Skip to content

Instantly share code, notes, and snippets.

View jmduke's full-sized avatar
🏠

Justin Duke jmduke

🏠
168 followers · 2 following
View GitHub Profile
@jmduke
jmduke / gist:5660594
Created May 28, 2013 04:54
Error when running pagoda
$ pagoda .
/Library/Ruby/Site/1.8/rubygems/core_ext/kernel_require.rb:45:in `gem_original_require': /Library/Ruby/Gems/1.8/gems/pagoda-jekyll-0.0.9/bin/../lib/pagoda/app.rb:39: syntax error, unexpected tIDENTIFIER, expecting tAMPER (SyntaxError)
...source, *%w[_posts], post_file)
^
/Library/Ruby/Gems/1.8/gems/pagoda-jekyll-0.0.9/bin/../lib/pagoda/app.rb:146: syntax error, unexpected tIDENTIFIER, expecting tAMPER
repo.add File.join(jekyll_site.source, *%w[_posts], filename)
^
from /Library/Ruby/Site/1.8/rubygems/core_ext/kernel_require.rb:45:in `require'
from /Library/Ruby/Gems/1.8/gems/pagoda-jekyll-0.0.9/bin/pagoda:20
from /usr/bin/pagoda:23:in `load'
@jmduke
jmduke / gist:7427030
Created November 12, 2013 07:37
Plotting retweets over time.
import matplotlib.pyplot as plt
from datetime import datetime, timedelta
import numpy as np
from math import log
import tweepy
import collections
import bisect
DATE_FORMAT = "%Y-%m-%d %H:%M:%S"
INTERVAL = timedelta(hours = 1)
@jmduke
jmduke / bigTech.py
Created November 24, 2013 01:56
Grab data from various organizations from Github.
import requests
import operator
companies = ["facebook", "aws", "google", "yahoo", "dropbox", "twitter", "paypal", "linkedin", "mozilla", "adobe"]
api_url = "https://api.github.com/orgs/{}/repos"
data = {}
for company in companies:
data[company] = {'forks': 0, 'stars': 0, 'repos': 0, 'languages': {}}
r = requests.get(api_url.format(company))
@jmduke
jmduke / gist:7654733
Created November 26, 2013 07:45
Analyze daily GitHub Explore emails
import requests
import operator
companies = ["hubspot"]
api_url = "https://api.github.com/orgs/{}/repos"
data = {}
for company in companies:
data[company] = {'forks': 0, 'stars': 0, 'repos': 0, 'languages': {}}
r = requests.get(api_url.format(company))
@jmduke
jmduke / gist:8130034
Created December 26, 2013 05:14
CSV of every single lego set.
This file has been truncated, but you can view the full file.
SetID,Number,Variant,Theme,SubTheme,Year,SetName,Minifigs,Pieces,UKPrice,USPrice,CAPrice,Image,ImageFilename,InstructionsAvailable,EAN,UPC
22696,"00","5","Samsonite","Model Maker","1969","Life Cereal Puppet Set",,88,,1,,"False","","False","",""
7326,"102A","1","LEGOLAND","Construction","1970","Front-End Loader",,57,,,,"True","102A-1","False","",""
7455,"442A","1","Classic","Accessories","1971","International Flags",,6,,,,"False","","False","",""
1232,"670F","1","Racers","Radio-Control","2004","Wheels Pack",,10,,,,"True","670F-1","False","",""
1,"671F","1","Racers","Radio-Control","2004","Antenna Pack",,13,,,,"True","671F-1","False","",""
4690,"673F","1","Racers","Radio-Control","2004","Gearbox Pack",,6,,,,"True","673F-1","False","",""
9434,"973PB507C01","1","Promotional","Minifigure","2009","LEGO World Denmark 2009 Minifigure",,4,,,,"False","","False","",""
9780,"ALPHARETTA","1","Promotional","LEGO Store Grand Opening Set","2012","Alpharetta Exclusive Minifigure Pack",3,15,,0,,"True","ALPHARETTA-1","False",""
@jmduke
jmduke / index.html
Last active January 1, 2016 15:39
Visualizing Seattle's 911 calls.
<!DOCTYPE html>
<head>
<link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet-0.7/leaflet.css" />
<link rel="stylesheet" href="http://leaflet.github.io/Leaflet.markercluster/dist/MarkerCluster.Default.css" />
<script src="http://cdn.leafletjs.com/leaflet-0.7/leaflet.js"></script>
<script src="http://leaflet.github.io/Leaflet.markercluster/dist/leaflet.markercluster-src.js" type='text/javascript'></script>
<script src="http://briangonzalez.github.io/jquery.adaptive-backgrounds.js/js/jquery.js"></script>
<style>
@jmduke
jmduke / gist:8382405
Created January 12, 2014 08:51
Fun with NFL scores.
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import vincent
# source: http://www.pro-football-reference.com/boxscores/game_scores.cgi
SOURCE_FILE = "./nflscores.csv"
data = pd.read_csv(SOURCE_FILE, header=0)
@jmduke
jmduke / gist:8501926
Created January 19, 2014 08:22
import nltk
import vincent
from curses.ascii import isdigit
from nltk.corpus import cmudict
import nltk.data
import sys
authors = ['kerouac', 'joyce', 'hemingway', 'milton', 'dickens', 'fitzgerald', 'nabokov', 'vonnegut']
d = cmudict.dict()
@jmduke
jmduke / gist:8501972
Created January 19, 2014 08:29
import nltk
import vincent
from curses.ascii import isdigit
from nltk.corpus import cmudict
import nltk.data
import sys
authors = ['kerouac', 'joyce', 'hemingway', 'milton', 'dickens', 'fitzgerald', 'nabokov', 'vonnegut']
d = cmudict.dict()
@jmduke
jmduke / gist:9474688
Created March 10, 2014 21:25
# -*- coding: utf-8 -*-
import re
from scrapy.item import Item, Field
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.selector import HtmlXPathSelector
from lxml.cssselect import css_to_xpath