nickjevershed

#calculate percentage of grouped items

df.groupby(level=0).apply(lambda x: 100*x/float(x.sum()))

#groupby week, assuming day/month/year date order

df = pd.read_csv('values.csv', parse_dates='date', dayfirst='true', index_col='date')
df.resample('w', how='count').to_csv('values.csv')

#transpose a column series to column headers

nickjevershed

user_score,genre1,genre2,studio,title,url,titles_match,year,rtId,indexNo,director,old_title,mpaa_rating,critic_score,lead_actor2,lead_actor1,title-orig,davScore,margScore,dav-marg,combined-score,reviewed-at,url,ratio
93,Drama,Romance,na,Fireworks (Hana-bi),http://www.rottentomatoes.com/m/1091981-fireworks/,no,1997,19686,2366,Takeshi Kitano,Hana-Bi,R,95,Kayoko Kishimoto,Takeshi Kitano,Hana-Bi,5,5,0,10,SBS,,58
76,Drama,Romance,Indiepix,Samson and Delilah,http://www.rottentomatoes.com/m/10011295-samson_and_delilah/,no,2010,770808521,57,Warwick Thornton,Samson & Delilah,Unrated,94,Marissa Gibson,Rowan McNamara,Samson & Delilah,5,5,0,10,ABC,http://www.abc.net.au/atthemovies/txt/s2542612.htm,88
83,Drama,,Warner Independent Pictures,"Good Night, And Good Luck",http://www.rottentomatoes.com/m/1152019-good_night_and_good_luck/,no,2005,8572,55,George Clooney,"Good Night, and Good Luck",PG,93,Patricia Clarkson,David Strathairn,"Good Night, and Good Luck",5,5,0,10,ABC,http://www.abc.net.au/atthemovies/txt/s1532953.htm,10

nickjevershed

import simplejson as json
import requests

#your spreadsheet key here. I'm using an example from the Victorian election campaign

key = "1THJ6MgfEk-1egiPFeDuvs4qEi02xTpz4fq9RtO7GijQ"

#google api request urls - I'm doing the first one just to get nice key values (there's probably a better way to do this)

url1 = "https://spreadsheets.google.com/feeds/cells/" + key + "/od6/public/values?alt=json"

nickjevershed

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

import csv

coalition = ["Chris Pearce","Petro Georgiou","Fran Bailey","Danna Vale","Michael Johnson","Margaret May","Julian McGauran","Mary Jo Fisher","David Hawker","Pat Farmer","Wilson Tuckey","Peter Lindsay","Joanna Gash","Judith Troeth","Alex Somlyay","Alexander Somlyay","Nick Minchin","Nigel Scullion","Alan Ferguson","Russell Trood","Guy Barnett","Chris Back","Eric Abetz","Judith Adams"," Chris Back","Cory Bernardi","Simon Birmingham","Ron Boswell","Ronald Boswell","Sue Boyce","George Brandis","David Bushby","Michaelia Cash","Richard Colbeck","Helen Coonan","Mathias Cormann","Sean Edwards","Alan Eggleston","David Fawcett","Concetta Fierravanti-Wells","Mitch Fifield","Mary Jo Fisher","Bill Heffernan","Gary Humphries","David Johnston","Barnaby Joyce","Helen Kroger","Ian Macdonald","Bridget McKenzie","Brett Mason","Fiona Nash","Marise Payne","Stephen Parry","Michael Ronaldson","Anne Ruston","Scott Ryan","Arthur Sinodinos","Dean Smith","John Williams","Patrick Secker","B

nickjevershed

import csv
import re
 
fList = ['client','detention','detain','manus','nauru','cocos','keeling','christmas','refugee','unaccompanied','humanitarian','minor','staff accomodation','curtin','villawood','scherger','inverbrackie','derby','construction camp','ita','idc','apod','irh','darwin airport','berrimah','bladin','wickham','phosphate','aqua','lilac','maribyrnong','inverbrackie','serco','transfield','g4s','gsl','toll']

nList = ['pontville','CI','weipa','regional','processing','IMA','tamil','farsi','afghanistan','screening','woomera','yongah']

offshore = ['manus', 'nauru']

onshore = ['cocos', 'coco', 'christmas', 'CI', 'phosphate', 'aqua', 'lilac','curtin', 'CIDC', 'villawood', 'VIDC', 'sydney irh', 'woomera', 'WIDC', 'scherger', 'SIDC', 'perth', 'PIDC', 'PIRH', 'yongah', 'maribyrnong', 'MIDC', 'melbourne ITA', 'MITA', 'adelaide ITA', 'AITA', 'inverbrackie', 'brisbane ita', 'BITA', 'DIMA', 'bladin', 'berrimah', 'wickham', 'darwin airport', 'weipa', 'derby', 'NIDC', 'northern immigration detention centre', 'd

nickjevershed

import csv
import re
 
fList = ['client','detention','detain','manus','nauru','cocos','keeling','christmas','refugee','unaccompanied','humanitarian','minor','staff accomodation','curtin','villawood','scherger','inverbrackie','derby','construction camp','ita','idc','apod','irh','darwin airport','berrimah','bladin','wickham','phosphate','aqua','lilac','maribyrnong','inverbrackie','serco','transfield','g4s','gsl','toll']

nList = ['pontville','CI','weipa','regional','processing','IMA','tamil','farsi','afghanistan','screening','woomera','yongah']

with open('immigration-contracts.csv','rU') as csvinput:
	with open('output.csv', 'w') as csvoutput:
		writer = csv.writer(csvoutput, lineterminator='\n')

nickjevershed

nickjevershed

#!/usr/bin/env python
import scraperwiki
import urllib2
import lxml.etree

urls = ["http://www.finance.gov.au/sites/default/files//sites/default/files/P33_ABBOTT_Tony.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_ALBANESE_Anthony.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_ALEXANDER_John.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BALDWIN_Bob.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BIRD_Sharon.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BISHOP_Bronwyn.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BOWEN_Chris.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BRADBURY_David.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_BURKE_Tony.pdf","http://www.finance.gov.au/sites/default/files//sites/default/files/P33_CAMERON_Doug.pdf","http://www.finance.gov.au/sites/defa

nickjevershed

import simplejson as json
 
with open("blah.json") as f:
	blah = json.load(f)
 
	print blah['features'][0]['properties']['headline']

nickjevershed

import sys
import os
import re
import subprocess
import tempfile
from PIL import Image


def parse_captcha(filename):
    """Return the text for thie image using Tesseract