christophergandrud

#' Caterpillar plot with thick and thin CI
#'
#' Caterpillar plots are plotted combining all chains for each parameter.
#'
#' @param D Data frame whith the simulations or list of data frame with simulations. If a list of data frames with simulations is passed, the names of the models are the names of the objects in the list.
#' @param X data frame with two columns, Parameter and the value for the x location. Parameter must be a character vector with the same names that the parameters in the D object. 
#' @param family Name of the family of parameters to plot, as given by a character vector or a regular expression. A family of parameters is considered to be any group of parameters with the same name but different numerical value between square brackets (as beta[1], beta[2], etc). 
#' @param thick_ci Vector of length 2 with the quantiles of the thick band for the credible interval
#' @param thin_ci Vector of length 2 with the quantiles of the thin band for the credible interval
#' @param line Numerical value in

christophergandrud

#' Extract parameter point estimates
#' 
#' @param D Data frame with the simulations or list of data frame with simulations. If a list of data frames with simulations is passed, the names of the models are the names of the objects in the list.
#' @param family Name of the family of parameters to plot, as given by a character vector or a regular expression. A family of parameters is considered to be any group of parameters with the same name but different numerical value between square brackets (as beta[1], beta[2], etc).
#' @param thick_ci Vector of length 2 with the quantiles of the thick band for the credible interval.
#' @param thin_ci Vector of length 2 with the quantiles of the thin band for the credible interval.
#' @param param_label_from Vector of strings (can be regular expressions) for the original paramater labels that you would like to replace in the plot lables using \code{param_label_to}. 
#' @param param_label_to Vector of strings for paramater labels you would like to use. Must be both the sam

christophergandrud

#' Simple function to transform a dependent variable that in [0,1] rather than 
#' (0, 1) to beta regression. Suggested by Smithson & Verkuilen (2006).
#' 
#' @param y vector of the dependent variable that is in [0, 1].

svTransform <- function(y)
{
    n <- length(y)
    transformed <- (y * (n-1) + 0.5)/n
    return(transformed)

christophergandrud

#' Convert text files in a directory to UTF-8 encoding
#' 
#' @param dir a character string naming the directory where the files are located.
#' @param new_dir a character string naming the directory where you would like the
#' converted files to be placed. 
#' 
#' @importFrom dplyr %>%

utf8_convert <- function(dir, new_dir){
    all_files <- list.files(dir)

christophergandrud

########################################
# Download GitHub users with more than 100 followers for Berlin, Brooklyn, 
# and London
# Christopher Gandrud
# 20 October 2014
########################################

library(httr)
library(dplyr)
library(rjson)

christophergandrud

christophergandrud

#' Sets valid working directory from vector of possible directories
#' 
#' @param character vector of possible working directores

set_valid_wd <- function(possible) {
    for (i in possible) {
        if (file.exists(i)) {
            setwd(i)
            message(sprintf('Working directory set as: %s', i))
        }

christophergandrud

#' Rescale a vector to be within 0 and 1
#' 
#' @param x a numeric vector to rescale
#' @param na.rm logical. Whether or not to remove NA (missing) values

range01 <- function(x, na.rm = T){
    (x - min(x, na.rm = na.rm)) / 
        (max(x, na.rm = na.rm) - min(x, na.rm = na.rm))
}

christophergandrud

#' Convert a vector into a matrix with two columns
#'
#' @param x a vector

equal_columns <- function(x) {
    round2 = function(x, digits) {
        posneg = sign(x)
        z = abs(x)*10 ^ digits
        z = z + 0.5
        z = trunc(z)

christophergandrud

# Load RCurl package
library(RCurl)


addresses <- read.csv("~/links.csv") # Create a .csv file with all of the links you want to crawl

for (i in addresses) full.text <- getURL(i) 

text.sub <- gsub("<.+?>", "", full.text) # Removes HTML tags
text <- data.frame(text.sub)