DASpringate

require(XML)
require(RCurl)
require(stringr)
require(rentrez)
require(rjson)
require(reshape2)
require(ggmap)
require(mapproj)
require(devtools)

DASpringate

#' R implementation of `cond` from Lisp
#' allows for arbitrary numbers of conditionals without ugly nested if statements
#' conditionals are entered as pairs of expressions (clauses), 
#' first the expression to be evaluated and second the return value if the expression is true
#' @param ... an even number of expressions as pairs (see example)
#' @param true the `else` expression (Taken from the Lisp (T resultN) see http://www.cis.upenn.edu/~matuszek/LispText/lisp-cond.html)
#' @return The paired value of the first true conditional expression or the value of true
#' @examples
#' x <- runif(1)
#' cond(x < 0.2, "lower tail",

DASpringate

# R code to produce a simulated dataset for an experiment on a made up insect. 
# Measures include sex, body length, thorax width, number of thoracic bristles and some measure of aggression behaviour. 
# Also there is exposure to some treatment stimulus/drug. 
# This simulation uses Copulas to generate correlated variables from binomial, Gaussian and Poisson distributions

require(copula)

set.seed(1888)

n <- 1000 

DASpringate

require(devtools)
load_all(".")

site <- "/home/me/mysite"
skeleton(site)
setup_example_site(site)
## buggy - Have to run twice to get the tags to work...
samatha(site, rss = FALSE, initial = TRUE)
samatha(site, rss = FALSE, initial = TRUE)

DASpringate

fast_rbind <- function(to_bind, cores = 12, splits = 10){
    # to_bind : list of dataframes to bind 
    require(multicore)
    myseq <- c(seq(from = 1,to = length(dat2), 
                   by = floor(length(dat2) / max(cores, splits))), 
               length(dat2))
    intermediates <- mclapply(1:length(myseq), 
                              function(x) {
                                  if(x != length(myseq)){
                                      do.call(`rbind`, dat2[myseq[x]:(myseq[x+1] -1)])    

DASpringate

#!/usr/bin/Rscript

# Extracts a variety of organism, environmental, sequencing and project metadata
# From saved GOLDstamp files (genomesonline.org) 
# and saves as a flatfile with 1 taxa per line
# See gist.github.com/2929217 to scrape the files from a treebase taxa list

require(XML)

url <- "http://www.treebase.org/treebase-web/search/study/taxa.html?id=10965"

DASpringate

#!/usr/bin/python2

# Quick and dirty web scraper for extracting html files of 
# Organism information, Genome Project Information, 
# Sequencing Information,  Environmental Metadata
# and organism metadata
# from GOLD databases based on treebase taxa lists, via ncbi
# Saves pages in the current directory 

from urllib2 import urlopen