Created
October 11, 2017 10:57
-
-
Save marco-c/c2055ae58a238faa80c93b0f733a6357 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": 1, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"from datetime import datetime, timedelta\n", | |
"from pyspark.sql import functions" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"num_days = 14\n", | |
"days = [datetime.utcnow().date() - timedelta(1) - timedelta(i) for i in range(0, num_days)]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 3, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [], | |
"source": [ | |
"dataset = SQLContext(sc).read.load(['s3://telemetry-parquet/socorro_crash/v2/crash_date=' + day.strftime('%Y%m%d') for day in days], 'parquet')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 4, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [ | |
"dataset = dataset\\\n", | |
".filter((dataset['product'] == 'Firefox') & (functions.instr(dataset['signature'], 'onepin-opensc-pkcs11.dll') != 0))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 5, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"658" | |
] | |
}, | |
"execution_count": 5, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dataset.count()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 6, | |
"metadata": { | |
"collapsed": false | |
}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[(u'0.15.0.0', 625), (u'0.14.0.0', 32), (u'0.12.5361.1102', 1)]" | |
] | |
}, | |
"execution_count": 6, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"dataset\\\n", | |
".select(functions.explode(dataset['json_dump']['modules']).alias('module')).rdd\\\n", | |
".filter(lambda v: 'onepin-opensc-pkcs11.dll' in v['module']['filename'].lower())\\\n", | |
".map(lambda v: (v['module']['version'], 1))\\\n", | |
".reduceByKey(lambda x, y: x + y)\\\n", | |
".sortBy(lambda v: v[1], ascending=False)\\\n", | |
".collect()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"collapsed": true | |
}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"metadata": { | |
"anaconda-cloud": {}, | |
"kernelspec": { | |
"display_name": "Python [default]", | |
"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": "2.7.12" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 0 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment