From 35966dd54445ede72d155d7ec130d5c2b16b3b94 Mon Sep 17 00:00:00 2001
From: Jonathan Kelly <jonathak@amazon.com>
Date: Mon, 20 Apr 2015 17:35:38 -0700
Subject: [PATCH] ZEPPELIN-55. Use HDFS in tutorial notebook so that it works
 with yarn-client

---
 notebook/2A94M5J1Z/note.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/notebook/2A94M5J1Z/note.json b/notebook/2A94M5J1Z/note.json
index d3b73b51f45..ab3701a97d4 100644
--- a/notebook/2A94M5J1Z/note.json
+++ b/notebook/2A94M5J1Z/note.json
@@ -34,7 +34,7 @@
     },
     {
       "title": "Prepare data",
-      "text": "import sys.process._\n//you will need \u0027wget\u0027 tool to download\n\"wget http://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip\" !\n\"mkdir data\" !\n\"unzip bank.zip -d data\" !\n\"rm bank.zip\" !",
+      "text": "import sys.process._\n\"rm -rf data bank.zip\" !\n//you will need \u0027wget\u0027 tool to download\n\"wget http://archive.ics.uci.edu/ml/machine-learning-databases/00222/bank.zip\" !\n\"rm -rf data\" !\n\"mkdir data\" !\n\"unzip bank.zip -d data\" !\n\"hdfs dfs -rm -r /user/zeppelin/data\" !\n\"hdfs dfs -copyFromLocal data /user/zeppelin\" !",
       "config": {
         "colWidth": 12.0,
         "graph": {
@@ -67,7 +67,7 @@
     },
     {
       "title": "Load data into table",
-      "text": "import sys.process._\n// sc is an existing SparkContext.\nval sqlContext \u003d new org.apache.spark.sql.SQLContext(sc)\n\n\nval zeppelinHome \u003d (\"pwd\" !!).replace(\"\\n\", \"\")\nval bankText \u003d sc.textFile(s\"$zeppelinHome/data/bank-full.csv\")\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\")\n\n",
+      "text": "// sc is an existing SparkContext.\nval sqlContext \u003d new org.apache.spark.sql.SQLContext(sc)\nval bankText \u003d sc.textFile(s\"hdfs:///user/zeppelin/data/bank-full.csv\")\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\")\n\n",
       "config": {
         "colWidth": 12.0,
         "graph": {