Navigation Menu

Skip to content

Instantly share code, notes, and snippets.

@olegchir
Created September 22, 2020 04:39
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save olegchir/249c374e567ee0ab8ba8b222a922698d to your computer and use it in GitHub Desktop.
Save olegchir/249c374e567ee0ab8ba8b222a922698d to your computer and use it in GitHub Desktop.
{
"body": {
"angularObjects": {},
"config": {
"isZeppelinNotebookCronEnable": false,
"looknfeel": "default"
},
"defaultInterpreterGroup": "spark",
"id": "2A94M5J1Z",
"info": {
"isRunning": false
},
"name": "2. Spark Basic Features",
"noteForms": {},
"noteParams": {},
"paragraphs": [
{
"apps": [],
"config": {
"colWidth": 12.0,
"editorHide": true,
"editorMode": "ace/mode/markdown",
"editorSetting": {
"editOnDblClick": true,
"language": "markdown"
},
"enabled": true,
"results": [
{
"graph": {
"groups": [],
"height": 300.0,
"keys": [],
"mode": "table",
"optionOpen": false,
"scatter": {},
"values": []
}
}
],
"tableHide": false
},
"dateCreated": "Feb 13, 2015 11:16:21 PM",
"dateFinished": "Sep 22, 2020 7:23:32 AM",
"dateStarted": "Sep 22, 2020 7:23:30 AM",
"dateUpdated": "Sep 22, 2020 7:23:30 AM",
"id": "20150213-231621_168813393",
"jobName": "paragraph_1423836981412_-1007008116",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"data": "<div class=\"markdown-body\">\n<h2>Welcome to Zeppelin.</h2>\n<h5>This is a live tutorial, you can run the code yourself. (Shift-Enter to Run)</h5>\n\n</div>",
"type": "HTML"
}
]
},
"runtimeInfos": {},
"settings": {
"forms": {},
"params": {}
},
"status": "FINISHED",
"text": "%md\n## Welcome to Zeppelin.\n##### This is a live tutorial, you can run the code yourself. (Shift-Enter to Run)",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 12.0,
"editorMode": "ace/mode/scala",
"editorSetting": {
"completionKey": "TAB",
"completionSupport": true,
"editOnDblClick": false,
"language": "scala"
},
"enabled": true,
"fontSize": 9.0,
"results": [
{
"graph": {
"height": 300.0,
"mode": "table",
"optionOpen": false
}
}
],
"title": true
},
"dateCreated": "Feb 10, 2015 1:52:59 AM",
"dateFinished": "Sep 22, 2020 7:23:53 AM",
"dateStarted": "Sep 22, 2020 7:23:32 AM",
"dateUpdated": "Sep 22, 2020 7:30:04 AM",
"id": "20150210-015259_1403135953",
"jobName": "paragraph_1423500779206_-1502780787",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"data": "\u001b[33mwarning: \u001b[0mthere was one deprecation warning; re-run with -deprecation for details\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 = ParallelCollectionRDD[0] at parallelize at <console>:24\ndefined class Bank\n\u001b[1m\u001b[34mbank\u001b[0m: \u001b[1m\u001b[32morg.apache.spark.sql.DataFrame\u001b[0m = [age: int, job: string ... 3 more fields]\n",
"type": "TEXT"
}
]
},
"runtimeInfos": {},
"settings": {
"forms": {},
"params": {}
},
"status": "FINISHED",
"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't need create them manually\n\n// load bank data\nval bankText = 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 = bankText.map(s => s.split(\";\")).filter(s => s(0) != \"\\\"age\\\"\").map(\n s => 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\")\nbank.groupBy(\"\")",
"title": "Load data into table",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 4.0,
"editorMode": "ace/mode/sql",
"editorSetting": {
"completionKey": "TAB",
"completionSupport": true,
"editOnDblClick": false,
"language": "sql"
},
"enabled": true,
"fontSize": 9.0,
"results": [
{
"graph": {
"commonSetting": {},
"groups": [],
"height": 366.0,
"keys": [
{
"aggr": "sum",
"index": 0.0,
"name": "age"
}
],
"mode": "multiBarChart",
"optionOpen": false,
"setting": {
"multiBarChart": {
"rotate": {
"degree": "-45"
},
"xLabelStatus": "default"
}
},
"values": [
{
"aggr": "sum",
"index": 1.0,
"name": "value"
}
]
},
"helium": {}
}
]
},
"dateCreated": "Feb 10, 2015 1:53:02 AM",
"dateFinished": "Sep 22, 2020 7:23:59 AM",
"dateStarted": "Sep 22, 2020 7:23:53 AM",
"dateUpdated": "Sep 22, 2020 7:23:53 AM",
"id": "20150210-015302_1492795503",
"jobName": "paragraph_1423500782552_-1439281894",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"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",
"type": "TABLE"
}
]
},
"runtimeInfos": {
"jobUrl": {
"group": "spark",
"interpreterSettingId": "spark",
"label": "SPARK JOB",
"propertyName": "jobUrl",
"tooltip": "View in Spark web UI",
"values": [
{
"jobUrl": "http://edge.example.com:4040/jobs/job?id=0"
}
]
}
},
"settings": {
"forms": {},
"params": {}
},
"status": "FINISHED",
"text": "%sql \nselect age, count(1) value\nfrom bank \nwhere age < 30 \ngroup by age \norder by age",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 4.0,
"editorMode": "ace/mode/sql",
"editorSetting": {
"completionKey": "TAB",
"completionSupport": true,
"editOnDblClick": false,
"language": "sql"
},
"enabled": true,
"fontSize": 9.0,
"results": [
{
"graph": {
"commonSetting": {},
"groups": [],
"height": 294.0,
"keys": [
{
"aggr": "sum",
"index": 0.0,
"name": "age"
}
],
"mode": "multiBarChart",
"optionOpen": false,
"setting": {
"multiBarChart": {
"rotate": {
"degree": "-45"
},
"xLabelStatus": "default"
}
},
"values": [
{
"aggr": "sum",
"index": 1.0,
"name": "value"
}
]
},
"helium": {}
}
]
},
"dateCreated": "Feb 12, 2015 2:54:04 PM",
"dateFinished": "Sep 22, 2020 7:24:01 AM",
"dateStarted": "Sep 22, 2020 7:23:59 AM",
"dateUpdated": "Sep 22, 2020 7:24:02 AM",
"id": "20150212-145404_867439529",
"jobName": "paragraph_1423720444030_-1424110477",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"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",
"type": "TABLE"
}
]
},
"runtimeInfos": {
"jobUrl": {
"group": "spark",
"interpreterSettingId": "spark",
"label": "SPARK JOB",
"propertyName": "jobUrl",
"tooltip": "View in Spark web UI",
"values": [
{
"jobUrl": "http://edge.example.com:4040/jobs/job?id=1"
}
]
}
},
"settings": {
"forms": {
"maxAge": {
"defaultValue": "30",
"displayName": "maxAge",
"hidden": false,
"name": "maxAge"
}
},
"params": {
"bdtMeta": {
"inlay": {
"state": {
"chart": {
"axes": {
"mergeYAxes": true
},
"series": [
{
"bars": [
{
"column": "value",
"index": 1.0,
"modifier": "Sum"
}
],
"categories": {
"column": "age",
"index": 0.0,
"modifier": "GroupAndSort"
},
"type": "Bar"
}
]
},
"currentPage": "Chart"
}
}
},
"maxAge": "35"
}
},
"status": "FINISHED",
"text": "%sql \nselect age, count(1) value \nfrom bank \nwhere age < ${maxAge=30} \ngroup by age \norder by age",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 4.0,
"editorMode": "ace/mode/sql",
"editorSetting": {
"completionKey": "TAB",
"completionSupport": true,
"editOnDblClick": false,
"language": "sql"
},
"enabled": true,
"fontSize": 9.0,
"results": [
{
"graph": {
"commonSetting": {},
"groups": [],
"height": 280.0,
"keys": [
{
"aggr": "sum",
"index": 0.0,
"name": "age"
}
],
"mode": "stackedAreaChart",
"optionOpen": false,
"setting": {
"stackedAreaChart": {
"rotate": {
"degree": "-45"
},
"xLabelStatus": "default"
}
},
"values": [
{
"aggr": "sum",
"index": 1.0,
"name": "value"
}
]
},
"helium": {}
}
],
"runOnSelectionChange": true
},
"dateCreated": "Feb 13, 2015 11:04:22 PM",
"dateFinished": "Sep 22, 2020 7:24:02 AM",
"dateStarted": "Sep 22, 2020 7:24:01 AM",
"dateUpdated": "Sep 22, 2020 7:24:01 AM",
"id": "20150213-230422_1600658137",
"jobName": "paragraph_1423836262027_-210588283",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"data": "age\tvalue\n19\t4\n20\t3\n21\t7\n22\t9\n23\t17\n24\t13\n25\t33\n26\t56\n27\t64\n28\t78\n29\t56\n30\t92\n31\t86\n32\t105\n33\t61\n34\t75\n35\t46\n36\t50\n37\t43\n38\t44\n39\t30\n40\t25\n41\t19\n42\t23\n43\t21\n44\t20\n45\t15\n46\t14\n47\t12\n48\t12\n49\t11\n50\t8\n51\t6\n52\t9\n53\t4\n55\t3\n56\t3\n57\t2\n58\t7\n59\t2\n60\t5\n66\t2\n69\t1\n",
"type": "TABLE"
}
]
},
"runtimeInfos": {
"jobUrl": {
"group": "spark",
"interpreterSettingId": "spark",
"label": "SPARK JOB",
"propertyName": "jobUrl",
"tooltip": "View in Spark web UI",
"values": [
{
"jobUrl": "http://edge.example.com:4040/jobs/job?id=2"
}
]
}
},
"settings": {
"forms": {
"marital": {
"defaultValue": "single",
"displayName": "marital",
"hidden": false,
"name": "marital",
"options": [
{
"value": "single"
},
{
"value": "divorced"
},
{
"value": "married"
}
]
}
},
"params": {
"marital": "single"
}
},
"status": "FINISHED",
"text": "%sql \nselect age, count(1) value \nfrom bank \nwhere marital=\"${marital=single,single|divorced|married}\" \ngroup by age \norder by age",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 12.0,
"editorHide": true,
"editorMode": "ace/mode/markdown",
"editorSetting": {
"editOnDblClick": true,
"language": "markdown"
},
"enabled": true,
"results": [
{
"graph": {
"height": 300.0,
"mode": "table",
"optionOpen": false
}
}
],
"tableHide": false
},
"dateCreated": "Feb 13, 2015 11:04:28 PM",
"dateFinished": "Sep 22, 2020 7:24:02 AM",
"dateStarted": "Sep 22, 2020 7:24:02 AM",
"dateUpdated": "Sep 22, 2020 7:24:02 AM",
"id": "20150213-230428_1231780373",
"jobName": "paragraph_1423836268492_216498320",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"data": "<div class=\"markdown-body\">\n<h2>Congratulations, it&rsquo;s done.</h2>\n<h5>You can create your own notebook in &lsquo;Notebook&rsquo; menu. Good luck!</h5>\n\n</div>",
"type": "HTML"
}
]
},
"runtimeInfos": {},
"settings": {
"forms": {},
"params": {}
},
"status": "FINISHED",
"text": "%md\n## Congratulations, it's done.\n##### You can create your own notebook in 'Notebook' menu. Good luck!",
"user": "anonymous"
},
{
"apps": [],
"config": {
"colWidth": 12.0,
"editorHide": true,
"editorMode": "ace/mode/markdown",
"editorSetting": {
"editOnDblClick": true,
"language": "markdown"
},
"enabled": true,
"results": [
{
"graph": {
"height": 300.0,
"mode": "table",
"optionOpen": false
}
}
],
"tableHide": false
},
"dateCreated": "Mar 26, 2015 9:46:58 PM",
"dateFinished": "Sep 22, 2020 7:24:02 AM",
"dateStarted": "Sep 22, 2020 7:24:02 AM",
"dateUpdated": "Sep 22, 2020 7:24:02 AM",
"id": "20150326-214658_12335843",
"jobName": "paragraph_1427420818407_872443482",
"progressUpdateIntervalMs": 500,
"results": {
"code": "SUCCESS",
"msg": [
{
"data": "<div class=\"markdown-body\">\n<p>About bank data</p>\n<pre><code>Citation 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'2011, 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</code></pre>\n\n</div>",
"type": "HTML"
}
]
},
"runtimeInfos": {},
"settings": {
"forms": {},
"params": {}
},
"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'2011, 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"
},
{
"apps": [],
"config": {},
"dateCreated": "Jul 3, 2015 1:30:47 PM",
"dateUpdated": "Sep 22, 2020 7:24:02 AM",
"id": "20150703-133047_853701097",
"jobName": "paragraph_1435955447812_-158639899",
"progressUpdateIntervalMs": 500,
"runtimeInfos": {},
"settings": {
"forms": {},
"params": {}
},
"status": "FINISHED",
"text": "",
"user": "anonymous"
}
],
"path": "/Spark Tutorial/2. Spark Basic Features"
},
"message": "",
"status": "OK"
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment