{"id":204232,"date":"2025-05-29T14:59:32","date_gmt":"2025-05-29T06:59:32","guid":{"rendered":"https:\/\/server.hk\/cnblog\/204232\/"},"modified":"2025-05-29T14:59:32","modified_gmt":"2025-05-29T06:59:32","slug":"%e5%a6%82%e4%bd%95%e4%bb%8e%e5%8c%85%e5%90%ab%e5%a4%9a%e5%88%97%e6%95%b0%e6%8d%ae%e7%9a%84-csv-%e6%96%87%e4%bb%b6%e4%b8%ad%e5%90%88%e5%b9%b6%e7%89%b9%e5%ae%9a%e5%88%97%e5%b9%b6%e8%ae%a1%e7%ae%97","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/204232\/","title":{"rendered":"\u5982\u4f55\u4ece\u5305\u542b\u591a\u5217\u6570\u636e\u7684 CSV \u6587\u4ef6\u4e2d\u5408\u5e76\u7279\u5b9a\u5217\u5e76\u8ba1\u7b97\u5404\u4e2a\u9009\u9879\u51fa\u73b0\u7684\u6bd4\u4f8b\uff1f"},"content":{"rendered":"

<\/b> <\/p>\n

\u5982\u4f55\u4ece\u5305\u542b\u591a\u5217\u6570\u636e\u7684 CSV \u6587\u4ef6\u4e2d\u5408\u5e76\u7279\u5b9a\u5217\u5e76\u8ba1\u7b97\u5404\u4e2a\u9009\u9879\u51fa\u73b0\u7684\u6bd4\u4f8b\uff1f<\/h1>\n

\u73cd\u60dc\u65f6\u95f4\uff0c\u52e4\u594b\u5b66\u4e60\uff01\u4eca\u5929\u7ed9\u5927\u5bb6\u5e26\u6765\uff0c\u6b63\u6587\u5185\u5bb9\u4e3b\u8981\u6d89\u53ca\u5230<\/span>\u7b49\u7b49\uff0c\u5982\u679c\u4f60\u6b63\u5728\u5b66\u4e60\u6587\u7ae0<\/span>\uff0c\u6216\u8005\u662f\u5bf9\u6587\u7ae0<\/span>\u6709\u7591\u95ee\uff0c\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u6211\uff01\u540e\u9762\u6211\u4f1a\u6301\u7eed\u66f4\u65b0\u76f8\u5173\u5185\u5bb9\u7684\uff0c\u5e0c\u671b\u90fd\u80fd\u5e2e\u5230\u6b63\u5728\u5b66\u4e60\u7684\u5927\u5bb6\uff01<\/p>\n

<\/p>\n

csv \u6587\u4ef6\u5408\u5e76\u4e0e\u5185\u5bb9\u6bd4\u4f8b\u8ba1\u7b97<\/strong><\/p>\n

\u95ee\u9898\uff1a<\/strong><\/p>\n

\u5982\u4f55\u4ece\u5305\u542b\u591a\u5217\u6570\u636e\u7684 csv \u6587\u4ef6\u4e2d\u8bfb\u53d6\u5185\u5bb9\u5e76\u5408\u5e76\u7279\u5b9a\u7684\u5217\uff0c\u540c\u65f6\u8ba1\u7b97\u5404\u4e2a\u9009\u9879\u51fa\u73b0\u7684\u6bd4\u4f8b\uff1f<\/p>\n

\u89e3\u51b3\u65b9\u6848\uff1a<\/strong><\/p>\n

\u4f7f\u7528 python \u7684 pandas \u5e93\u6765\u5904\u7406 csv \u6587\u4ef6\uff1a<\/p>\n

import pandas as pd\nfrom collections import Counter\n\n# \u8bfb\u53d6 CSV \u6587\u4ef6\ndf = pd.read_csv('test.csv', encoding='cp932')\n\n# \u83b7\u53d6 CMD \u5217\u4f5c\u4e3a\u4e3b\u952e\nindex_list_cmd = df['cmd'].tolist()\n\n# \u8ba1\u7b97 CMD \u51fa\u73b0\u7684\u6b21\u6570\nidxLstCmd_cnt = Counter(list(index_list_cmd))\n\n# \u53bb\u9664\u91cd\u590d\u7684 CMD\nindex_list_cmd = sorted(set(index_list_cmd), key=list(index_list_cmd).index)\n\n# \u8ba1\u7b97\u6bcf\u4e2a CMD \u51fa\u73b0\u7684\u6b21\u6570\ncntLst = []\nfor lst_i in range(len(index_list_cmd)):\n    cntLst.append(idxLstCmd_cnt[index_list_cmd[lst_i]])\n\n# \u5408\u5e76 OPT \u5217\nindex_list_opt_idx = []\n\n# \u5220\u9664\u4e4b\u524d\u4fdd\u5b58\u7684\u6587\u4ef6\nif os.path.isfile(useRateF):\n    os.remove(useRateF)\n\n# \u904d\u5386 CMD\nfor cmd_i in range(len(index_list_cmd)):\n    # \u83b7\u5f97 OPT \u5217\u7684 index\n    index_list_opt_idx = list(df['opt'][df['cmd'] == index_list_cmd[cmd_i]].index.values)\n\n    index_list_opt = []\n\n    # \u904d\u5386 OPT\n    for opt_i in range(len(index_list_opt_idx)):\n        try:\n            index_list_opt.append(df.loc[int(index_list_opt_idx[opt_i]), 'opt'])\n        except:\n            print(index_list_cmd[cmd_i])\n            print(index_list_opt_idx[opt_i])\n            print(opt_i)\n\n    # \u5217\u8868\u8f6c\u5b57\u7b26\u4e32\n    str_idxLstOpt = ' '.join(index_list_opt)\n\n    # \u5b57\u7b26\u4e32\u8f6c\u56de\u5217\u8868\n    lst_idxLstOpt = str_idxLstOpt.split(' ')\n\n    # \u8ba1\u7b97 OPT \u51fa\u73b0\u7684\u6bd4\u4f8b\n    for tag in sorted(set(lst_idxLstOpt), key=lst_idxLstOpt.index):\n        with open(useRateF, 'a', encoding='utf-8_sig') as uf:\n            uf.writelines(str(index_list_cmd[cmd_i]) + ',' + tag + ',' + str(lst_idxLstOpt.count(tag)\/cntLst[cmd_i]))\n            uf.writelines('\\n')<\/pre>\n
\u8fd9\u4e2a\u811a\u672c\u5c06\u8bfb\u53d6 csv \u6587\u4ef6\uff0c\u5408\u5e76 opt \u5217\uff0c\u5e76\u8f93\u51fa\u6bcf\u4e2a cmd \u9009\u9879\u51fa\u73b0\u7684\u6bd4\u4f8b\u3002<\/p>\n
\u4eca\u5929\u5173\u4e8e\u300a\u5982\u4f55\u4ece\u5305\u542b\u591a\u5217\u6570\u636e\u7684 CSV \u6587\u4ef6\u4e2d\u5408\u5e76\u7279\u5b9a\u5217\u5e76\u8ba1\u7b97\u5404\u4e2a\u9009\u9879\u51fa\u73b0\u7684\u6bd4\u4f8b\uff1f\u300b\u7684\u5185\u5bb9\u5c31\u4ecb\u7ecd\u5230\u8fd9\u91cc\u4e86\uff0c\u662f\u4e0d\u662f\u5b66\u8d77\u6765\u4e00\u76ee\u4e86\u7136\uff01\u60f3\u8981\u4e86\u89e3\u66f4\u591a\u5173\u4e8e\u7684\u5185\u5bb9\u8bf7\u5173\u6ce8\u516c\u4f17\u53f7\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"
\u5982\u4f55\u4ece\u5305\u542b\u591a\u5217\u6570\u636e\u7684 CSV \u6587...<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4925],"tags":[],"class_list":["post-204232","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204232","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=204232"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204232\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=204232"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=204232"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=204232"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}