{"id":1077388,"date":"2025-01-08T12:01:52","date_gmt":"2025-01-08T04:01:52","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1077388.html"},"modified":"2025-01-08T12:01:55","modified_gmt":"2025-01-08T04:01:55","slug":"python%e4%b8%ad%e5%a6%82%e4%bd%95%e7%a7%bb%e9%99%a4%e7%9b%b8%e5%90%8c%e7%9a%84%e7%ad%89%e5%88%97-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1077388.html","title":{"rendered":"python\u4e2d\u5982\u4f55\u79fb\u9664\u76f8\u540c\u7684\u7b49\u5217"},"content":{"rendered":"<p style=\"text-align:center;\" ><img decoding=\"async\" src=\"https:\/\/cdn-kb.worktile.com\/kb\/wp-content\/uploads\/2024\/04\/24181454\/35541350-56f9-4444-ae76-bc3190d10240.webp\" alt=\"python\u4e2d\u5982\u4f55\u79fb\u9664\u76f8\u540c\u7684\u7b49\u5217\" \/><\/p>\n<p><p> \u5728Python\u4e2d\uff0c\u79fb\u9664\u76f8\u540c\u7684\u7b49\u5217\u901a\u5e38\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528Pandas\u5e93\u6765\u5b9e\u73b0\u3002<strong>\u53ef\u4ee5\u4f7f\u7528drop_duplicates()\u65b9\u6cd5\u3001\u57fa\u4e8e\u5217\u7684\u7b5b\u9009\u64cd\u4f5c\u3001\u7ed3\u5408\u6761\u4ef6\u8fc7\u6ee4\u7b49\u65b9\u5f0f\u6765\u79fb\u9664\u91cd\u590d\u7684\u5217<\/strong>\u3002\u5176\u4e2d\uff0c<strong>drop_duplicates()<\/strong> \u662f\u4e00\u79cd\u5e38\u89c1\u4e14\u6709\u6548\u7684\u65b9\u6cd5\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\u3002<\/p>\n<\/p>\n<p><h3>\u4e00\u3001\u4f7f\u7528Pandas\u5e93<\/h3>\n<\/p>\n<p><p>Pandas\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u6570\u636e\u5904\u7406\u5e93\uff0c\u63d0\u4f9b\u4e86\u591a\u79cd\u65b9\u6cd5\u6765\u5904\u7406\u548c\u64cd\u4f5c\u6570\u636e\u6846\uff0c\u5305\u62ec\u79fb\u9664\u91cd\u590d\u7684\u5217\u3002<\/p>\n<\/p>\n<p><h4>1. \u4f7f\u7528 <code>drop_duplicates()<\/code> \u65b9\u6cd5<\/h4>\n<\/p>\n<p><p><code>drop_duplicates()<\/code> \u65b9\u6cd5\u53ef\u4ee5\u7528\u6765\u79fb\u9664\u6570\u636e\u6846\u4e2d\u91cd\u590d\u7684\u5217\u3002\u8fd9\u4e2a\u65b9\u6cd5\u975e\u5e38\u7b80\u4fbf\u4e14\u9ad8\u6548\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<h2><strong>\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n<p>data = {&#39;A&#39;: [1, 2, 3], &#39;B&#39;: [1, 2, 3], &#39;C&#39;: [4, 5, 6], &#39;D&#39;: [1, 2, 3]}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<h2><strong>\u79fb\u9664\u91cd\u590d\u7684\u5217<\/strong><\/h2>\n<p>df = df.T.drop_duplicates().T<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h4>2. \u57fa\u4e8e\u5217\u7684\u7b5b\u9009\u64cd\u4f5c<\/h4>\n<\/p>\n<p><p>\u6211\u4eec\u8fd8\u53ef\u4ee5\u901a\u8fc7\u624b\u52a8\u7b5b\u9009\u548c\u6bd4\u8f83\u5217\u6765\u79fb\u9664\u91cd\u590d\u7684\u5217\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<h2><strong>\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n<p>data = {&#39;A&#39;: [1, 2, 3], &#39;B&#39;: [1, 2, 3], &#39;C&#39;: [4, 5, 6], &#39;D&#39;: [1, 2, 3]}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<h2><strong>\u83b7\u53d6\u6240\u6709\u5217\u7684\u540d\u79f0<\/strong><\/h2>\n<p>columns = df.columns<\/p>\n<h2><strong>\u521d\u59cb\u5316\u4e00\u4e2a\u7a7a\u5217\u8868\u6765\u5b58\u50a8\u9700\u8981\u4fdd\u7559\u7684\u5217<\/strong><\/h2>\n<p>keep_columns = []<\/p>\n<h2><strong>\u8fed\u4ee3\u6240\u6709\u5217<\/strong><\/h2>\n<p>for i in range(len(columns)):<\/p>\n<p>    duplicate = False<\/p>\n<p>    for j in range(i):<\/p>\n<p>        if df[columns[i]].equals(df[columns[j]]):<\/p>\n<p>            duplicate = True<\/p>\n<p>            break<\/p>\n<p>    if not duplicate:<\/p>\n<p>        keep_columns.append(columns[i])<\/p>\n<h2><strong>\u4ec5\u4fdd\u7559\u672a\u91cd\u590d\u7684\u5217<\/strong><\/h2>\n<p>df = df[keep_columns]<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e8c\u3001\u7ed3\u5408\u6761\u4ef6\u8fc7\u6ee4<\/h3>\n<\/p>\n<p><p>\u6709\u65f6\u5019\uff0c\u6211\u4eec\u53ef\u80fd\u9700\u8981\u7ed3\u5408\u67d0\u4e9b\u6761\u4ef6\u6765\u8fc7\u6ee4\u548c\u79fb\u9664\u91cd\u590d\u7684\u5217\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8b\uff1a<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import pandas as pd<\/p>\n<h2><strong>\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n<p>data = {&#39;A&#39;: [1, 2, 3], &#39;B&#39;: [1, 2, 3], &#39;C&#39;: [4, 5, 6], &#39;D&#39;: [1, 2, 3]}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<h2><strong>\u5b9a\u4e49\u4e00\u4e2a\u51fd\u6570\u6765\u68c0\u67e5\u5217\u662f\u5426\u91cd\u590d<\/strong><\/h2>\n<p>def is_duplicate(df, col1, col2):<\/p>\n<p>    return df[col1].equals(df[col2])<\/p>\n<h2><strong>\u521d\u59cb\u5316\u4e00\u4e2a\u7a7a\u5217\u8868\u6765\u5b58\u50a8\u9700\u8981\u4fdd\u7559\u7684\u5217<\/strong><\/h2>\n<p>keep_columns = []<\/p>\n<h2><strong>\u8fed\u4ee3\u6240\u6709\u5217<\/strong><\/h2>\n<p>for i in range(len(df.columns)):<\/p>\n<p>    duplicate = False<\/p>\n<p>    for j in range(i):<\/p>\n<p>        if is_duplicate(df, df.columns[i], df.columns[j]):<\/p>\n<p>            duplicate = True<\/p>\n<p>            break<\/p>\n<p>    if not duplicate:<\/p>\n<p>        keep_columns.append(df.columns[i])<\/p>\n<h2><strong>\u4ec5\u4fdd\u7559\u672a\u91cd\u590d\u7684\u5217<\/strong><\/h2>\n<p>df = df[keep_columns]<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u4e09\u3001\u4f7f\u7528NumPy\u548c\u96c6\u5408\u64cd\u4f5c<\/h3>\n<\/p>\n<p><p>\u5982\u679c\u4f60\u66f4\u559c\u6b22\u4f7f\u7528NumPy\u6216\u5176\u4ed6\u65b9\u6cd5\uff0c\u4e5f\u53ef\u4ee5\u901a\u8fc7\u8fd9\u79cd\u65b9\u5f0f\u5b9e\u73b0\u3002<\/p>\n<\/p>\n<p><pre><code class=\"language-python\">import numpy as np<\/p>\n<h2><strong>\u521b\u5efa\u4e00\u4e2a\u793a\u4f8b\u6570\u636e\u6846<\/strong><\/h2>\n<p>data = {&#39;A&#39;: [1, 2, 3], &#39;B&#39;: [1, 2, 3], &#39;C&#39;: [4, 5, 6], &#39;D&#39;: [1, 2, 3]}<\/p>\n<p>df = pd.DataFrame(data)<\/p>\n<h2><strong>\u8f6c\u6362\u4e3aNumPy\u6570\u7ec4<\/strong><\/h2>\n<p>array = df.values<\/p>\n<h2><strong>\u521d\u59cb\u5316\u4e00\u4e2a\u5217\u8868\u6765\u5b58\u50a8\u672a\u91cd\u590d\u7684\u5217\u7d22\u5f15<\/strong><\/h2>\n<p>keep_indices = []<\/p>\n<h2><strong>\u8fed\u4ee3\u6240\u6709\u5217<\/strong><\/h2>\n<p>for i in range(array.shape[1]):<\/p>\n<p>    duplicate = False<\/p>\n<p>    for j in range(i):<\/p>\n<p>        if np.array_equal(array[:, i], array[:, j]):<\/p>\n<p>            duplicate = True<\/p>\n<p>            break<\/p>\n<p>    if not duplicate:<\/p>\n<p>        keep_indices.append(i)<\/p>\n<h2><strong>\u4ec5\u4fdd\u7559\u672a\u91cd\u590d\u7684\u5217<\/strong><\/h2>\n<p>df = df.iloc[:, keep_indices]<\/p>\n<p>print(df)<\/p>\n<p><\/code><\/pre>\n<\/p>\n<p><h3>\u603b\u7ed3<\/h3>\n<\/p>\n<p><p>\u901a\u8fc7\u4ee5\u4e0a\u51e0\u79cd\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u6709\u6548\u5730\u79fb\u9664Python\u4e2d\u6570\u636e\u6846\u7684\u91cd\u590d\u5217\u3002<strong>Pandas\u5e93\u63d0\u4f9b\u4e86\u6700\u7b80\u4fbf\u7684\u65b9\u6cd5\uff0c\u4f7f\u7528 <code>drop_duplicates()<\/code> \u53ef\u4ee5\u5feb\u901f\u79fb\u9664\u91cd\u590d\u5217<\/strong>\u3002\u540c\u65f6\uff0c\u6211\u4eec\u4e5f\u53ef\u4ee5\u901a\u8fc7\u624b\u52a8\u5217\u7b5b\u9009\u64cd\u4f5c\u3001\u7ed3\u5408\u6761\u4ef6\u8fc7\u6ee4\u548cNumPy\u6570\u7ec4\u64cd\u4f5c\u6765\u5b9e\u73b0\u8fd9\u4e00\u76ee\u6807\u3002\u6839\u636e\u5177\u4f53\u9700\u6c42\u9009\u62e9\u5408\u9002\u7684\u65b9\u6cd5\uff0c\u53ef\u4ee5\u4f7f\u6211\u4eec\u7684\u6570\u636e\u5904\u7406\u5de5\u4f5c\u66f4\u52a0\u9ad8\u6548\u548c\u7075\u6d3b\u3002<\/p>\n<\/p>\n<h2><strong>\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n<p> <strong>\u5982\u4f55\u5728Python\u4e2d\u5904\u7406\u91cd\u590d\u7684\u5217\uff1f<\/strong><br \/>\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528Pandas\u5e93\u6765\u8f7b\u677e\u5904\u7406\u6570\u636e\u6846\u4e2d\u7684\u91cd\u590d\u5217\u3002\u9996\u5148\uff0c\u4f7f\u7528<code>pandas.DataFrame<\/code>\u521b\u5efa\u6570\u636e\u6846\uff0c\u7136\u540e\u901a\u8fc7<code>DataFrame.loc<\/code>\u548c<code>DataFrame.columns<\/code>\u5c5e\u6027\u7ed3\u5408<code>DataFrame.duplicated()<\/code>\u65b9\u6cd5\u6765\u8bc6\u522b\u548c\u79fb\u9664\u91cd\u590d\u7684\u5217\u3002\u5177\u4f53\u7684\u4ee3\u7801\u793a\u4f8b\u53ef\u4ee5\u53c2\u8003\u4ee5\u4e0b\u5185\u5bb9\uff1a<\/p>\n<pre><code class=\"language-python\">import pandas as pd\n\n# \u521b\u5efa\u793a\u4f8b\u6570\u636e\u6846\ndata = {\n    &#39;A&#39;: [1, 2, 3],\n    &#39;B&#39;: [4, 5, 6],\n    &#39;A&#39;: [7, 8, 9],  # \u91cd\u590d\u5217\n}\n\ndf = pd.DataFrame(data)\n\n# \u79fb\u9664\u91cd\u590d\u5217\ndf = df.loc[:, ~df.columns.duplicated()]\n<\/code><\/pre>\n<p><strong>\u5728\u79fb\u9664\u5217\u65f6\u4f1a\u5f71\u54cd\u6570\u636e\u5417\uff1f<\/strong><br \/>\u79fb\u9664\u91cd\u590d\u5217\u65f6\uff0c\u4fdd\u7559\u7684\u5217\u4f1a\u6839\u636e\u6570\u636e\u6846\u7684\u987a\u5e8f\u800c\u5b9a\u3002\u5982\u679c\u4e24\u4e2a\u5217\u540d\u76f8\u540c\uff0cPandas\u9ed8\u8ba4\u4fdd\u7559\u7b2c\u4e00\u4e2a\u51fa\u73b0\u7684\u5217\u3002\u56e0\u6b64\uff0c\u5efa\u8bae\u5728\u79fb\u9664\u4e4b\u524d\u786e\u8ba4\u9700\u8981\u4fdd\u7559\u7684\u5217\uff0c\u4ee5\u514d\u4e22\u5931\u91cd\u8981\u6570\u636e\u3002<\/p>\n<p><strong>\u6709\u6ca1\u6709\u5176\u4ed6\u65b9\u6cd5\u53ef\u4ee5\u5904\u7406\u91cd\u590d\u5217\uff1f<\/strong><br \/>\u9664\u4e86\u4f7f\u7528Pandas\u5e93\u5916\uff0cPython\u7684\u6807\u51c6\u5e93\u4e5f\u53ef\u4ee5\u5b9e\u73b0\u76f8\u4f3c\u7684\u529f\u80fd\u3002\u901a\u8fc7\u5c06\u5217\u540d\u8f6c\u6362\u4e3a\u96c6\u5408\u6765\u6392\u9664\u91cd\u590d\u9879\uff0c\u867d\u7136\u8fd9\u79cd\u65b9\u6cd5\u6bd4\u8f83\u7e41\u7410\uff0c\u4f46\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\u53ef\u80fd\u66f4\u9002\u5408\u7279\u5b9a\u9700\u6c42\u3002\u4f7f\u7528\u5b57\u5178\u6216\u96c6\u5408\u53ef\u4ee5\u5e2e\u52a9\u786e\u4fdd\u5217\u540d\u7684\u552f\u4e00\u6027\uff0c\u4ece\u800c\u5b9e\u73b0\u53bb\u91cd\u3002<\/p>\n<p><strong>\u79fb\u9664\u91cd\u590d\u5217\u540e\u5982\u4f55\u9a8c\u8bc1\u7ed3\u679c\uff1f<\/strong><br \/>\u5728\u79fb\u9664\u91cd\u590d\u5217\u540e\uff0c\u53ef\u4ee5\u4f7f\u7528<code>DataFrame.info()<\/code>\u6216<code>DataFrame.head()<\/code>\u65b9\u6cd5\u6765\u9a8c\u8bc1\u6570\u636e\u6846\u7684\u7ed3\u6784\u548c\u5185\u5bb9\u3002\u8fd9\u5c06\u5e2e\u52a9\u4f60\u786e\u8ba4\u6570\u636e\u6846\u4e2d\u53ea\u4fdd\u7559\u4e86\u552f\u4e00\u7684\u5217\uff0c\u5e76\u4e14\u6570\u636e\u7684\u5b8c\u6574\u6027\u6ca1\u6709\u53d7\u5230\u5f71\u54cd\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\uff0c\u79fb\u9664\u76f8\u540c\u7684\u7b49\u5217\u901a\u5e38\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528Pandas\u5e93\u6765\u5b9e\u73b0\u3002\u53ef\u4ee5\u4f7f\u7528drop_duplicates( [&hellip;]","protected":false},"author":3,"featured_media":1077394,"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\/1077388"}],"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=1077388"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1077388\/revisions"}],"predecessor-version":[{"id":1077397,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1077388\/revisions\/1077397"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1077394"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1077388"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1077388"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1077388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}