rufuspollock

,Millions LU journeys adjusted for odd days,Millions bus journeys adjusted for odd days - new measure,Millions bus plus underground journeys adjusted for odd days - new measure,LU Average,Bus Average,LU plus bus average,LU growth,Bus growth,LU plus bus growth,LU moving average annual growth,Bus moving average annual growth,LU plus busmoving average annual growth,,,,,,,,
2006/2007 - 1,72.3,151.3,223.5,73.9,138.8,212.7,-5.4%,-1.5%,-2.9%,-1.6%,0.6%,-0.2%,,,,,,,,
2006/2007 - 2,75.6,158.9,234.5,73.8,139.1,212.9,-2.5%,3.4%,1.3%,-2.1%,0.8%,-0.2%,,,,,,,,
2006/2007 - 3,74.3,158.4,232.7,73.6,139.6,213.2,-2.7%,4.4%,1.9%,-2.6%,1.1%,-0.2%,,,,,,,,
2006/2007 - 4,77.4,161.5,238.9,74.1,140.1,214.2,8.2%,4.9%,6.0%,-1.7%,1.4%,0.3%,,,,,,,,
2006/2007 - 5,73.7,153.5,227.2,74.8,141.1,215.9,15.0%,9.9%,11.6%,0.2%,2.3%,1.6%,,,,,,,,
2006/2007 - 6,74.1,153.2,227.3,75.2,141.7,216.9,7.9%,5.8%,6.5%,1.2%,3.0%,2.3%,,,,,,,,
2006/2007 - 7,81.1,165.1,246.2,75.6,142.1,217.7,6.1%,4.0%,4.8%,1.8%,3.5%,2.9%,,,,,,,,
2006/2007 - 8,83.4,166.5,250.0,76.0

rufuspollock

// Parse a summary to extract title, tags, location and start and end
parseNoteSummary = function(text) {
  var result = {
    title: '',
    tags: []
  };
  var ourtext = text;
  regex = / #([\w-\.]+)/;
  while(ourtext.search(regex)!=-1) {
    var out = ourtext.match(regex)[1];

rufuspollock

<?xml version="1.0" encoding="utf-8"?>
<Root xmlns:wb="http://www.worldbank.org">
  <data>
    <record>
      <field name="Country or Area" key="ARB">Arab World</field>
      <field name="Item" key="SP.POP.TOTL">Population, total</field>
      <field name="Year">1960</field>
      <field name="Value">96388069</field>
    </record>
    <record>

rufuspollock

import csv
import json
import geojson

fp = 'data/US_Rendition_FOIA.csv'
fpout = 'data/US_Rendition_FOIA.geojson.csv'
jsonout = 'data/US_Rendition_FOIA.geojson.json'

jsondata = []
def convert():

rufuspollock

#!/usr/bin/env python
import urlparse
import mimetypes
import os
import ConfigParser
import urllib2
import json
import csv
import time

rufuspollock

'''Simple script for creating demo data in CKAN

Requires existence of a tester user. You can create this by doing::

   paster create-test-data user
'''
import ckanclient

base_location = 'http://localhost:5000/api'
api_key = 'tester'

rufuspollock

'''This is a test using the real setup with elasticsearch.

It requires you to run nginx on port 8088 with config as per
https://github.com/okfn/elastic-proxy/blob/master/elasticproxy plus,
obviously, elasticsearch on port 9200.
'''
import json
import paste.fixture
import paste.proxy

rufuspollock

Test model (dimensions and mapping):

ostool cfg.ini csvimport --model=model.json --dry-run --raise-on-error --max-lines=1 data.csv

Dry run:

ostool cfg.ini csvimport --model=model.json --dry-run data.csv

rufuspollock

# Get user stories out a spreadsheet and into mediawiki syntax
# 
# Designed for this set here
# https://docs.google.com/spreadsheet/ccc?key=0Aon3JiuouxLUdFhMVEVFWXhxWXRKaU04LUF2ZTVsTVE&hl=en_GB#gid=0
# Pass it link to gdocs csv as argument on command line
# E.g.
# 
# python userstories.py "https://docs.google.com/spreadsheet/pub?hl=en_GB&hl=en_GB&key=0Aon3JiuouxLUdFhMVEVFWXhxWXRKaU04LUF2ZTVsTVE&single=true&gid=0&output=csv"
#
import urllib

rufuspollock

import ckanclient

base_location = 'http://localhost:5000/api'
api_key = 'tester'
client = ckanclient.CkanClient(base_location, api_key)
pkg = dict(
    name='test-ckanext-datapreview',
    title='Test CKANext Data Preview',
    resources=[
        dict(