{"id":36757,"date":"2023-11-29T19:35:57","date_gmt":"2023-12-20T06:56:02","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/"},"modified":"2024-05-04T11:21:21","modified_gmt":"2024-05-04T03:21:21","slug":"%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/","title":{"rendered":"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec"},"content":{"rendered":"<h4>Word2Vec\uff1a\u8bcd\u5411\u91cf<\/h4>\n<p>Word2Vec\u662f\u7531\u8c37\u6b4c\u7814\u7a76\u6240\u57282013\u5e74\u63d0\u51fa\u7684\u4e00\u4e2a\u7b97\u6cd5\uff0c\u8be5\u7b97\u6cd5\u57fa\u4e8e\u5047\u8bbe&#8221;\u5728\u76f8\u540c\u4e0a\u4e0b\u6587\u4e2d\u4f7f\u7528\u7684\u5355\u8bcd\u5177\u6709\u76f8\u540c\u7684\u542b\u4e49&#8221;\uff0c\u4f7f\u7528\u5411\u91cf\u6765\u8868\u793a\u5355\u8bcd\u7684\u7279\u5f81\u3002\u901a\u8fc7\u5c06\u5355\u8bcd\u53ca\u5176\u542b\u4e49\u5411\u91cf\u5316\uff0c\u8bed\u4e49\u4e0a\u76f8\u4f3c\u7684\u5355\u8bcd\u88ab\u8868\u793a\u4e3a\u5728\u7a7a\u95f4\u4e2d\u9760\u8fd1\u7684\u5411\u91cf\uff0c\u56e0\u6b64\u8be5\u7b97\u6cd5\u53ef\u7528\u4e8e\u63d0\u53d6\u8fd1\u4e49\u8bcd\u3002<\/p>\n<h4>\u4e3b\u9898 (Zh\u01d4 t\u00ed)<\/h4>\n<p>\u8fd9\u6b21\u6211\u4eec\u5c06\u4f7f\u7528Apache Spark\u7684MLlib\uff0c\u5c1d\u8bd5\u4f7f\u7528Word2Vec\u3002\u4f5c\u4e3a\u4e3b\u9898\uff0c\u6211\u4eec\u5c06\u52a0\u8f7d\u7ef4\u57fa\u767e\u79d1\u7684\u201c\u662d\u548c\u201d\u548c\u201c\u5e73\u6210\u201d\u7b49\u6587\u7ae0\uff0c\u7136\u540e\u5c06\u5b83\u4eec\u4f5c\u4e3a\u8f93\u5165\u6765\u751f\u6210\u6a21\u578b\u3002\u6211\u4eec\u60f3\u8981\u770b\u770b\uff0c\u5f53\u6211\u4eec\u8f93\u5165\u5404\u79cd\u672f\u8bed\u65f6\uff0c\u80fd\u5f97\u5230\u54ea\u4e9b\u8fd1\u4e49\u8bcd\u3002<\/p>\n<h4>\u6838\u5fc3\u7a0b\u5e8f (natively in Chinese)<\/h4>\n<p>\u6267\u884c\u4f7f\u7528\u7684\u662f spark-shell\uff0c\u4f46\u6838\u5fc3\u7a0b\u5e8f\u9700\u8981\u4e8b\u5148\u5199\u5728\u6587\u4ef6\u4e2d\uff0c\u5e76\u52a0\u8f7d\u5e76\u4f7f\u7528\u5b83\u3002\u4ee5\u4e0b\u662f\u8be5\u7a0b\u5e8f\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"k\">import<\/span> <span class=\"nn\">java.io.StringReader<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.spark.mllib.feature.<\/span><span class=\"o\">{<\/span><span class=\"nc\">Word2Vec<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Word2VecModel<\/span><span class=\"o\">}<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.lucene.analysis.ja.JapaneseTokenizer<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.lucene.analysis.tokenattributes.CharTermAttribute<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.lucene.analysis.ja.tokenattributes.BaseFormAttribute<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.lucene.analysis.ja.tokenattributes.PartOfSpeechAttribute<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.spark.mllib.linalg.Vectors<\/span>\r\n\r\n<span class=\"k\">import<\/span> <span class=\"nn\">scala.collection.mutable.ArrayBuffer<\/span>\r\n<span class=\"k\">def<\/span> <span class=\"nf\">tokenize<\/span><span class=\"o\">(<\/span><span class=\"n\">sentence<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span><span class=\"o\">)<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Seq<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"o\">{<\/span>\r\n  <span class=\"k\">val<\/span> <span class=\"nv\">word<\/span><span class=\"k\">:<\/span> <span class=\"kt\">ArrayBuffer<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">ArrayBuffer<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]()<\/span>\r\n  <span class=\"k\">lazy<\/span> <span class=\"k\">val<\/span> <span class=\"nv\">stream<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">JapaneseTokenizer<\/span><span class=\"o\">(<\/span>\r\n    <span class=\"k\">new<\/span> <span class=\"nc\">StringReader<\/span><span class=\"o\">(<\/span><span class=\"n\">sentence<\/span><span class=\"o\">),<\/span>\r\n    <span class=\"kc\">null<\/span><span class=\"o\">,<\/span>\r\n    <span class=\"kc\">false<\/span><span class=\"o\">,<\/span>\r\n    <span class=\"nv\">JapaneseTokenizer<\/span><span class=\"o\">.<\/span><span class=\"py\">Mode<\/span><span class=\"o\">.<\/span><span class=\"py\">NORMAL<\/span><span class=\"o\">)<\/span>\r\n\r\n  <span class=\"k\">try<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"nf\">while<\/span><span class=\"o\">(<\/span><span class=\"nv\">stream<\/span><span class=\"o\">.<\/span><span class=\"py\">incrementToken<\/span><span class=\"o\">())<\/span> <span class=\"o\">{<\/span>\r\n      <span class=\"k\">var<\/span> <span class=\"n\">charAtt<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">stream<\/span><span class=\"o\">.<\/span><span class=\"py\">getAttribute<\/span><span class=\"o\">(<\/span>\r\n        <span class=\"n\">classOf<\/span><span class=\"o\">[<\/span><span class=\"kt\">CharTermAttribute<\/span><span class=\"o\">]<\/span>\r\n      <span class=\"o\">).<\/span><span class=\"py\">toString<\/span>\r\n\r\n      <span class=\"k\">var<\/span> <span class=\"n\">bfAtt<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">stream<\/span><span class=\"o\">.<\/span><span class=\"py\">getAttribute<\/span><span class=\"o\">(<\/span>\r\n        <span class=\"n\">classOf<\/span><span class=\"o\">[<\/span><span class=\"kt\">BaseFormAttribute<\/span><span class=\"o\">]<\/span>\r\n      <span class=\"o\">).<\/span><span class=\"py\">getBaseForm<\/span>\r\n\r\n      <span class=\"k\">var<\/span> <span class=\"n\">partOfSpeech<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">stream<\/span><span class=\"o\">.<\/span><span class=\"py\">getAttribute<\/span><span class=\"o\">(<\/span>\r\n        <span class=\"n\">classOf<\/span><span class=\"o\">[<\/span><span class=\"kt\">PartOfSpeechAttribute<\/span><span class=\"o\">]<\/span>\r\n      <span class=\"o\">).<\/span><span class=\"py\">getPartOfSpeech<\/span><span class=\"o\">().<\/span><span class=\"py\">split<\/span><span class=\"o\">(<\/span><span class=\"s\">\"-\"<\/span><span class=\"o\">)(<\/span><span class=\"mi\">0<\/span><span class=\"o\">)<\/span>\r\n\r\n      <span class=\"o\">(<\/span><span class=\"n\">partOfSpeech<\/span><span class=\"o\">,<\/span> <span class=\"n\">bfAtt<\/span><span class=\"o\">)<\/span> <span class=\"k\">match<\/span> <span class=\"o\">{<\/span>\r\n        <span class=\"nf\">case<\/span> <span class=\"o\">(<\/span><span class=\"s\">\"\u540d\u8a5e\"<\/span><span class=\"o\">,<\/span> <span class=\"k\">_<\/span><span class=\"o\">)<\/span>  <span class=\"k\">=&gt;<\/span> <span class=\"n\">word<\/span> <span class=\"o\">+=<\/span> <span class=\"n\">charAtt<\/span>\r\n        <span class=\"nf\">case<\/span> <span class=\"o\">(<\/span><span class=\"s\">\"\u52d5\u8a5e\"<\/span><span class=\"o\">,<\/span> <span class=\"kc\">null<\/span><span class=\"o\">)<\/span>  <span class=\"k\">=&gt;<\/span> <span class=\"n\">word<\/span> <span class=\"o\">+=<\/span> <span class=\"n\">charAtt<\/span>\r\n        <span class=\"nf\">case<\/span> <span class=\"o\">(<\/span><span class=\"s\">\"\u52d5\u8a5e\"<\/span><span class=\"o\">,<\/span> <span class=\"n\">baseForm<\/span><span class=\"o\">)<\/span>  <span class=\"k\">=&gt;<\/span> <span class=\"n\">word<\/span> <span class=\"o\">+=<\/span> <span class=\"n\">baseForm<\/span>\r\n        <span class=\"nf\">case<\/span> <span class=\"o\">(<\/span><span class=\"k\">_<\/span><span class=\"o\">,<\/span> <span class=\"k\">_<\/span><span class=\"o\">)<\/span>  <span class=\"k\">=&gt;<\/span>\r\n      <span class=\"o\">}<\/span>\r\n    <span class=\"o\">}<\/span>\r\n  <span class=\"o\">}<\/span> <span class=\"k\">finally<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"nv\">stream<\/span><span class=\"o\">.<\/span><span class=\"py\">close<\/span>\r\n  <span class=\"o\">}<\/span>\r\n  <span class=\"nv\">word<\/span><span class=\"o\">.<\/span><span class=\"py\">toSeq<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<h4>\u4e0b\u8f7d\u6570\u636e\u6e90<\/h4>\n<p>\u6211\u5011\u4f7f\u7528\u4ee5\u4e0b\u9801\u9762\u7684\u5167\u5bb9\u3002\u6211\u5011\u53ea\u5c07\u5167\u5bb9\u7c98\u8cbc\u5230\u6587\u672c\u4e2d\uff0c\u4e0d\u5305\u62ecHTML\u6a19\u7c64\u3002<br \/>\n\u9019\u4e9b\u6587\u672c\u6587\u4ef6\u5c07\u4fdd\u5b58\u5728\/data\/mllib\/word2vec\u4e0b\u3002<br \/>\n\u662d\u548c<br \/>\n\u5e73\u6210<br \/>\n\u4ee4\u548c<\/p>\n<h4>\u542f\u52a8 spark-shell<\/h4>\n<p>\u8fd9\u6b21\u4f7f\u7528\u7684\u662f Spark(\u7248\u672c2.1.1)\u3002<br \/>\n\u4f7f\u7528 -i \u9009\u9879\u6765\u52a0\u8f7d\u4e0a\u8ff0\u7684 word2vec.scala \u5e76\u542f\u52a8 spark-shell\u3002<br \/>\n\u8fd9\u6837\u5728 spark-shell \u4e2d\u5c31\u53ef\u4ee5\u4f7f\u7528 tokenize() \u51fd\u6570\u4e86\u3002<\/p>\n<pre class=\"post-pre\"><code>\/usr\/hdp\/2.6.2.0-205\/spark2\/bin\/spark-shell <span class=\"nt\">--master<\/span> <span class=\"nb\">local<\/span> <span class=\"nt\">--deploy-mode<\/span> client <span class=\"nt\">--packages<\/span> org.apache.lucene:lucene-kuromoji:3.6.2 <span class=\"nt\">--conf<\/span> spark.serializer<span class=\"o\">=<\/span>org.apache.spark.serializer.KryoSerializer <span class=\"nt\">-i<\/span> \/spark\/src\/mllib\/word2vec.scala\r\n<\/code><\/pre>\n<h4>\u6267\u884c\u547d\u4ee4<\/h4>\n<p>\u4ee5\u4e0b\u662f\u5728spark-shell\u4e2d\u7684\u547d\u4ee4\uff1a<br \/>\n1. \u8bfb\u53d6\u6587\u672c\u6587\u4ef6<br \/>\n\u8bfb\u53d6\u9884\u5148\u51c6\u5907\u597d\u7684\u6587\u672c\u6587\u4ef6\u5e76\u8fdb\u884c\u5206\u8bcd\u3002<\/p>\n<pre class=\"post-pre\"><code>val input <span class=\"o\">=<\/span> sc.textFile<span class=\"o\">(<\/span><span class=\"s2\">\"\/data\/mllib\/word2vec\"<\/span><span class=\"o\">)<\/span>.map<span class=\"o\">(<\/span>line <span class=\"o\">=&gt;<\/span> tokenize<span class=\"o\">(<\/span>line<span class=\"o\">))<\/span>\r\n<\/code><\/pre>\n<p>\u8bbe\u7f6e\u5355\u8bcd\u51fa\u73b0\u7684\u4e0b\u9650\u6570\u548c\u751f\u6210\u5355\u8bcd\u5411\u91cf\u7684\u7ef4\u5ea6\u6570\u91cf\u3002<\/p>\n<pre class=\"post-pre\"><code>val word2vec <span class=\"o\">=<\/span> new Word2Vec<span class=\"o\">()<\/span>\r\nword2vec.setMinCount<span class=\"o\">(<\/span>3<span class=\"o\">)<\/span>\r\nword2vec.setVectorSize<span class=\"o\">(<\/span>30<span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<p>3. \u6a21\u578b\u7684\u751f\u6210<br \/>\n\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u6a21\u578b\u5c06\u4f1a\u5b8c\u6210\u3002<\/p>\n<pre class=\"post-pre\"><code>val model <span class=\"o\">=<\/span> word2vec.fit<span class=\"o\">(<\/span>input<span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h4>\u8bd5\u7740\u5bfb\u627e\u540c\u4e49\u8bcd<\/h4>\n<p>\u6309\u987a\u5e8f\u4ece\u5f97\u5206\u9ad8\u7684\u5f00\u59cb\uff0c\u68c0\u6d4b\u51fa\u4e94\u4e2a\u9879\u76ee\u3002<\/p>\n<pre class=\"post-pre\"><code>model.findSynonyms<span class=\"o\">(<\/span><span class=\"s2\">\"\u5e73\u6210\"<\/span>,5<span class=\"o\">)<\/span>\r\nres2: Array<span class=\"o\">((<\/span>\u662d\u548c,0.8683416787288002<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>\u5e74,0.7191081645948658<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>:,0.7109386795501776<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>1970,0.6096518744108191<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>\u65e5\u672c,0.5882052253525422<span class=\"o\">))<\/span>\r\n<\/code><\/pre>\n<p>&#8220;\u662d\u548c&#8221;\u4f5c\u4e3a\u4e0e&#8221;\u5e73\u6210&#8221;\u76f8\u4f3c\u7684\u8bcd\u6c47\u88ab\u68c0\u6d4b\u5230\u4f4d\u4e8e\u9876\u90e8\uff08\u5373\u4f7f\u662f\u5076\u7136\uff09\uff0c\u8fd9\u771f\u662f\u592a\u68d2\u4e86\u3002<br \/>\n&#8220;:&#8221;\u8fd9\u79cd\u610f\u4e49\u4e0d\u660e\u7684\u7b26\u53f7\u5e94\u8be5\u88ab\u9884\u5148\u79fb\u9664\uff0c\u4f5c\u4e3a\u6a21\u578b\u751f\u6210\u4e4b\u524d\u9700\u8981\u5904\u7406\u7684\u6587\u672c\u3002<\/p>\n<pre class=\"post-pre\"><code>model.findSynonyms<span class=\"o\">(<\/span><span class=\"s2\">\"\u662d\u548c\"<\/span>,5<span class=\"o\">)<\/span>\r\nres3: Array[<span class=\"o\">(<\/span>String, Double<span class=\"o\">)]<\/span> <span class=\"o\">=<\/span> Array<span class=\"o\">((<\/span>\u5e73\u6210,0.8683416675677946<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>\u5e74,0.7414342466252306<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>\u73fe\u4ee3,0.7280670946869915<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>\u6557\u6226,0.6568551583363003<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span>1970,0.6326117643599328<span class=\"o\">))<\/span>\r\n<\/code><\/pre>\n<p>\u5982\u679c\u901a\u8fc7\u201c\u662d\u548c\u201d\u8fdb\u884c\u641c\u7d22\uff0c\u4f1a\u53d1\u73b0\u201c\u5e73\u6210\u201d\u4f5c\u4e3a\u9876\u7ea7\u540c\u4e49\u8bcd\u51fa\u73b0\u3002<br \/>\n\u53ef\u80fd\u5e94\u8be5\u5728\u6587\u672c\u4e2d\u5254\u9664\u660e\u663e\u8868\u793a\u65f6\u4ee3\u7684\u5173\u952e\u8bcd\uff0c\u4f8b\u5982\u201c1970\u201d\u7b49\u3002<\/p>\n<pre class=\"post-pre\"><code>model.findSynonyms<span class=\"o\">(<\/span><span class=\"s2\">\"\u4ee4\u548c\"<\/span>,5<span class=\"o\">)<\/span>\r\njava.lang.IllegalStateException: \u4ee4\u548c not <span class=\"k\">in <\/span>vocabulary\r\n<\/code><\/pre>\n<p>\u751f\u6210\u7684\u6a21\u578b\u4e2d\u5e94\u8be5\u9891\u7e41\u51fa\u73b0\u4e86\u201c\u4ee4\u548c\u201d\u8fd9\u4e2a\u8bcd\u8bed\uff0c\u4f46\u662f\u5728\u6240\u4f7f\u7528\u7684lucene-kuromoji\u7248\u672c\u4e2d\u6ca1\u6709\u5c06\u5b83\u6ce8\u518c\u4e3a\u4e00\u4e2a\u5355\u8bcd\u3002\u8fd9\u53ef\u80fd\u662f\u56e0\u4e3a\u6240\u4f7f\u7528\u7684\u7248\u672c\u8f83\u65e7\uff0c\u5bfc\u81f4\u65e0\u6cd5\u5bf9\u201c\u4ee4\u548c\u201d\u8fdb\u884c\u8bcd\u6cd5\u5206\u6790\u3002<\/p>\n<pre class=\"post-pre\"><code>model.findSynonyms<span class=\"o\">(<\/span><span class=\"s2\">\"\u5143\u53f7\"<\/span>,5<span class=\"o\">)<\/span>\r\nres9: Array[<span class=\"o\">(<\/span>String, Double<span class=\"o\">)]<\/span> <span class=\"o\">=<\/span> Array<span class=\"o\">((<\/span>\u4ee4,0.7863372339299479<span class=\"o\">)<\/span>, <span class=\"o\">(<\/span><span class=\"s1\">''',0.7558561207740144), (\u548c,0.7263245520368361), (\u6dd1,0.7139302506327456), (\u66f2,0.7057422726424456))\r\n<\/span><\/code><\/pre>\n<p>\u9664\u4e86\u201c\u4ee4\u201d\u6392\u540d\u7b2c\u4e00\u548c\u5355\u5f15\u53f7\u6392\u540d\u7b2c\u4e8c\u4e4b\u5916\uff0c\u6211\u4eec\u53d1\u73b0\u201c\u548c\u201d\u6392\u540d\u7b2c\u4e8c\u4f5c\u4e3a\u201c\u5143\u53f7\u201d\u7684\u540c\u4e49\u8bcd\u88ab\u68c0\u6d4b\u51fa\u6765\u3002\u867d\u7136\u6211\u4eec\u4e0d\u77e5\u9053\u8fd9\u662f\u5426\u6e90\u81ea\u4e8e\u539f\u672c\u7684\u8bcd\u6c47\u201c\u4ee4\u548c\u201d\uff0c\u4f46\u7ed3\u679c\u5341\u5206\u6709\u8da3\u3002<\/p>\n<p>\u53ea\u8f93\u5165\u4e863\u9875\u7ef4\u57fa\u767e\u79d1\u4fe1\u606f\uff0c\u4f46\u6211\u53d1\u73b0\u9690\u7ea6\u627e\u5230\u4e86\u76f8\u5173\u7684\u8bcd\u8bed\u3002<br \/>\n\u7136\u800c\uff0c\u589e\u52a0\u4fe1\u606f\u91cf\u5e76\u4e0d\u610f\u5473\u7740\u63d0\u9ad8\u51c6\u786e\u6027\uff0c\u56e0\u4e3a\u989d\u5916\u7684\u7b26\u53f7\u548c\u6570\u5b57\u7b49\u5197\u4f59\u4fe1\u606f\u5b58\u5728\uff0c\u51c6\u786e\u6027\u4f1a\u4e0b\u964d\u3002<br \/>\n\u5982\u4f55\u786e\u4fdd\u8f93\u5165\u4fe1\u606f\u7684\u4e00\u81f4\u6027\u548c\u9ad8\u8d28\u91cf\u53ef\u80fd\u6210\u4e3a\u826f\u597d\u6a21\u578b\u751f\u6210\u7684\u4e00\u4e2a\u5173\u952e\u8981\u7d20\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Word2Vec\uff1a\u8bcd\u5411\u91cf Word2Vec\u662f\u7531\u8c37\u6b4c\u7814\u7a76\u6240\u57282013\u5e74\u63d0\u51fa\u7684\u4e00\u4e2a\u7b97\u6cd5\uff0c\u8be5\u7b97\u6cd5\u57fa\u4e8e\u5047\u8bbe&#038;#8221 [&hellip;]<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-36757","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528-apache-spark-\u8fdb\u884c-word2vec\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec\" \/>\n<meta property=\"og:description\" content=\"Word2Vec\uff1a\u8bcd\u5411\u91cf Word2Vec\u662f\u7531\u8c37\u6b4c\u7814\u7a76\u6240\u57282013\u5e74\u63d0\u51fa\u7684\u4e00\u4e2a\u7b97\u6cd5\uff0c\u8be5\u7b97\u6cd5\u57fa\u4e8e\u5047\u8bbe&amp;#8221 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528-apache-spark-\u8fdb\u884c-word2vec\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-12-20T06:56:02+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-04T03:21:21+00:00\" \/>\n<meta name=\"author\" content=\"\u6587, \u7fd4\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6587, \u7fd4\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/\",\"name\":\"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-12-20T06:56:02+00:00\",\"dateModified\":\"2024-05-04T03:21:21+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c\",\"name\":\"\u6587, \u7fd4\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g\",\"caption\":\"\u6587, \u7fd4\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/wenxiang\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528-apache-spark-\u8fdb\u884c-word2vec\/","og_locale":"zh_CN","og_type":"article","og_title":"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec","og_description":"Word2Vec\uff1a\u8bcd\u5411\u91cf Word2Vec\u662f\u7531\u8c37\u6b4c\u7814\u7a76\u6240\u57282013\u5e74\u63d0\u51fa\u7684\u4e00\u4e2a\u7b97\u6cd5\uff0c\u8be5\u7b97\u6cd5\u57fa\u4e8e\u5047\u8bbe&#8221 [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528-apache-spark-\u8fdb\u884c-word2vec\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-12-20T06:56:02+00:00","article_modified_time":"2024-05-04T03:21:21+00:00","author":"\u6587, \u7fd4","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6587, \u7fd4","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"1 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/","name":"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-12-20T06:56:02+00:00","dateModified":"2024-05-04T03:21:21+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u4f7f\u7528 Apache Spark \u8fdb\u884c Word2Vec"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c","name":"\u6587, \u7fd4","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/920c3d673e0bccacc98e5e6b7149bb3c22edd8d39cb753e5d7d7e471498118a1?s=96&d=mm&r=g","caption":"\u6587, \u7fd4"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/wenxiang\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8-apache-spark-%e8%bf%9b%e8%a1%8c-word2vec\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36757","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=36757"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36757\/revisions"}],"predecessor-version":[{"id":98024,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36757\/revisions\/98024"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=36757"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=36757"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=36757"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}