| { |
| "paragraphs": [ |
| { |
| "text": "%md\n## Welcome to Zeppelin.\n##### This is a live tutorial, you can run the code yourself. (Shift-Enter to Run)", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:10.172", |
| "progress": 0, |
| "config": { |
| "colWidth": 12.0, |
| "editorHide": true, |
| "results": [ |
| { |
| "graph": { |
| "mode": "table", |
| "height": 300.0, |
| "optionOpen": false, |
| "keys": [], |
| "values": [], |
| "groups": [], |
| "scatter": {} |
| } |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "markdown", |
| "editOnDblClick": true |
| }, |
| "editorMode": "ace/mode/markdown", |
| "tableHide": false, |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "HTML", |
| "data": "\u003cdiv class\u003d\"markdown-body\"\u003e\n\u003ch2\u003eWelcome to Zeppelin.\u003c/h2\u003e\n\u003ch5\u003eThis is a live tutorial, you can run the code yourself. (Shift-Enter to Run)\u003c/h5\u003e\n\n\u003c/div\u003e" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": {}, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423836981412_-1007008116", |
| "id": "20150213-231621_168813393", |
| "dateCreated": "2015-02-13 23:16:21.000", |
| "dateStarted": "2021-07-26 04:36:10.174", |
| "dateFinished": "2021-07-26 04:36:10.184", |
| "status": "FINISHED" |
| }, |
| { |
| "title": "Load data into table", |
| "text": "import org.apache.commons.io.IOUtils\nimport java.net.URL\nimport java.nio.charset.Charset\n\n// Zeppelin creates and injects sc (SparkContext) and sqlContext (HiveContext or SqlContext)\n// So you don\u0027t need create them manually\n\n// load bank data\nval bankText \u003d sc.parallelize(\n IOUtils.toString(\n new URL(\"https://s3.amazonaws.com/apache-zeppelin/tutorial/bank/bank.csv\"),\n Charset.forName(\"utf8\")).split(\"\\n\"))\n\ncase class Bank(age: Integer, job: String, marital: String, education: String, balance: Integer)\n\nval bank \u003d bankText.map(s \u003d\u003e s.split(\";\")).filter(s \u003d\u003e s(0) !\u003d \"\\\"age\\\"\").map(\n s \u003d\u003e Bank(s(0).toInt, \n s(1).replaceAll(\"\\\"\", \"\"),\n s(2).replaceAll(\"\\\"\", \"\"),\n s(3).replaceAll(\"\\\"\", \"\"),\n s(5).replaceAll(\"\\\"\", \"\").toInt\n )\n).toDF()\nbank.registerTempTable(\"bank\")", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:10.274", |
| "progress": 0, |
| "config": { |
| "colWidth": 12.0, |
| "title": true, |
| "enabled": true, |
| "editorMode": "ace/mode/scala", |
| "results": [ |
| { |
| "graph": { |
| "mode": "table", |
| "height": 300.0, |
| "optionOpen": false |
| } |
| } |
| ], |
| "editorSetting": { |
| "language": "scala", |
| "editOnDblClick": false, |
| "completionKey": "TAB", |
| "completionSupport": true |
| }, |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "TEXT", |
| "data": "\u001b[33mwarning: \u001b[0mthere was one deprecation warning (since 2.0.0); for details, enable `:setting -deprecation\u0027 or `:replay -deprecation\u0027\nimport sqlContext.implicits._\nimport org.apache.commons.io.IOUtils\nimport java.net.URL\nimport java.nio.charset.Charset\n\u001b[1m\u001b[34mbankText\u001b[0m: \u001b[1m\u001b[32morg.apache.spark.rdd.RDD[String]\u001b[0m \u003d ParallelCollectionRDD[505] at parallelize at \u003cconsole\u003e:32\ndefined class Bank\n\u001b[1m\u001b[34mbank\u001b[0m: \u001b[1m\u001b[32morg.apache.spark.sql.DataFrame\u001b[0m \u003d [age: int, job: string ... 3 more fields]\n" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": {}, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423500779206_-1502780787", |
| "id": "20150210-015259_1403135953", |
| "dateCreated": "2015-02-10 01:52:59.000", |
| "dateStarted": "2021-07-26 04:36:10.276", |
| "dateFinished": "2021-07-26 04:36:13.186", |
| "status": "FINISHED" |
| }, |
| { |
| "text": "%sql \nselect age, count(1) value\nfrom bank \nwhere age \u003c 30 \ngroup by age \norder by age", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:13.281", |
| "progress": 15, |
| "config": { |
| "colWidth": 4.0, |
| "results": [ |
| { |
| "graph": { |
| "mode": "multiBarChart", |
| "height": 366.0, |
| "optionOpen": false, |
| "setting": { |
| "multiBarChart": { |
| "rotate": { |
| "degree": "-45" |
| }, |
| "xLabelStatus": "default" |
| } |
| }, |
| "commonSetting": {}, |
| "keys": [ |
| { |
| "name": "age", |
| "index": 0.0, |
| "aggr": "sum" |
| } |
| ], |
| "groups": [], |
| "values": [ |
| { |
| "name": "value", |
| "index": 1.0, |
| "aggr": "sum" |
| } |
| ] |
| }, |
| "helium": {} |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "sql", |
| "editOnDblClick": false, |
| "completionKey": "TAB", |
| "completionSupport": true |
| }, |
| "editorMode": "ace/mode/sql", |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "TABLE", |
| "data": "age\tvalue\n19\t4\n20\t3\n21\t7\n22\t9\n23\t20\n24\t24\n25\t44\n26\t77\n27\t94\n28\t103\n29\t97\n" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": { |
| "jobUrl": { |
| "propertyName": "jobUrl", |
| "label": "SPARK JOB", |
| "tooltip": "View in Spark web UI", |
| "group": "spark", |
| "values": [ |
| { |
| "jobUrl": "http://3745c7ed824d:4040/jobs/job?id\u003d210" |
| } |
| ], |
| "interpreterSettingId": "spark" |
| } |
| }, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423500782552_-1439281894", |
| "id": "20150210-015302_1492795503", |
| "dateCreated": "2015-02-10 01:53:02.000", |
| "dateStarted": "2021-07-26 04:36:13.283", |
| "dateFinished": "2021-07-26 04:36:14.677", |
| "status": "FINISHED" |
| }, |
| { |
| "text": "%sql \nselect age, count(1) value \nfrom bank \nwhere age \u003c ${maxAge\u003d30} \ngroup by age \norder by age", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:14.692", |
| "progress": 58, |
| "config": { |
| "colWidth": 4.0, |
| "results": [ |
| { |
| "graph": { |
| "mode": "multiBarChart", |
| "height": 294.0, |
| "optionOpen": false, |
| "setting": { |
| "multiBarChart": { |
| "rotate": { |
| "degree": "-45" |
| }, |
| "xLabelStatus": "default" |
| } |
| }, |
| "commonSetting": {}, |
| "keys": [ |
| { |
| "name": "age", |
| "index": 0.0, |
| "aggr": "sum" |
| } |
| ], |
| "groups": [], |
| "values": [ |
| { |
| "name": "value", |
| "index": 1.0, |
| "aggr": "sum" |
| } |
| ] |
| }, |
| "helium": {} |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "sql", |
| "editOnDblClick": false, |
| "completionKey": "TAB", |
| "completionSupport": true |
| }, |
| "editorMode": "ace/mode/sql", |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": { |
| "maxAge": "35" |
| }, |
| "forms": { |
| "maxAge": { |
| "type": "TextBox", |
| "name": "maxAge", |
| "displayName": "maxAge", |
| "defaultValue": "30", |
| "hidden": false |
| } |
| } |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "TABLE", |
| "data": "age\tvalue\n19\t4\n20\t3\n21\t7\n22\t9\n23\t20\n24\t24\n25\t44\n26\t77\n27\t94\n28\t103\n29\t97\n30\t150\n31\t199\n32\t224\n33\t186\n34\t231\n" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": { |
| "jobUrl": { |
| "propertyName": "jobUrl", |
| "label": "SPARK JOB", |
| "tooltip": "View in Spark web UI", |
| "group": "spark", |
| "values": [ |
| { |
| "jobUrl": "http://3745c7ed824d:4040/jobs/job?id\u003d211" |
| } |
| ], |
| "interpreterSettingId": "spark" |
| } |
| }, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423720444030_-1424110477", |
| "id": "20150212-145404_867439529", |
| "dateCreated": "2015-02-12 14:54:04.000", |
| "dateStarted": "2021-07-26 04:36:14.700", |
| "dateFinished": "2021-07-26 04:36:15.404", |
| "status": "FINISHED" |
| }, |
| { |
| "text": "%sql \nselect age, count(1) value \nfrom bank \nwhere marital\u003d\"${marital\u003dsingle,single|divorced|married}\" \ngroup by age \norder by age", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:15.497", |
| "progress": 51, |
| "config": { |
| "colWidth": 4.0, |
| "results": [ |
| { |
| "graph": { |
| "mode": "stackedAreaChart", |
| "height": 280.0, |
| "optionOpen": false, |
| "setting": { |
| "stackedAreaChart": { |
| "rotate": { |
| "degree": "-45" |
| }, |
| "xLabelStatus": "default" |
| } |
| }, |
| "commonSetting": {}, |
| "keys": [ |
| { |
| "name": "age", |
| "index": 0.0, |
| "aggr": "sum" |
| } |
| ], |
| "groups": [], |
| "values": [ |
| { |
| "name": "value", |
| "index": 1.0, |
| "aggr": "sum" |
| } |
| ] |
| }, |
| "helium": {} |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "sql", |
| "editOnDblClick": false, |
| "completionKey": "TAB", |
| "completionSupport": true |
| }, |
| "editorMode": "ace/mode/sql", |
| "fontSize": 9.0, |
| "runOnSelectionChange": true |
| }, |
| "settings": { |
| "params": { |
| "marital": "single" |
| }, |
| "forms": { |
| "marital": { |
| "type": "Select", |
| "options": [ |
| { |
| "value": "single" |
| }, |
| { |
| "value": "divorced" |
| }, |
| { |
| "value": "married" |
| } |
| ], |
| "name": "marital", |
| "displayName": "marital", |
| "defaultValue": "single", |
| "hidden": false |
| } |
| } |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "TABLE", |
| "data": "age\tvalue\n19\t4\n20\t3\n21\t7\n22\t9\n23\t17\n24\t13\n25\t33\n26\t56\n27\t64\n28\t78\n29\t56\n30\t92\n31\t86\n32\t105\n33\t61\n34\t75\n35\t46\n36\t50\n37\t43\n38\t44\n39\t30\n40\t25\n41\t19\n42\t23\n43\t21\n44\t20\n45\t15\n46\t14\n47\t12\n48\t12\n49\t11\n50\t8\n51\t6\n52\t9\n53\t4\n55\t3\n56\t3\n57\t2\n58\t7\n59\t2\n60\t5\n66\t2\n69\t1\n" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": { |
| "jobUrl": { |
| "propertyName": "jobUrl", |
| "label": "SPARK JOB", |
| "tooltip": "View in Spark web UI", |
| "group": "spark", |
| "values": [ |
| { |
| "jobUrl": "http://3745c7ed824d:4040/jobs/job?id\u003d212" |
| } |
| ], |
| "interpreterSettingId": "spark" |
| } |
| }, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423836262027_-210588283", |
| "id": "20150213-230422_1600658137", |
| "dateCreated": "2015-02-13 23:04:22.000", |
| "dateStarted": "2021-07-26 04:36:15.502", |
| "dateFinished": "2021-07-26 04:36:16.265", |
| "status": "FINISHED" |
| }, |
| { |
| "text": "%md\n## Congratulations, it\u0027s done.\n##### You can create your own notebook in \u0027Notebook\u0027 menu. Good luck!", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:16.300", |
| "progress": 0, |
| "config": { |
| "colWidth": 12.0, |
| "editorHide": true, |
| "results": [ |
| { |
| "graph": { |
| "mode": "table", |
| "height": 300.0, |
| "optionOpen": false |
| } |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "markdown", |
| "editOnDblClick": true |
| }, |
| "editorMode": "ace/mode/markdown", |
| "tableHide": false, |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "HTML", |
| "data": "\u003cdiv class\u003d\"markdown-body\"\u003e\n\u003ch2\u003eCongratulations, it\u0026rsquo;s done.\u003c/h2\u003e\n\u003ch5\u003eYou can create your own notebook in \u0026lsquo;Notebook\u0026rsquo; menu. Good luck!\u003c/h5\u003e\n\n\u003c/div\u003e" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": {}, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1423836268492_216498320", |
| "id": "20150213-230428_1231780373", |
| "dateCreated": "2015-02-13 23:04:28.000", |
| "dateStarted": "2021-07-26 04:36:16.302", |
| "dateFinished": "2021-07-26 04:36:16.308", |
| "status": "FINISHED" |
| }, |
| { |
| "text": "%md\n\nAbout bank data\n\n```\nCitation Request:\n This dataset is public available for research. The details are described in [Moro et al., 2011]. \n Please include this citation if you plan to use this database:\n\n [Moro et al., 2011] S. Moro, R. Laureano and P. Cortez. Using Data Mining for Bank Direct Marketing: An Application of the CRISP-DM Methodology. \n In P. Novais et al. (Eds.), Proceedings of the European Simulation and Modelling Conference - ESM\u00272011, pp. 117-121, Guimarães, Portugal, October, 2011. EUROSIS.\n\n Available at: [pdf] http://hdl.handle.net/1822/14838\n [bib] http://www3.dsi.uminho.pt/pcortez/bib/2011-esm-1.txt\n```", |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:16.402", |
| "progress": 0, |
| "config": { |
| "colWidth": 12.0, |
| "editorHide": true, |
| "results": [ |
| { |
| "graph": { |
| "mode": "table", |
| "height": 300.0, |
| "optionOpen": false |
| } |
| } |
| ], |
| "enabled": true, |
| "editorSetting": { |
| "language": "markdown", |
| "editOnDblClick": true |
| }, |
| "editorMode": "ace/mode/markdown", |
| "tableHide": false, |
| "fontSize": 9.0 |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "results": { |
| "code": "SUCCESS", |
| "msg": [ |
| { |
| "type": "HTML", |
| "data": "\u003cdiv class\u003d\"markdown-body\"\u003e\n\u003cp\u003eAbout bank data\u003c/p\u003e\n\u003cpre\u003e\u003ccode\u003eCitation Request:\n This dataset is public available for research. The details are described in [Moro et al., 2011]. \n Please include this citation if you plan to use this database:\n\n [Moro et al., 2011] S. Moro, R. Laureano and P. Cortez. Using Data Mining for Bank Direct Marketing: An Application of the CRISP-DM Methodology. \n In P. Novais et al. (Eds.), Proceedings of the European Simulation and Modelling Conference - ESM\u00272011, pp. 117-121, Guimarães, Portugal, October, 2011. EUROSIS.\n\n Available at: [pdf] http://hdl.handle.net/1822/14838\n [bib] http://www3.dsi.uminho.pt/pcortez/bib/2011-esm-1.txt\n\u003c/code\u003e\u003c/pre\u003e\n\n\u003c/div\u003e" |
| } |
| ] |
| }, |
| "apps": [], |
| "runtimeInfos": {}, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1427420818407_872443482", |
| "id": "20150326-214658_12335843", |
| "dateCreated": "2015-03-26 21:46:58.000", |
| "dateStarted": "2021-07-26 04:36:16.404", |
| "dateFinished": "2021-07-26 04:36:16.413", |
| "status": "FINISHED" |
| }, |
| { |
| "user": "anonymous", |
| "dateUpdated": "2021-07-26 04:36:16.504", |
| "progress": 0, |
| "config": { |
| "colWidth": 12.0, |
| "fontSize": 9.0, |
| "enabled": true, |
| "results": {}, |
| "editorSetting": { |
| "language": "scala", |
| "editOnDblClick": false, |
| "completionKey": "TAB", |
| "completionSupport": true |
| }, |
| "editorMode": "ace/mode/scala" |
| }, |
| "settings": { |
| "params": {}, |
| "forms": {} |
| }, |
| "apps": [], |
| "runtimeInfos": {}, |
| "progressUpdateIntervalMs": 500, |
| "jobName": "paragraph_1435955447812_-158639899", |
| "id": "20150703-133047_853701097", |
| "dateCreated": "2015-07-03 13:30:47.000", |
| "status": "FINISHED" |
| } |
| ], |
| "name": "2. Spark Basic Features", |
| "id": "2A94M5J1Z", |
| "defaultInterpreterGroup": "spark", |
| "noteParams": {}, |
| "noteForms": {}, |
| "angularObjects": {}, |
| "config": { |
| "looknfeel": "default", |
| "isZeppelinNotebookCronEnable": false |
| }, |
| "info": { |
| "isRunning": true |
| } |
| } |
