jhofman

#!/usr/bin/env python

from lxml import etree
from urllib import urlopen

if __name__=='__main__':
    
    url = 'http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/schedConf/presentations'
    tree = etree.parse(urlopen(url), etree.HTMLParser())
    

jhofman

#!/usr/bin/env python
#
# file: scrapple.py
#
# description: checks apple.come for iphone 5s in-store pickup availability
#
# usage: ./scrapple.py [zip] [att|verizon|sprint] [16|32|64] [grey|silver|gold]
#
#  or in a crontab:
#  */5 * * * * /path/to/scrapple.py 10012 verizon 32 grey && mailx -s 5s 2125551212@vtext.com

jhofman

#!/usr/bin/env python
#
# file: bookmark_starred.py
#
# description: mirrors starred github repos to delicious
#
# usage: bookmark_starred.py GITHUB_USER DELICIOUS_USER
#
# requirements: requests

jhofman

#!/bin/bash
#
# script to show word-style "track changes" from a previous git revision
#

if [ $# -lt 2 ]
then
    echo "usage: $0 <rev> <maintex>"
    echo "  rev is the prefix of a git revision hash"
    echo "  see 'git log' for revision hashes"

jhofman

#!/bin/bash
#
# Scrape income distribution data from whatsmypercent.com
#
# Output is in incomes.csv (percentile,income)
#

# start at $100 / year
income=100

jhofman

library(dplyr)

# create a dummy dataframe with 100,000 groups and 1,000,000 rows
# and partition by group_id
df <- data.frame(group_id=sample(1:1e5, 1e6, replace=T),
                 val=sample(1:100, 1e6, replace=T)) %>%
      group_by(group_id)

# filter rows with a value of 1 naively
system.time(df %>% filter(val == 1))

jhofman

all: pediacities_nyc_neighborhood_populations.csv

pediacities_nyc_neighborhood_populations.csv: pediacities_nyc_neighborhoods.json extract_neighborhood_populations.sh
	extract_neighborhood_populations.sh

pediacities_nyc_neighborhoods.json: download_neighborhood_pages.sh
	download_neighborhood_pages.sh

jhofman

library(tidyverse)
library(forcats)

# The original plot
## This has an ugly legend title, maybe we should remove it and modify the labels
ggplot(mtcars, aes(x = mpg, y = disp, col = as.factor(cyl))) +
  geom_point()

# Approach 1: Modify the plot

jhofman

#!/usr/bin/env python
#
# file: scrapple_x.py
#
# description: checks apple.come for iphone x in-store pickup availability
#
# usage: ./scrapple.py [zip] [att|verizon|sprint|tmobile] [64|256] [grey|silver]
#
#  or in a crontab:
#  */5 * * * * /path/to/scrapple.py 12345 tmobile 64 grey && mailx -s "iphone x" 2125551212@vtext.com

jhofman

library(tidyverse)
library(digest)

# create a dummy dataframe with 100,000 groups and 1,000,000 rows
# where group ids are md5 hash of integers from 1 to 100,000
set.seed(42)
md5 <- Vectorize(function(x) digest(x, algo="md5"))
df <- data.frame(group_id=sample(md5(1:1e4), 1e6, replace=T),
                 val=sample(1:100, 1e6, replace=T))