Created
August 1, 2019 20:48
-
-
Save roaramburu/2c2839241252141ceec810d58b9fed29 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"from blazingsql import BlazingContext\n", | |
"import cudf\n", | |
"import dask_cudf\n", | |
"import dask\n", | |
"from dask.distributed import Client" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"client = Client('127.0.0.1:8786')\n", | |
"bc = BlazingContext(dask_client=client)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"# Use HDFS\n", | |
"bc.hdfs('bsql_data', host='35.203.181.221', port=54310, user='hadoop')\n", | |
"table_list = ['hdfs://bsql_data/netflow_parquet/1_0_0.parquet', 'hdfs://bsql_data/netflow_parquet/1_1_0.parquet', 'hdfs://bsql_data/netflow_parquet/1_2_0.parquet', 'hdfs://bsql_data/netflow_parquet/1_3_0.parquet']" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"bc.create_table('netflow', table_list)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"result = bc.sql('''SELECT\n", | |
" a.firstSeenSrcIp as source,\n", | |
" a.firstSeenDestIp as destination,\n", | |
" count(a.firstSeenDestPort) as targetPorts,\n", | |
" SUM(a.firstSeenSrcTotalBytes) as bytesOut,\n", | |
" SUM(a.firstSeenDestTotalBytes) as bytesIn,\n", | |
" SUM(a.durationSeconds) as durationSeconds,\n", | |
" MIN(parsedDate) as firstFlowDate,\n", | |
" MAX(parsedDate) as lastFlowDate,\n", | |
" COUNT(*) as attemptCount\n", | |
" FROM\n", | |
" main.netflow a\n", | |
" GROUP BY\n", | |
" a.firstSeenSrcIp,\n", | |
" a.firstSeenDestIp''').get()\n", | |
"\n", | |
"print(result.head())" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.7.3" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment