{"id":36437,"date":"2023-09-03T05:47:01","date_gmt":"2024-02-27T13:37:40","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/"},"modified":"2024-04-30T21:20:12","modified_gmt":"2024-04-30T13:20:12","slug":"apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/","title":{"rendered":"Apache Spark &#8211; \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 &#8211;"},"content":{"rendered":"<h1>\u9996\u5148<\/h1>\n<p>\u9019\u7bc7\u6587\u7ae0\u8a66\u5716\u901a\u904e\u8209\u4f8b\u4f86\u7e3d\u7d50Apache Spark\u7684\u5206\u5340\u6982\u5ff5\u3002<br \/>\n\u6709\u95dcApache Spark\u7684\u6982\u8ff0\uff0c\u8acb\u53c3\u95b1&#8221;Apache Spark \u9032\u884c\u5206\u6563\u8655\u7406\u5165\u9580&#8221;\u3002<\/p>\n<h1>\u901a\u8fc7\u4f8b\u9898\u6765\u4e86\u89e3\u5206\u533a\u7684\u6982\u5ff5\u548c\u64cd\u4f5c\u65b9\u6cd5\u3002<\/h1>\n<p>\u4ee5\u4e0b\u662f\u7528Apache Spark\u6f14\u793a\u5206\u5e03\u5904\u7406\u7684\u793a\u4f8b\u56fe\u89e3\u3002<br \/>\n\u9996\u5148\u4ecb\u7ecd\u4e86\u4f7f\u7528\u7684\u51fd\u6570\u8bf4\u660e\uff0c\u63a5\u7740\u662f\u5904\u7406\u7684\u56fe\u50cf\uff0c\u6700\u540e\u6309\u6e90\u4ee3\u7801\u7684\u987a\u5e8f\u8fdb\u884c\u4ecb\u7ecd\u3002<br \/>\n\u4ecb\u7ecd\u4e86\u4f7f\u7528\u4e0d\u540c\u5206\u533a\u65b9\u5f0f\u7684\u4e09\u4e2a\u4f8b\u5b50\uff1a<br \/>\n&#8211; filter\u51fd\u6570\u7684\u4f8b\u5b50<br \/>\n&#8211; flatmap\u51fd\u6570\u7684\u4f8b\u5b50<br \/>\n&#8211; reduceByKey\u51fd\u6570\u7684\u4f8b\u5b50<\/p>\n<h2>filter\u51fd\u6570\u7684\u793a\u4f8b<\/h2>\n<p>\u5728\u8fdb\u884c\u8981\u7d20\u5355\u4f4d\u8f6c\u6362\u65f6\uff0c\u53ef\u4f7f\u7528map()\u548cfilter\u7b49\u65b9\u6cd5\u3002<\/p>\n<div>\n<div class=\"post-table\">\u95a2\u6570\u8aac\u660emap()\u5f15\u6570\u306b\u95a2\u6570\u3092\u4e00\u3064\u53d6\u308a\u3001\u305d\u306e\u95a2\u6570\u3092RDD\u5185\u306e\u5404\u8981\u7d20\u306b\u9069\u5fdc\u3057\u3001\u305d\u306e\u7d50\u679c\u3092\u65b0\u3057\u3044\u5024\u3068\u3059\u308bRDD\u3092\u8fd4\u3059filter()\u5f15\u6570\u306b\u95a2\u6570\u3092\u4e00\u3064\u53d6\u308a\u3001\u305d\u306e\u30d5\u30a3\u30eb\u30bf\u95a2\u6570\u304c\u771f\u306b\u306a\u308b\u8981\u7d20\u3060\u3051\u3092\u542b\u3080RDD\u3092\u8fd4\u3059<\/div>\n<\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/7-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 18.15.57.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/8-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 18.16.04.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/9-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 18.16.07.png\" \/><\/div>\n<p>\u6e90\u4ee3\u7801\u5728\u8fd9\u91cc<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">package<\/span> <span class=\"nn\">other<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaRDD<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaSparkContext<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"cm\">\/**\r\n * Created by hirokinaganuma on 2016\/10\/11.\r\n *\/<\/span>\r\n<span class=\"kd\">public<\/span> <span class=\"kd\">class<\/span> <span class=\"nc\">Sample02<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"kd\">public<\/span> <span class=\"kd\">static<\/span> <span class=\"kt\">void<\/span> <span class=\"nf\">main<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span><span class=\"o\">[]<\/span> <span class=\"n\">args<\/span><span class=\"o\">)<\/span> <span class=\"kd\">throws<\/span> <span class=\"nc\">Exception<\/span> <span class=\"o\">{<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">master<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"o\">(<\/span><span class=\"n\">args<\/span><span class=\"o\">.<\/span><span class=\"na\">length<\/span> <span class=\"o\">&gt;<\/span> <span class=\"mi\">0<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"n\">args<\/span><span class=\"o\">[<\/span><span class=\"mi\">0<\/span><span class=\"o\">];<\/span>\r\n        <span class=\"o\">}<\/span> <span class=\"k\">else<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"local\"<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        <span class=\"nc\">JavaSparkContext<\/span> <span class=\"n\">sc<\/span> <span class=\"o\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">JavaSparkContext<\/span><span class=\"o\">(<\/span><span class=\"n\">master<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"basicavg\"<\/span><span class=\"o\">,<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"SPARK_HOME\"<\/span><span class=\"o\">),<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"JARS\"<\/span><span class=\"o\">));<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">input<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/input\/*.txt\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">result<\/span> <span class=\"o\">=<\/span> <span class=\"n\">input<\/span><span class=\"o\">.<\/span><span class=\"na\">filter<\/span><span class=\"o\">(<\/span><span class=\"n\">s<\/span><span class=\"o\">-&gt;<\/span> <span class=\"o\">!<\/span><span class=\"n\">s<\/span><span class=\"o\">.<\/span><span class=\"na\">contains<\/span><span class=\"o\">(<\/span><span class=\"s\">\"Triangle\"<\/span><span class=\"o\">));<\/span>\r\n        <span class=\"n\">result<\/span><span class=\"o\">.<\/span><span class=\"na\">saveAsTextFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/output\/output02\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">stop<\/span><span class=\"o\">();<\/span>\r\n    <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>Rectangle\r\nCircle\r\nTriangle\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>Circle\r\nRectangle\r\nTriangle\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>Triangle\r\nRectangle\r\n<\/code><\/pre>\n<p>RDD\u662f\u4e00\u79cd\u5206\u5e03\u5f0f\u96c6\u5408\uff0c\u53ef\u4ee5\u4fdd\u5b58\u5927\u91cf\u7684\u6570\u636e\u5143\u7d20\u3002RDD\u662f\u8bbe\u8ba1\u7528\u4e8e\u5728\u7531\u591a\u53f0\u673a\u5668\u7ec4\u6210\u7684\u96c6\u7fa4\u4e0a\u8fdb\u884c\u5206\u5e03\u5f0f\u5904\u7406\u7684\uff0c\u5728\u5185\u90e8\u88ab\u5212\u5206\u4e3a\u591a\u4e2a\u5757\uff0c\u79f0\u4e3apartition\u3002\u5728Spark\u4e2d\uff0cpartition\u6210\u4e3a\u5206\u5e03\u5f0f\u5904\u7406\u7684\u5355\u4f4d\u3002\u901a\u8fc7\u5728\u6bcf\u4e2apartition\u4e0a\u5728\u591a\u53f0\u673a\u5668\u4e0a\u8fdb\u884c\u5904\u7406\uff0c\u53ef\u4ee5\u5904\u7406\u65e0\u6cd5\u5728\u5355\u4e2a\u673a\u5668\u4e0a\u5904\u7406\u7684\u6570\u636e\u3002<\/p>\n<p>\u5c06\u88ab\u5206\u5272\u7684\u6587\u4ef6\u4f5c\u4e3a\u4e00\u4e2aRDD\u6765\u5904\u7406\uff0c\u53ea\u9700\u7f16\u5199input.filter(s -&gt; !s.contains(&#8220;Triangle&#8221;))\uff0c\u5373\u53ef\u5b9e\u73b0\u65e0\u9700\u5206\u5e03\u5f0f\u610f\u8bc6\u7684\u7f16\u7a0b\u3002<\/p>\n<h2>flatMap\u51fd\u6570\u7684\u793a\u4f8b<\/h2>\n<p>\u6b64\u51fd\u6570\u662f\u4ece\u4e00\u4e2a\u5143\u7d20\u751f\u6210\u591a\u4e2a\u5143\u7d20\u7684\u4e00\u5bf9\u591a\u5173\u7cfb\u8f6c\u6362\uff0c\u800c\u4e0d\u662f\u50cf filter \u548c map \u51fd\u6570\u4e00\u6837\u662f\u4e00\u5bf9\u4e00\u7684\u5173\u7cfb\u3002<\/p>\n<div>\n<div class=\"post-table\">\u95a2\u6570\u8aac\u660eflatMap()\u5f15\u6570\u306b\u95a2\u6570\u3092\u4e00\u3064\u53d6\u308a\u3001\u305d\u306e\u95a2\u6570\u3092RDD\u5185\u306e\u5404\u8981\u7d20\u306b\u9069\u5fdc\u3057\u3066\u547c\u3070\u308c\u308b\u304c\u3001\u3053\u306e\u95a2\u6570\u306f\u305d\u306e\u7d50\u679c\u3092\u8fd4\u3059Iterator\u3092\u8fd4\u3057\u307e\u3059\u3002\u305d\u308c\u3089\u306eIterator\u5168\u3066\u304b\u3089\u8fd4\u3055\u308c\u305f\u8981\u7d20\u3092\u5024\u3068\u3059\u308bRDD\u3092\u6700\u512a\u7684\u306b\u8fd4\u3057\u307e\u3059<\/div>\n<\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/20-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 20.09.53.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/21-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 20.09.55.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/22-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 20.09.57.png\" \/><\/div>\n<p>\u6e90\u4ee3\u7801\u5728\u8fd9\u91cc\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaRDD<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaSparkContext<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.function.FlatMapFunction<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">java.util.Arrays<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"cm\">\/**\r\n * Created by hirokinaganuma on 2016\/10\/11.\r\n *\/<\/span>\r\n<span class=\"kd\">public<\/span> <span class=\"kd\">class<\/span> <span class=\"nc\">Sample03<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"kd\">public<\/span> <span class=\"kd\">static<\/span> <span class=\"kt\">void<\/span> <span class=\"nf\">main<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span><span class=\"o\">[]<\/span> <span class=\"n\">args<\/span><span class=\"o\">)<\/span> <span class=\"kd\">throws<\/span> <span class=\"nc\">Exception<\/span> <span class=\"o\">{<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">master<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"o\">(<\/span><span class=\"n\">args<\/span><span class=\"o\">.<\/span><span class=\"na\">length<\/span> <span class=\"o\">&gt;<\/span> <span class=\"mi\">0<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"n\">args<\/span><span class=\"o\">[<\/span><span class=\"mi\">0<\/span><span class=\"o\">];<\/span>\r\n        <span class=\"o\">}<\/span> <span class=\"k\">else<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"local\"<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        <span class=\"nc\">JavaSparkContext<\/span> <span class=\"n\">sc<\/span> <span class=\"o\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">JavaSparkContext<\/span><span class=\"o\">(<\/span><span class=\"n\">master<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"basicavg\"<\/span><span class=\"o\">,<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"SPARK_HOME\"<\/span><span class=\"o\">),<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"JARS\"<\/span><span class=\"o\">));<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">input<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/input\/flatmap\/*.txt\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">result<\/span> <span class=\"o\">=<\/span> <span class=\"n\">input<\/span><span class=\"o\">.<\/span><span class=\"na\">flatMap<\/span><span class=\"o\">(<\/span>\r\n                <span class=\"k\">new<\/span> <span class=\"nc\">FlatMapFunction<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">String<\/span><span class=\"o\">&gt;()<\/span> <span class=\"o\">{<\/span>\r\n                    <span class=\"kd\">public<\/span> <span class=\"nc\">Iterable<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"nf\">call<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span> <span class=\"n\">x<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n                        <span class=\"k\">return<\/span> <span class=\"nc\">Arrays<\/span><span class=\"o\">.<\/span><span class=\"na\">asList<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span><span class=\"o\">.<\/span><span class=\"na\">split<\/span><span class=\"o\">(<\/span><span class=\"s\">\" \"<\/span><span class=\"o\">));<\/span>\r\n                    <span class=\"o\">}<\/span>\r\n                <span class=\"o\">}<\/span>\r\n        <span class=\"o\">);<\/span>\r\n        <span class=\"n\">result<\/span><span class=\"o\">.<\/span><span class=\"na\">saveAsTextFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/output\/output03\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">stop<\/span><span class=\"o\">();<\/span>\r\n    <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>I am from Fukuoka\r\nHello Apache Spark\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>Tokyo Institute of Technology\r\n<\/code><\/pre>\n<h2>reduceByKey\u51fd\u6570\u7684\u793a\u4f8b<\/h2>\n<p>reduceByKey\u662f\u4e00\u500b\u9700\u8981\u4ee5\u524d\u7684RDD\u4e2d\u7684\u5143\u7d20\u8207\u5176\u4ed6\u5206\u7247\u4e2d\u7684\u5143\u7d20\u9032\u884c\u6574\u5408\u8655\u7406\u7684\u64cd\u4f5c\u3002\u9019\u500b\u8f49\u63db\u91dd\u5c0d\u7684\u662f\u4e00\u500b\u7531\u9375\u503c\u5c0d\u5143\u7d20\u7d44\u6210\u7684RDD\uff0c\u5b83\u5c07\u5177\u6709\u76f8\u540c\u9375\u7684\u5143\u7d20\u9032\u884c\u5408\u4f75\u8655\u7406\u3002Spark\u6309\u7167\u6bcf\u500b\u5206\u7247\u7368\u7acb\u9032\u884c\u5206\u6563\u8655\u7406\uff0c\u6240\u4ee5\u5177\u6709\u76f8\u540c\u9375\u7684\u5143\u7d20\u5fc5\u9808\u5b8c\u5168\u5305\u542b\u5728\u540c\u4e00\u500b\u5206\u7247\u4e2d\u3002\u56e0\u6b64\uff0c\u5728reduce\u64cd\u4f5c\u4e4b\u524d\u9700\u8981\u9032\u884c\u91cd\u5206\u4f48(shuffle)\u3002\u91cd\u5206\u4f48\u64cd\u4f5c\u6839\u64da\u9375\u5c07\u8fd4\u9084\u524d\u7684RDD\u5143\u7d20\u91cd\u65b0\u5206\u914d\u5230\u8f49\u63db\u5f8c\u7684RDD\u5206\u7247\u4e2d\u3002\u56e0\u6b64\uff0c\u91cd\u5206\u4f48\u53ef\u4ee5\u4fdd\u8b49\u5177\u6709\u76f8\u540c\u9375\u7684\u5143\u7d20\u88ab\u5305\u542b\u5728\u540c\u4e00\u500b\u5206\u7247\u4e2d\u3002<\/p>\n<p>\u5716\u4e2d\u6c92\u6709\u8868\u9054\u51fa\u4f86\uff0c\u4f46\u662f\u5728\u9032\u884c\u91cd\u5206\u4f48\u4e4b\u524d\uff0c\u5728\u6bcf\u500b\u5206\u7247\u5167\u90e8\u57f7\u884c\u4e86reduce\u64cd\u4f5c\uff0c\u4ee5\u6e1b\u5c11\u901a\u4fe1\u6210\u672c\u3002<\/p>\n<div>\n<div class=\"post-table\">\u95a2\u6570\u8aac\u660ereduceByKey()\u5f15\u6570\u306b\u95a2\u6570\u3092\u4e00\u3064\u53d6\u308a\u3001\u305d\u306e\u95a2\u6570\u306f\u540c\u3058\u30ad\u30fc\u306e\u5024\u3092\u7d50\u5408\u3059\u308b\u969b\u306ereduce\u51e6\u7406\u3067\u3042\u308b<\/div>\n<\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/30-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 21.32.57.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/31-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 21.33.05.png\" \/><\/div>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/32-0.png\" alt=\"\u30b9\u30af\u30ea\u30fc\u30f3\u30b7\u30e7\u30c3\u30c8 2016-10-11 21.33.07.png\" \/><\/div>\n<p>\u6e90\u4ee3\u7801\u5728\u8fd9\u91cc\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaPairRDD<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaRDD<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.JavaSparkContext<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.function.FlatMapFunction<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.function.Function2<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">org.apache.spark.api.java.function.PairFunction<\/span><span class=\"o\">;<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">scala.Tuple2<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">java.util.Arrays<\/span><span class=\"o\">;<\/span>\r\n\r\n<span class=\"cm\">\/**\r\n * Created by hirokinaganuma on 2016\/10\/11.\r\n *\/<\/span>\r\n<span class=\"kd\">public<\/span> <span class=\"kd\">class<\/span> <span class=\"nc\">Sample04<\/span> <span class=\"o\">{<\/span>\r\n    <span class=\"kd\">public<\/span> <span class=\"kd\">static<\/span> <span class=\"kt\">void<\/span> <span class=\"nf\">main<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span><span class=\"o\">[]<\/span> <span class=\"n\">args<\/span><span class=\"o\">)<\/span> <span class=\"kd\">throws<\/span> <span class=\"nc\">Exception<\/span> <span class=\"o\">{<\/span>\r\n        <span class=\"nc\">String<\/span> <span class=\"n\">master<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"k\">if<\/span> <span class=\"o\">(<\/span><span class=\"n\">args<\/span><span class=\"o\">.<\/span><span class=\"na\">length<\/span> <span class=\"o\">&gt;<\/span> <span class=\"mi\">0<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"n\">args<\/span><span class=\"o\">[<\/span><span class=\"mi\">0<\/span><span class=\"o\">];<\/span>\r\n        <span class=\"o\">}<\/span> <span class=\"k\">else<\/span> <span class=\"o\">{<\/span>\r\n            <span class=\"n\">master<\/span> <span class=\"o\">=<\/span> <span class=\"s\">\"local\"<\/span><span class=\"o\">;<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        <span class=\"nc\">JavaSparkContext<\/span> <span class=\"n\">sc<\/span> <span class=\"o\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nc\">JavaSparkContext<\/span><span class=\"o\">(<\/span><span class=\"n\">master<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"basicavg\"<\/span><span class=\"o\">,<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"SPARK_HOME\"<\/span><span class=\"o\">),<\/span> <span class=\"nc\">System<\/span><span class=\"o\">.<\/span><span class=\"na\">getenv<\/span><span class=\"o\">(<\/span><span class=\"s\">\"JARS\"<\/span><span class=\"o\">));<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">input<\/span> <span class=\"o\">=<\/span> <span class=\"n\">sc<\/span><span class=\"o\">.<\/span><span class=\"na\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/input\/reducebykey\/*.txt\"<\/span><span class=\"o\">);<\/span>\r\n        <span class=\"nc\">JavaRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">words<\/span> <span class=\"o\">=<\/span> <span class=\"n\">input<\/span><span class=\"o\">.<\/span><span class=\"na\">flatMap<\/span><span class=\"o\">(<\/span>\r\n                <span class=\"k\">new<\/span> <span class=\"nc\">FlatMapFunction<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">String<\/span><span class=\"o\">&gt;()<\/span> <span class=\"o\">{<\/span>\r\n                    <span class=\"kd\">public<\/span> <span class=\"nc\">Iterable<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">&gt;<\/span> <span class=\"nf\">call<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span> <span class=\"n\">x<\/span><span class=\"o\">)<\/span> <span class=\"o\">{<\/span>\r\n                        <span class=\"k\">return<\/span> <span class=\"nc\">Arrays<\/span><span class=\"o\">.<\/span><span class=\"na\">asList<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span><span class=\"o\">.<\/span><span class=\"na\">split<\/span><span class=\"o\">(<\/span><span class=\"s\">\" \"<\/span><span class=\"o\">));<\/span>\r\n                    <span class=\"o\">}<\/span>\r\n                <span class=\"o\">}<\/span>\r\n        <span class=\"o\">);<\/span>\r\n\r\n        <span class=\"nc\">JavaPairRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">pairrdd<\/span> <span class=\"o\">=<\/span> <span class=\"n\">words<\/span><span class=\"o\">.<\/span><span class=\"na\">mapToPair<\/span><span class=\"o\">(<\/span>\r\n                <span class=\"k\">new<\/span> <span class=\"nc\">PairFunction<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">&gt;(){<\/span>\r\n                    <span class=\"kd\">public<\/span> <span class=\"nc\">Tuple2<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">&gt;<\/span> <span class=\"nf\">call<\/span><span class=\"o\">(<\/span><span class=\"nc\">String<\/span> <span class=\"n\">x<\/span><span class=\"o\">){<\/span>\r\n                        <span class=\"k\">return<\/span> <span class=\"k\">new<\/span> <span class=\"nf\">Tuple2<\/span><span class=\"o\">(<\/span><span class=\"n\">x<\/span><span class=\"o\">,<\/span> <span class=\"mi\">1<\/span><span class=\"o\">);<\/span>\r\n                    <span class=\"o\">}<\/span>\r\n                <span class=\"o\">}<\/span>\r\n        <span class=\"o\">);<\/span>\r\n\r\n        <span class=\"nc\">JavaPairRDD<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">String<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">&gt;<\/span> <span class=\"n\">output<\/span> <span class=\"o\">=<\/span> <span class=\"n\">pairrdd<\/span><span class=\"o\">.<\/span><span class=\"na\">reduceByKey<\/span><span class=\"o\">(<\/span><span class=\"k\">new<\/span> <span class=\"nc\">Function2<\/span><span class=\"o\">&lt;<\/span><span class=\"nc\">Integer<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span><span class=\"o\">&gt;(){<\/span>\r\n            <span class=\"kd\">public<\/span> <span class=\"nc\">Integer<\/span> <span class=\"nf\">call<\/span><span class=\"o\">(<\/span><span class=\"nc\">Integer<\/span> <span class=\"n\">x<\/span><span class=\"o\">,<\/span> <span class=\"nc\">Integer<\/span> <span class=\"n\">y<\/span><span class=\"o\">){<\/span>\r\n                <span class=\"k\">return<\/span> <span class=\"n\">x<\/span><span class=\"o\">+<\/span><span class=\"n\">y<\/span><span class=\"o\">;<\/span>\r\n            <span class=\"o\">}<\/span>\r\n        <span class=\"o\">});<\/span>\r\n\r\n        <span class=\"n\">output<\/span><span class=\"o\">.<\/span><span class=\"na\">saveAsTextFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"bin\/output\/output04\"<\/span><span class=\"o\">);<\/span>\r\n    <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>fish\r\ncat\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>cat\r\nfish\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>fish\r\n<\/code><\/pre>\n<pre class=\"post-pre\"><code>cat\r\ncat\r\ndog\r\n<\/code><\/pre>\n<h1>Apache Spark\u7684partition\u662f\u4ec0\u4e48\u610f\u601d\uff1f<\/h1>\n<p>RDD\u662f\u4e00\u79cd\u5206\u5e03\u5f0f\u96c6\u5408\uff0c\u4ee5\u5927\u91cf\u6570\u636e\u4f5c\u4e3a\u5143\u7d20\u3002RDD\u662f\u5728\u7531\u591a\u53f0\u673a\u5668\u7ec4\u6210\u7684\u96c6\u7fa4\u4e0a\u8fdb\u884c\u5206\u5e03\u5f0f\u5904\u7406\u8bbe\u8ba1\u7684\uff0c\u5185\u90e8\u88ab\u5206\u5272\u6210\u4e86\u79f0\u4e3apartition\u7684\u5757\u3002\u5728Spark\u4e2d\uff0cpartition\u6210\u4e3a\u4e86\u5206\u5e03\u5f0f\u5904\u7406\u7684\u5355\u4f4d\u3002\u901a\u8fc7\u5728\u6bcf\u4e2apartition\u4e0a\u591a\u53f0\u673a\u5668\u4e0a\u5904\u7406RDD\uff0c\u53ef\u4ee5\u5904\u7406\u65e0\u6cd5\u5728\u5355\u53f0\u673a\u5668\u4e0a\u5904\u7406\u7684\u6570\u636e\u3002<\/p>\n<h2>\u58eb\u6c14<\/h2>\n<p>\u5728\u5206\u6563\u8ba1\u7b97\u4e2d\uff0c\u901a\u4fe1\u6210\u672c\u975e\u5e38\u9ad8\uff0c\u6700\u5c0f\u5316\u7f51\u7edc\u6d41\u91cf\u53ef\u4ee5\u5927\u5e45\u63d0\u5347\u6027\u80fd\u3002<br \/>\n\u4e3a\u4e86\u51cf\u5c11\u901a\u4fe1\u91cf\uff0c\u9700\u8981\u901a\u8fc7\u63a7\u5236RDD\u7684\u5206\u533a\u6765\u4f18\u5316Spark\u7a0b\u5e8f\u3002<\/p>\n<p>\u4f8b\u5982\uff0cSpark\u53ef\u4ee5\u901a\u8fc7\u7f16\u7a0b\u6765\u786e\u4fdd\u952e\u7684\u96c6\u5408\u51fa\u73b0\u5728\u96c6\u4e2d\u7684\u8282\u70b9\u4e0a\uff08\u901a\u8fc7reduceByKey()\u8fdb\u884c\u4ecb\u7ecd\uff09\u3002\u7279\u522b\u662f\u5728\u6570\u636e\u96c6\u591a\u6b21\u91cd\u7528\u952e\u64cd\u4f5c\uff08\u5982\u8fde\u63a5\uff09\u7684\u60c5\u51b5\u4e0b\uff0c\u5206\u533a\u662f\u5f88\u6709\u7528\u7684\u3002\u8fd9\u662f\u56e0\u4e3aSpark\u7684\u8bb8\u591a\u64cd\u4f5c\u90fd\u4f1a\u901a\u8fc7\u7f51\u7edc\u8fdb\u884c\u57fa\u4e8e\u952e\u7684\u6d17\u724c\u3002\u5b83\u4eec\u90fd\u53ef\u4ee5\u53d7\u76ca\u4e8e\u5206\u533a\u3002<\/p>\n<h2>\u6570\u636e\u7684\u5206\u533a<\/h2>\n<p>\u5728Java\u6216Scala\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528partitioner\u5c5e\u6027\u6765\u6307\u5b9aRDD\u7684\u5206\u533a\u65b9\u6cd5\u3002\u5728spark.Partitioner\u5bf9\u8c61\u7684\u503c\u4e2d\uff0c\u60a8\u5c06\u8bbe\u7f6e\u4e00\u4e2a\u6307\u793aRDD\u4e2d\u6bcf\u4e2a\u952e\u7684\u76ee\u6807\u5206\u533a\u7684\u5185\u5bb9\u3002<\/p>\n<p>\u5f53\u5728\u5206\u533a\u5316\u7684RDD\u4e0a\u6267\u884c\u50cfreduceByKey()\u8fd9\u6837\u7684\u64cd\u4f5c\u65f6\uff0c\u6bcf\u4e2a\u952e\u7684\u6240\u6709\u503c\u90fd\u5728\u5355\u4e2a\u673a\u5668\u4e0a\u672c\u5730\u8ba1\u7b97\uff0c\u5e76\u4e14\u53ea\u6709\u6700\u7ec8\u7684reduce()\u503c\u4f1a\u4ece\u6bcf\u4e2a\u5de5\u4f5c\u8282\u70b9\u8fd4\u56de\u4e3b\u8282\u70b9\uff08\u5982\u524d\u9762\u8bb2\u8fc7\u7684\uff09\u3002<\/p>\n<p>\u66f4\u8be6\u7ec6\u5730\u8bf4\uff0c\u5728shuffle\u8fc7\u7a0b\u4e2d\uff0c\u5c06\u5177\u6709\u76f8\u540c\u952e\u7684\u5143\u7d20\u5206\u914d\u5230\u540c\u4e00\u4e2apartition\u662fpartitioner\u7684\u5de5\u4f5c\u3002partitioner\u6839\u636e\u8f6c\u6362\u540e\u7684RDD\u7684partition\u6570\u548c\u5206\u914d\u5bf9\u8c61\u952e\u7684\u5185\u5bb9\u6765\u786e\u5b9a\u5206\u914d\u5143\u7d20\u7684\u76ee\u6807partition\u3002\u5728Spark\u4e2d\uff0c\u9ed8\u8ba4\u60c5\u51b5\u4e0b\u4f7f\u7528\u952e\u7684\u54c8\u5e0c\u503c\u9664\u4ee5\u8f6c\u6362\u540e\u7684RDD\u7684partition\u6570\u6240\u5f97\u7684\u4f59\u6570\u6765\u786e\u5b9a\u5206\u914d\u7684\u76ee\u6807partition\u3002<\/p>\n<p>\u53e6\u5916\uff0c\u5982\u679c\u8981\u5bf9\u4e24\u4e2aRDD\u8fdb\u884c\u64cd\u4f5c\uff0c\u5e76\u4e14\u4e8b\u5148\u8fdb\u884c\u4e86\u5206\u533a\u5904\u7406\uff0c\u90a3\u4e48\u81f3\u5c11\u4e24\u4e2aRDD\u4e2d\u7684\u4e00\u4e2a\u5c06\u4e0d\u4f1a\u8fdb\u884c\u6d17\u724c\u3002<br \/>\n\u6b64\u5916\uff0cSpark\u4f1a\u4e86\u89e3\u6bcf\u4e2a\u64cd\u4f5c\u5bf9\u5206\u533a\u7684\u5185\u90e8\u5f71\u54cd\uff0c\u56e0\u6b64\u4f1a\u81ea\u52a8\u4e3a\u7531\u6570\u636e\u5206\u533a\u64cd\u4f5c\u751f\u6210\u7684RDD\u8bbe\u7f6e\u5206\u533a\u5668\u3002<\/p>\n<h2>\u6301\u7eed\u5b58\u5728\u4f18\u5316<\/h2>\n<p>\u4f46\u662f\uff0c\u5728\u5bf9RDD\u8fdb\u884c\u5206\u533a\u5e76\u5c06\u751f\u6210\u7684RDD\u7528\u4f5c\u8f6c\u6362\u76ee\u6807\u65f6\uff0c\u5e94\u8be5\u4f7f\u7528persist()\u8fdb\u884c\u6301\u4e45\u5316\u3002\u539f\u56e0\u662f\uff0c\u63a5\u4e0b\u6765\u5bf9RDD\u7684\u64cd\u4f5c\u5c06\u91cd\u65b0\u8bc4\u4f30\u7531\u5206\u533a\u751f\u6210\u7684\u6574\u4e2aRDD\u7cfb\u5217\uff0c\u56e0\u6b64\u5bf9\u5206\u533a\u4e4b\u524d\u7684RDD\u8fdb\u884c\u591a\u6b21\u54c8\u5e0c\u5206\u533a\u662f\u6ca1\u6709\u610f\u4e49\u7684\u3002<\/p>\n<h1>\u8bf7\u53c2\u8003<\/h1>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">http:\/\/www.ne.jp\/asahi\/hishidama\/home\/tech\/scala\/spark\/partition.html<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">https:\/\/jaceklaskowski.gitbooks.io\/mastering-apache-spark\/content\/<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">http:\/\/qiita.com\/Hiroki11x\/items\/4f5129094da4c91955bc<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u9996\u5148 \u9019\u7bc7\u6587\u7ae0\u8a66\u5716\u901a\u904e\u8209\u4f8b\u4f86\u7e3d\u7d50Apache Spark\u7684\u5206\u5340\u6982\u5ff5\u3002 \u6709\u95dcApache Spark\u7684\u6982\u8ff0\uff0c\u8acb\u53c3 [&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-36437","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>Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 - 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\/apache-spark-\u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 -\" \/>\n<meta property=\"og:description\" content=\"\u9996\u5148 \u9019\u7bc7\u6587\u7ae0\u8a66\u5716\u901a\u904e\u8209\u4f8b\u4f86\u7e3d\u7d50Apache Spark\u7684\u5206\u5340\u6982\u5ff5\u3002 \u6709\u95dcApache Spark\u7684\u6982\u8ff0\uff0c\u8acb\u53c3 [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-\u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-27T13:37:40+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-30T13:20:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/7-0.png\" \/>\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=\"3 \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\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/\",\"name\":\"Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2024-02-27T13:37:40+00:00\",\"dateModified\":\"2024-04-30T13:20:12+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Apache Spark &#8211; \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 &#8211;\"}]},{\"@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\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 - 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\/apache-spark-\u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9\/","og_locale":"zh_CN","og_type":"article","og_title":"Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 -","og_description":"\u9996\u5148 \u9019\u7bc7\u6587\u7ae0\u8a66\u5716\u901a\u904e\u8209\u4f8b\u4f86\u7e3d\u7d50Apache Spark\u7684\u5206\u5340\u6982\u5ff5\u3002 \u6709\u95dcApache Spark\u7684\u6982\u8ff0\uff0c\u8acb\u53c3 [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-\u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2024-02-27T13:37:40+00:00","article_modified_time":"2024-04-30T13:20:12+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d28bd37434c4406c414d3\/7-0.png"}],"author":"\u6587, \u7fd4","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6587, \u7fd4","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/","name":"Apache Spark - \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2024-02-27T13:37:40+00:00","dateModified":"2024-04-30T13:20:12+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/64d5cc7727fffbff2f9a2a8da1de3e5c"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"Apache Spark &#8211; \u5173\u4e8e\u5206\u533a\u7684\u5185\u5bb9 &#8211;"}]},{"@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\/apache-spark-%e5%85%b3%e4%ba%8e%e5%88%86%e5%8c%ba%e7%9a%84%e5%86%85%e5%ae%b9\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36437","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=36437"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36437\/revisions"}],"predecessor-version":[{"id":94362,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36437\/revisions\/94362"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=36437"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=36437"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=36437"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}