{"id":1024632,"date":"2024-12-30T14:15:26","date_gmt":"2024-12-30T06:15:26","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1024632.html"},"modified":"2024-12-30T14:15:28","modified_gmt":"2024-12-30T06:15:28","slug":"python%e5%a6%82%e4%bd%95%e6%b1%82%e5%b9%b3%e5%9d%87%e8%af%8d%e9%95%bf-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1024632.html","title":{"rendered":"python\u5982\u4f55\u6c42\u5e73\u5747\u8bcd\u957f"},"content":{"rendered":"

\"python\u5982\u4f55\u6c42\u5e73\u5747\u8bcd\u957f\"<\/p>\n

Python\u6c42\u5e73\u5747\u8bcd\u957f\u7684\u65b9\u6cd5<\/strong>\u6709\uff1a\u8bfb\u53d6\u6587\u672c\u3001\u5206\u5272\u5355\u8bcd\u3001\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6\u3001\u6c42\u5e73\u5747\u503c\u3001\u4f7f\u7528\u5185\u7f6e\u51fd\u6570\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u63cf\u8ff0\uff1a<\/p>\n<\/p>\n

\u8bfb\u53d6\u6587\u672c<\/strong>\uff1a\u5728\u6c42\u5e73\u5747\u8bcd\u957f\u4e4b\u524d\uff0c\u6211\u4eec\u9700\u8981\u8bfb\u53d6\u6587\u672c\u6570\u636e\u3002Python\u63d0\u4f9b\u4e86\u591a\u79cd\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\u7684\u65b9\u6cd5\uff0c\u4f8b\u5982\u4f7f\u7528open()\u51fd\u6570\u3001pandas\u5e93\u7b49\u3002\u6211\u4eec\u53ef\u4ee5\u9009\u62e9\u9002\u5408\u81ea\u5df1\u7684\u65b9\u6cd5\u8bfb\u53d6\u6587\u672c\u5185\u5bb9\u3002<\/p>\n<\/p>\n

\u5206\u5272\u5355\u8bcd<\/strong>\uff1a\u8bfb\u53d6\u6587\u672c\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u5c06\u6587\u672c\u5206\u5272\u6210\u5355\u8bcd\u3002Python\u7684split()\u65b9\u6cd5\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u5b57\u7b26\u4e32\u6309\u7a7a\u683c\u5206\u5272\u6210\u5355\u8bcd\u5217\u8868\u3002\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u66f4\u590d\u6742\u7684\u5206\u5272\u64cd\u4f5c\u3002<\/p>\n<\/p>\n

\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6<\/strong>\uff1a\u5206\u5272\u540e\u7684\u5355\u8bcd\u5217\u8868\u4e2d\uff0c\u6bcf\u4e2a\u5355\u8bcd\u7684\u957f\u5ea6\u53ef\u4ee5\u901a\u8fc7len()\u51fd\u6570\u8ba1\u7b97\u5f97\u5230\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u6216map()\u51fd\u6570\u6765\u904d\u5386\u5355\u8bcd\u5217\u8868\u5e76\u8ba1\u7b97\u6bcf\u4e2a\u5355\u8bcd\u7684\u957f\u5ea6\u3002<\/p>\n<\/p>\n

\u6c42\u5e73\u5747\u503c<\/strong>\uff1a\u8ba1\u7b97\u51fa\u6240\u6709\u5355\u8bcd\u7684\u957f\u5ea6\u540e\uff0c\u6211\u4eec\u9700\u8981\u6c42\u51fa\u8fd9\u4e9b\u957f\u5ea6\u7684\u5e73\u5747\u503c\u3002\u5e73\u5747\u503c\u7684\u8ba1\u7b97\u65b9\u6cd5\u662f\u5c06\u6240\u6709\u5355\u8bcd\u957f\u5ea6\u76f8\u52a0\uff0c\u7136\u540e\u9664\u4ee5\u5355\u8bcd\u603b\u6570\u3002<\/p>\n<\/p>\n

\u4f7f\u7528\u5185\u7f6e\u51fd\u6570<\/strong>\uff1aPython\u63d0\u4f9b\u4e86\u4e00\u4e9b\u5185\u7f6e\u51fd\u6570\u548c\u5e93\u51fd\u6570\uff0c\u53ef\u4ee5\u7b80\u5316\u4e0a\u8ff0\u6b65\u9aa4\u3002\u4f8b\u5982\uff0c\u4f7f\u7528numpy\u5e93\u7684mean()\u51fd\u6570\u53ef\u4ee5\u5feb\u901f\u8ba1\u7b97\u5e73\u5747\u503c\u3002<\/p>\n<\/p>\n

\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u6bcf\u4e2a\u6b65\u9aa4\uff0c\u5e76\u63d0\u4f9b\u793a\u4f8b\u4ee3\u7801\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u8bfb\u53d6\u6587\u672c<\/p>\n

\u8bfb\u53d6\u6587\u672c\u662f\u6c42\u5e73\u5747\u8bcd\u957f\u7684\u7b2c\u4e00\u6b65\u3002Python\u63d0\u4f9b\u4e86\u591a\u79cd\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\u7684\u65b9\u6cd5\uff0c\u5e38\u7528\u7684\u65b9\u6cd5\u6709\u4f7f\u7528open()\u51fd\u6570\u548cpandas\u5e93\u3002<\/p>\n<\/p>\n

    \n
  1. \u4f7f\u7528open()\u51fd\u6570\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\uff1a<\/li>\n<\/ol>\n

    with open('text.txt', 'r', encoding='utf-8') as file:<\/p>\n
        text = file.read()<\/p>\n
    <\/code><\/pre>\n<\/p>\n
      \n
    1. \u4f7f\u7528pandas\u5e93\u8bfb\u53d6\u6587\u672c\u6587\u4ef6\uff1a<\/li>\n<\/ol>\n
      import pandas as pd<\/p>\n
      df = pd.read_csv('text.txt', sep='\\n', header=None)<\/p>\n
      text = ' '.join(df[0].tolist())<\/p>\n
      <\/code><\/pre>\n<\/p>\n
      \u4e8c\u3001\u5206\u5272\u5355\u8bcd<\/p>\n
      \u8bfb\u53d6\u6587\u672c\u5185\u5bb9\u540e\uff0c\u6211\u4eec\u9700\u8981\u5c06\u6587\u672c\u5206\u5272\u6210\u5355\u8bcd\u3002Python\u7684split()\u65b9\u6cd5\u53ef\u4ee5\u8f7b\u677e\u5730\u5c06\u5b57\u7b26\u4e32\u6309\u7a7a\u683c\u5206\u5272\u6210\u5355\u8bcd\u5217\u8868\u3002\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u8fdb\u884c\u66f4\u590d\u6742\u7684\u5206\u5272\u64cd\u4f5c\u3002<\/p>\n<\/p>\n
        \n
      1. \u4f7f\u7528split()\u65b9\u6cd5\u5206\u5272\u5355\u8bcd\uff1a<\/li>\n<\/ol>\n
        words = text.split()<\/p>\n
        <\/code><\/pre>\n<\/p>\n
          \n
        1. \u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u5206\u5272\u5355\u8bcd\uff1a<\/li>\n<\/ol>\n
          import re<\/p>\n
          words = re.findall(r'\\b\\w+\\b', text)<\/p>\n
          <\/code><\/pre>\n<\/p>\n
          \u4e09\u3001\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6<\/p>\n
          \u5206\u5272\u540e\u7684\u5355\u8bcd\u5217\u8868\u4e2d\uff0c\u6bcf\u4e2a\u5355\u8bcd\u7684\u957f\u5ea6\u53ef\u4ee5\u901a\u8fc7len()\u51fd\u6570\u8ba1\u7b97\u5f97\u5230\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u6216map()\u51fd\u6570\u6765\u904d\u5386\u5355\u8bcd\u5217\u8868\u5e76\u8ba1\u7b97\u6bcf\u4e2a\u5355\u8bcd\u7684\u957f\u5ea6\u3002<\/p>\n<\/p>\n
            \n
          1. \u4f7f\u7528\u5217\u8868\u63a8\u5bfc\u5f0f\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6\uff1a<\/li>\n<\/ol>\n
            word_lengths = [len(word) for word in words]<\/p>\n
            <\/code><\/pre>\n<\/p>\n
              \n
            1. \u4f7f\u7528map()\u51fd\u6570\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6\uff1a<\/li>\n<\/ol>\n
              word_lengths = list(map(len, words))<\/p>\n
              <\/code><\/pre>\n<\/p>\n
              \u56db\u3001\u6c42\u5e73\u5747\u503c<\/p>\n
              \u8ba1\u7b97\u51fa\u6240\u6709\u5355\u8bcd\u7684\u957f\u5ea6\u540e\uff0c\u6211\u4eec\u9700\u8981\u6c42\u51fa\u8fd9\u4e9b\u957f\u5ea6\u7684\u5e73\u5747\u503c\u3002\u5e73\u5747\u503c\u7684\u8ba1\u7b97\u65b9\u6cd5\u662f\u5c06\u6240\u6709\u5355\u8bcd\u957f\u5ea6\u76f8\u52a0\uff0c\u7136\u540e\u9664\u4ee5\u5355\u8bcd\u603b\u6570\u3002<\/p>\n<\/p>\n
                \n
              1. \u4f7f\u7528sum()\u548clen()\u51fd\u6570\u6c42\u5e73\u5747\u503c\uff1a<\/li>\n<\/ol>\n
                average_length = sum(word_lengths) \/ len(word_lengths)<\/p>\n
                <\/code><\/pre>\n<\/p>\n
                  \n
                1. \u4f7f\u7528numpy\u5e93\u7684mean()\u51fd\u6570\u6c42\u5e73\u5747\u503c\uff1a<\/li>\n<\/ol>\n
                  import numpy as np<\/p>\n
                  average_length = np.mean(word_lengths)<\/p>\n
                  <\/code><\/pre>\n<\/p>\n
                  \u4e94\u3001\u5b8c\u6574\u793a\u4f8b\u4ee3\u7801<\/p>\n<\/p>\n
                  import re<\/p>\n
                  import numpy as np<\/p>\n
                  \u8bfb\u53d6\u6587\u672c\u6587\u4ef6<\/strong><\/h2>\n
                  with open('text.txt', 'r', encoding='utf-8') as file:<\/p>\n
                      text = file.read()<\/p>\n
                  \u5206\u5272\u5355\u8bcd<\/strong><\/h2>\n
                  words = re.findall(r'\\b\\w+\\b', text)<\/p>\n
                  \u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6<\/strong><\/h2>\n
                  word_lengths = [len(word) for word in words]<\/p>\n
                  \u6c42\u5e73\u5747\u503c<\/strong><\/h2>\n
                  average_length = np.mean(word_lengths)<\/p>\n
                  print(f'\u5e73\u5747\u8bcd\u957f: {average_length}')<\/p>\n
                  <\/code><\/pre>\n<\/p>\n
                  \u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u5730\u5728Python\u4e2d\u6c42\u51fa\u6587\u672c\u7684\u5e73\u5747\u8bcd\u957f\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u60a8\u6709\u6240\u5e2e\u52a9\u3002\u5982\u679c\u60a8\u6709\u4efb\u4f55\u7591\u95ee\u6216\u5efa\u8bae\uff0c\u8bf7\u968f\u65f6\u7559\u8a00\u8ba8\u8bba\u3002<\/p>\n<\/p>\n
                  \u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
                   \u5982\u4f55\u5728Python\u4e2d\u8ba1\u7b97\u6587\u672c\u7684\u5e73\u5747\u8bcd\u957f\uff1f<\/strong>
                  \u5728Python\u4e2d\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u6b65\u9aa4\u5b9e\u73b0\uff1a\u9996\u5148\uff0c\u8bfb\u53d6\u6587\u672c\u5185\u5bb9\u5e76\u5c06\u5176\u62c6\u5206\u4e3a\u5355\u8bcd\u3002\u63a5\u7740\uff0c\u8ba1\u7b97\u6bcf\u4e2a\u5355\u8bcd\u7684\u957f\u5ea6\uff0c\u5e76\u6c42\u53d6\u8fd9\u4e9b\u957f\u5ea6\u7684\u5e73\u5747\u503c\u3002\u53ef\u4ee5\u4f7f\u7528\u5185\u7f6e\u7684\u5b57\u7b26\u4e32\u5904\u7406\u65b9\u6cd5\u548c\u5217\u8868\u89e3\u6790\u6765\u5b9e\u73b0\u8fd9\u4e00\u8fc7\u7a0b\u3002\u793a\u4f8b\u4ee3\u7801\u5982\u4e0b\uff1a<\/p>\n
                  text = "\u8fd9\u662f\u4e00\u4e2a\u793a\u4f8b\u6587\u672c\uff0c\u7528\u4e8e\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\u3002"\nwords = text.split()  # \u5c06\u6587\u672c\u62c6\u5206\u4e3a\u5355\u8bcd\navg_length = sum(len(word) for word in words) \/ len(words)  # \u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\nprint(avg_length)\n<\/code><\/pre>\n
                  \u5728\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\u65f6\uff0c\u662f\u5426\u9700\u8981\u8003\u8651\u6807\u70b9\u7b26\u53f7\uff1f<\/strong>
                  \u5728\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\u65f6\uff0c\u6807\u70b9\u7b26\u53f7\u7684\u5904\u7406\u975e\u5e38\u91cd\u8981\u3002\u901a\u5e38\u60c5\u51b5\u4e0b\uff0c\u4e3a\u4e86\u5f97\u5230\u66f4\u51c6\u786e\u7684\u5e73\u5747\u8bcd\u957f\uff0c\u5efa\u8bae\u5728\u62c6\u5206\u5355\u8bcd\u4e4b\u524d\u5148\u53bb\u9664\u6807\u70b9\u7b26\u53f7\u3002\u8fd9\u53ef\u4ee5\u901a\u8fc7\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6216\u5b57\u7b26\u4e32\u7684\u66ff\u6362\u65b9\u6cd5\u6765\u5b9e\u73b0\u3002\u8fd9\u6837\u53ef\u4ee5\u786e\u4fdd\u8ba1\u7b97\u7684\u8bcd\u957f\u66f4\u7b26\u5408\u5b9e\u9645\u8bcd\u6c47\u7684\u957f\u5ea6\u3002<\/p>\n
                  \u6709\u65e0\u73b0\u6210\u7684Python\u5e93\u53ef\u4ee5\u7b80\u5316\u5e73\u5747\u8bcd\u957f\u7684\u8ba1\u7b97\uff1f<\/strong>
                  \u786e\u5b9e\u6709\u4e00\u4e9bPython\u5e93\u53ef\u4ee5\u5e2e\u52a9\u7b80\u5316\u6587\u672c\u5904\u7406\uff0c\u8fdb\u800c\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\u3002\u4f8b\u5982\uff0c\u4f7f\u7528nltk<\/code>\u5e93\u53ef\u4ee5\u8f7b\u677e\u5730\u8fdb\u884c\u6587\u672c\u5206\u6790\u548c\u5904\u7406\u3002\u901a\u8fc7\u8be5\u5e93\u4e2d\u7684\u5206\u8bcd\u5de5\u5177\uff0c\u53ef\u4ee5\u5feb\u901f\u83b7\u53d6\u5355\u8bcd\u5217\u8868\uff0c\u5e76\u8fdb\u884c\u540e\u7eed\u7684\u5e73\u5747\u8bcd\u957f\u8ba1\u7b97\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u793a\u4f8b\uff1a<\/p>\n
                  import nltk\nnltk.download('punkt')  # \u4e0b\u8f7dpunkt\u5206\u8bcd\u6a21\u578b\nfrom nltk.tokenize import word_tokenize\n\ntext = "\u8fd9\u662f\u4e00\u4e2a\u793a\u4f8b\u6587\u672c\uff0c\u7528\u4e8e\u8ba1\u7b97\u5e73\u5747\u8bcd\u957f\u3002"\nwords = word_tokenize(text)  # \u4f7f\u7528nltk\u8fdb\u884c\u5206\u8bcd\navg_length = sum(len(word) for word in words) \/ len(words)\nprint(avg_length)\n<\/code><\/pre>\n
                  \u901a\u8fc7\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u8ba1\u7b97\u6587\u672c\u7684\u5e73\u5747\u8bcd\u957f\uff0c\u5e76\u6839\u636e\u9700\u8981\u8fdb\u884c\u4f18\u5316\u548c\u8c03\u6574\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u6c42\u5e73\u5747\u8bcd\u957f\u7684\u65b9\u6cd5\u6709\uff1a\u8bfb\u53d6\u6587\u672c\u3001\u5206\u5272\u5355\u8bcd\u3001\u8ba1\u7b97\u5355\u8bcd\u957f\u5ea6\u3001\u6c42\u5e73\u5747\u503c\u3001\u4f7f\u7528\u5185\u7f6e\u51fd\u6570\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u63cf\u8ff0\uff1a \u8bfb […]","protected":false},"author":3,"featured_media":1024638,"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\/1024632"}],"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=1024632"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1024632\/revisions"}],"predecessor-version":[{"id":1024641,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1024632\/revisions\/1024641"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1024638"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1024632"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1024632"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1024632"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}