{"id":1694,"date":"2023-05-04T11:40:32","date_gmt":"2023-05-04T03:40:32","guid":{"rendered":"http:\/\/viplao.com\/?p=1694"},"modified":"2023-07-11T06:36:12","modified_gmt":"2023-07-10T22:36:12","slug":"%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98","status":"publish","type":"post","link":"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/","title":{"rendered":"\u6570\u5b57\u5316\u8fd0\u7ef4 \u2013 PYTHON \u65e5\u5e38\u6570\u636e\u5206\u6790 \u2013\u65b0\u95fb\u6587\u672c\u5206\u7c7b\u5b9e\u6218"},"content":{"rendered":"\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_71 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">\u6587\u7ae0\u76ee\u5f55<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 eztoc-toggle-hide-by-default' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E8%BD%BD%E5%85%A5%E5%8F%8A%E6%B8%85%E6%B4%97\" title=\"\u6587\u672c\u6570\u636e\u8f7d\u5165\u53ca\u6e05\u6d17\">\u6587\u672c\u6570\u636e\u8f7d\u5165\u53ca\u6e05\u6d17<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E6%8A%8A%E6%95%B0%E6%8D%AE%E9%9B%86%E5%88%86%E4%B8%BA%E8%AE%AD%E7%BB%83%E9%9B%86%E5%92%8C%E6%B5%8B%E8%AF%95%E9%9B%86\" title=\"\u628a\u6570\u636e\u96c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\">\u628a\u6570\u636e\u96c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E4%B8%AD%E6%96%87%E5%88%86%E8%AF%8D\" title=\"\u4e2d\u6587\u5206\u8bcd\">\u4e2d\u6587\u5206\u8bcd<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E5%BC%95%E5%85%A5%E5%81%9C%E7%94%A8%E8%AF%8D\" title=\"\u5f15\u5165\u505c\u7528\u8bcd\">\u5f15\u5165\u505c\u7528\u8bcd<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E6%96%87%E6%9C%AC%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96%EF%BC%88%E8%AF%8D%E5%BA%93%E8%A1%A8%E7%A4%BA%E6%B3%95%EF%BC%89\" title=\"\u6587\u672c\u7279\u5f81\u63d0\u53d6\uff08\u8bcd\u5e93\u8868\u793a\u6cd5\uff09\">\u6587\u672c\u7279\u5f81\u63d0\u53d6\uff08\u8bcd\u5e93\u8868\u793a\u6cd5\uff09<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E5%BB%BA%E6%A8%A1\" title=\"\u673a\u5668\u5b66\u4e60\u5efa\u6a21\">\u673a\u5668\u5b66\u4e60\u5efa\u6a21<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#%E6%96%87%E6%9C%AC%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96TF-IDF\" title=\"\u6587\u672c\u7279\u5f81\u63d0\u53d6(TF-IDF)\">\u6587\u672c\u7279\u5f81\u63d0\u53d6(TF-IDF)<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/#N-gram%E6%A8%A1%E5%9E%8B\" title=\"N-gram\u6a21\u578b\">N-gram\u6a21\u578b<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E6%96%87%E6%9C%AC%E6%95%B0%E6%8D%AE%E8%BD%BD%E5%85%A5%E5%8F%8A%E6%B8%85%E6%B4%97\"><\/span>\u6587\u672c\u6570\u636e\u8f7d\u5165\u53ca\u6e05\u6d17<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>\u641c\u72d7\u65b0\u95fb\u6570\u636e\u6e90\uff1a<a href=\"https:\/\/link.zhihu.com\/?target=http%3A\/\/www.sogou.com\/labs\/resource\/ca.php\" target=\"_blank\" rel=\"noreferrer noopener\">http:\/\/www.sogou.com\/labs\/resource\/ca.php<\/a><\/p>\n\n\n\n<p>\u6211\u4eec\u4ece\u641c\u72d7\u4e0b\u8f7d\u7684\u6570\u636e\u662f\u7c7b\u4f3cXML\u7684\u5e26\u6807\u7b7e\u5bf9\u7684\u6570\u636e\uff0c\u56e0\u6b64\u9700\u8981\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u6216\u8005BeautifulSoup\u7b49\u5de5\u5177\u5904\u7406\u4e3adataframe\u683c\u5f0f\uff0c\u5982\u4e0b\u56fe\uff0c\u5927\u5bb6\u901a\u8fc7\u7f51\u7edc\u722c\u866b\u83b7\u53d6\u7684\u6570\u636e\u5904\u7406\u65b9\u6cd5\u4e5f\u7c7b\u4f3c\u3002<\/p>\n\n\n\n<figure class=\"wp-block-image\"><img decoding=\"async\" src=\"https:\/\/pic4.zhimg.com\/80\/v2-b430c5eda09e45285467b717543f7927_720w.webp\" alt=\"\"\/><\/figure>\n\n\n\n<p>\u6587\u672c\u6570\u636e\u63d0\u53d6\u8fd9\u91cc\u5c31\u4e0d\u8d58\u8ff0\u4e86\uff0c\u4e0b\u9762\u76f4\u63a5\u8bfb\u5165\u5904\u7406\u540e\u7684csv\u6587\u4ef6<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>import pandas as pd\nimport jieba\ndata = pd.read_table('news_data\/news_data.txt')<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E6%8A%8A%E6%95%B0%E6%8D%AE%E9%9B%86%E5%88%86%E4%B8%BA%E8%AE%AD%E7%BB%83%E9%9B%86%E5%92%8C%E6%B5%8B%E8%AF%95%E9%9B%86\"><\/span>\u628a\u6570\u636e\u96c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>sk-learn\u5e93\u4e2dtrain_test_split\u51fd\u6570\u53ef\u4ee5\u628a\u6570\u636e\u96c6\u968f\u673a\u5212\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\uff0c\u8bad\u7ec3\u96c6\u7528\u4e8e\u6a21\u578b\u8bad\u7ec3\uff0c\u6d4b\u8bd5\u96c6\u7528\u4e8e\u68c0\u9a8c\u6a21\u578b\u7684\u4f18\u52a3\uff0crandom_state\u53c2\u6570\u662f\u6307\u5b9a\u968f\u673a\u79cd\u5b50\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from sklearn.model_selection import train_test_split\n\nx_train, x_test, y_train, y_test = train_test_split(data&#91;'\u65b0\u95fb\u5185\u5bb9'], data&#91;'\u7c7b\u522b'], random_state=1)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E4%B8%AD%E6%96%87%E5%88%86%E8%AF%8D\"><\/span>\u4e2d\u6587\u5206\u8bcd<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>\u6211\u4eec\u4f7f\u7528jieba\u5e93\u8fdb\u884c\u5206\u8bcd,\u5e76\u4ee5\u7a7a\u683c\u628a\u5206\u8bcd\u8fde\u6210\u5b57\u7b26\u4e32\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>def fenci(train_data):\n    words_df = train_data.apply(lambda x:' '.join(jieba.cut(x)))\n    return words_df\n\nx_train_fenci = fenci(x_train)\nx_train_fenci&#91;:5]<\/code><\/pre>\n\n\n\n<p>\u5206\u8bcd\u540e\u7684\u6570\u636e\u5982\u4e0b\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>3186    \u4e2d\u65b0\u7f51 \u4e0a\u6d77 \uff16 \u6708 \uff11 \uff14 \u65e5\u7535 \uff08 \u8bb0\u8005 \u4e8e\u4fca \uff09 \u4eca\u5e74 \u7684 \u7236\u4eb2\u8282 \uff0c \u4eba\u4eec \u53ef \u901a\u8fc7...\n632     \u76ee\u524d \u6b63\u503c \u4e2d \u62a5 \u53d1\u5e03 \u4e4b\u9645 \uff0c \u591a\u5bb6 \u5238\u5546 \u8ba4\u4e3a \uff0c \u4e0a\u534a\u5e74 \u94f6\u884c \u6574\u4f53 \u5229\u6da6 \u589e\u901f \u4e0b...\n577     \u4f5c\u4e3a \u4e2d\u975e \u5408\u4f5c \u8bba\u575b \u7684 \u91cd\u8981 \u5206 \u8bba\u575b \u4e4b\u4e00 \uff0c \u4e2d \u975e\u91d1\u878d \u5408\u4f5c \u8bba\u575b \u5c06 \u4e8e \uff11 \uff13...\n2406    \u96c5\u864e \u4f53\u80b2\u8baf \u3000 \u5317\u4eac \u65f6\u95f4 \uff17 \u6708 \uff13 \u65e5 \u4e0b\u5348 \uff0c \u708e\u708e\u590f\u65e5 \u4e2d \u5c71\u4e1c \u7403\u8ff7 \u7ec8\u4e8e \u8fce\u6765...\n4686    \u6b27\u83b1\u96c5\u96c6\u56e2 \u7684 \u836f\u5986 \u54c1\u724c \u7406\u80a4\u6cc9 \uff08 \u53f3\u56fe \uff09 \u548c \u8587 \u59ff \uff08 \u5de6\u56fe \uff09 \u3002 \u3000 \u8d44\u6599 \u56fe...\nName: \u65b0\u95fb\u5185\u5bb9, dtype: object<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E5%BC%95%E5%85%A5%E5%81%9C%E7%94%A8%E8%AF%8D\"><\/span>\u5f15\u5165\u505c\u7528\u8bcd<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<pre class=\"wp-block-code\"><code>infile = open(\"stopwords.txt\",encoding='utf-8')\nstopwords_lst = infile.readlines()\nstopwords = &#91;x.strip() for x in stopwords_lst]<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E6%96%87%E6%9C%AC%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96%EF%BC%88%E8%AF%8D%E5%BA%93%E8%A1%A8%E7%A4%BA%E6%B3%95%EF%BC%89\"><\/span>\u6587\u672c\u7279\u5f81\u63d0\u53d6\uff08\u8bcd\u5e93\u8868\u793a\u6cd5\uff09<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>CountVectorizer\u65e8\u5728\u901a\u8fc7\u8ba1\u6570\u6765\u5c06\u4e00\u4e2a\u6587\u6863\u8f6c\u6362\u4e3a\u5411\u91cf\u3002\u5f53\u4e0d\u5b58\u5728\u5148\u9a8c\u5b57\u5178\u65f6\uff0cCountvectorizer\u4f5c\u4e3aEstimator\u63d0\u53d6\u8bcd\u6c47\u8fdb\u884c\u8bad\u7ec3\uff0c\u5e76\u751f\u6210\u4e00\u4e2aCountVectorizerModel\u7528\u4e8e\u5b58\u50a8\u76f8\u5e94\u7684\u8bcd\u6c47\u5411\u91cf\u7a7a\u95f4\u3002\u8be5\u6a21\u578b\u4ea7\u751f\u6587\u6863\u5173\u4e8e\u8bcd\u8bed\u7684\u7a00\u758f\u8868\u793a\u3002\u4e0b\u9762\u4e3e\u4e00\u4e2a\u4f8b\u5b50\u793a\u8303\uff1a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code><em>#\u7528\u4e8e\u8f6c\u8bcd\u5411\u91cf\u7684\u8bed\u6599<\/em>\nyuliao = &#91;'dog cat fish dog dog dog','cat eat fish','i like eat fish']\n\n<em>#sklearn\u5e93CountVectorizer\u8f6c\u8bcd\u5411\u91cf<\/em>\nfrom sklearn.feature_extraction.text import CountVectorizer\ncv = CountVectorizer()\nvector = cv.fit_transform(yuliao)\nvector.todense()<\/code><\/pre>\n\n\n\n<p>\u8f6c\u6362\u540e\u7684\u77e9\u9635\u4e3a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>matrix(&#91;&#91;1, 4, 0, 1, 0],\n        &#91;1, 0, 1, 1, 0],\n        &#91;0, 0, 1, 1, 1]], dtype=int64)<\/code><\/pre>\n\n\n\n<p>\u63a5\u4e0b\u6765\u6211\u4eec\u770b\u4e0b\u63d0\u53d6\u5230\u7684\u7279\u5f81\u5206\u522b\u662f<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code><em>#\u63d0\u53d6\u5230\u7684\u6587\u672c\u7279\u5f81<\/em>\ncv.vocabulary_<\/code><\/pre>\n\n\n\n<p>\u5f97\u5230\u7684\u6587\u672c\u7279\u5f81<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>{'cat': 0, 'dog': 1, 'eat': 2, 'fish': 3, 'like': 4}<\/code><\/pre>\n\n\n\n<p>\u4ece\u4e0a\u9762\u7684\u4f8b\u5b50\u53ef\u4ee5\u770b\u51fa\uff0c\u8bed\u6599\u4e2d\u6bcf\u4e2a\u8bcd\u4f5c\u4e3a\u4e00\u4e2a\u7279\u5f81\uff0c\u8bcd\u9891\u6570\u4f5c\u4e3a\u7279\u5f81\u7684\u503c\uff0c\u5982\u7b2c\u4e00\u53e5\u4e2ddog\u51fa\u73b0\u4e864\u6b21\uff0c\u56e0\u6b64\u7279\u5f81\u503c\u4e3a4\u3002\u4e0b\u9762\u6211\u4eec\u4f7f\u7528CountVectorizer\u628a\u5206\u8bcd\u540e\u7684\u65b0\u95fb\u6587\u672c\u8f6c\u4e3a\u5411\u91cf\u3002sklearn\u5e93\u4e2d\u53ef\u4ee5\u6307\u5b9astopwords\uff0c\u6211\u4eec\u628a\u4e4b\u524d\u51c6\u5907\u597d\u7684\u505c\u7528\u8bcd\u8868\u7a7f\u8fdb\u53bb\u5c31\u597d\uff0c\u8fd9\u6837\u6211\u4eec\u7684\u6587\u672c\u7279\u5f81\u63d0\u53d6\u5c31\u505a\u597d\u5566\u3002<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>vectorizer = CountVectorizer(stop_words=stopwords, max_features=5000)\nvectorizer.fit(x_train_fenci)<\/code><\/pre>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0%E5%BB%BA%E6%A8%A1\"><\/span>\u673a\u5668\u5b66\u4e60\u5efa\u6a21<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>\u8fd9\u91cc\u6211\u4eec\u4f7f\u7528\u6734\u7d20\u8d1d\u53f6\u65af\u5206\u7c7b\u5668\uff0c\u5173\u4e8e\u6734\u7d20\u8d1d\u53f6\u65af\u7b97\u6cd5\uff0c\u5218\u5efa\u5e73\u7684\u535a\u5ba2\u5199\u5f97\u975e\u5e38\u4e0d\u9519\uff0c\u6211\u5c31\u4e0d\u518d\u82b1\u65f6\u95f4\u6574\u7406\u5566\uff0c\u7ed9\u5927\u5bb6\u63a8\u8350\u4e00\u6ce2<a href=\"https:\/\/link.zhihu.com\/?target=https%3A\/\/www.cnblogs.com\/pinard\/p\/6069267.html\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/www.cnblogs.com\/pinard\/p\/6069267.html<\/a><\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from sklearn.naive_bayes import MultinomialNB\nclassifier = MultinomialNB()\n<em>#\u6a21\u578b\u8bad\u7ec3<\/em>\nclassifier.fit(vectorizer.transform(x_train_fenci), y_train)\n<em>#\u4f7f\u7528\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u8fdb\u884c\u9884\u6d4b<\/em>\nclassifier.score(vectorizer.transform(fenci(x_test)), y_test)<\/code><\/pre>\n\n\n\n<p>\u5f97\u5230\u7684\u51c6\u786e\u7387\u4e3a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>0.80479999999999996<\/code><\/pre>\n\n\n\n<p>\u9884\u6d4b\u7684\u51c6\u786e\u7387\u662f80.5%\uff0c\u68d2\u68d2\u54d2<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"%E6%96%87%E6%9C%AC%E7%89%B9%E5%BE%81%E6%8F%90%E5%8F%96TF-IDF\"><\/span>\u6587\u672c\u7279\u5f81\u63d0\u53d6(TF-IDF)<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p><strong>TF-IDF<\/strong>\uff08term frequency\u2013inverse document frequency\uff09\uff0c\u8bcd\u9891-\u9006\u6587\u4ef6\u9891\u7387\u3002<\/p>\n\n\n\n<blockquote class=\"wp-block-quote\">\n<p>\u662f\u4e00\u79cd\u7528\u4e8e\u8d44\u8baf\u68c0\u7d22\u4e0e\u8d44\u8baf\u63a2\u52d8\u7684\u5e38\u7528\u52a0\u6743\u6280\u672f\u3002TF-IDF\u662f\u4e00\u79cd\u7edf\u8ba1\u65b9\u6cd5\uff0c\u7528\u4ee5\u8bc4\u4f30\u4e00\u5b57\u8bcd\u5bf9\u4e8e\u4e00\u4e2a\u6587\u4ef6\u96c6\u6216\u4e00\u4e2a\u8bed\u6599\u5e93\u4e2d\u7684\u5176\u4e2d\u4e00\u4efd\u6587\u4ef6\u7684\u91cd\u8981\u7a0b\u5ea6\u3002\u5b57\u8bcd\u7684\u91cd\u8981\u6027\u968f\u7740\u5b83\u5728\u6587\u4ef6\u4e2d\u51fa\u73b0\u7684\u6b21\u6570\u6210\u6b63\u6bd4\u589e\u52a0\uff0c\u4f46\u540c\u65f6\u4f1a\u968f\u7740\u5b83\u5728\u8bed\u6599\u5e93\u4e2d\u51fa\u73b0\u7684\u9891\u7387\u6210\u53cd\u6bd4\u4e0b\u964d<\/p>\n<\/blockquote>\n\n\n\n<p>\u4e00\u4e2a\u8bcd\u8bed\u5728\u4e00\u7bc7\u6587\u7ae0\u4e2d\u51fa\u73b0\u6b21\u6570\u8d8a\u591a, \u540c\u65f6\u5728\u6240\u6709\u6587\u6863\u4e2d\u51fa\u73b0\u6b21\u6570\u8d8a\u5c11, \u8d8a\u80fd\u591f\u4ee3\u8868\u8be5\u6587\u7ae0.<\/p>\n\n\n\n<p>\u4e0b\u9762\u76f4\u63a5\u7ed9\u51fa\u4e00\u4e2a\u8bcdx\u7684IDF\u7684\u57fa\u672c\u516c\u5f0f\u5982\u4e0b\uff1a<\/p>\n\n\n\n<p>IDF(x)=lg\u2061NN(x)&nbsp;\u5176\u4e2d\uff0cN\u4ee3\u8868\u8bed\u6599\u5e93\u4e2d\u6587\u672c\u7684\u603b\u6570\uff0c\u800cN(x)\u4ee3\u8868\u8bed\u6599\u5e93\u4e2d\u5305\u542b\u8bcdx\u7684\u6587\u672c\u603b\u6570<\/p>\n\n\n\n<p>TF\u2212IDF(x)=TF(x)\u2217IDF(x)&nbsp;\u5176\u4e2dTF(x)\u6307\u8bcdx\u5728\u5f53\u524d\u6587\u672c\u4e2d\u7684\u8bcd\u9891<\/p>\n\n\n\n<p><strong>\u8bcd\u5e93\u8868\u793a\u6cd5\u7684\u7f3a\u70b9<\/strong>\uff1a\u4e00\u4e9b\u666e\u904d\u51fa\u73b0\u7684\u8bcd\uff0c\u8bcd\u9891\u8f83\u9ad8\uff0c\u770b\u8d77\u6765\u4f3c\u4e4e\u662f\u66f4\u91cd\u8981\u7684\u7279\u5f81\uff0c\u4f46\u56e0\u4e3a\u8fd9\u4e2a\u8bcd\u666e\u904d\u51fa\u73b0\uff0c\u8fd9\u4e2a\u8bcd\u53ef\u80fd\u4e0d\u662f\u975e\u5e38\u7684\u91cd\u8981\u3002\u5982\u679c\u6211\u4eec\u7684\u5411\u91cf\u5316\u7279\u5f81\u4ec5\u4ec5\u7528\u8bcd\u9891\u8868\u793a\u5c31\u65e0\u6cd5\u53cd\u5e94\u8fd9\u4e00\u70b9\u3002\u56e0\u6b64\u6211\u4eec\u9700\u8981\u8fdb\u4e00\u6b65\u7684\u9884\u5904\u7406\u6765\u53cd\u5e94\u6587\u672c\u7684\u8fd9\u4e2a\u7279\u5f81\uff0c\u800c\u8fd9\u4e2a\u9884\u5904\u7406\u5c31\u662fTF-IDF\u3002<\/p>\n\n\n\n<p><strong>\u7528scikit-learn\u8fdb\u884cTF-IDF\u9884\u5904\u7406<\/strong><\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from sklearn.feature_extraction.text import TfidfVectorizer\n<em>#\u4f7f\u7528tf-idf\u628a\u6587\u672c\u8f6c\u4e3a\u5411\u91cf<\/em>\ntv = TfidfVectorizer(stop_words=stopwords, max_features=5000, lowercase = False)\ntv.fit(x_train_fenci)\n<em>#\u6a21\u578b\u8bad\u7ec3<\/em>\nclassifier.fit(tv.transform(fenci(x_train)), y_train)\n<em>#\u5229\u7528\u8bad\u7ec3\u597d\u7684\u6a21\u578b\u6d4b\u8bd5<\/em>\nclassifier.score(tv.transform(fenci(x_test)), y_test)<\/code><\/pre>\n\n\n\n<p>\u5f97\u5230\u7684\u51c6\u786e\u7387\u4e3a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>0.81599999999999995<\/code><\/pre>\n\n\n\n<p>\u53ef\u4ee5\u770b\u51fa\u4f7f\u7528TF-IDF\u9884\u5904\u7406\u540e\uff0c\u5f97\u5230\u7684\u9884\u6d4b\u51c6\u786e\u7387\u6709\u4e86\u660e\u663e\u7684\u63d0\u9ad8\u3002<\/p>\n\n\n\n<p>TF-IDF\u662f\u975e\u5e38\u5e38\u7528\u7684\u6587\u672c\u6316\u6398\u9884\u5904\u7406\u57fa\u672c\u6b65\u9aa4\uff0c\u4f7f\u7528\u4e86IF-IDF\u5e76\u6807\u51c6\u5316\u4ee5\u540e\uff0c\u6211\u4eec\u5c31\u53ef\u4ee5\u4f7f\u7528\u5404\u4e2a\u6587\u672c\u7684\u8bcd\u7279\u5f81\u5411\u91cf\u4f5c\u4e3a\u6587\u672c\u7684\u7279\u5f81\uff0c\u8fdb\u884c\u5206\u7c7b\u6216\u8005\u805a\u7c7b\u5206\u6790\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"N-gram%E6%A8%A1%E5%9E%8B\"><\/span>N-gram\u6a21\u578b<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>\u5728\u6734\u7d20\u8d1d\u53f6\u65af\u7b97\u6cd5\u4e2d\uff0c\u4e3a\u4e86\u907f\u514d\u7ef4\u5ea6\u707e\u96be\uff0c\u6709\u4e00\u4e2a\u5927\u80c6\u7684\u5047\u8bbe\uff0c\u5373X\u7684n\u4e2a\u7ef4\u5ea6\u4e4b\u95f4\u76f8\u4e92\u72ec\u7acb:&nbsp;P(X1=x1,X2=x2,&#8230;Xn=xn|Y=Ck)=P(X1=x1|Y=Ck)P(X2=x2|Y=Ck)&#8230;P(Xn=xn|Y=Ck)&nbsp;\u8fd9\u4e2a\u5047\u8bbe\u4e0b\uff0c\u6761\u4ef6\u5206\u5e03\u5927\u5927\u7684\u7b80\u5316\u4e86\uff0c\u4f46\u662f\u8fd9\u4e5f\u53ef\u80fd\u5e26\u6765\u9884\u6d4b\u7684\u4e0d\u51c6\u786e\u6027\u3002n\u4e2a\u7ef4\u5ea6\u76f8\u4e92\u72ec\u7acb\uff0c\u5c31\u662f\u5b8c\u5168\u6ca1\u6709\u8003\u8651\u4e0a\u4e0b\u6587\u8bed\u5883\uff0c\u628a\u6bcf\u4e2a\u8bcd\u62c6\u5f00\u5355\u72ec\u770b\uff0c\u8fd9\u4e48\u770b\u7684\u8bdd\uff0c\u732b\u5403\u9c7c\u3001\u9c7c\u5403\u732b\u5f97\u5230\u7684\u7279\u5f81\u5411\u91cf\u662f\u5b8c\u5168\u4e00\u6837\u7684\u3002<\/p>\n\n\n\n<p>N-gram\u6a21\u578b\u5c31\u662f\u5047\u8bbe$X_n$\u4e0e\u9644\u8fd1n\u4e2a\u8bcd\u662f\u76f8\u5173\u7684\uff0c\u6bd4\u5982\u5f53n=(1,2)\u65f6\uff0c\u732b\u5403\u9c7c\u63d0\u53d6\u5230\u7684\u7279\u5f81\u5c31\u662f[&#8216;\u732b&#8217;,&#8217;\u5403&#8217;,&#8217;\u9c7c&#8217;,&#8217;\u732b\u5403&#8217;,&#8217;\u5403\u9c7c&#8217;]\uff0c\u4e3a\u4e86\u5e73\u8861\u8ba1\u7b97\u91cf\u548c\u4e0a\u4e0b\u6587\u5173\u7cfb\uff0cN\u4e00\u822c\u53d62\u6216\u80053\u3002\u6734\u7d20\u8d1d\u53f6\u65afn\u4e2a\u7ef4\u5ea6\u4e4b\u95f4\u5b8c\u5168\u76f8\u4e92\u72ec\u7acb\u7684\u5047\u8bbe\uff0c\u5c31\u662fN-gram\u7684n=1\u65f6\u7684\u60c5\u51b5<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code><em>#\u8f6c\u8bcd\u5411\u91cf<\/em>\ntv_2gram = TfidfVectorizer(stop_words=stopwords, max_features=5000, ngram_range=(1,2),lowercase = False)\ntv_2gram.fit(x_train_fenci)\n<em>#\u8bad\u7ec3\u6a21\u578b<\/em>\nclf_2gram = MultinomialNB()\nclf_2gram.fit(tv_2gram.transform(fenci(x_train)), y_train)\n<em>#\u9884\u6d4b<\/em>\nclf_2gram.score(tv_2gram.transform(fenci(x_test)), y_test)<\/code><\/pre>\n\n\n\n<p>\u5f97\u5230\u7684\u51c6\u786e\u7387\u4e3a<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>0.81679999999999997<\/code><\/pre>\n\n\n\n<p>\u53ef\u4ee5\u770b\u51fa\uff0c\u6307\u5b9aN-gram\u6a21\u578bn=2\u65f6\uff0c\u589e\u52a0\u4e86\u9644\u8fd12\u4e2a\u8bcd\u7684\u5173\u8054\uff0c\u9884\u6d4b\u7684\u51c6\u786e\u7387\u53c8\u4e0a\u5347\u4e86\u4e00\u4e22\u4e22<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u672c\u6570\u636e\u8f7d\u5165\u53ca\u6e05\u6d17 \u641c\u72d7\u65b0\u95fb\u6570\u636e\u6e90\uff1ahttp:\/\/www.sogou.com\/labs\/resour&hellip; <a href=\"http:\/\/viplao.com\/index.php\/2023\/05\/04\/%e8%bf%90%e7%bb%b4%e5%b7%a5%e5%85%b7-python-%e6%97%a5%e5%b8%b8%e6%95%b0%e6%8d%ae%e5%88%86%e6%9e%90-%e6%96%b0%e9%97%bb%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb%e5%ae%9e%e6%88%98\/\" class=\"more-link read-more\" rel=\"bookmark\">\u7ee7\u7eed\u9605\u8bfb <span class=\"screen-reader-text\">\u6570\u5b57\u5316\u8fd0\u7ef4 \u2013 PYTHON \u65e5\u5e38\u6570\u636e\u5206\u6790 \u2013\u65b0\u95fb\u6587\u672c\u5206\u7c7b\u5b9e\u6218<\/span><i class=\"fa fa-arrow-right\"><\/i><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[14,26,28],"views":794,"_links":{"self":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/1694"}],"collection":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/comments?post=1694"}],"version-history":[{"count":2,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/1694\/revisions"}],"predecessor-version":[{"id":2191,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/posts\/1694\/revisions\/2191"}],"wp:attachment":[{"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/media?parent=1694"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/categories?post=1694"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/viplao.com\/index.php\/wp-json\/wp\/v2\/tags?post=1694"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}