{"id":204681,"date":"2025-05-29T14:30:39","date_gmt":"2025-05-29T06:30:39","guid":{"rendered":"https:\/\/server.hk\/cnblog\/204681\/"},"modified":"2025-05-29T14:30:39","modified_gmt":"2025-05-29T06:30:39","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%ae%9e%e7%8e%b0%e8%af%8d%e7%bb%84%e7%ba%a7%e7%9a%84tf-idf%e8%ae%a1%e7%ae%97%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/204681\/","title":{"rendered":"\u5982\u4f55\u7528Python\u5b9e\u73b0\u8bcd\u7ec4\u7ea7\u7684TF-IDF\u8ba1\u7b97\uff1f"},"content":{"rendered":"

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

\u5982\u4f55\u7528Python\u5b9e\u73b0\u8bcd\u7ec4\u7ea7\u7684TF-IDF\u8ba1\u7b97\uff1f<\/h1>\n<\/p>\n

<\/p>\n

\u5982\u4f55\u7528python\u5b9e\u73b0\u8bcd\u7ec4\u7ea7tf-idf<\/strong><\/p>\n

tfidfvectorizer\u662f\u4e00\u4e2a\u53ef\u7528\u4e8e\u8ba1\u7b97tf-idf\u503c\u7684python\u5e93\u3002\u4f46\u662f\uff0c\u5982\u679c\u4f60\u7684\u7279\u5f81\u8bcd\u5df2\u7ecf\u9884\u5148\u6574\u7406\u597d\uff0c\u5e76\u4e14\u4e0d\u5e0c\u671b\u5e93\u5c06\u5b83\u4eec\u62c6\u5206\u6210\u5355\u4e2a\u5355\u8bcd\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u5176\u4ed6\u65b9\u6cd5\u3002<\/p>\n

\u4f7f\u7528tfidfvectorizer<\/strong><\/p>\n

\u5982\u679c\u4f60\u9700\u8981\u4fdd\u6301\u672f\u8bed\u7684\u5b8c\u6574\u6027\uff0c\u8bf7\u4f7f\u7528\u4ee5\u4e0b\u6b65\u9aa4\uff1a<\/p>\n

    \n
  1. \u5c06\u4f60\u7684\u8bcd\u7ec4\u4f5c\u4e3a\u5b57\u7b26\u4e32\u5217\u8868\u3002<\/li>\n
  2. \u8bbe\u7f6etfidfvectorizer\u7684ngram_range\u53c2\u6570\u4e3a(1, 1)\uff0c\u8868\u793a\u53ea\u8003\u8651\u5355\u4e2a\u8bcd\u7ec4\u3002<\/li>\n
  3. \u4f7f\u7528fit_transform\u65b9\u6cd5\u6765\u8ba1\u7b97tf-idf\u503c\u3002<\/li>\n<\/ol>\n

    \u81ea\u5b9a\u4e49tf-idf\u8ba1\u7b97<\/strong><\/p>\n

    \u5982\u679c\u4f60\u66f4\u559c\u6b22\u81ea\u5df1\u7f16\u5199tf-idf\u8ba1\u7b97\u7a0b\u5e8f\uff0c\u8bf7\u9075\u5faa\u4ee5\u4e0b\u6b65\u9aa4\uff1a<\/p>\n

      \n
    1. \u8ba1\u7b97\u8bcd\u7ec4\u7684\u9891\u7387\u5e76\u5b58\u50a8\u5728\u5b57\u5178\u4e2d\u3002<\/li>\n
    2. \u8ba1\u7b97\u603b\u8bcd\u7ec4\u6570\u3002<\/li>\n
    3. \u8ba1\u7b97\u6bcf\u4e2a\u8bcd\u7ec4\u5728\u6587\u6863\u4e2d\u7684tf\u3002<\/li>\n
    4. \u8ba1\u7b97\u6bcf\u4e2a\u8bcd\u7ec4\u5728\u6574\u4e2a\u8bed\u6599\u5e93\u4e2d\u7684idf\u3002<\/li>\n
    5. \u5c06tf\u548cidf\u76f8\u4e58\u4ee5\u83b7\u5f97tf-idf\u503c\u3002<\/li>\n<\/ol>\n

      \u793a\u4f8b\u4ee3\u7801<\/strong><\/p>\n

      \u4ee5\u4e0b\u662f\u4e00\u4e2a\u793a\u4f8bpython\u4ee3\u7801\uff0c\u7528\u4e8e\u81ea\u5b9a\u4e49\u8ba1\u7b97\u8bcd\u7ec4\u7ea7tf-idf\u503c\uff1a<\/p>\n

      import math\n\ndef tf_idf(doc, terms):\n  \"\"\"\u8ba1\u7b97\u8bcd\u7ec4\u7684TF-IDF\u503c\u3002\n\n  \u53c2\u6570\uff1a\n    doc: \u6587\u6863\u4f5c\u4e3a\u5b57\u7b26\u4e32\u3002\n    terms: \u4f5c\u4e3a\u5b57\u7b26\u4e32\u5217\u8868\u7684\u9884\u5b9a\u4e49\u8bcd\u7ec4\u3002\n\n  \u8fd4\u56de\uff1a\n    \u8bcd\u7ec4\u5230\u5176TF-IDF\u503c\u7684\u5b57\u5178\u3002\n  \"\"\"\n\n  tf = {}\n  for term in terms:\n    tf[term] = doc.count(term)\n\n  total_terms = sum(tf.values())\n  idf = {}\n  for term in terms:\n    idf[term] = math.log(total_terms \/ (tf[term] + 1))\n\n  return {term: tf[term] * idf[term] for term in terms}<\/pre>\n
      \u4eca\u5929\u5e26\u5927\u5bb6\u4e86\u89e3\u4e86\u7684\u76f8\u5173\u77e5\u8bc6\uff0c\u5e0c\u671b\u5bf9\u4f60\u6709\u6240\u5e2e\u52a9\uff1b\u5173\u4e8e\u6587\u7ae0\u7684\u6280\u672f\u77e5\u8bc6\u6211\u4eec\u4f1a\u4e00\u70b9\u70b9\u6df1\u5165\u4ecb\u7ecd\uff0c\u6b22\u8fce\u5927\u5bb6\u5173\u6ce8\u516c\u4f17\u53f7\uff0c\u4e00\u8d77\u5b66\u4e60\u7f16\u7a0b~<\/p>\n","protected":false},"excerpt":{"rendered":"
      \u5982\u4f55\u7528Python\u5b9e\u73b0\u8bcd\u7ec4\u7ea7\u7684T...<\/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-204681","post","type-post","status-publish","format-standard","hentry","category-4925"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204681","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=204681"}],"version-history":[{"count":0,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/204681\/revisions"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=204681"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=204681"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=204681"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}