Kyle Willett willettk

## quench_collate.py
import re
import csv
import numpy as np
import operator
from astropy.io import fits as pyfits

'''
To create the full collated data for GZ: Quench:

>>> import quench_collate as qc

## remove_sdss_duplicates
#!/bin/sh

for img in *.jpg; do
    filename=${img%.*}
    newfilename=${img%.*}_cropped
    convert "$filename.jpg" -crop 100x100+162+162 "$newfilename.jpg"
done

# Probably needs to be run on subsets of images if using the full GZ set due to memory limitation
# Include at least one black image (badimage_cropped.jpg) so subset has a comparison

## gist:7797723
parseLong(substring(split($41,"/")[4],toInteger(0),length(split($41,"/")[4])-4))

## gist:7797882
cat filelist.txt | awk '{print "cp source_dir/" $1, " targetdir/"}' | bash

## gist:7798902
tar -cvf target_dir/foo.tar -T source_dir/filelist.txt > target_dir/results.txt

## gist:7919434
perl -nle'print $& if m{\b([yuiophjklbnm]+( |$)){3}' chatlines.txt

## Mongo stuff
# Get the average classification counts for each group of subjects in Galaxy Zoo

db.galaxy_zoo_subjects.aggregate([{$group : {_id : "$metadata.survey", nClass : {$avg : "$classification_count"}}}])

# Export data from MongoDB to a CSV file from the shell command line

mongoexport --db ouroboros --collection galaxy_zoo_subjects --csv --fields classification_count --query '{"metadata.survey":"ukidss"}' --out ukidss_nclass.csv

## gist:b89da6aace158fc8348e

import pandas
import numpy
import matplotlib.pyplot as plt

data = pandas.read_csv('/Users/willettk/Astronomy/meetings/garching2014/participants.csv',names=('person','country','institution'))

darkblue = '#00008b'

colordict = {

## gist:ff7c5ee7338b4e77d527
Success of missions to Mars by space agency*
Information from https://en.wikipedia.org/wiki/List_of_missions_to_Mars

China: 0/1
ESA: 1/2
Japan: 0/1
India: 1/1
USA: 17/23
Russia/USSR: 2/21

## Nobel Banquet Menus
from bs4 import BeautifulSoup as bs
import requests
import io

# Scrape the Nobel website to get data on what was served at the Nobel banquets.
# Can be turned into word clouds via Tagxedo

def get_result(year):

    result = requests.get('http://www.nobelprize.org/ceremonies/menus/menu-%4i.html' % year)
	import re
	import csv
	import numpy as np
	import operator
	from astropy.io import fits as pyfits

	'''
	To create the full collated data for GZ: Quench:

	>>> import quench_collate as qc
	#!/bin/sh

	for img in *.jpg; do
	filename=${img%.*}
	newfilename=${img%.*}_cropped
	convert "$filename.jpg" -crop 100x100+162+162 "$newfilename.jpg"
	done

	# Probably needs to be run on subsets of images if using the full GZ set due to memory limitation
	# Include at least one black image (badimage_cropped.jpg) so subset has a comparison
	# Get the average classification counts for each group of subjects in Galaxy Zoo

	db.galaxy_zoo_subjects.aggregate([{$group : {_id : "$metadata.survey", nClass : {$avg : "$classification_count"}}}])

	# Export data from MongoDB to a CSV file from the shell command line

	mongoexport --db ouroboros --collection galaxy_zoo_subjects --csv --fields classification_count --query '{"metadata.survey":"ukidss"}' --out ukidss_nclass.csv

	import pandas
	import numpy
	import matplotlib.pyplot as plt

	data = pandas.read_csv('/Users/willettk/Astronomy/meetings/garching2014/participants.csv',names=('person','country','institution'))

	darkblue = '#00008b'

	colordict = {
	Success of missions to Mars by space agency*
	Information from https://en.wikipedia.org/wiki/List_of_missions_to_Mars

	China: 0/1
	ESA: 1/2
	Japan: 0/1
	India: 1/1
	USA: 17/23
	Russia/USSR: 2/21
	from bs4 import BeautifulSoup as bs
	import requests
	import io

	# Scrape the Nobel website to get data on what was served at the Nobel banquets.
	# Can be turned into word clouds via Tagxedo

	def get_result(year):

	result = requests.get('http://www.nobelprize.org/ceremonies/menus/menu-%4i.html' % year)