Elgato_dark/zeppelin
1
0
Fork 0
mirror of https://github.com/apache/zeppelin synced 2026-05-24 09:38:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Add pig tutorial note

Browse source
This commit is contained in:
Jeff Zhang 2017-01-01 21:47:54 +08:00
parent 25216f8090
commit 88385f27bb
2 changed files with 327 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/interpreter/pig.md
View file

@ -99,4 +99,4 @@ c = group b by Category;
foreach c generate group as category, COUNT($1) as count;
```
Data is shared between `%pig` and `%pig.query`, so that you can do some common work in `%pig`, and do different kinds of query based on the data of `%pig`.
Data is shared between `%pig` and `%pig.query`, so that you can do some common work in `%pig`, and do different kinds of query based on the data of `%pig`. There's one pig tutorial note in zeppelin for your reference.

326
notebook/2C7BDKAHN/note.json Normal file
View file

@ -0,0 +1,326 @@
{
"paragraphs": [
{
"text": "%md\n\nThis pig tutorial use pig to do the same thing as spark tutorial.\n",
"user": "user1",
"dateUpdated": "Jan 1, 2017 9:43:30 PM",
"config": {
"colWidth": 12.0,
"enabled": true,
"results": {},
"editorSetting": {
"language": "markdown",
"editOnDblClick": true
},
"editorMode": "ace/mode/markdown",
"editorHide": true,
"tableHide": false
},
"settings": {
"params": {},
"forms": {}
},
"results": {
"code": "SUCCESS",
"msg": [
{
"type": "HTML",
"data": "\u003cdiv class\u003d\"markdown-body\"\u003e\n\u003cp\u003eThis pig tutorial use pig to do the same thing as spark tutorial.\u003c/p\u003e\n\u003c/div\u003e"
}
]
},
"apps": [],
"jobName": "paragraph_1483278047624_1595771060",
"id": "20170101-214047_1432767446",
"dateCreated": "Jan 1, 2017 9:40:47 PM",
"dateStarted": "Jan 1, 2017 9:43:30 PM",
"dateFinished": "Jan 1, 2017 9:43:31 PM",
"status": "FINISHED",
"progressUpdateIntervalMs": 500
},
{
"text": "%sh\n\nwget https://s3.amazonaws.com/apache-zeppelin/tutorial/bank/bank.csv\nhadoop fs -put bank.csv .\n\n",
"user": "user1",
"dateUpdated": "Jan 1, 2017 9:46:58 PM",
"config": {
"colWidth": 12.0,
"enabled": true,
"results": {},
"editorSetting": {
"language": "sh",
"editOnDblClick": false
},
"editorMode": "ace/mode/sh"
},
"settings": {
"params": {},
"forms": {}
},
"apps": [],
"jobName": "paragraph_1483278233939_-1920020061",
"id": "20170101-214353_1707095371",
"dateCreated": "Jan 1, 2017 9:43:53 PM",
"dateStarted": "Jan 1, 2017 9:46:58 PM",
"dateFinished": "Jan 1, 2017 9:47:03 PM",
"status": "FINISHED",
"errorMessage": "",
"progressUpdateIntervalMs": 500
},
{
"text": "%pig\n\nbankText \u003d load \u0027bank.csv\u0027 using PigStorage(\u0027;\u0027);\nbank \u003d foreach bankText generate $0 as age, $1 as job, $2 as marital, $3 as education, $5 as balance; \nbank \u003d filter bank by age !\u003d \u0027\"age\"\u0027;\nbank \u003d foreach bank generate (int)age, REPLACE(job,\u0027\"\u0027,\u0027\u0027) as job, REPLACE(marital, \u0027\"\u0027, \u0027\u0027) as marital, (int)(REPLACE(balance, \u0027\"\u0027, \u0027\u0027)) as balance;\n\n-- The following statement is optional, it depends on your needs.\n-- store bank into \u0027clean_bank.csv\u0027 using PigStorage(\u0027;\u0027);\n",
"user": "user1",
"dateUpdated": "Jan 2, 2017 11:41:21 AM",
"config": {
"colWidth": 12.0,
"enabled": true,
"results": {},
"editorSetting": {
"language": "pig",
"editOnDblClick": false
},
"editorMode": "ace/mode/pig"
},
"settings": {
"params": {},
"forms": {}
},
"results": {
"code": "SUCCESS",
"msg": []
},
"apps": [],
"jobName": "paragraph_1482905200045_-1233984644",
"id": "20161228-140640_1560978333",
"dateCreated": "Dec 28, 2016 2:06:40 PM",
"dateStarted": "Jan 2, 2017 11:41:21 AM",
"dateFinished": "Jan 2, 2017 11:41:23 AM",
"status": "FINISHED",
"progressUpdateIntervalMs": 500
},
{
"text": "%pig.query\n\nbank_data \u003d filter bank by age \u003c 30;\nb \u003d group bank_data by age;\nforeach b generate group as age, COUNT($1) as count;\n\n",
"user": "user1",
"dateUpdated": "Jan 2, 2017 11:41:34 AM",
"config": {
"colWidth": 4.0,
"enabled": true,
"results": {
"0": {
"graph": {
"mode": "multiBarChart",
"height": 300.0,
"optionOpen": false
},
"helium": {}
}
},
"editorSetting": {
"language": "pig",
"editOnDblClick": false
},
"editorMode": "ace/mode/pig"
},
"settings": {
"params": {},
"forms": {}
},
"results": {
"code": "SUCCESS",
"msg": [
{
"type": "TABLE",
"data": "age\tcount\n19\t4\n20\t3\n21\t7\n22\t9\n23\t20\n24\t24\n25\t44\n26\t77\n27\t94\n28\t103\n29\t97\n"
}
]
},
"apps": [],
"jobName": "paragraph_1482905250090_1355268184",
"id": "20161228-140730_1903342877",
"dateCreated": "Dec 28, 2016 2:07:30 PM",
"dateStarted": "Jan 2, 2017 11:41:34 AM",
"dateFinished": "Jan 2, 2017 11:41:35 AM",
"status": "FINISHED",
"progressUpdateIntervalMs": 500
},
{
"text": "%pig.query\n\nbank_data \u003d filter bank by age \u003c ${maxAge\u003d40};\nb \u003d group bank_data by age;\nforeach b generate group as age, COUNT($1) as count;",
"user": "user1",
"dateUpdated": "Jan 2, 2017 11:41:30 AM",
"config": {
"colWidth": 4.0,
"enabled": true,
"results": {
"0": {
"graph": {
"mode": "pieChart",
"height": 300.0,
"optionOpen": false
},
"helium": {}
}
},
"editorSetting": {
"language": "pig",
"editOnDblClick": false
},
"editorMode": "ace/mode/pig"
},
"settings": {
"params": {
"maxAge": "36"
},
"forms": {
"maxAge": {
"name": "maxAge",
"defaultValue": "40",
"hidden": false
}
}
},
"results": {
"code": "SUCCESS",
"msg": [
{
"type": "TABLE",
"data": "age\tcount\n19\t4\n20\t3\n21\t7\n22\t9\n23\t20\n24\t24\n25\t44\n26\t77\n27\t94\n28\t103\n29\t97\n30\t150\n31\t199\n32\t224\n33\t186\n34\t231\n35\t180\n"
}
]
},
"apps": [],
"jobName": "paragraph_1482911358985_1722452666",
"id": "20161228-154918_1551591203",
"dateCreated": "Dec 28, 2016 3:49:18 PM",
"dateStarted": "Jan 2, 2017 11:41:30 AM",
"dateFinished": "Jan 2, 2017 11:41:31 AM",
"status": "FINISHED",
"progressUpdateIntervalMs": 500
},
{
"text": "%pig.query\n\nbank_data \u003d filter bank by marital\u003d\u003d\u0027${marital\u003dsingle,single|divorced|married}\u0027;\nb \u003d group bank_data by age;\nforeach b generate group as age, COUNT($1) as count;\n\n\n\n",
"user": "user1",
"dateUpdated": "Jan 2, 2017 11:42:11 AM",
"config": {
"colWidth": 4.0,
"enabled": true,
"results": {
"0": {
"graph": {
"mode": "scatterChart",
"height": 300.0,
"optionOpen": false,
"setting": {
"stackedAreaChart": {
"style": "stack"
}
},
"commonSetting": {},
"keys": [
{
"name": "group",
"index": 0.0,
"aggr": "sum"
}
],
"groups": [],
"values": [
{
"name": "null",
"index": 1.0,
"aggr": "sum"
}
]
},
"helium": {}
}
},
"editorSetting": {
"language": "pig",
"editOnDblClick": false
},
"editorMode": "ace/mode/pig"
},
"settings": {
"params": {
"marital": "married"
},
"forms": {
"marital": {
"name": "marital",
"defaultValue": "single",
"options": [
{
"value": "single"
},
{
"value": "divorced"
},
{
"value": "married"
}
],
"hidden": false
}
}
},
"results": {
"code": "SUCCESS",
"msg": [
{
"type": "TABLE",
"data": "age\tcount\n23\t3\n24\t11\n25\t11\n26\t18\n27\t26\n28\t23\n29\t37\n30\t56\n31\t104\n32\t105\n33\t103\n34\t142\n35\t109\n36\t117\n37\t100\n38\t99\n39\t88\n40\t105\n41\t97\n42\t91\n43\t79\n44\t68\n45\t76\n46\t82\n47\t78\n48\t91\n49\t87\n50\t74\n51\t63\n52\t66\n53\t75\n54\t56\n55\t68\n56\t50\n57\t78\n58\t67\n59\t56\n60\t36\n61\t15\n62\t5\n63\t7\n64\t6\n65\t4\n66\t7\n67\t5\n68\t1\n69\t5\n70\t5\n71\t5\n72\t4\n73\t6\n74\t2\n75\t3\n76\t1\n77\t5\n78\t2\n79\t3\n80\t6\n81\t1\n83\t2\n86\t1\n87\t1\n"
}
]
},
"apps": [],
"jobName": "paragraph_1482906179178_-901386451",
"id": "20161228-142259_575675591",
"dateCreated": "Dec 28, 2016 2:22:59 PM",
"dateStarted": "Jan 2, 2017 11:41:27 AM",
"dateFinished": "Jan 2, 2017 11:41:28 AM",
"status": "FINISHED",
"progressUpdateIntervalMs": 500
},
{
"text": "%pig\n",
"dateUpdated": "Dec 28, 2016 3:50:36 PM",
"config": {},
"settings": {
"params": {},
"forms": {}
},
"apps": [],
"jobName": "paragraph_1482911436320_-1651936394",
"id": "20161228-155036_1854903164",
"dateCreated": "Dec 28, 2016 3:50:36 PM",
"status": "READY",
"progressUpdateIntervalMs": 500
}
],
"name": "Zeppelin Tutorial/Pig Tutorial",
"id": "2C7BDKAHN",
"angularObjects": {
"2C3DR183X:shared_process": [],
"2C5VH924X:shared_process": [],
"2C686X8ZH:shared_process": [],
"2C66Z9XPQ:shared_process": [],
"2C3JKFMJU:shared_process": [],
"2C69WE69N:shared_process": [],
"2C3RWCVAG:shared_process": [],
"2C4HKDCQW:shared_process": [],
"2C4BJDRRZ:shared_process": [],
"2C6V3D44K:shared_process": [],
"2C3VECEG2:shared_process": [],
"2C5SRRXHM:shared_process": [],
"2C5DCRVGM:shared_process": [],
"2C66GE1VB:shared_process": [],
"2C3PTPMUH:shared_process": [],
"2C48Y7FSJ:shared_process": [],
"2C4ZD49PF:shared_process": [],
"2C63XW4XE:shared_process": [],
"2C4UB1UZA:shared_process": [],
"2C5S1R21W:shared_process": [],
"2C3SQSB7V:shared_process": []
},
"config": {},
"info": {}
}