mittenchops’s gists

mittenchops / alldigits.py

Created February 12, 2014 19:45

regexes for a number with an optional decimal place+decimal digits

	# It took 15 tries.
	digits = re.findall(r'[0-9]+', cleaned_text)
	digits2 = re.findall(r'[0-9]\d*(\.\d+)?', cleaned_text)
	digits3 = re.findall(r'[0-9]+((\.([0-9]+))?', cleaned_text)
	digits4 = re.findall(r'[0-9]+(\.)?([0-9]+)?', cleaned_text)
	digits5 = re.findall(r'\d+\.?\d*?', cleaned_text)
	digits6 = re.findall(r'\d+(\.\d*)?', cleaned_text)
	digits7 = re.findall(r'\d+(\.?\d*)?', cleaned_text)
	digits8 = re.findall(r'\d+(\.?\d*)', cleaned_text)
	digits9 = re.findall(r'\d+(\.{1}\d*)?', cleaned_text)

mittenchops / htmlclean.py

Created February 9, 2014 18:45

HTML Cleaner

	import requests
	from lxml.html.clean import Cleaner

	url = "http://en.wikipedia.org/wiki/Zipf%27s_law"
	html = requests.get(url).text
	cleaner = Cleaner(allow_tags=[''], remove_unknown_tags=False, remove_tags=['<div>','</div>'])
	cleaner.scripts = True
	cleaner.page_structure = True
	cleaner.javascript = True
	cleaner.style = True

mittenchops / rsplit.R

Created February 6, 2014 21:57

rsplit for R

	rsplit <- function(mydf, chr){
	sapply(sapply(mydf, strsplit,chr, USE.NAMES=F),function(x){x[length(x)]})
	}

	# USAGE
	# val <- rsplit(df$long_url,"/")

mittenchops / count_hist.sh

Created February 4, 2014 20:45

Count unique urls where url is the first field in a json, get the top 10 repeats

cat file.json | awk '{print $2}' | sort | uniq -c | sort -rn | head

mittenchops / to_acronym.sh

Last active January 4, 2016 01:58

sed to turn text to acronyms

	# from http://ask.metafilter.com/255675/Decoding-cancer-addled-ramblings
	sed 's/\B\w*//g;s/\s//g' full_file.txt > acronym_file.txt

mittenchops / emacs.txt

Last active January 2, 2016 00:59

emacs review!

	# navigation
	C-a # beginning of line
	C-e # end of line
	M-> # eof
	M-< # head of file
	M-g g 100 # goto line 100

	# general
	C-h f thing-name # describe a function named thing-name
	M-x load-library RET icicles RET

mittenchops / defaultdictionaries.py

Created December 20, 2013 17:04

Function defaults done correctly in python

	"""
	# In addition, the use of mutable objects as default values may lead to unintended behavior:

	def foo(x, items=[]):
	items.append(x)
	return items
	foo(1) # returns [1]
	foo(2) # returns [1, 2]
	foo(3) # returns [1, 2, 3]

mittenchops / phoneparser.py

Created October 11, 2013 20:13

Useful phone number parser. Clean to USA!

	# all straight from here:
	# https://github.com/daviddrysdale/python-phonenumbers

	import phonenumbers

	def numberizer(num):
	z = phonenumbers.parse(num,"US")
	return(phonenumbers.format_number(z,phonenumbers.PhoneNumberFormat.NATIONAL))

mittenchops / argmax.py

Last active December 25, 2015 07:19

argmax function: return the entry from list X where the argument arg is at a maximum.

	def argmax(arg, X):
	"""
	>>> zee = [{"cool":{"stuff":1,"things":0.5}},{"cool":{"stuff":2,"things":0.25}}]
	>>> argmax("cool.stuff",zee)
	{'cool': {'things': 0.25, 'stuff': 2}}
	>>> argmax("cool.things",zee)
	{'cool': {'things': 0.5, 'stuff': 1}}
	"""
	ranked = sorted(X, key=lambda x: -getByDot(x,arg))
	leader = filter(lambda x: getByDot(x,arg) == reduce(max,[getByDot(r, arg) for r in ranked]),ranked)[0]

mittenchops / unicodesolved.py

Created October 9, 2013 19:47

encoding fixed everywhere. Start every file with this to ensure that both interactive and script-mode always work.

	#!/usr/bin/env python
	# -- coding: utf-8 --

	######################################
	#### THIS IS IMPORTANT EVERYWHERE ####
	import sys #
	reload(sys) #
	sys.setdefaultencoding("UTF-8") #
	#sys.getdefaultencoding() #
	######################################

adam mittenchops