StarMirror/data-science-ipython-notebooks
1
0
Fork 0
mirror of https://github.com/donnemartin/data-science-ipython-notebooks.git synced 2024-03-22 13:30:56 +08:00
Code Issues Projects Releases Wiki Activity

Added Spark broadcast variables snippets.

Browse Source
This commit is contained in:
Donne Martin 2015-03-30 19:01:07 -04:00
parent b3fb4ae219
commit 7195c5bc82
1 changed files with 52 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
spark/spark.ipynb
View File

@ -1,7 +1,7 @@
{
"metadata": {
"name": "",
"signature": "sha256:0fb24b809c8caadd2f68f7898036387e846da3f839a97e63be9a65aa17f3dbb1"
"signature": "sha256:cf2651f340403267ecf82871c01a4f9deb80df25b8345be4f56dc02db970a5a7"
},
"nbformat": 3,
"nbformat_minor": 0,
@ -25,7 +25,8 @@
"* Writing and Running a Spark Application\n",
"* Configuring Spark Applications\n",
"* Streaming\n",
"* Streaming with States"
"* Streaming with States\n",
"* Broadcast Variables"
]
},
{
@ -1080,18 +1081,65 @@
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Broadcast Variables"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Read in list of items to broadcast from a local file:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"input": [
"broadcast_file = \"broadcast.txt\"\n",
"broadcast_list = list(map(lambda l: l.strip(), open(broadcast_file)))"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Broadcast the target list to all workers:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"input": [
"broadcast_list_sc = sc.broadcast(broadcast_list)"
],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Filter based on the broadcast list:"
]
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"log_file = \"hdfs://localhost/user/logs/*\"\n",
"filtered_data = sc.textFile(log_file)\\\n",
" .filter(lambda line: any(item in line for item in broadcast_list_sc.value))\n",
"\n",
"filtered_data.take(10)"
],
"language": "python",
"metadata": {},
"outputs": []