{"id":135007,"date":"2024-10-31T06:20:17","date_gmt":"2024-10-30T22:20:17","guid":{"rendered":"https:\/\/server.hk\/cnblog\/135007\/"},"modified":"2024-10-31T06:20:18","modified_gmt":"2024-10-30T22:20:18","slug":"r%e8%aa%9e%e8%a8%80%e7%82%bahadoop%e9%9b%86%e7%be%a4%e6%95%b8%e6%93%9a%e7%b5%b1%e8%a8%88%e5%88%86%e6%9e%90%e5%b8%b6%e4%be%86%e9%9d%a9%e5%91%bd%e6%80%a7%e8%ae%8a%e5%8c%96","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/135007\/","title":{"rendered":"R\u8a9e\u8a00\u70baHadoop\u96c6\u7fa4\u6578\u64da\u7d71\u8a08\u5206\u6790\u5e36\u4f86\u9769\u547d\u6027\u8b8a\u5316"},"content":{"rendered":"<h1 id=\"r%e8%aa%9e%e8%a8%80%e7%82%bahadoop%e9%9b%86%e7%be%a4%e6%95%b8%e6%93%9a%e7%b5%b1%e8%a8%88%e5%88%86%e6%9e%90%e5%b8%b6%e4%be%86%e9%9d%a9%e5%91%bd%e6%80%a7%e8%ae%8a%e5%8c%96-lHgVqKonow\">R\u8a9e\u8a00\u70baHadoop\u96c6\u7fa4\u6578\u64da\u7d71\u8a08\u5206\u6790\u5e36\u4f86\u9769\u547d\u6027\u8b8a\u5316<\/h1>\n<p>\u96a8\u8457\u5927\u6578\u64da\u6642\u4ee3\u7684\u4f86\u81e8\uff0c\u6578\u64da\u5206\u6790\u7684\u9700\u6c42\u65e5\u76ca\u589e\u52a0\u3002Hadoop\u4f5c\u70ba\u4e00\u500b\u958b\u6e90\u7684\u5206\u4f48\u5f0f\u8a08\u7b97\u5e73\u53f0\uff0c\u5df2\u7d93\u6210\u70ba\u8655\u7406\u548c\u5206\u6790\u6d77\u91cf\u6578\u64da\u7684\u4e3b\u6d41\u5de5\u5177\u4e4b\u4e00\u3002\u800cR\u8a9e\u8a00\uff0c\u4f5c\u70ba\u4e00\u7a2e\u5f37\u5927\u7684\u7d71\u8a08\u8a08\u7b97\u548c\u5716\u5f62\u7e6a\u88fd\u5de5\u5177\uff0c\u5247\u5728\u6578\u64da\u5206\u6790\u9818\u57df\u4e2d\u4f54\u64da\u4e86\u91cd\u8981\u5730\u4f4d\u3002\u5c07R\u8a9e\u8a00\u8207Hadoop\u96c6\u7fa4\u7d50\u5408\uff0c\u70ba\u6578\u64da\u7d71\u8a08\u5206\u6790\u5e36\u4f86\u4e86\u9769\u547d\u6027\u7684\u8b8a\u5316\u3002<\/p>\n<h2 id=\"hadoop%e8%88%87r%e8%aa%9e%e8%a8%80%e7%9a%84%e7%b5%90%e5%90%88-lHgVqKonow\">Hadoop\u8207R\u8a9e\u8a00\u7684\u7d50\u5408<\/h2>\n<p>Hadoop\u7684\u6838\u5fc3\u662f\u5176\u5206\u4f48\u5f0f\u6587\u4ef6\u7cfb\u7d71\uff08HDFS\uff09\u548cMapReduce\u8a08\u7b97\u6a21\u578b\u3002\u9019\u4f7f\u5f97Hadoop\u80fd\u5920\u5728\u591a\u53f0\u4f3a\u670d\u5668\u4e0a\u4e26\u884c\u8655\u7406\u5927\u91cf\u6578\u64da\u3002R\u8a9e\u8a00\u5247\u4ee5\u5176\u7c21\u6f54\u7684\u8a9e\u6cd5\u548c\u5f37\u5927\u7684\u6578\u64da\u8655\u7406\u80fd\u529b\uff0c\u6210\u70ba\u6578\u64da\u79d1\u5b78\u5bb6\u548c\u7d71\u8a08\u5b78\u5bb6\u7684\u9996\u9078\u5de5\u5177\u3002\u901a\u904e\u5c07R\u8a9e\u8a00\u8207Hadoop\u7d50\u5408\uff0c\u4f7f\u7528\u8005\u53ef\u4ee5\u5728Hadoop\u96c6\u7fa4\u4e0a\u9032\u884c\u9ad8\u6548\u7684\u6578\u64da\u5206\u6790\uff0c\u9019\u4e00\u904e\u7a0b\u901a\u5e38\u6d89\u53ca\u4ee5\u4e0b\u5e7e\u500b\u6b65\u9a5f\uff1a<\/p>\n<ul>\n<li><strong>\u6578\u64da\u5b58\u5132\uff1a<\/strong>\u5c07\u6578\u64da\u5b58\u5132\u5728HDFS\u4e2d\uff0c\u4fbf\u65bc\u5927\u898f\u6a21\u6578\u64da\u7684\u7ba1\u7406\u548c\u8a2a\u554f\u3002<\/li>\n<li><strong>\u6578\u64da\u8655\u7406\uff1a<\/strong>\u4f7f\u7528MapReduce\u6a21\u578b\u9032\u884c\u6578\u64da\u7684\u521d\u6b65\u8655\u7406\uff0c\u5c07\u6578\u64da\u8f49\u63db\u70baR\u8a9e\u8a00\u53ef\u4ee5\u8655\u7406\u7684\u683c\u5f0f\u3002<\/li>\n<li><strong>\u6578\u64da\u5206\u6790\uff1a<\/strong>\u5229\u7528R\u8a9e\u8a00\u7684\u7d71\u8a08\u5206\u6790\u529f\u80fd\uff0c\u5c0d\u8655\u7406\u5f8c\u7684\u6578\u64da\u9032\u884c\u6df1\u5165\u5206\u6790\u3002<\/li>\n<li><strong>\u7d50\u679c\u53ef\u8996\u5316\uff1a<\/strong>\u4f7f\u7528R\u8a9e\u8a00\u7684\u5716\u5f62\u7e6a\u88fd\u529f\u80fd\uff0c\u5c07\u5206\u6790\u7d50\u679c\u4ee5\u53ef\u8996\u5316\u7684\u65b9\u5f0f\u5448\u73fe\u3002<\/li>\n<\/ul>\n<h2 id=\"r%e8%aa%9e%e8%a8%80%e7%9a%84%e5%84%aa%e5%8b%a2-lHgVqKonow\">R\u8a9e\u8a00\u7684\u512a\u52e2<\/h2>\n<p>R\u8a9e\u8a00\u5728\u6578\u64da\u5206\u6790\u65b9\u9762\u7684\u512a\u52e2\u4e3b\u8981\u9ad4\u73fe\u5728\u4ee5\u4e0b\u5e7e\u500b\u65b9\u9762\uff1a<\/p>\n<ul>\n<li><strong>\u8c50\u5bcc\u7684\u51fd\u6578\u5eab\uff1a<\/strong>R\u8a9e\u8a00\u64c1\u6709\u5927\u91cf\u7684\u7d71\u8a08\u548c\u6578\u64da\u5206\u6790\u51fd\u6578\u5eab\uff0c\u5982dplyr\u3001ggplot2\u7b49\uff0c\u9019\u4e9b\u51fd\u6578\u5eab\u80fd\u5920\u7c21\u5316\u6578\u64da\u8655\u7406\u548c\u53ef\u8996\u5316\u7684\u904e\u7a0b\u3002<\/li>\n<li><strong>\u9748\u6d3b\u6027\uff1a<\/strong>R\u8a9e\u8a00\u7684\u8a9e\u6cd5\u9748\u6d3b\uff0c\u4f7f\u7528\u8005\u53ef\u4ee5\u6839\u64da\u9700\u6c42\u81ea\u5b9a\u7fa9\u51fd\u6578\uff0c\u6eff\u8db3\u7279\u5b9a\u7684\u5206\u6790\u9700\u6c42\u3002<\/li>\n<li><strong>\u793e\u7fa4\u652f\u6301\uff1a<\/strong>R\u8a9e\u8a00\u64c1\u6709\u6d3b\u8e8d\u7684\u958b\u767c\u8005\u793e\u7fa4\uff0c\u4f7f\u7528\u8005\u53ef\u4ee5\u8f15\u9b06\u7372\u5f97\u5e6b\u52a9\u548c\u8cc7\u6e90\u3002<\/li>\n<\/ul>\n<h2 id=\"%e5%af%a6%e9%9a%9b%e6%87%89%e7%94%a8%e6%a1%88%e4%be%8b-lHgVqKonow\">\u5be6\u969b\u61c9\u7528\u6848\u4f8b<\/h2>\n<p>\u5728\u5be6\u969b\u61c9\u7528\u4e2d\uff0cR\u8a9e\u8a00\u8207Hadoop\u7684\u7d50\u5408\u5df2\u7d93\u5728\u591a\u500b\u9818\u57df\u5c55\u73fe\u51fa\u5176\u5f37\u5927\u7684\u80fd\u529b\u3002\u4f8b\u5982\uff0c\u5728\u91d1\u878d\u884c\u696d\uff0c\u5206\u6790\u5e2b\u53ef\u4ee5\u5229\u7528Hadoop\u8655\u7406\u5927\u91cf\u7684\u4ea4\u6613\u6578\u64da\uff0c\u7136\u5f8c\u4f7f\u7528R\u8a9e\u8a00\u9032\u884c\u98a8\u96aa\u8a55\u4f30\u548c\u9810\u6e2c\u6a21\u578b\u7684\u5efa\u7acb\u3002\u5728\u91ab\u7642\u9818\u57df\uff0c\u7814\u7a76\u4eba\u54e1\u53ef\u4ee5\u901a\u904eHadoop\u5206\u6790\u60a3\u8005\u7684\u5065\u5eb7\u6578\u64da\uff0c\u4e26\u5229\u7528R\u8a9e\u8a00\u9032\u884c\u75be\u75c5\u9810\u6e2c\u548c\u6cbb\u7642\u6548\u679c\u8a55\u4f30\u3002<\/p>\n<pre><code>\n# \u4f7f\u7528R\u8a9e\u8a00\u9023\u63a5Hadoop\nlibrary(rmr2)\n\n# \u5b9a\u7fa9MapReduce\u51fd\u6578\nmap_function &lt;- function(k, v) {\n    keyval(v$category, v$value)\n}\n\nreduce_function &lt;- function(k, v) {\n    sum(v)\n}\n\n# \u57f7\u884cMapReduce\nresult &lt;- mrpmapreduce(input = &quot;hdfs:\/\/path\/to\/data&quot;, \n                       map = map_function, \n                       reduce = reduce_function)\n<\/code><\/pre>\n<h2 id=\"%e7%b5%90%e8%ab%96-lHgVqKonow\">\u7d50\u8ad6<\/h2>\n<p>\u7e3d\u7684\u4f86\u8aaa\uff0cR\u8a9e\u8a00\u8207Hadoop\u7684\u7d50\u5408\u70ba\u6578\u64da\u7d71\u8a08\u5206\u6790\u5e36\u4f86\u4e86\u9769\u547d\u6027\u7684\u8b8a\u5316\u3002\u9019\u7a2e\u7d50\u5408\u4e0d\u50c5\u63d0\u9ad8\u4e86\u6578\u64da\u8655\u7406\u7684\u6548\u7387\uff0c\u9084\u64f4\u5c55\u4e86\u6578\u64da\u5206\u6790\u7684\u53ef\u80fd\u6027\u3002\u96a8\u8457\u5927\u6578\u64da\u6280\u8853\u7684\u6301\u7e8c\u767c\u5c55\uff0c\u672a\u4f86R\u8a9e\u8a00\u5728Hadoop\u96c6\u7fa4\u4e2d\u7684\u61c9\u7528\u5c07\u6703\u66f4\u52a0\u5ee3\u6cdb\uff0c\u70ba\u5404\u884c\u5404\u696d\u7684\u6578\u64da\u5206\u6790\u63d0\u4f9b\u66f4\u5f37\u5927\u7684\u652f\u6301\u3002<\/p>\n<p>\u5982\u679c\u60a8\u5c0d\u65bc\u5982\u4f55\u5728\u9999\u6e2f\u4f7f\u7528 <a href=\"https:\/\/server.hk\">VPS<\/a> \u9032\u884c\u6578\u64da\u5206\u6790\u611f\u8208\u8da3\uff0c\u6216\u60f3\u4e86\u89e3\u66f4\u591a\u95dc\u65bc <a href=\"https:\/\/server.hk\">\u9999\u6e2f\u4f3a\u670d\u5668<\/a> \u7684\u8cc7\u8a0a\uff0c\u6b61\u8fce\u8a2a\u554f\u6211\u5011\u7684\u7db2\u7ad9\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>R\u8a9e\u8a00\u70baHadoop\u96c6\u7fa4\u6578\u64da\u7d71\u8a08\u5206\u6790\u5e36\u4f86\u9769\u547d\u6027\u8b8a\u5316\uff0c\u63d0\u5347\u6578\u64da\u8655\u7406\u6548\u7387\uff0c\u52a9\u529b\u7cbe\u6e96\u6c7a\u7b56\u8207\u6df1\u5165\u6d1e\u5bdf\u3002<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[101],"tags":[],"class_list":["post-135007","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135007","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"}],"replies":[{"embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/comments?post=135007"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135007\/revisions"}],"predecessor-version":[{"id":135008,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135007\/revisions\/135008"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=135007"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=135007"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=135007"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}