dpastoor

packages <- c(
  "bear",
  "data.table",
  "deSolve",
  "devtools",
  "dplyr",
  "formatR",
  "ggplot2",
  "gridExtra",
  "installr",

dpastoor

#' Simplified loading and installing of packages
#'
#' This is a wrapper to \code{\link{require}} and \code{\link{install.packages}}.
#' Specifically, this will first try to load the package(s) and if not found
#' it will install then load the packages. Additionally, if the 
#' \code{update=TRUE} parameter is specified it will check the currently 
#' installed package version with what is available on CRAN (or mirror) and 
#' install the newer version.
#' 
#' @param pkgs a character vector with the names of the packages to load.

dpastoor

#’ Create a Kaplan-Meier plot using ggplot2
#’
#’ @param sfit a \code{\link[survival]{survfit}} object
#’ @param returns logical: if \code{TRUE}, return an ggplot object
#’ @param xlabs x-axis label
#’ @param ylabs y-axis label
#’ @param ystratalabs The strata labels. \code{Default = levels(summary(sfit)$strata)}
#’ @param ystrataname The legend name. Default = “Strata”
#’ @param timeby numeric: control the granularity along the time-axis
#’ @param main plot title

dpastoor

library("shiny")
library("plotly")
library("ggplot2")

shinyServer(function(input, output) {
  output$text <- renderText({
    ggiris <- qplot(Petal.Width, Sepal.Length, data=iris, color=Species)
    py <- plotly("RgraphingAPI", "ektgzomjbx")
    res <- py$ggplotly(ggiris)
    iframe <- paste("<iframe height=\"600\" id=\"igraph\" scrolling=\"no\" seamless=\"seamless\" src=\"", 

dpastoor

{
 "metadata": {
  "name": "",
  "signature": "sha256:9f8cc010920e3ba427bf8782337a847d8f5129fe6b3a868aad7eeaa6fb3187c2"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [

dpastoor

#' Get URLs to blog post full text for all posts
#' by scraping them out of each page of the
#' main blog aggregator
# from: https://github.com/benmarwick/dayofarchaeology/blob/master/001_scrape_for_links_to_fulltext.r


library(RCurl)
library(XML)

n <- 100 # determined by inspecting the first page

dpastoor

save.xlsx <- function (file, ...)
  {
      require(xlsx, quietly = TRUE)
      objects <- list(...)
      fargs <- as.list(match.call(expand.dots = TRUE))
      objnames <- as.character(fargs)[-c(1, 2)]
      nobjects <- length(objects)
      for (i in 1:nobjects) {
          if (i == 1)
              write.xlsx(objects[[i]], file, sheetName = objnames[i])

dpastoor

import os
import random
import string
import tempfile
import subprocess

def random_id(length=8):
    return ''.join(random.sample(string.ascii_letters + string.digits, length))

TEMPLATE_SERIAL = """

dpastoor

library(ggplot2)
library(stringr)
### functions -------------

cov_convergence <- function(wd) {
  setwd(wd)
  dir_list <- list.dirs(recursive=FALSE)
  
  results <- lapply(str_replace_all(dir_list, pattern="./", ""), function(x) {
    num <- str_replace_all(x, pattern="sse_", "")

dpastoor

Update: The timings are now updated with runs from R v3.1.0.

A small note on this tweet from @KevinUshey and this tweet from @ChengHLee:

The number of rows, while is important, is only one of the factors that influence the time taken to perform the join. From my benchmarking experience, the two features that I found to influence join speed, especially on hash table based approaches (ex: dplyr), much more are:

• The number of unique groups.
• The number of columns to perform the join based on - note that this is also related to the previous point as in most cases, more the columns, more the number of unique groups.

That is, these features influence join speed in spite of having the same number of rows.