{"id":135081,"date":"2024-10-31T07:33:05","date_gmt":"2024-10-30T23:33:05","guid":{"rendered":"https:\/\/server.hk\/cnblog\/135081\/"},"modified":"2024-10-31T07:33:06","modified_gmt":"2024-10-30T23:33:06","slug":"spark%e4%b8%ad%e7%9a%84%e6%a0%b8%e5%bf%83%e6%a6%82%e5%bf%b5rdd%ef%bc%8c%e6%88%91%e5%80%91%e4%ba%86%e8%a7%a3%e5%a4%9a%e5%b0%91%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/server.hk\/cnblog\/135081\/","title":{"rendered":"Spark\u4e2d\u7684\u6838\u5fc3\u6982\u5ff5RDD\uff0c\u6211\u5011\u4e86\u89e3\u591a\u5c11\uff1f"},"content":{"rendered":"<h1 id=\"spark%e4%b8%ad%e7%9a%84%e6%a0%b8%e5%bf%83%e6%a6%82%e5%bf%b5rdd%ef%bc%8c%e6%88%91%e5%80%91%e4%ba%86%e8%a7%a3%e5%a4%9a%e5%b0%91%ef%bc%9f-SoBeorekMi\">Spark\u4e2d\u7684\u6838\u5fc3\u6982\u5ff5RDD\uff0c\u6211\u5011\u4e86\u89e3\u591a\u5c11\uff1f<\/h1>\n<p>\u5728\u5927\u6578\u64da\u8655\u7406\u7684\u9818\u57df\u4e2d\uff0cApache Spark\u4f5c\u70ba\u4e00\u500b\u5f37\u5927\u7684\u958b\u6e90\u8a08\u7b97\u6846\u67b6\uff0c\u5df2\u7d93\u6210\u70ba\u8a31\u591a\u4f01\u696d\u548c\u958b\u767c\u8005\u7684\u9996\u9078\u3002Spark\u7684\u6838\u5fc3\u6982\u5ff5\u4e4b\u4e00\u662f\u5f48\u6027\u5206\u4f48\u5f0f\u6578\u64da\u96c6\uff08Resilient Distributed Dataset\uff0c\u7c21\u7a31RDD\uff09\u3002\u672c\u6587\u5c07\u6df1\u5165\u63a2\u8a0eRDD\u7684\u57fa\u672c\u6982\u5ff5\u3001\u7279\u6027\u53ca\u5176\u5728\u6578\u64da\u8655\u7406\u4e2d\u7684\u61c9\u7528\u3002<\/p>\n<h2 id=\"%e4%bb%80%e9%ba%bc%e6%98%afrdd%ef%bc%9f-SoBeorekMi\">\u4ec0\u9ebc\u662fRDD\uff1f<\/h2>\n<p>RDD\u662f\u4e00\u7a2e\u4e0d\u53ef\u8b8a\u7684\u5206\u4f48\u5f0f\u6578\u64da\u96c6\uff0c\u5141\u8a31\u7528\u6236\u5728\u96c6\u7fa4\u4e0a\u9032\u884c\u4e26\u884c\u8a08\u7b97\u3002RDD\u7684\u8a2d\u8a08\u4f7f\u5176\u80fd\u5920\u5728\u6545\u969c\u767c\u751f\u6642\u81ea\u52d5\u6062\u5fa9\uff0c\u9019\u662f\u5176\u201c\u5f48\u6027\u201d\u7279\u6027\u7684\u4f86\u6e90\u3002\u7528\u6236\u53ef\u4ee5\u901a\u904e\u5169\u7a2e\u65b9\u5f0f\u5275\u5efaRDD\uff1a\u5f9e\u73fe\u6709\u7684\u6578\u64da\u96c6\uff08\u5982HDFS\u3001S3\u7b49\uff09\u4e2d\u52a0\u8f09\uff0c\u6216\u901a\u904e\u5c0d\u5176\u4ed6RDD\u9032\u884c\u8f49\u63db\u4f86\u751f\u6210\u3002<\/p>\n<h2 id=\"rdd%e7%9a%84%e7%89%b9%e6%80%a7-SoBeorekMi\">RDD\u7684\u7279\u6027<\/h2>\n<ul>\n<li><strong>\u4e0d\u53ef\u8b8a\u6027\uff1a<\/strong>\u4e00\u65e6\u5275\u5efa\uff0cRDD\u7684\u5167\u5bb9\u7121\u6cd5\u66f4\u6539\u3002\u9019\u610f\u5473\u8457\u6bcf\u6b21\u5c0dRDD\u7684\u64cd\u4f5c\u90fd\u6703\u751f\u6210\u4e00\u500b\u65b0\u7684RDD\uff0c\u9019\u6709\u52a9\u65bc\u7c21\u5316\u4e26\u884c\u8a08\u7b97\u4e2d\u7684\u6578\u64da\u7ba1\u7406\u3002<\/li>\n<li><strong>\u5206\u4f48\u5f0f\u8a08\u7b97\uff1a<\/strong>RDD\u7684\u6578\u64da\u5206\u4f48\u5728\u96c6\u7fa4\u7684\u591a\u500b\u7bc0\u9ede\u4e0a\uff0c\u9019\u4f7f\u5f97\u8a08\u7b97\u53ef\u4ee5\u4e26\u884c\u9032\u884c\uff0c\u5f9e\u800c\u63d0\u9ad8\u4e86\u8655\u7406\u901f\u5ea6\u3002<\/li>\n<li><strong>\u5bb9\u932f\u6027\uff1a<\/strong>RDD\u80fd\u5920\u81ea\u52d5\u6062\u5fa9\u4e1f\u5931\u7684\u6578\u64da\u3002\u7576\u67d0\u500b\u7bc0\u9ede\u5931\u6548\u6642\uff0cSpark\u53ef\u4ee5\u6839\u64daRDD\u7684\u8840\u7d71\u4fe1\u606f\uff08lineage\uff09\u91cd\u65b0\u8a08\u7b97\u4e1f\u5931\u7684\u6578\u64da\u3002<\/li>\n<li><strong>\u652f\u6301\u591a\u7a2e\u64cd\u4f5c\uff1a<\/strong>RDD\u652f\u6301\u5169\u985e\u64cd\u4f5c\uff1a\u8f49\u63db\uff08\u5982map\u3001filter\u3001flatMap\u7b49\uff09\u548c\u884c\u52d5\uff08\u5982count\u3001collect\u3001reduce\u7b49\uff09\u3002\u8f49\u63db\u64cd\u4f5c\u6703\u751f\u6210\u65b0\u7684RDD\uff0c\u800c\u884c\u52d5\u64cd\u4f5c\u5247\u6703\u8fd4\u56de\u7d50\u679c\u7d66\u9a45\u52d5\u7a0b\u5e8f\u3002<\/li>\n<\/ul>\n<h2 id=\"rdd%e7%9a%84%e5%89%b5%e5%bb%ba%e8%88%87%e6%93%8d%e4%bd%9c-SoBeorekMi\">RDD\u7684\u5275\u5efa\u8207\u64cd\u4f5c<\/h2>\n<p>\u5275\u5efaRDD\u7684\u65b9\u5f0f\u6709\u591a\u7a2e\uff0c\u4ee5\u4e0b\u662f\u4e00\u4e9b\u5e38\u898b\u7684\u65b9\u6cd5\uff1a<\/p>\n<h3 id=\"%e5%be%9e%e9%9b%86%e5%90%88%e5%89%b5%e5%bb%bardd-SoBeorekMi\">\u5f9e\u96c6\u5408\u5275\u5efaRDD<\/h3>\n<pre><code>val data = Seq(1, 2, 3, 4, 5)\nval rdd = sparkContext.parallelize(data)<\/code><\/pre>\n<h3 id=\"%e5%be%9e%e5%a4%96%e9%83%a8%e6%95%b8%e6%93%9a%e6%ba%90%e5%89%b5%e5%bb%bardd-SoBeorekMi\">\u5f9e\u5916\u90e8\u6578\u64da\u6e90\u5275\u5efaRDD<\/h3>\n<pre><code>val rddFromFile = sparkContext.textFile(\"hdfs:\/\/path\/to\/file.txt\")<\/code><\/pre>\n<h3 id=\"rdd%e7%9a%84%e8%bd%89%e6%8f%9b%e6%93%8d%e4%bd%9c-SoBeorekMi\">RDD\u7684\u8f49\u63db\u64cd\u4f5c<\/h3>\n<p>\u8f49\u63db\u64cd\u4f5c\u662f\u5c0dRDD\u9032\u884c\u8655\u7406\u7684\u4e3b\u8981\u65b9\u5f0f\uff0c\u4ee5\u4e0b\u662f\u4e00\u4e9b\u793a\u4f8b\uff1a<\/p>\n<pre><code>val squaredRDD = rdd.map(x =&gt; x * x)\nval filteredRDD = rdd.filter(x =&gt; x % 2 == 0)<\/code><\/pre>\n<h3 id=\"rdd%e7%9a%84%e8%a1%8c%e5%8b%95%e6%93%8d%e4%bd%9c-SoBeorekMi\">RDD\u7684\u884c\u52d5\u64cd\u4f5c<\/h3>\n<p>\u884c\u52d5\u64cd\u4f5c\u6703\u89f8\u767c\u8a08\u7b97\u4e26\u8fd4\u56de\u7d50\u679c\uff0c\u4ee5\u4e0b\u662f\u4e00\u4e9b\u793a\u4f8b\uff1a<\/p>\n<pre><code>val count = rdd.count()\nval collectedData = rdd.collect()<\/code><\/pre>\n<h2 id=\"rdd%e7%9a%84%e6%87%89%e7%94%a8%e5%a0%b4%e6%99%af-SoBeorekMi\">RDD\u7684\u61c9\u7528\u5834\u666f<\/h2>\n<p>RDD\u5728\u8a31\u591a\u5927\u6578\u64da\u8655\u7406\u5834\u666f\u4e2d\u767c\u63ee\u8457\u91cd\u8981\u4f5c\u7528\uff0c\u5305\u62ec\u4f46\u4e0d\u9650\u65bc\uff1a<\/p>\n<ul>\n<li>\u6578\u64da\u6e05\u6d17\uff1a\u901a\u904e\u904e\u6ffe\u548c\u8f49\u63db\u64cd\u4f5c\uff0cRDD\u53ef\u4ee5\u7528\u65bc\u6e05\u7406\u548c\u6e96\u5099\u6578\u64da\u3002<\/li>\n<li>\u6578\u64da\u5206\u6790\uff1a\u4f7f\u7528RDD\u9032\u884c\u5404\u7a2e\u6578\u64da\u5206\u6790\u64cd\u4f5c\uff0c\u5982\u7d71\u8a08\u8a08\u7b97\u548c\u6578\u64da\u6316\u6398\u3002<\/li>\n<li>\u6a5f\u5668\u5b78\u7fd2\uff1aRDD\u53ef\u4ee5\u4f5c\u70ba\u6a5f\u5668\u5b78\u7fd2\u7b97\u6cd5\u7684\u8f38\u5165\uff0c\u652f\u6301\u5927\u898f\u6a21\u6578\u64da\u96c6\u7684\u8a13\u7df4\u548c\u9810\u6e2c\u3002<\/li>\n<\/ul>\n<h2 id=\"%e7%b8%bd%e7%b5%90-SoBeorekMi\">\u7e3d\u7d50<\/h2>\n<p>\u5f48\u6027\u5206\u4f48\u5f0f\u6578\u64da\u96c6\uff08RDD\uff09\u662fApache Spark\u7684\u6838\u5fc3\u7d44\u4ef6\u4e4b\u4e00\uff0c\u63d0\u4f9b\u4e86\u9ad8\u6548\u7684\u6578\u64da\u8655\u7406\u80fd\u529b\u3002\u901a\u904e\u5176\u4e0d\u53ef\u8b8a\u6027\u3001\u5206\u4f48\u5f0f\u8a08\u7b97\u548c\u5bb9\u932f\u6027\uff0cRDD\u4f7f\u5f97\u5927\u6578\u64da\u8655\u7406\u8b8a\u5f97\u66f4\u52a0\u7c21\u55ae\u548c\u53ef\u9760\u3002\u7121\u8ad6\u662f\u5728\u6578\u64da\u6e05\u6d17\u3001\u5206\u6790\u9084\u662f\u6a5f\u5668\u5b78\u7fd2\u4e2d\uff0cRDD\u90fd\u80fd\u5920\u767c\u63ee\u91cd\u8981\u4f5c\u7528\u3002\u5c0d\u65bc\u9700\u8981\u9ad8\u6548\u6578\u64da\u8655\u7406\u7684\u4f01\u696d\u4f86\u8aaa\uff0c\u9078\u64c7\u5408\u9069\u7684\u8a08\u7b97\u5e73\u53f0\u81f3\u95dc\u91cd\u8981\u3002\u4e86\u89e3\u66f4\u591a\u95dc\u65bc<a href=\"https:\/\/server.hk\">\u9999\u6e2fVPS<\/a>\u548c<a href=\"https:\/\/server.hk\">\u96f2\u4f3a\u670d\u5668<\/a>\u7684\u8cc7\u8a0a\uff0c\u5c07\u6709\u52a9\u65bc\u60a8\u5728\u5927\u6578\u64da\u8655\u7406\u4e2d\u505a\u51fa\u66f4\u660e\u667a\u7684\u9078\u64c7\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u63a2\u7d22Spark\u4e2d\u7684\u6838\u5fc3\u6982\u5ff5RDD\uff0c\u4e86\u89e3\u5176\u5b9a\u7fa9\u3001\u7279\u6027\u53ca\u5728\u5927\u6578\u64da\u8655\u7406\u4e2d\u7684\u91cd\u8981\u6027\uff0c\u63d0\u5347\u6578\u64da\u8655\u7406\u6548\u7387\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-135081","post","type-post","status-publish","format-standard","hentry","category-database"],"_links":{"self":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135081","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=135081"}],"version-history":[{"count":1,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135081\/revisions"}],"predecessor-version":[{"id":135082,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/posts\/135081\/revisions\/135082"}],"wp:attachment":[{"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/media?parent=135081"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/categories?post=135081"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/server.hk\/cnblog\/wp-json\/wp\/v2\/tags?post=135081"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}