\u4ef6\u7684\u4e0d\u540c\u5de5\u4f5c\u8868\u4e2d\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u5c06Excel\u6587\u4ef6\u5408\u5e76\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528pandas\u5e93\u3001openpyxl\u5e93\u3001xlrd\u5e93\u7b49\uff0c\u5176\u4e2dpanda [&hellip;]","protected":false},"author":3,"featured_media":1066728,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1066718"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1066718"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1066718\/revisions"}],"predecessor-version":[{"id":1066734,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1066718\/revisions\/1066734"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1066728"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1066718"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1066718"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1066718"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}