kburnham
kburnham
/ gist:0d619494039af4a0172b
Created
July 17, 2015 16:46
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "metadata": { | |
| "name": "", | |
| "signature": "sha256:479d65b161afda29d9bddd2391ff8427ccdc214abf259212993ef9b90a02a3d4" | |
| }, | |
| "nbformat": 3, | |
| "nbformat_minor": 0, | |
| "worksheets": [ | |
| { | |
| "cells": [ |
kburnham
/ gist:52ed403af3a4291df853
Created
June 17, 2015 15:06
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <div id="chartContainer"> | |
| <script src="http://d3js.org/d3.v3.min.js"></script> | |
| <script src="http://dimplejs.org/dist/dimple.v2.1.2.min.js"></script> | |
| <script type="text/javascript"> | |
| var svg = dimple.newSvg("#chartContainer", 590, 400); |
kburnham
/ gist:f43481b1f45a7a6ddf89
Created
January 27, 2015 18:20
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #clean the religion and denomination names | |
| def clean_religion(entry): | |
| new_entry = entry.lower() | |
| if new_entry == "latter_day_saints": | |
| return "Mormon" | |
| if new_entry == "roman_catholic": | |
| return "Catholic" | |
| if 'jehovahs' in new_entry: | |
| return "Jehovah's Witness" | |
| return entry.replace('_',' ').title() |
kburnham
/ gist:d270210d20ec3489eb2d
Created
January 26, 2015 22:48
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def count_tags(filename): | |
| tags = {} | |
| for item, elem in ET.iterparse(filename): | |
| if elem.tag not in tags: | |
| tags[elem.tag] = 1 | |
| else: | |
| tags[elem.tag] += 1 | |
| return tags | |
| tags = count_tags('austin_texas.osm') |
kburnham
/ gist:81958309de1db42fe789
Last active
August 29, 2015 14:11
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def process_line(line, fields): | |
| classification_list = ['family', 'class', 'phylum','order','kingdom', 'genus'] | |
| spider_dict = {} | |
| spider_dict['classification'] = {} | |
| for field in fields: | |
| new_value = line[field].strip() | |
| if line[field].strip() == 'NULL': | |
| new_value = None | |
| if fields[field] == 'label': | |
| new_value = re.sub(r'\([^)]*\)', '', line[field]).strip() #http://stackoverflow.com/questions/640001/how-can-i-remove-text-within-parentheses-with-a-regex |
kburnham
/ gist:693e69b1d774cdbb7fc3
Last active
August 29, 2015 14:11
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def process_file(filename, fields): | |
| classification_list = ['family', 'class', 'phylum','order','kingdom', 'genus'] | |
| process_fields = fields.keys() | |
| data = [] | |
| with open(filename, "r") as f: | |
| reader = csv.DictReader(f) | |
| for i in range(3): | |
| l = reader.next() | |
| for line in reader: |