nickjevershed’s gists

nickjevershed / getgenres.py

Created January 24, 2014 00:09

Classifies a csv of songs with last.fm tags, EchoNest terms and genres, gets the number of YouTube views, and a few other things

	#!/usr/bin/env python
	#coding=utf-8
	import pylast
	import csv
	import urllib
	import requests
	import simplejson
	import time

	#Gets Last FM data - top 3 tags, duration of track, and lastFM listener count

nickjevershed / donations.py

Created February 3, 2014 05:02

Scraper for Australian political party annual returns

	import csv
	import mechanize
	import lxml.html
	import scraperwiki

	annDonorsurl = "http://periodicdisclosures.aec.gov.au/AnalysisDonor.aspx"

	annReportingPeriods={
	"1998-1999":"1",
	"1999-2000":"2",

nickjevershed / Labor-network-graph.html

Created March 31, 2014 22:37

Network graph for Labor funds via associated entities

	<!DOCTYPE html>
	<meta charset="utf-8">
	<title>How money flows to the Labor party \| The Guardian</title>
	<style>

	body {
	margin:0;
	}

	.donorContainer {

nickjevershed / csv-read-write.py

Last active August 29, 2015 13:57

A template for reading a csv, then writing to a new csv with a new row

	import csv

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

	#Get the headers from the old csv, add to new csv and add our new column header

	headers = reader.next()

nickjevershed / checkloop.py

Created April 1, 2014 05:45

checks for source/target loops and tells you what they are

	dons = #source-target dataset here

	for s in dons:
	for ss in dons:
	if s['sourceName'] == ss['targetName'] and s['targetName'] == ss['sourceName']:
	print s['sourceName'], s['targetName']

nickjevershed / parse_captcha.py

Created June 20, 2014 01:09

OCR for captchas

	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

nickjevershed / blah.py

Last active August 29, 2015 14:02

	import simplejson as json

	with open("blah.json") as f:
	blah = json.load(f)

	print blah['features'][0]['properties']['headline']

nickjevershed / expenses-pdf-scraper.py

Created July 23, 2014 09:30

A scraper for getting politicians' travel expenses from PDF

	#!/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 / detention-centres.csv

Created August 19, 2014 06:02

List of Australian detention centres and locations

nickjevershed / immi-contracts.py

Created August 22, 2014 01:35

classification of immigration department contracts

	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')

Nick Evershed nickjevershed