{"id":36335,"date":"2024-01-02T11:40:57","date_gmt":"2023-11-12T15:36:56","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/"},"modified":"2024-05-04T16:27:39","modified_gmt":"2024-05-04T08:27:39","slug":"apache-spark-%e9%85%8d%e7%bd%ae","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/","title":{"rendered":"Apache Spark \u914d\u7f6e"},"content":{"rendered":"<p>\u6709\u5173Apache Spark\u8bbe\u7f6e\u7684\u6b65\u9aa4\u3002<\/p>\n<h1>\u5b89\u88c5<\/h1>\n<pre class=\"post-pre\"><code>brew <span class=\"nb\">install <\/span>apache-spark\r\n<\/code><\/pre>\n<p>\u51c6\u5907\u5df2\u7ecf\u5b8c\u6210\u3002<\/p>\n<h1>\u542f\u52a8REPL<\/h1>\n<p>\u5728 REPL \u4e2d\uff0c\u4f60\u53ef\u4ee5\u5c1d\u8bd5\u8bb8\u591a\u4e0d\u540c\u7684\u4e1c\u897f\u3002<\/p>\n<pre class=\"post-pre\"><code>spark-shell\r\n<\/code><\/pre>\n<h1>\u8bd5\u7740\u73a9\u4e00\u73a9<\/h1>\n<p>\u5c1d\u8bd5\u9605\u8bfb README \u7b49\u7b49\u3002<br \/>\nsh\u00ec README .)<\/p>\n<pre class=\"post-pre\"><code><span class=\"n\">scala<\/span><span class=\"o\">&gt;<\/span> <span class=\"k\">val<\/span> <span class=\"nv\">textFile<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">spark<\/span><span class=\"o\">.<\/span><span class=\"py\">read<\/span><span class=\"o\">.<\/span><span class=\"py\">textFile<\/span><span class=\"o\">(<\/span><span class=\"s\">\"README.md\"<\/span><span class=\"o\">)<\/span>\r\n<span class=\"n\">textFile<\/span><span class=\"k\">:<\/span> <span class=\"kt\">org.apache.spark.sql.Dataset<\/span><span class=\"o\">[<\/span><span class=\"kt\">String<\/span><span class=\"o\">]<\/span> <span class=\"k\">=<\/span> <span class=\"o\">[<\/span><span class=\"kt\">value:<\/span> <span class=\"kt\">string<\/span><span class=\"o\">]<\/span>\r\n\r\n<span class=\"n\">scala<\/span><span class=\"o\">&gt;<\/span> <span class=\"nv\">textFile<\/span><span class=\"o\">.<\/span><span class=\"py\">first<\/span>\r\n<span class=\"n\">res0<\/span><span class=\"k\">:<\/span> <span class=\"kt\">String<\/span> <span class=\"o\">=<\/span> <span class=\"k\">#<\/span> <span class=\"n\">\u4ffa\u306e\u30a2\u30d1\u30c3\u30c1\u30b9\u30d1\u30fc\u30af<\/span>\r\n\r\n<span class=\"nv\">textFile<\/span><span class=\"o\">.<\/span><span class=\"py\">count<\/span>\r\n<span class=\"n\">res1<\/span><span class=\"k\">:<\/span> <span class=\"kt\">Long<\/span> <span class=\"o\">=<\/span> <span class=\"mi\">167<\/span>\r\n<\/code><\/pre>\n<p>\u8bd5\u7740\u521b\u5efa\u4e00\u4e2a\u5408\u9002\u7684 DataFrame \u7b49\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"n\">scala<\/span><span class=\"o\">&gt;<\/span> <span class=\"k\">:<\/span><span class=\"kt\">paste<\/span>\r\n<span class=\"c1\">\/\/ Entering paste mode (ctrl-D to finish)<\/span>\r\n\r\n<span class=\"k\">import<\/span> <span class=\"nn\">org.apache.spark.sql.SparkSession<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">spark<\/span> <span class=\"k\">=<\/span> <span class=\"nv\">SparkSession<\/span><span class=\"o\">.<\/span><span class=\"py\">builder<\/span><span class=\"o\">.<\/span><span class=\"py\">appName<\/span><span class=\"o\">(<\/span><span class=\"k\">this<\/span><span class=\"o\">.<\/span><span class=\"py\">getClass<\/span><span class=\"o\">.<\/span><span class=\"py\">getName<\/span><span class=\"o\">).<\/span><span class=\"py\">getOrCreate<\/span><span class=\"o\">()<\/span>\r\n<span class=\"k\">import<\/span> <span class=\"nn\">spark.implicits._<\/span>\r\n\r\n<span class=\"k\">val<\/span> <span class=\"nv\">people<\/span> <span class=\"k\">=<\/span> <span class=\"nc\">Seq<\/span><span class=\"o\">(<\/span>\r\n  <span class=\"o\">(<\/span><span class=\"s\">\"Spark\u592a\u90ce\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"spark-taro@example.com\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"2021-01-01\"<\/span><span class=\"o\">,<\/span> <span class=\"mi\">11<\/span><span class=\"o\">),<\/span>\r\n  <span class=\"o\">(<\/span><span class=\"s\">\"Spark\u4e8c\u90ce\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"spark-jiro@example.com\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"2021-02-02\"<\/span><span class=\"o\">,<\/span> <span class=\"mi\">12<\/span><span class=\"o\">),<\/span>\r\n  <span class=\"o\">(<\/span><span class=\"s\">\"Spark\u4e09\u90ce\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"spark-saburo@example.com\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"2021-03-03\"<\/span><span class=\"o\">,<\/span> <span class=\"mi\">13<\/span><span class=\"o\">)<\/span>\r\n<span class=\"o\">).<\/span><span class=\"py\">toDF<\/span><span class=\"o\">(<\/span><span class=\"s\">\"name\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"email\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"birthday\"<\/span><span class=\"o\">,<\/span> <span class=\"s\">\"age\"<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"c1\">\/\/ Exiting paste mode, now interpreting.<\/span>\r\n<span class=\"o\">...<\/span>\r\n\r\n<span class=\"n\">scala<\/span><span class=\"o\">&gt;<\/span> <span class=\"nv\">people<\/span><span class=\"o\">.<\/span><span class=\"py\">printSchema<\/span><span class=\"o\">()<\/span>\r\n<span class=\"n\">root<\/span>\r\n <span class=\"o\">|--<\/span> <span class=\"n\">name<\/span><span class=\"k\">:<\/span> <span class=\"kt\">string<\/span> <span class=\"o\">(<\/span><span class=\"kt\">nullable<\/span> <span class=\"o\">=<\/span> <span class=\"kt\">true<\/span><span class=\"o\">)<\/span>\r\n <span class=\"o\">|--<\/span> <span class=\"n\">email<\/span><span class=\"k\">:<\/span> <span class=\"kt\">string<\/span> <span class=\"o\">(<\/span><span class=\"kt\">nullable<\/span> <span class=\"o\">=<\/span> <span class=\"kt\">true<\/span><span class=\"o\">)<\/span>\r\n <span class=\"o\">|--<\/span> <span class=\"n\">birthday<\/span><span class=\"k\">:<\/span> <span class=\"kt\">string<\/span> <span class=\"o\">(<\/span><span class=\"kt\">nullable<\/span> <span class=\"o\">=<\/span> <span class=\"kt\">true<\/span><span class=\"o\">)<\/span>\r\n <span class=\"o\">|--<\/span> <span class=\"n\">age<\/span><span class=\"k\">:<\/span> <span class=\"kt\">integer<\/span> <span class=\"o\">(<\/span><span class=\"kt\">nullable<\/span> <span class=\"o\">=<\/span> <span class=\"kt\">false<\/span><span class=\"o\">)<\/span>\r\n\r\n<span class=\"n\">scala<\/span><span class=\"o\">&gt;<\/span> <span class=\"nv\">people<\/span><span class=\"o\">.<\/span><span class=\"py\">show<\/span><span class=\"o\">(<\/span><span class=\"mi\">3<\/span><span class=\"o\">)<\/span>\r\n<span class=\"o\">+---------+--------------------+----------+---+<\/span>\r\n<span class=\"o\">|<\/span>     <span class=\"n\">name<\/span><span class=\"o\">|<\/span>               <span class=\"n\">email<\/span><span class=\"o\">|<\/span>  <span class=\"n\">birthday<\/span><span class=\"o\">|<\/span><span class=\"n\">age<\/span><span class=\"o\">|<\/span>\r\n<span class=\"o\">+---------+--------------------+----------+---+<\/span>\r\n<span class=\"o\">|<\/span><span class=\"nc\">Spark\u592a\u90ce<\/span><span class=\"o\">|<\/span><span class=\"n\">spark<\/span><span class=\"o\">-<\/span><span class=\"n\">taro<\/span><span class=\"nd\">@exampl<\/span><span class=\"o\">...|<\/span><span class=\"mi\">2021<\/span><span class=\"o\">-<\/span><span class=\"mi\">01<\/span><span class=\"o\">-<\/span><span class=\"mi\">01<\/span><span class=\"o\">|<\/span> <span class=\"mi\">11<\/span><span class=\"o\">|<\/span>\r\n<span class=\"o\">|<\/span><span class=\"nc\">Spark\u4e8c\u90ce<\/span><span class=\"o\">|<\/span><span class=\"n\">spark<\/span><span class=\"o\">-<\/span><span class=\"n\">jiro<\/span><span class=\"nd\">@exampl<\/span><span class=\"o\">...|<\/span><span class=\"mi\">2021<\/span><span class=\"o\">-<\/span><span class=\"mi\">02<\/span><span class=\"o\">-<\/span><span class=\"mi\">02<\/span><span class=\"o\">|<\/span> <span class=\"mi\">12<\/span><span class=\"o\">|<\/span>\r\n<span class=\"o\">|<\/span><span class=\"nc\">Spark\u4e09\u90ce<\/span><span class=\"o\">|<\/span><span class=\"n\">spark<\/span><span class=\"o\">-<\/span><span class=\"n\">saburo<\/span><span class=\"nd\">@exam<\/span><span class=\"o\">...|<\/span><span class=\"mi\">2021<\/span><span class=\"o\">-<\/span><span class=\"mi\">03<\/span><span class=\"o\">-<\/span><span class=\"mi\">03<\/span><span class=\"o\">|<\/span> <span class=\"mi\">13<\/span><span class=\"o\">|<\/span>\r\n<span class=\"o\">+---------+--------------------+----------+---+<\/span>\r\n<\/code><\/pre>\n<p>\u8bf7\u5c1d\u8bd5\u5404\u79cd\u4e0d\u540c\u7684\u4e8b\u60c5\u3002<br \/>\n\u7ed3\u675f\u4e86\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6709\u5173Apache Spark\u8bbe\u7f6e\u7684\u6b65\u9aa4\u3002 \u5b89\u88c5 brew install apache-spark \u51c6\u5907\u5df2\u7ecf\u5b8c [&hellip;]<\/p>\n","protected":false},"author":5,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-36335","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 \u914d\u7f6e - 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-\u914d\u7f6e\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Apache Spark \u914d\u7f6e\" \/>\n<meta property=\"og:description\" content=\"\u6709\u5173Apache Spark\u8bbe\u7f6e\u7684\u6b65\u9aa4\u3002 \u5b89\u88c5 brew install apache-spark \u51c6\u5907\u5df2\u7ecf\u5b8c [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-\u914d\u7f6e\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-11-12T15:36:56+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-04T08:27:39+00:00\" \/>\n<meta name=\"author\" content=\"\u6e05, \u5b87\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u6e05, \u5b87\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/\",\"name\":\"Apache Spark \u914d\u7f6e - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-11-12T15:36:56+00:00\",\"dateModified\":\"2024-05-04T08:27:39+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/1a6ecd3d914d22a5ac32791ffc1fbd8e\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Apache Spark \u914d\u7f6e\"}]},{\"@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\/1a6ecd3d914d22a5ac32791ffc1fbd8e\",\"name\":\"\u6e05, \u5b87\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/4b2016c18459a605fc469c7566608f5686491baa112d0871ee613f61b7210565?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/4b2016c18459a605fc469c7566608f5686491baa112d0871ee613f61b7210565?s=96&d=mm&r=g\",\"caption\":\"\u6e05, \u5b87\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyu\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Apache Spark \u914d\u7f6e - 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-\u914d\u7f6e\/","og_locale":"zh_CN","og_type":"article","og_title":"Apache Spark \u914d\u7f6e","og_description":"\u6709\u5173Apache Spark\u8bbe\u7f6e\u7684\u6b65\u9aa4\u3002 \u5b89\u88c5 brew install apache-spark \u51c6\u5907\u5df2\u7ecf\u5b8c [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-\u914d\u7f6e\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-11-12T15:36:56+00:00","article_modified_time":"2024-05-04T08:27:39+00:00","author":"\u6e05, \u5b87","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u6e05, \u5b87","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"1 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/","name":"Apache Spark \u914d\u7f6e - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-11-12T15:36:56+00:00","dateModified":"2024-05-04T08:27:39+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/1a6ecd3d914d22a5ac32791ffc1fbd8e"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"Apache Spark \u914d\u7f6e"}]},{"@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\/1a6ecd3d914d22a5ac32791ffc1fbd8e","name":"\u6e05, \u5b87","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/4b2016c18459a605fc469c7566608f5686491baa112d0871ee613f61b7210565?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/4b2016c18459a605fc469c7566608f5686491baa112d0871ee613f61b7210565?s=96&d=mm&r=g","caption":"\u6e05, \u5b87"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/qingyu\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/apache-spark-%e9%85%8d%e7%bd%ae\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36335","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\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=36335"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36335\/revisions"}],"predecessor-version":[{"id":99415,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/36335\/revisions\/99415"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=36335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=36335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=36335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}