Instantly share code, notes, and snippets.

View ms-regionen.md
View flatten.py
#!/usr/bin/env python3
import flatten_json
import sys
import json
if __name__ == '__main__':
if len(sys.argv) < 3:
print(f'usage: {sys.argv[0]} in.csv out.csv')
f_out = open(sys.argv[2], 'w')
View getting-started-with-superset-airbnb-data-exploration-platform.md

Getting Started With Superset: Airbnb’s data exploration platform

These instructions are for Amazon Linux Version 2

Update Python and PIP versions on EC2 (Amazon AMI)

sudo yum update -y
sudo yum install python3 -y
View ami-mappings.yaml
Mappings:
RegionMap:
ap-south-1:
"AMALINUX" : "ami-531a4c3c"
eu-west-3:
"AMALINUX" : "ami-8ee056f3"
eu-west-2:
"AMALINUX" : "ami-403e2524"
eu-west-1:
"AMALINUX" : "ami-d834aba1"
View scanbd.conf
/*
* $Id: scanbd.conf 213 2015-10-05 06:52:50Z wimalopaan $
*
* scanbd - KMUX scanner button daemon
*
* Copyright (C) 2008 - 2015 Wilhelm Meier (wilhelm.meier@fh-kl.de)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
View scanbd.conf
global {
# log to console. put to 'false' once you're done with testing
debug = true
# 1=error, 2=warn, 3=info, 4-7=debug
# 3 was sufficient for me (shows when script is triggered)
debug-level = 3
scriptdir = /etc/scanbd/scripts
View memleak.py
import time
import tracemalloc
import pympler.muppy, pympler.summary
import gc
import sys
tracemalloc.start()
collection = []
start = time.time()
View interval_count.py
import datetime
with open("myfile.csv") as f:
window_from = None
window_to = None
warm = cold = 0
for line in f:
milliseconds, topics = line.split(",")
if milliseconds == 'milliseconds':
continue
View test_min_value.sh
min=40000
for i in {1..10000}; do
a=$(./test)
min=$((a<min?a:min));
done
echo $min
View queue_and_workers_read_file_example.py
import multiprocessing
import queue
import time
def worker(input, output):
for line in iter(input.get, None):
output.put(len(line))
if __name__ == '__main__':
num_processes = 3