Skip to content

Instantly share code, notes, and snippets.

@danielfrg
Created April 23, 2018 21:47
Show Gist options
  • Save danielfrg/e63a2bc6ba5b872d56b71e1dbd9c9524 to your computer and use it in GitHub Desktop.
Save danielfrg/e63a2bc6ba5b872d56b71e1dbd9c9524 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"Current session configs: <tt>{'conf': {'spark.yarn.appMasterEnv.PYSPARK_PYTHON': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/python', 'spark.yarn.appMasterEnv.PYSPARK_DRIVER_PYTHON': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/python', 'spark.yarn.executorEnv.PYSPARK_PYTHON': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/python', 'spark.pyspark.python': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/python', 'spark.pyspark.driver.python': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/python', 'spark.r.command': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/R', 'spark.r.driver.command': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/Rscript', 'spark.r.shell.command': '/opt/cloudera/parcels/bzrspark-0.1.0/bin/R'}, 'kind': 'sparkr'}</tt><br>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"No active sessions."
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%%configure -f\n",
"{\"conf\": {\"spark.yarn.appMasterEnv.PYSPARK_PYTHON\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/python\",\n",
" \"spark.yarn.appMasterEnv.PYSPARK_DRIVER_PYTHON\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/python\",\n",
" \"spark.yarn.executorEnv.PYSPARK_PYTHON\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/python\",\n",
" \"spark.pyspark.python\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/python\",\n",
" \"spark.pyspark.driver.python\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/python\",\n",
" \"spark.r.command\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/R\",\n",
" \"spark.r.driver.command\": \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/Rscript\",\n",
" \"spark.r.shell.command\" : \"/opt/cloudera/parcels/bzrspark-0.1.0/bin/R\"\n",
" }\n",
"}"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Starting Spark application\n"
]
},
{
"data": {
"text/html": [
"<table>\n",
"<tr><th>ID</th><th>YARN Application ID</th><th>Kind</th><th>State</th><th>Spark UI</th><th>Driver log</th><th>Current session?</th></tr><tr><td>2</td><td>application_1519680446611_0031</td><td>sparkr</td><td>idle</td><td><a target=\"_blank\" href=\"http://ip-172-31-10-169.ec2.internal:8088/proxy/application_1519680446611_0031/\">Link</a></td><td><a target=\"_blank\" href=\"http://ip-172-31-7-137.ec2.internal:8042/node/containerlogs/container_1519680446611_0031_01_000001/centos\">Link</a></td><td>✔</td></tr></table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"SparkContext available as 'sc'.\n",
"SqlContext available as 'sqlContext'.\n",
"Java ref type org.apache.spark.api.java.JavaSparkContext id 0 "
]
}
],
"source": [
"sc"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1] 2"
]
}
],
"source": [
"1+1"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1] \"ip-172-31-7-137.ec2.internal, /yarn/nm/usercache/centos/filecache/76/sparkr.zip, /opt/cloudera/parcels/bzrspark-0.1.0/lib/R/library\""
]
}
],
"source": [
"noop <- function(x) {\n",
" path <- toString(.libPaths())\n",
" host <- toString(Sys.info()['nodename'])\n",
" host_path <- toString(cbind(host,path))\n",
" host_path\n",
"}\n",
"noop(1)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1] \"/yarn/nm/usercache/centos/filecache/76/sparkr.zip, /opt/cloudera/parcels/bzrspark-0.1.0/lib/R/library\""
]
}
],
"source": [
"toString(.libPaths())"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"library(sparklyr)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Attaching package: ‘dplyr’\n",
"\n",
"The following objects are masked from ‘package:SparkR’:\n",
"\n",
" arrange, between, collect, contains, count, cume_dist, dense_rank,\n",
" desc, distinct, explain, filter, first, group_by, intersect, lag,\n",
" last, lead, mutate, n, n_distinct, ntile, percent_rank, rename,\n",
" row_number, sample_frac, select, sql, summarize\n",
"\n",
"The following objects are masked from ‘package:stats’:\n",
"\n",
" filter, lag\n",
"\n",
"The following objects are masked from ‘package:base’:\n",
"\n",
" intersect, setdiff, setequal, union\n"
]
}
],
"source": [
"library(dplyr)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1] \"Error in library(ggplot2): there is no package called ‘ggplot2’\\n----LIVY_END_OF_ERROR----\"\n",
"Warning messages:\n",
"1: In png(\"/yarn/nm/usercache/centos/appcache/application_1519680446611_0031/container_1519680446611_0031_01_000001/tmp/5603796457509368919.png\") :\n",
" unable to load shared object '/opt/cloudera/parcels/bzrspark-0.1.0/lib/R/library/grDevices/libs//cairo.so':\n",
" libXrender.so.1: cannot open shared object file: No such file or directory\n",
"2: In png(\"/yarn/nm/usercache/centos/appcache/application_1519680446611_0031/container_1519680446611_0031_01_000001/tmp/5603796457509368919.png\") :\n",
" failed to load cairo DLL"
]
}
],
"source": [
"library(ggplot2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.11"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment