Files
docker-stacks/all-spark-notebook/test/data/local_toree.ipynb
Romain c83024c950 Add spark notebook tests and change examples
* Test added for all kernels
* Same examples as provided in the documentation (`specifics.md`)
* Used the same use case for all examples: sum of the first 100 whole numbers

Note: I've not automatically tested `local_sparklyr.ipynb` since it creates by default the `metastore_db` dir and the `derby.log` file in the working directory. Since I mount it in `RO` it's not working. I'm struggling to set it elsewhere...
2020-05-29 06:54:46 +02:00

89 lines
1.6 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Waiting for a Spark session to start..."
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"spark://master:7077\n"
]
}
],
"source": [
"// should print the value of --master in the kernel spec\n",
"println(sc.master)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Waiting for a Spark session to start..."
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"rdd = ParallelCollectionRDD[0] at parallelize at <console>:28\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/plain": [
"5050.0"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"// Sum of the first 100 whole numbers\n",
"val rdd = sc.parallelize(0 to 100)\n",
"rdd.sum()\n",
"// 5050"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Apache Toree - Scala",
"language": "scala",
"name": "apache_toree_scala"
},
"language_info": {
"codemirror_mode": "text/x-scala",
"file_extension": ".scala",
"mimetype": "text/x-scala",
"name": "scala",
"pygments_lexer": "scala",
"version": "2.11.12"
}
},
"nbformat": 4,
"nbformat_minor": 4
}