{"id":1046,"date":"2020-07-05T06:49:28","date_gmt":"2020-07-04T22:49:28","guid":{"rendered":"http:\/\/cnliutz.uicp.io\/?p=1046"},"modified":"2020-07-05T06:49:28","modified_gmt":"2020-07-04T22:49:28","slug":"%e5%88%a9%e7%94%a8python%e6%9d%a5%e5%81%9c%e8%af%8d","status":"publish","type":"post","link":"http:\/\/qbtobjow.ipyingshe.net:5347\/?p=1046","title":{"rendered":"\u5229\u7528python\u6765\u505c\u8bcd"},"content":{"rendered":"\n<pre class=\"wp-block-code\"><code>#\u5229\u7528python\u6765\u505c\u8bcd--Rmarkdown\uff08Rstudio\uff09\u5185\u8fd0\u884c\u65f6\u6709\u9519\u8bef\uff01\uff1f python\u547d\u4ee4\u884c\u8fd0\u884c\u6ca1\u95ee\u9898\n{python}\n# jieba.load_userdict('userdict.txt')\n# \u521b\u5efa\u505c\u7528\u8bcdlist\ndef stopwordslist(filepath):\n    stopwords = &#91;line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]\n    return stopwords\n# \u5bf9\u53e5\u5b50\u8fdb\u884c\u5206\u8bcd\ndef seg_sentence(sentence):\n    sentence_seged = sentence.strip()\n    stopwords = stopwordslist('C:\/Users\/czliu\/Documents\/R\/tingci.txt')  # \u8fd9\u91cc\u52a0\u8f7d\u505c\u7528\u8bcd\u7684\u8def\u5f84\n    outstr = ''\n    for word in sentence_seged:\n        if word not in stopwords:\n            if word != '\\t':\n                outstr += word\n                outstr += \" \"\n    return outstr\n\ninputs = open('C:\/Users\/czliu\/Documents\/R\/a.txt', 'r', encoding='utf-8')\noutputs = open('C:\/Users\/czliu\/Documents\/R\/yuliao.txt', 'w', encoding='utf-8')\nfor line in inputs:\n    line_seg = seg_sentence(line)  # \u8fd9\u91cc\u7684\u8fd4\u56de\u503c\u662f\u5b57\u7b26\u4e32\n    outputs.write(line_seg + '\\n')\noutputs.close()\ninputs.close()\n```\n\u4ee5\u4e0a\u4ee3\u7801\uff0c\u539f\u662f\u653e\u5728rstudio-Rmarkdown\u5185\u8fd0\u884c\u7684\u3002<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10],"tags":[],"class_list":["post-1046","post","type-post","status-publish","format-standard","hentry","category-python"],"_links":{"self":[{"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/posts\/1046","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1046"}],"version-history":[{"count":1,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/posts\/1046\/revisions"}],"predecessor-version":[{"id":1047,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=\/wp\/v2\/posts\/1046\/revisions\/1047"}],"wp:attachment":[{"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1046"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1046"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/qbtobjow.ipyingshe.net:5347\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1046"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}