{"id":47050,"date":"2023-03-22T16:39:46","date_gmt":"2023-09-19T01:18:44","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/"},"modified":"2024-04-29T20:04:47","modified_gmt":"2024-04-29T12:04:47","slug":"%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/","title":{"rendered":"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f"},"content":{"rendered":"<p>\u9019\u662f\u95dc\u65bc\u9019\u500b\u7b46\u8a18\u672c\u756b\u5eca\u7684\u50b3\u611f\u5668\u6578\u64da\u6d41\u61c9\u7528\u7a0b\u5e8f\u7684\u64cd\u4f5c\u6b65\u9a5f\u3002<\/p>\n<p>&nbsp;<\/p>\n<p>\u7b14\u8bb0\u672c\u7684\u7ffb\u8bd1\u7248\u5728\u8fd9\u91cc\u3002<\/p>\n<p>&nbsp;<\/p>\n<h1>\u521b\u5efa\u5047\u611f\u6d4b\u6570\u636e<\/h1>\n<p>\u751f\u6210\u7531100\u4e2a\u6587\u4ef6\u7ec4\u6210\u7684100\u4e2a\u8bb0\u5f55\u7684\u6570\u636e\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"o\">%<\/span><span class=\"n\">scala<\/span>\r\n\r\n<span class=\"c1\">\/\/ --- \u30c7\u30fc\u30bf\u3092\u751f\u6210\u3059\u308b\u30d1\u30b9\u3092\u8a2d\u5b9a\u30fb\u9069\u5b9c\u5909\u66f4\u3057\u3066\u304f\u3060\u3055\u3044 ---<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">path<\/span> <span class=\"k\">=<\/span> <span class=\"s\">\"\/tmp\/takaakiyayoidatabrickscom\/Streaming\/sdevices\/\"<\/span>\r\n<span class=\"nv\">dbutils<\/span><span class=\"o\">.<\/span><span class=\"py\">fs<\/span><span class=\"o\">.<\/span><span class=\"py\">mkdirs<\/span><span class=\"o\">(<\/span><span class=\"n\">path<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">numFiles<\/span> <span class=\"k\">=<\/span> <span class=\"mi\">100<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">numDataPerFile<\/span> <span class=\"k\">=<\/span> <span class=\"mi\">100<\/span>\r\n\r\n<span class=\"k\">import<\/span> <span class=\"nn\">scala.util.Random<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">deviceTypes<\/span> <span class=\"k\">=<\/span> <span class=\"nc\">Seq<\/span><span class=\"o\">(<\/span><span class=\"s\">\"SensorTypeA\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"SensorTypeB\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"SensorTypeC\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"SensorTypeD\"<\/span><span class=\"o\">)<\/span>\r\n<span class=\"k\">val<\/span> <span class=\"nv\">startTime<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">System<\/span><span class=\"o\">.<\/span><span class=\"py\">currentTimeMillis<\/span>\r\n<span class=\"nv\">dbutils<\/span><span class=\"o\">.<\/span><span class=\"py\">fs<\/span><span class=\"o\">.<\/span><span class=\"py\">rm<\/span><span class=\"o\">(<\/span><span class=\"n\">path<\/span><span class=\"o\">,<\/span> <span class=\"kc\">true<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"o\">(<\/span><span class=\"mi\">1<\/span> <span class=\"n\">to<\/span> <span class=\"n\">numFiles<\/span><span class=\"o\">).<\/span><span class=\"py\">par<\/span><span class=\"o\">.<\/span><span class=\"py\">foreach<\/span> <span class=\"o\">{<\/span> <span class=\"n\">fileId<\/span> <span class=\"k\">=&gt;<\/span>\r\n  <span class=\"k\">val<\/span> <span class=\"nv\">file<\/span> <span class=\"k\">=<\/span> <span class=\"n\">s<\/span><span class=\"s\">\"$path\/file-$fileId.json\"<\/span>\r\n  <span class=\"k\">val<\/span> <span class=\"nv\">data<\/span> <span class=\"k\">=<\/span> <span class=\"o\">(<\/span><span class=\"mi\">1<\/span> <span class=\"n\">to<\/span> <span class=\"n\">numDataPerFile<\/span><span class=\"o\">).<\/span><span class=\"py\">map<\/span> <span class=\"o\">{<\/span> <span class=\"n\">x<\/span> <span class=\"k\">=&gt;<\/span> \r\n    <span class=\"k\">val<\/span> <span class=\"nv\">timestamp<\/span> <span class=\"k\">=<\/span> <span class=\"k\">new<\/span> <span class=\"nv\">java<\/span><span class=\"o\">.<\/span><span class=\"py\">sql<\/span><span class=\"o\">.<\/span><span class=\"py\">Timestamp<\/span><span class=\"o\">(<\/span><span class=\"n\">startTime<\/span> <span class=\"o\">+<\/span> <span class=\"o\">(<\/span><span class=\"n\">fileId<\/span> <span class=\"o\">*<\/span> <span class=\"mi\">60000<\/span><span class=\"o\">)<\/span> <span class=\"o\">+<\/span> <span class=\"o\">(<\/span><span class=\"nv\">Random<\/span><span class=\"o\">.<\/span><span class=\"py\">nextInt<\/span><span class=\"o\">()<\/span> <span class=\"o\">%<\/span> <span class=\"mi\">10000<\/span><span class=\"o\">))<\/span>\r\n    <span class=\"k\">val<\/span> <span class=\"nv\">deviceId<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">Random<\/span><span class=\"o\">.<\/span><span class=\"py\">nextInt<\/span><span class=\"o\">(<\/span><span class=\"mi\">100<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"k\">val<\/span> <span class=\"nv\">deviceType<\/span> <span class=\"k\">=<\/span> <span class=\"nf\">deviceTypes<\/span><span class=\"o\">(<\/span><span class=\"nv\">Random<\/span><span class=\"o\">.<\/span><span class=\"py\">nextInt<\/span><span class=\"o\">(<\/span><span class=\"nv\">deviceTypes<\/span><span class=\"o\">.<\/span><span class=\"py\">size<\/span><span class=\"o\">))<\/span>\r\n    <span class=\"k\">val<\/span> <span class=\"nv\">signalStrength<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">math<\/span><span class=\"o\">.<\/span><span class=\"py\">abs<\/span><span class=\"o\">(<\/span><span class=\"nv\">Random<\/span><span class=\"o\">.<\/span><span class=\"py\">nextDouble<\/span> <span class=\"o\">%<\/span> <span class=\"mi\">100<\/span><span class=\"o\">)<\/span>\r\n    <span class=\"n\">s<\/span><span class=\"s\">\"\"\"{\"timestamp\":\"$timestamp\",\"deviceId\":$deviceId,\"deviceType\":\"$deviceType\",\"signalStrength\":$signalStrength}\"\"\"<\/span>\r\n  <span class=\"o\">}.<\/span><span class=\"py\">mkString<\/span><span class=\"o\">(<\/span><span class=\"s\">\"\\n\"<\/span><span class=\"o\">)<\/span>\r\n  <span class=\"nv\">dbutils<\/span><span class=\"o\">.<\/span><span class=\"py\">fs<\/span><span class=\"o\">.<\/span><span class=\"py\">put<\/span><span class=\"o\">(<\/span><span class=\"n\">file<\/span><span class=\"o\">,<\/span> <span class=\"n\">data<\/span><span class=\"o\">)<\/span>\r\n<span class=\"o\">}<\/span>\r\n<span class=\"nv\">dbutils<\/span><span class=\"o\">.<\/span><span class=\"py\">fs<\/span><span class=\"o\">.<\/span><span class=\"py\">head<\/span><span class=\"o\">(<\/span><span class=\"nv\">dbutils<\/span><span class=\"o\">.<\/span><span class=\"py\">fs<\/span><span class=\"o\">.<\/span><span class=\"py\">ls<\/span><span class=\"o\">(<\/span><span class=\"n\">s<\/span><span class=\"s\">\"$path\/file-1.json\"<\/span><span class=\"o\">).<\/span><span class=\"py\">head<\/span><span class=\"o\">.<\/span><span class=\"py\">path<\/span><span class=\"o\">)<\/span>\r\n<\/code><\/pre>\n<h1>\u6d41\u5a92\u4f53\u4f20\u611f\u5668\u6570\u636e\u5904\u7406<\/h1>\n<p>\u5728\u6784\u5efa\u7aef\u5230\u7aef\u7684\u8fde\u7eed\u5e94\u7528\u7a0b\u5e8f\u7684\u76ee\u6807\u4e2d\uff0c\u7ed3\u6784\u5316\u6d41\u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u529f\u80fd\u3002\u5728\u9ad8\u7ea7\u522b\u4e0a\uff0c\u5b83\u63d0\u4f9b\u4ee5\u4e0b\u529f\u80fd\uff1a<\/p>\n<ol>\n<li style=\"list-style-type: none;\">\n<ol>\u6240\u6709\u7684\u6570\u636e\u8bb0\u5f55\u90fd\u88ab\u4fdd\u5b58\u5728\u524d\u7f00(\u5206\u533a)\u4e2d\uff0c\u5e76\u4e14\u6309\u987a\u5e8f\u8fdb\u884c\u5904\u7406\u548c\u8ba1\u6570\uff0c\u6240\u4ee5\u8f93\u51fa\u8868\u59cb\u7ec8\u4fdd\u6301\u4e00\u81f4\u6027\u3002<\/ol>\n<\/li>\n<\/ol>\n<p>\u5bb9\u9519\u6027\u5305\u62ec\u4e0e\u8f93\u51fa\u540c\u6b65\u7684\u4ea4\u4e92\uff0c\u5e76\u901a\u8fc7\u7ed3\u6784\u5316\u6d41\u5904\u7406\u6574\u4f53\u3002<\/p>\n<p>\u5177\u6709\u5904\u7406\u5ef6\u8fdf\u6570\u636e\u548c\u4e0d\u6309\u987a\u5e8f\u7684\u6570\u636e\u80fd\u529b\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/10-0.png\" alt=\"\" \/><\/div>\n<h2>1- \u9171\u6599<\/h2>\n<p>\u6211\u4eec\u53ef\u4ee5\u5c06\u8f93\u5165\u6570\u636e\u6e90\u89c6\u4e3a\u201c\u8f93\u5165\u8868\u201d\u3002\u6d41\u4e2d\u5230\u8fbe\u7684\u6240\u6709\u6570\u636e\u9879\u90fd\u4f1a\u88ab\u89c6\u4e3a\u8f93\u5165\u8868\u4e2d\u7684\u65b0\u884c\u6dfb\u52a0\u8fdb\u53bb\u3002<\/p>\n<h2>2-\u8fde\u7eed\u5904\u7406\u548c\u67e5\u8be2<\/h2>\n<p>\u63a5\u4e0b\u6765\uff0c\u5f00\u53d1\u8005\u4f1a\u5b9a\u4e49\u4e00\u4e2a\u67e5\u8be2\uff0c\u5c06\u8be5\u6e90\u6216\u8f93\u5165\u8868\u89c6\u4e3a\u9759\u6001\u8868\uff0c\u4ee5\u8ba1\u7b97\u5c06\u88ab\u5199\u5165\u8f93\u51fa sink \u7684\u6700\u7ec8\u7ed3\u679c\u8868\u3002Spark \u4f1a\u81ea\u52a8\u5c06\u8fd9\u79cd\u6279\u5904\u7406\u67e5\u8be2\u8f6c\u6362\u4e3a\u6d41\u5904\u7406\u6267\u884c\u8ba1\u5212\uff0c\u8fd9\u79f0\u4e3a\u589e\u91cf\u66f4\u65b0\uff1aSpark \u4f1a\u786e\u5b9a\u9700\u8981\u7ef4\u62a4\u4ec0\u4e48\u6837\u7684\u72b6\u6001\u6765\u66f4\u65b0\u7ed3\u679c\uff0c\u6bcf\u5f53\u8bb0\u5f55\u5230\u8fbe\u65f6\u3002\u6700\u540e\uff0c\u5f00\u53d1\u8005\u4f1a\u6307\u5b9a\u89e6\u53d1\u5668\u4ee5\u63a7\u5236\u4f55\u65f6\u66f4\u65b0\u7ed3\u679c\u3002\u6bcf\u6b21\u89e6\u53d1\u5668\u88ab\u6267\u884c\u65f6\uff0cSpark \u4f1a\u68c0\u67e5\u65b0\u6570\u636e\uff08\u8f93\u5165\u8868\u7684\u65b0\u884c\uff09\uff0c\u5e76\u4ee5\u589e\u91cf\u65b9\u5f0f\u66f4\u65b0\u7ed3\u679c\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/15-0.png\" alt=\"\" \/><\/div>\n<h2>3-\u6d17\u7897.<\/h2>\n<p>\u8fd9\u4e2a\u6a21\u578b\u7684\u6700\u540e\u90e8\u5206\u662f\u8f93\u51fa\u6a21\u5f0f\u3002\u6bcf\u5f53\u7ed3\u679c\u8868\u66f4\u65b0\u65f6\uff0c\u5f00\u53d1\u4eba\u5458\u5e0c\u671b\u80fd\u591f\u5c06\u66f4\u6539\u5199\u5165\u5916\u90e8\u7cfb\u7edf\uff0c\u5982S3\u3001HDFS\u548c\u6570\u636e\u5e93\u3002\u901a\u5e38\u60c5\u51b5\u4e0b\uff0c\u5e0c\u671b\u4ee5\u589e\u91cf\u65b9\u5f0f\u8fdb\u884c\u8f93\u51fa\u5199\u5165\u3002\u9274\u4e8e\u6b64\uff0c\u7ed3\u6784\u5316\u6d41\u5904\u7406\u63d0\u4f9b\u4e86\u4e09\u79cd\u8f93\u51fa\u6a21\u5f0f\u3002<\/p>\n<p>Append: \u6700\u5f8c\u306e\u30c8\u30ea\u30ac\u30fc\u4ee5\u964d\u306b\u7d50\u679c\u30c6\u30fc\u30d6\u30eb\u306b\u8ffd\u52a0\u3055\u308c\u305f\u65b0\u898f\u884c\u306e\u307f\u304c\u3001\u5916\u90e8\u30b9\u30c8\u30ec\u30fc\u30b8\u306b\u66f8\u304d\u8fbc\u307e\u308c\u307e\u3059\u3002<\/p>\n<p>Complete: \u96c6\u8a08\u306e\u3088\u3046\u306b\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u3055\u308c\u305f\u7d50\u679c\u30c6\u30fc\u30d6\u30eb\u5168\u4f53\u304c\u5916\u90e8\u30b9\u30c8\u30ec\u30fc\u30b8\u306b\u66f8\u304d\u8fbc\u307e\u308c\u307e\u3059\u3002<\/p>\n<p>Update: \u6700\u5f8c\u306e\u30c8\u30ea\u30ac\u30fc\u4ee5\u964d\u306b\u7d50\u679c\u30c6\u30fc\u30d6\u30eb\u66f4\u65b0\u3055\u308c\u305f\u884c\u306e\u307f\u304c\u3001\u5916\u90e8\u30b9\u30c8\u30ec\u30fc\u30b8\u4e0a\u3067\u5909\u66f4\u3055\u308c\u307e\u3059\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/19-0.png\" alt=\"undefined\" \/><\/div>\n<h2>\u4f7f\u7528PySpark\u7684\u7ed3\u6784\u5316\u6d41API\u6765\u521b\u5efa\u8fde\u7eed\u5904\u7406\u5e94\u7528\u7a0b\u5e8f\u7684\u793a\u4f8b\u3002<\/h2>\n<p>\u8bbe\u7f6e\u8f93\u51fa\u3001\u68c0\u67e5\u70b9\u548c\u4e0d\u826f\u8bb0\u5f55\u7684\u6587\u4ef6\u8def\u5f84\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c1\"># Cmd3\u306e4\u884c\u76ee\u306e\u30d1\u30b9\u304b\u3089 \/sdevices\/ \u3092\u9664\u5916\u3057\u3066\u304f\u3060\u3055\u3044\r\n<\/span><span class=\"n\">base_path<\/span> <span class=\"o\">=<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">\/tmp\/takaakiyayoidatabrickscom\/Streaming<\/span><span class=\"sh\">\"<\/span>\r\n\r\n<span class=\"n\">output_path<\/span> <span class=\"o\">=<\/span> <span class=\"sa\">f<\/span><span class=\"sh\">\"<\/span><span class=\"si\">{<\/span><span class=\"n\">base_path<\/span><span class=\"si\">}<\/span><span class=\"s\">\/out\/iot-stream\/<\/span><span class=\"sh\">\"<\/span>\r\n<span class=\"n\">checkpoint_path<\/span> <span class=\"o\">=<\/span> <span class=\"sa\">f<\/span><span class=\"sh\">\"<\/span><span class=\"si\">{<\/span><span class=\"n\">base_path<\/span><span class=\"si\">}<\/span><span class=\"s\">\/out\/iot-stream-checkpoint<\/span><span class=\"sh\">\"<\/span>\r\n<span class=\"c1\">#\r\n# \u30c1\u30a7\u30c3\u30af\u30dd\u30a4\u30f3\u30c8\u30d1\u30b9\u306e\u4f5c\u6210\r\n#\r\n<\/span><span class=\"n\">dbutils<\/span><span class=\"p\">.<\/span><span class=\"n\">fs<\/span><span class=\"p\">.<\/span><span class=\"nf\">rm<\/span><span class=\"p\">(<\/span><span class=\"n\">checkpoint_path<\/span><span class=\"p\">,<\/span><span class=\"bp\">True<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30c1\u30a7\u30c3\u30af\u30dd\u30a4\u30f3\u30c8\u306e\u4e0a\u66f8\u304d\r\n<\/span><span class=\"n\">dbutils<\/span><span class=\"p\">.<\/span><span class=\"n\">fs<\/span><span class=\"p\">.<\/span><span class=\"nf\">mkdirs<\/span><span class=\"p\">(<\/span><span class=\"n\">checkpoint_path<\/span><span class=\"p\">)<\/span>\r\n<span class=\"c1\">#\r\n#\r\n<\/span><span class=\"n\">bad_records_path<\/span> <span class=\"o\">=<\/span> <span class=\"sa\">f<\/span><span class=\"sh\">\"<\/span><span class=\"si\">{<\/span><span class=\"n\">base_path<\/span><span class=\"si\">}<\/span><span class=\"s\">\/badRecordsPath\/streaming-sensor\/<\/span><span class=\"sh\">\"<\/span>\r\n<span class=\"n\">dbutils<\/span><span class=\"p\">.<\/span><span class=\"n\">fs<\/span><span class=\"p\">.<\/span><span class=\"nf\">rm<\/span><span class=\"p\">(<\/span><span class=\"n\">bad_records_path<\/span><span class=\"p\">,<\/span> <span class=\"bp\">True<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u3092\u7a7a\u306b\r\n<\/span><span class=\"n\">dbutils<\/span><span class=\"p\">.<\/span><span class=\"n\">fs<\/span><span class=\"p\">.<\/span><span class=\"nf\">mkdirs<\/span><span class=\"p\">(<\/span><span class=\"n\">bad_records_path<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u4f20\u611f\u5668\u7684\u6570\u636e\u662f\u600e\u6837\u7684\u5462\uff1f<\/h3>\n<pre class=\"post-pre\"><code><span class=\"n\">sensor_path<\/span> <span class=\"o\">=<\/span> <span class=\"sa\">f<\/span><span class=\"sh\">\"<\/span><span class=\"si\">{<\/span><span class=\"n\">base_path<\/span><span class=\"si\">}<\/span><span class=\"s\">\/sdevices\/<\/span><span class=\"sh\">\"<\/span>\r\n<span class=\"n\">sensor_file_name<\/span><span class=\"o\">=<\/span> <span class=\"n\">sensor_path<\/span> <span class=\"o\">+<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">file-1.json<\/span><span class=\"sh\">\"<\/span>\r\n<span class=\"n\">dbutils<\/span><span class=\"p\">.<\/span><span class=\"n\">fs<\/span><span class=\"p\">.<\/span><span class=\"nf\">head<\/span><span class=\"p\">(<\/span><span class=\"n\">sensor_file_name<\/span><span class=\"p\">,<\/span> <span class=\"mi\">233<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/25-0.png\" alt=\"Screen Shot 2022-08-08 at 13.25.56.png\" \/><\/div>\n<h3>\u5b9a\u4e49\u8f93\u5165\u6d41\u548c\u8f93\u51fa\u6d41\u7684\u67b6\u6784<\/h3>\n<p>\u4e3a\u4e86\u6027\u80fd\u8003\u8651\uff0c\u826f\u597d\u7684\u6700\u4f73\u5b9e\u8df5\u662f\u5728Spark\u4e2d\u5b9a\u4e49\u6a21\u5f0f\u800c\u4e0d\u662f\u63a8\u65ad\u6a21\u5f0f\u3002\u5982\u679c\u6ca1\u6709\u6a21\u5f0f\uff0c\u5219Spark\u4f1a\u542f\u52a8\u51e0\u4e2a\u4f5c\u4e1a\uff1a\u4e00\u4e2a\u7528\u4e8e\u8bfb\u53d6\u5934\u6587\u4ef6\u7684\u4f5c\u4e1a\uff0c\u4e00\u4e2a\u7528\u4e8e\u8bfb\u53d6\u90e8\u5206\u5206\u533a\u4ee5\u9a8c\u8bc1\u6570\u636e\u5339\u914d\u6a21\u5f0f\u7684\u4f5c\u4e1a\u3002<\/p>\n<p>\u5982\u679c\u51fa\u73b0\u95ee\u9898\uff0c\u53ef\u4ee5\u7acb\u5373\u751f\u6210\u9519\u8bef\uff0c\u5e76\u4e14\u5f53\u5b58\u5728\u7f3a\u5931\u503c\u6216\u6570\u636e\u7c7b\u578b\u4e0d\u5339\u914d\u65f6\uff0c\u53ef\u4ee5\u8bbe\u7f6e\u4e00\u4e2a\u9009\u9879\u6765\u51b3\u5b9a\u662f\u5426\u63a5\u53d7\uff0c\u6216\u7528NaN\u6216null\u8fdb\u884c\u66ff\u6362\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql.functions<\/span> <span class=\"kn\">import<\/span> <span class=\"o\">*<\/span>\r\n<span class=\"kn\">from<\/span> <span class=\"n\">pyspark.sql.types<\/span> <span class=\"kn\">import<\/span> <span class=\"o\">*<\/span>\r\n\r\n<span class=\"c1\"># \u30aa\u30ea\u30b8\u30ca\u30eb\u306e\u5165\u529b\u30b9\u30ad\u30fc\u30de\r\n<\/span><span class=\"n\">jsonSchema<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span>\r\n  <span class=\"nc\">StructType<\/span><span class=\"p\">()<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">timestamp<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">TimestampType<\/span><span class=\"p\">())<\/span> <span class=\"c1\"># \u30bd\u30fc\u30b9\u306e\u30a4\u30d9\u30f3\u30c8\u6642\u9593\r\n<\/span>  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">deviceId<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">LongType<\/span><span class=\"p\">())<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">deviceType<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">StringType<\/span><span class=\"p\">())<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">signalStrength<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">DoubleType<\/span><span class=\"p\">())<\/span>\r\n<span class=\"p\">)<\/span>\r\n<span class=\"c1\"># \u3044\u304f\u3064\u304b\u306eETL(\u5909\u63db\u304a\u3088\u3073\u30ab\u30e9\u30e0\u306e\u8ffd\u52a0)\u3092\u884c\u3046\u306e\u3067\u30ab\u30e9\u30e0\u3092\u8ffd\u52a0\u3057\u3066\u30b9\u30ad\u30fc\u30de\u3092\u5909\u66f4\u3057\u307e\u3059\u3002\r\n# \u3053\u306e\u5909\u63db\u30c7\u30fc\u30bf\u306f\u3001\u51e6\u7406\u3084\u30ec\u30dd\u30fc\u30c8\u751f\u6210\u306b\u4f7f\u7528\u3067\u304d\u308b\u3088\u3046\u306bSQL\u30c6\u30fc\u30d6\u30eb\u3092\u4f5c\u6210\u5143\u3068\u3057\u3066\u306eParquet\u30d5\u30a1\u30a4\u30eb\u306b\u683c\u7d0d\u3055\u308c\u307e\u3059\u3002\r\n<\/span><span class=\"n\">parquetSchema<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span>\r\n  <span class=\"nc\">StructType<\/span><span class=\"p\">()<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">timestamp<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">TimestampType<\/span><span class=\"p\">())<\/span> <span class=\"c1\"># \u30bd\u30fc\u30b9\u306e\u30a4\u30d9\u30f3\u30c8\u6642\u9593\r\n<\/span>  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">deviceId<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">LongType<\/span><span class=\"p\">())<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">deviceType<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">StringType<\/span><span class=\"p\">())<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">signalStrength<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">DoubleType<\/span><span class=\"p\">())<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">INPUT_FILE_NAME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">StringType<\/span><span class=\"p\">())<\/span> <span class=\"c1\"># \u3053\u306e\u30c7\u30fc\u30bf\u30a2\u30a4\u30c6\u30e0\u3092\u8aad\u307f\u8fbc\u3093\u3060\u30d5\u30a1\u30a4\u30eb\u540d\r\n<\/span>  <span class=\"p\">.<\/span><span class=\"nf\">add<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nc\">TimestampType<\/span><span class=\"p\">()))<\/span> <span class=\"c1\"># \u51e6\u7406\u4e2d\u306e\u30a8\u30b0\u30bc\u30ad\u30e5\u30fc\u30bf\u30fc\u306e\u6642\u9593\r\n<\/span><\/code><\/pre>\n<h3>\u4ece\u5bf9\u8c61\u5b58\u50a8\u6e90\u8bfb\u53d6\u6d41<\/h3>\n<p>\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u6211\u4eec\u53ef\u4ee5\u901a\u8fc7\u4e00\u6b21\u6027\u4ece\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6570\u636e\u6765\u6a21\u62dfKafka\u5b9e\u65f6\u6d41\u3002\u4f46\u662f\uff0c\u6211\u4eec\u4e5f\u53ef\u4ee5\u5c06\u5176\u4f5c\u4e3aApache Kafka\u7684\u4e3b\u9898\u3002<\/p>\n<div>\u8bf7\u7559\u610f\uff1a<br \/>\n\u7531\u4e8e\u6559\u7a0b\u9700\u8981\uff0c\u6211\u4eec\u6545\u610f\u5c06\u5904\u7406\u901f\u5ea6\u653e\u6162\u4e86\u3002<\/div>\n<pre class=\"post-pre\"><code><span class=\"n\">inputDF<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span> <span class=\"n\">spark<\/span> \r\n          <span class=\"p\">.<\/span><span class=\"n\">readStream<\/span> \r\n          <span class=\"p\">.<\/span><span class=\"nf\">schema<\/span><span class=\"p\">(<\/span><span class=\"n\">jsonSchema<\/span><span class=\"p\">)<\/span> \r\n          <span class=\"p\">.<\/span><span class=\"nf\">option<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">maxFilesPerTrigger<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">)<\/span>  <span class=\"c1\"># \u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u306e\u305f\u3081\u306b\u51e6\u7406\u3092\u9045\u304f\u3057\u3066\u3044\u307e\u3059\r\n<\/span>          <span class=\"p\">.<\/span><span class=\"nf\">option<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">badRecordsPath<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">bad_records_path<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u3044\u304b\u306a\u308b\u4e0d\u6b63\u30ec\u30b3\u30fc\u30c9\u306f\u3053\u3061\u3089\u306b\u683c\u7d0d\u3055\u308c\u307e\u3059\r\n<\/span>          <span class=\"p\">.<\/span><span class=\"nf\">json<\/span><span class=\"p\">(<\/span><span class=\"n\">sensor_path<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30bd\u30fc\u30b9\r\n<\/span>          <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">INPUT_FILE_NAME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nf\">input_file_name<\/span><span class=\"p\">())<\/span> <span class=\"c1\"># \u30d5\u30a1\u30a4\u30eb\u30d1\u30b9\u3092\u4fdd\u6301\r\n<\/span>          <span class=\"p\">.<\/span><span class=\"nf\">withColumn<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"nf\">current_timestamp<\/span><span class=\"p\">())<\/span> <span class=\"c1\"># \u51e6\u7406\u6642\u523b\u306e\u30bf\u30a4\u30e0\u30b9\u30bf\u30f3\u30d7\u3092\u8ffd\u52a0\r\n<\/span>          <span class=\"p\">.<\/span><span class=\"nf\">withWatermark<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">1 minute<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30aa\u30d7\u30b7\u30e7\u30f3: \u9806\u5e8f\u304c\u9045\u308c\u305f\u30c7\u30fc\u30bf\u306b\u5bfe\u3059\u308b\u30a6\u30a3\u30f3\u30c9\u30a6\r\n<\/span>         <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u5411Parquet\u6587\u4ef6\u540c\u6b65\u5199\u5165\u6d41\u3002<\/h3>\n<pre class=\"post-pre\"><code><span class=\"n\">query<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">inputDF<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"n\">writeStream<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">format<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">parquet<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u5f8c\u6bb5\u51e6\u7406\u3042\u308b\u3044\u306f\u5fc5\u8981\u306b\u5fdc\u3058\u3066\u30d0\u30c3\u30c1\u30af\u30a8\u30ea\u30fc\u306e\u305f\u3081\u306b\u4fdd\u5b58\u3092\u884c\u3046\u30b7\u30f3\u30af\r\n<\/span>         <span class=\"p\">.<\/span><span class=\"nf\">option<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">path<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">output_path<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">option<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">checkpointLocation<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">checkpoint_path<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u969c\u5bb3\u5fa9\u65e7\u306e\u305f\u3081\u306e\u30c1\u30a7\u30c3\u30af\u30dd\u30a4\u30f3\u30c8\u306e\u8ffd\u52a0\r\n<\/span>         <span class=\"p\">.<\/span><span class=\"nf\">outputMode<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">append<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">queryName<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">devices<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30aa\u30d7\u30b7\u30e7\u30f3\u3068\u3057\u3066\u3001\u30af\u30a8\u30ea\u30fc\u3092\u5b9f\u884c\u3059\u308b\u969b\u306b\u6307\u5b9a\u3059\u308b\u30af\u30a8\u30ea\u30fc\u540d\u3092\u6307\u5b9a\r\n<\/span>         <span class=\"p\">.<\/span><span class=\"nf\">trigger<\/span><span class=\"p\">(<\/span><span class=\"n\">processingTime<\/span><span class=\"o\">=<\/span><span class=\"sh\">'<\/span><span class=\"s\">5 seconds<\/span><span class=\"sh\">'<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">start<\/span><span class=\"p\">()<\/span> \r\n        <span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/36-0.png\" alt=\"Screen Shot 2022-08-08 at 13.28.55.png\" \/><\/div>\n<h4>\u4ece\u8f93\u5165\u6d41\u521b\u5efa\u4e00\u4e2a\u4e34\u65f6\u8868\uff0c\u4ee5\u4fbf\u80fd\u591f\u5feb\u901f\u6267\u884cSQL\u67e5\u8be2\u3002<\/h4>\n<pre class=\"post-pre\"><code><span class=\"n\">inputDF<\/span><span class=\"p\">.<\/span><span class=\"nf\">createOrReplaceTempView<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">parquet_sensors<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<h3>\u5bf9\u7531\u8f93\u5165\u6d41\u521b\u5efa\u7684\u4e34\u65f6\u8868\u6267\u884c\u67e5\u8be2<\/h3>\n<pre class=\"post-pre\"><code><span class=\"o\">%<\/span><span class=\"k\">sql<\/span> <span class=\"k\">select<\/span> <span class=\"o\">*<\/span> <span class=\"k\">from<\/span> <span class=\"n\">parquet_sensors<\/span> <span class=\"k\">where<\/span> <span class=\"n\">deviceType<\/span> <span class=\"o\">=<\/span> <span class=\"s1\">'SensorTypeD'<\/span> <span class=\"k\">or<\/span> <span class=\"n\">deviceType<\/span> <span class=\"o\">=<\/span> <span class=\"s1\">'SensorTypeA'<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/41-0.png\" alt=\"Screen Shot 2022-08-08 at 13.30.05.png\" \/><\/div>\n<h3>\u5bf9\u4fdd\u5b58\u5728\u8f93\u5165\u6d41\u4e2d\u7684Parquet\u6587\u4ef6\u8fdb\u884c\u9644\u52a0\u5904\u7406\uff0c\u5e76\u6267\u884c\u67e5\u8be2\u3002<\/h3>\n<pre class=\"post-pre\"><code><span class=\"n\">spark<\/span><span class=\"p\">.<\/span><span class=\"n\">conf<\/span><span class=\"p\">.<\/span><span class=\"nf\">set<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">spark.sql.shuffle.partitions<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">1<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u512a\u308c\u305f\u30af\u30a8\u30ea\u30fc\u6027\u80fd\u306e\u305f\u3081\u306b\u30b7\u30e3\u30c3\u30d5\u30eb\u30b5\u30a4\u30ba\u3092\u5c0f\u3055\u304f\u7dad\u6301\r\n<\/span><span class=\"n\">devices<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">spark<\/span><span class=\"p\">.<\/span><span class=\"n\">readStream<\/span>\r\n           <span class=\"p\">.<\/span><span class=\"nf\">schema<\/span><span class=\"p\">(<\/span><span class=\"n\">parquetSchema<\/span><span class=\"p\">)<\/span>\r\n           <span class=\"p\">.<\/span><span class=\"nf\">format<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">parquet<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n           <span class=\"p\">.<\/span><span class=\"nf\">option<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">maxFilesPerTrigger<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"mi\">1<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30c7\u30e2\u306e\u305f\u3081\u306b\u9045\u304f\u3057\u3066\u3044\u307e\u3059\r\n<\/span>           <span class=\"p\">.<\/span><span class=\"nf\">load<\/span><span class=\"p\">(<\/span><span class=\"n\">output_path<\/span><span class=\"p\">)<\/span>\r\n           <span class=\"p\">.<\/span><span class=\"nf\">withWatermark<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">1 minute<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u9806\u5e8f\u3092\u5b88\u3089\u306a\u3044\u30c7\u30fc\u30bf\u306b\u5bfe\u3059\u308b\u30a6\u30a3\u30f3\u30c9\u30a6\r\n<\/span>          <span class=\"p\">)<\/span>\r\n\r\n <span class=\"c1\"># \u3088\u308a\u8907\u96d1\u306a\u96c6\u8a08\u30af\u30a8\u30ea\u30fc\u3092\u884c\u3046\u305f\u3081\u306b\u4e00\u6642\u30c6\u30fc\u30d6\u30eb\u3092\u4f5c\u6210\r\n<\/span><span class=\"n\">devices<\/span><span class=\"p\">.<\/span><span class=\"nf\">createOrReplaceTempView<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">sensors<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u5373\u4f7f\u964d\u4f4e\u4e86\u8d28\u91cf\uff0c\u6211\u4eec\u8fd8\u662f\u4f1a\u7ee7\u7eed\u6267\u884c\u6d41\u67e5\u8be2\u3002<\/p>\n<h4>\u54ea\u4e2a\u6587\u4ef6\u88ab\u5904\u7406\u4e86\uff1f<\/h4>\n<pre class=\"post-pre\"><code><span class=\"nf\">display<\/span><span class=\"p\">(<\/span>\r\n  <span class=\"n\">devices<\/span><span class=\"p\">.<\/span>\r\n  <span class=\"nf\">select<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">INPUT_FILE_NAME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">groupBy<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">INPUT_FILE_NAME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">count<\/span><span class=\"p\">()<\/span>\r\n  <span class=\"p\">.<\/span><span class=\"nf\">orderBy<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">PROCESSED_TIME<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"n\">ascending<\/span><span class=\"o\">=<\/span><span class=\"bp\">False<\/span><span class=\"p\">)<\/span>\r\n<span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/47-0.png\" alt=\"Screen Shot 2022-08-08 at 13.31.38.png\" \/><\/div>\n<h4>\u6709\u591a\u5c11\u6570\u636e\u7ecf\u8fc7\u4e86\uff1f<\/h4>\n<pre class=\"post-pre\"><code><span class=\"o\">%<\/span><span class=\"n\">sql<\/span> <span class=\"n\">select<\/span> <span class=\"nf\">count<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"p\">)<\/span> <span class=\"k\">from<\/span> <span class=\"n\">sensors<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/50-0.png\" alt=\"Screen Shot 2022-08-08 at 13.32.14.png\" \/><\/div>\n<h4>\u6bcf\u79cd\u4f20\u611f\u5668\u7c7b\u578b\u7684\u5f3a\u5ea6\u6700\u5c0f\u503c\u3001\u6700\u5927\u503c\u548c\u5e73\u5747\u503c\u5206\u522b\u5982\u4f55\uff1f<\/h4>\n<p>\u5728Spark SQL\u4e2d\u4f7f\u7528min()\u3001max()\u548cavg()\u51fd\u6570\u3002<\/p>\n<div>\u8bf7\u6ce8\u610f\uff0c\u5728Python\u7b14\u8bb0\u672c\u4e2d\uff0c\u60a8\u53ef\u4ee5\u4f7f\u7528%sql\u9b54\u672f\u547d\u4ee4\u6765\u4f7f\u7528SQL\u3002<\/div>\n<pre class=\"post-pre\"><code><span class=\"o\">%<\/span><span class=\"k\">sql<\/span> \r\n\r\n<span class=\"k\">select<\/span> <span class=\"k\">count<\/span><span class=\"p\">(<\/span><span class=\"o\">*<\/span><span class=\"p\">),<\/span> <span class=\"n\">deviceType<\/span><span class=\"p\">,<\/span> <span class=\"k\">min<\/span><span class=\"p\">(<\/span><span class=\"n\">signalStrength<\/span><span class=\"p\">),<\/span> <span class=\"k\">max<\/span><span class=\"p\">(<\/span><span class=\"n\">signalStrength<\/span><span class=\"p\">),<\/span> <span class=\"k\">avg<\/span><span class=\"p\">(<\/span><span class=\"n\">signalStrength<\/span><span class=\"p\">)<\/span> \r\n  <span class=\"k\">from<\/span> <span class=\"n\">sensors<\/span> \r\n    <span class=\"k\">group<\/span> <span class=\"k\">by<\/span> <span class=\"n\">deviceType<\/span> \r\n    <span class=\"k\">order<\/span> <span class=\"k\">by<\/span> <span class=\"n\">deviceType<\/span> <span class=\"k\">asc<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/55-0.png\" alt=\"Screen Shot 2022-08-08 at 13.33.22.png\" \/><\/div>\n<h4>\u8ba9\u6211\u4eec\u521b\u5efa\u4e00\u4e2a\u6d41\u6765\u6c47\u603b\u8bbe\u5907\u548c\u6bcf5\u79d2\u7a97\u53e3\u7684\u4fe1\u53f7\u8ba1\u6570\u3002<\/h4>\n<div>\u8bf7\u6ce8\u610f\uff0c\u8fd9\u662f\u4e00\u4e2a\u5f39\u6027\u7a97\u53e3\uff0c\u800c\u4e0d\u662f\u6ed1\u52a8\u7a97\u53e3\u3002\u5927\u5c0f\u4e3a5\u79d2\u3002<\/div>\n<p>\u4f8b\u5982\uff0c\u5bf9\u4e8e\u5c3a\u5bf8\u4e3a5\u7684\u65f6\u3001\u5206\u7684\u6eda\u52a8\u7a97\u53e3\uff0c\u5982\u4e0b\u6240\u793a\u3002<\/p>\n<p>[(00:00 &#8211; 00:05), (00:05 &#8211; 00:10), (00:10 &#8211; 00:15)] \u53ef\u63d0\u4f9b\u4e00\u79cd\u9009\u62e9:<\/p>\n<p>\u8be5\u6d3b\u52a8\u5c06\u5c5e\u4e8e\u8fd9\u4e9b\u6eda\u52a8\u7a97\u53e3\u4e2d\u7684\u4efb\u610f\u4e00\u4e2a\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"p\">(<\/span><span class=\"n\">devices<\/span>\r\n <span class=\"p\">.<\/span><span class=\"nf\">groupBy<\/span><span class=\"p\">(<\/span>\r\n   <span class=\"nf\">window<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">timestamp<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">5 seconds<\/span><span class=\"sh\">\"<\/span><span class=\"p\">),<\/span>\r\n   <span class=\"sh\">\"<\/span><span class=\"s\">deviceId<\/span><span class=\"sh\">\"<\/span>\r\n <span class=\"p\">)<\/span>\r\n <span class=\"p\">.<\/span><span class=\"nf\">count<\/span><span class=\"p\">()<\/span>\r\n <span class=\"p\">.<\/span><span class=\"nf\">createOrReplaceTempView<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">sensor_counts<\/span><span class=\"sh\">\"<\/span><span class=\"p\">))<\/span> <span class=\"c1\"># \u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u3092\u7528\u3044\u3066\u4e00\u6642\u30d3\u30e5\u30fc\u3092\u4f5c\u6210\r\n<\/span><\/code><\/pre>\n<h4>\u5728\u8fd95\u79d2\u7684\u65f6\u95f4\u7a97\u53e3\u5185\uff0c\u54ea\u4e2a\u8bbe\u5907\u7ecf\u5386\u4e86\u4fe1\u53f7\u7684\u4e22\u5931\uff1f<\/h4>\n<pre class=\"post-pre\"><code><span class=\"o\">%<\/span><span class=\"n\">sql<\/span> <span class=\"n\">select<\/span> <span class=\"o\">*<\/span> <span class=\"k\">from<\/span> <span class=\"n\">sensor_counts<\/span> <span class=\"n\">where<\/span> <span class=\"n\">count<\/span> <span class=\"o\">&lt;<\/span> <span class=\"mi\">5<\/span> <span class=\"n\">order<\/span> <span class=\"n\">by<\/span> <span class=\"n\">window<\/span><span class=\"p\">.<\/span><span class=\"n\">start<\/span> <span class=\"n\">desc<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/64-0.png\" alt=\"Screen Shot 2022-08-08 at 13.34.39.png\" \/><\/div>\n<h3>\u53ef\u80fd\u5b58\u5728\u7740\u4f20\u8f93\u4fe1\u53f7\u672a\u53d1\u9001\u7684\u611f\u5e94\u5668\u8b66\u62a5\u53ef\u80fd\u8981\u53d1\u9001\u8b66\u62a5\u3002<\/h3>\n<p>\u8ba9\u6211\u4eec\u4ece\u4e34\u65f6\u8868sensor_counts\u4e2d\u521b\u5efa\u4e00\u4e2a\u6570\u636e\u5e27\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"n\">lost_sensor_signals<\/span> <span class=\"o\">=<\/span> <span class=\"p\">(<\/span><span class=\"n\">spark<\/span><span class=\"p\">.<\/span><span class=\"nf\">table<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">sensor_counts<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">filter<\/span><span class=\"p\">(<\/span><span class=\"nf\">col<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">count<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"o\">&lt;<\/span> <span class=\"mi\">5<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">.<\/span><span class=\"nf\">select<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">window.start<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">window.end<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">deviceId<\/span><span class=\"sh\">\"<\/span><span class=\"p\">,<\/span> <span class=\"sh\">\"<\/span><span class=\"s\">count<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span>\r\n         <span class=\"p\">)<\/span>\r\n\r\n<span class=\"c1\"># \u30c7\u30fc\u30bf\u30d5\u30ec\u30fc\u30e0\u306e\u8868\u793a\r\n<\/span><span class=\"nf\">display<\/span><span class=\"p\">(<\/span><span class=\"n\">lost_sensor_signals<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/68-0.png\" alt=\"Screen Shot 2022-08-08 at 13.35.14.png\" \/><\/div>\n<h5>\u4e3a\u4e86\u5c06\u5de5\u4eba\u7684\u65e5\u5fd7\u5199\u5165\uff0c\u5229\u7528foreach\u673a\u5236\u3002<\/h5>\n<p>\u8fd9\u4e2a\u53ef\u4ee5\u7528\u4e8e\u76d1\u63a7\u7684\u76ee\u7684\u3002\u53e6\u4e00\u4e2a\u5de5\u4f5c\u53ef\u4ee5\u626b\u63cf\u65e5\u5fd7\u4ee5\u83b7\u5f97\u8b66\u62a5\uff0c\u5e76\u5c06\u5176\u53d1\u5e03\u5230Kafka\u7684\u4e3b\u9898\u4e2d\uff0c\u6216\u8005\u5c06\u5176\u53d1\u5e03\u5230Ganglia\u3002\u5982\u679c\u6709\u53ef\u7528\u7684Kafka\u670d\u52a1\u5668\u6216\u53ef\u4ee5\u901a\u8fc7REST API\u4f7f\u7528\u7684Ganglia\u670d\u52a1\uff0c\u90a3\u4e48\u5c1d\u8bd5\u4e00\u4e0b\u4f1a\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u7ec3\u4e60\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"k\">def<\/span> <span class=\"nf\">processRow<\/span><span class=\"p\">(<\/span><span class=\"n\">row<\/span><span class=\"p\">):<\/span>\r\n  <span class=\"c1\"># \u4eca\u6642\u70b9\u3067\u306f\u30ed\u30b0\u30d5\u30a1\u30a4\u30eb\u306b\u66f8\u304d\u8fbc\u307f\u3092\u884c\u3044\u307e\u3059\u304c\u3001\u3053\u306e\u30ed\u30b8\u30c3\u30af\u306f\u5bb9\u6613\u306bKafka\u306e\u30c8\u30d4\u30c3\u30af\u3084\u3001Ganglia\u3084PagerDuty\u306e\u3088\u3046\u306a\u30e2\u30cb\u30bf\u30ea\u30f3\u30b0\u3001\u30da\u30fc\u30b8\u30f3\u30b0\u30b5\u30fc\u30d3\u30b9\u306b\u30a2\u30e9\u30fc\u30c8\u3092\u767a\u884c\u3059\u308b\u3088\u3046\u306b\u62e1\u5f35\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059\r\n<\/span>  <span class=\"nf\">print<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">ALERT from Sensors: Between {} and {}, device {} reported only {} times<\/span><span class=\"sh\">\"<\/span><span class=\"p\">.<\/span><span class=\"nf\">format<\/span><span class=\"p\">(<\/span><span class=\"n\">row<\/span><span class=\"p\">.<\/span><span class=\"n\">start<\/span><span class=\"p\">,<\/span> <span class=\"n\">row<\/span><span class=\"p\">.<\/span><span class=\"n\">end<\/span><span class=\"p\">,<\/span> <span class=\"n\">row<\/span><span class=\"p\">.<\/span><span class=\"n\">deviceId<\/span><span class=\"p\">,<\/span> <span class=\"n\">row<\/span><span class=\"p\">[<\/span><span class=\"mi\">3<\/span><span class=\"p\">]))<\/span>\r\n  \r\n<span class=\"p\">(<\/span><span class=\"n\">lost_sensor_signals<\/span>\r\n <span class=\"p\">.<\/span><span class=\"n\">writeStream<\/span>\r\n <span class=\"p\">.<\/span><span class=\"nf\">outputMode<\/span><span class=\"p\">(<\/span><span class=\"sh\">\"<\/span><span class=\"s\">complete<\/span><span class=\"sh\">\"<\/span><span class=\"p\">)<\/span> <span class=\"c1\"># \u30e2\u30cb\u30bf\u30ea\u30f3\u30b0\u306e\u305f\u3081\u306bKafka\u306e\"alerts\"\u30c8\u30d4\u30c3\u30af\u306b\u3059\u308b\u3053\u3068\u3082\u3067\u304d\u307e\u3059\r\n<\/span> <span class=\"p\">.<\/span><span class=\"nf\">foreach<\/span><span class=\"p\">(<\/span><span class=\"n\">processRow<\/span><span class=\"p\">)<\/span>\r\n <span class=\"p\">.<\/span><span class=\"nf\">start<\/span><span class=\"p\">()<\/span>\r\n<span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u8fd9\u662f\u4e00\u4e2a\u751f\u6210\u7ed3\u679c\u7684\u793a\u4f8b\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/73-0.png\" alt=\"\" \/><\/div>\n<h2>\u6570\u636e\u6e05\u7406<\/h2>\n<h3>\u83b7\u53d6\u6240\u6709\u6b63\u5728\u8fd0\u884c\u7684\u67e5\u8be2<\/h3>\n<pre class=\"post-pre\"><code><span class=\"n\">sqm<\/span> <span class=\"o\">=<\/span> <span class=\"n\">spark<\/span><span class=\"p\">.<\/span><span class=\"n\">streams<\/span>\r\n<span class=\"p\">[<\/span><span class=\"n\">q<\/span><span class=\"p\">.<\/span><span class=\"n\">name<\/span> <span class=\"k\">for<\/span> <span class=\"n\">q<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">sqm<\/span><span class=\"p\">.<\/span><span class=\"n\">active<\/span><span class=\"p\">]<\/span>\r\n<\/code><\/pre>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/77-0.png\" alt=\"Screen Shot 2022-08-08 at 13.36.28.png\" \/><\/div>\n<h3>\u505c\u6b62\u6d41\u5a92\u4f53<\/h3>\n<pre class=\"post-pre\"><code><span class=\"p\">[<\/span><span class=\"n\">q<\/span><span class=\"p\">.<\/span><span class=\"nf\">stop<\/span><span class=\"p\">()<\/span> <span class=\"k\">for<\/span> <span class=\"n\">q<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">sqm<\/span><span class=\"p\">.<\/span><span class=\"n\">active<\/span><span class=\"p\">]<\/span>\r\n<\/code><\/pre>\n<h3>Databricks \u514d\u8d39\u8bd5\u7528<\/h3>\n<p>Databricks \u514d\u8d39\u8bd5\u7528<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9019\u662f\u95dc\u65bc\u9019\u500b\u7b46\u8a18\u672c\u756b\u5eca\u7684\u50b3\u611f\u5668\u6578\u64da\u6d41\u61c9\u7528\u7a0b\u5e8f\u7684\u64cd\u4f5c\u6b65\u9a5f\u3002 &nbsp; \u7b14\u8bb0\u672c\u7684\u7ffb\u8bd1\u7248\u5728\u8fd9\u91cc\u3002 &nbsp;  [&hellip;]<\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-47050","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\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f - 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\u4f20\u611f\u5668\u6570\u636e\u7684spark\u6d41\u5e94\u7528\u7a0b\u5e8f\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f\" \/>\n<meta property=\"og:description\" content=\"\u9019\u662f\u95dc\u65bc\u9019\u500b\u7b46\u8a18\u672c\u756b\u5eca\u7684\u50b3\u611f\u5668\u6578\u64da\u6d41\u61c9\u7528\u7a0b\u5e8f\u7684\u64cd\u4f5c\u6b65\u9a5f\u3002 &nbsp; \u7b14\u8bb0\u672c\u7684\u7ffb\u8bd1\u7248\u5728\u8fd9\u91cc\u3002 &nbsp; [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684spark\u6d41\u5e94\u7528\u7a0b\u5e8f\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-09-19T01:18:44+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-29T12:04:47+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/10-0.png\" \/>\n<meta name=\"author\" content=\"\u65b0, \u97f5\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u65b0, \u97f5\" \/>\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\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/\",\"name\":\"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-09-19T01:18:44+00:00\",\"dateModified\":\"2024-04-29T12:04:47+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/4ba4019495123db3038fd0809e6959c9\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f\"}]},{\"@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\/4ba4019495123db3038fd0809e6959c9\",\"name\":\"\u65b0, \u97f5\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/d484b6c6e4ae82e8a9efea989e1d2af46d9b6ef128101e63b18f559fca0ae627?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/d484b6c6e4ae82e8a9efea989e1d2af46d9b6ef128101e63b18f559fca0ae627?s=96&d=mm&r=g\",\"caption\":\"\u65b0, \u97f5\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yunxin\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f - 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\u4f20\u611f\u5668\u6570\u636e\u7684spark\u6d41\u5e94\u7528\u7a0b\u5e8f\/","og_locale":"zh_CN","og_type":"article","og_title":"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f","og_description":"\u9019\u662f\u95dc\u65bc\u9019\u500b\u7b46\u8a18\u672c\u756b\u5eca\u7684\u50b3\u611f\u5668\u6578\u64da\u6d41\u61c9\u7528\u7a0b\u5e8f\u7684\u64cd\u4f5c\u6b65\u9a5f\u3002 &nbsp; \u7b14\u8bb0\u672c\u7684\u7ffb\u8bd1\u7248\u5728\u8fd9\u91cc\u3002 &nbsp; [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684spark\u6d41\u5e94\u7528\u7a0b\u5e8f\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-09-19T01:18:44+00:00","article_modified_time":"2024-04-29T12:04:47+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d7c48913a08637a69bd1b\/10-0.png"}],"author":"\u65b0, \u97f5","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u65b0, \u97f5","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"3 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/","name":"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-09-19T01:18:44+00:00","dateModified":"2024-04-29T12:04:47+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/4ba4019495123db3038fd0809e6959c9"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u4f7f\u7528\u4f20\u611f\u5668\u6570\u636e\u7684Spark\u6d41\u5e94\u7528\u7a0b\u5e8f"}]},{"@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\/4ba4019495123db3038fd0809e6959c9","name":"\u65b0, \u97f5","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/d484b6c6e4ae82e8a9efea989e1d2af46d9b6ef128101e63b18f559fca0ae627?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/d484b6c6e4ae82e8a9efea989e1d2af46d9b6ef128101e63b18f559fca0ae627?s=96&d=mm&r=g","caption":"\u65b0, \u97f5"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yunxin\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e4%bd%bf%e7%94%a8%e4%bc%a0%e6%84%9f%e5%99%a8%e6%95%b0%e6%8d%ae%e7%9a%84spark%e6%b5%81%e5%ba%94%e7%94%a8%e7%a8%8b%e5%ba%8f\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47050","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\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=47050"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47050\/revisions"}],"predecessor-version":[{"id":87359,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/47050\/revisions\/87359"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=47050"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=47050"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=47050"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}