n8thangreen

data_long = melt(CDIdata, id.vars=c("rowID", "ribotype", "severe", "LoS.total", "LoS.preinf", "LoS.postinf", "discharge.status"))
data_long$value = as.numeric(as.character(data_long$value))

# Change discharge to death in hospital
data_long$variable = factor(data_long$variable, levels=c(unique(as.character(data_long$variable)), "Death in hospital"))
d =  data_long$variable=="Discharged" & data_long$discharge.status == "3"
data_long$variable[d] = "Death in hospital"

#write.csv(data_long, file="data_long.csv")

n8thangreen

map.tb <- function(map.data, g=NA, brks=NA, title="", value="tb", file=FALSE){
  ## plot UK choropleth maps
  ## developed using LA and ETS data but 
  ## can be applied more generally
  ##
  ## map.data: map object loaded by readOGR()
  ## g: number of groups for values; max(g)=9
  ## brks: given break points to group values
  ## title: plot title
  ## value: variable name of colouring value (string)

n8thangreen

\documentclass{article}
\usepackage[margin=0.5in]{geometry}

\begin{document}
\Sexpr{cat(sub("_", "\\\\\\_", version$platform))}

% !Rnw root = TB_root.Rnw

%% some of the output is missing when compiled to PDF
%% when the regression is fit to models with lots of variable levels

n8thangreen

covariateShift <- function(data, resla, riskfac, ssize=10000){
  ## importance sampling approach
  ## when different distributions for the
  ## training and test data
  
  require(plyr)
  
  Natsal.riskfac.table <- DistnTable(data, riskfac)
  Natsal.riskfac.table <- colNameReplace(Natsal.riskfac.table, "(all)", "Natsalfreq")

n8thangreen

## read from Excel workbook
require(XLConnect)
wb = loadWorkbook("C:/Users/ngreen1/Documents/IDEA/raw_data/TB_database_patientdata_300614.xlsx")
tab.names <- getSheets(wb)
TBlist <- sapply(1:length(tab.names), function(x) readWorksheet(wb, sheet=x, header=TRUE))
names(TBlist) <- tab.names

## extract only columns of interest
require(plyr)
extractNames <- readLines("C:/Users/ngreen1/Documents/IDEA/raw_data/relevant_fields.csv")

n8thangreen

library("rmeta", lib.loc="C:/Program Files/R/R-3.1.0/library")

names <- c("Premature", "Not premature",
           NA,"Surgical","Not surgical",
           NA,"Congenital","Not congenital",
           NA,"Catheter","Not catheter",
           NA,"Other","Not other",
           NA,"Tai","Not Tai",
           NA,"Cancer","Not cancer")
  

n8thangreen

library("plotrix", lib.loc="C:/Program Files/R/R-3.1.0/library")
library(Hmisc)

NATSAL.dat <<- read.csv("~/Chlamydia/data/NATSAL/Natsal-3_extract_2April2014.csv")


plotCInatsal <- function(varname, save=TRUE){
  
  tab <- table(NATSAL.dat$cttestly=="yes", NATSAL.dat[,varname])
  tab.df <- data.frame(addmargins(tab))

n8thangreen

#--run in the old version of R
setwd("C:/Temp/")
packages <- installed.packages()[,"Package"]
save(packages, file="Rpackages")
Followed by this in the new version:

#--run in the new version
setwd("C:/Temp/")
load("Rpackages")
for (p in setdiff(packages, installed.packages()[,"Package"]))

n8thangreen

## ----setup, include=FALSE------------------------------------------------
knitr::opts_chunk$set(echo = TRUE)

## ---- echo=T, eval=T-----------------------------------------------------
2 + 2

## ---- echo=T, eval=T-----------------------------------------------------
a <- 2 + 2

## ---- echo=T,eval=T------------------------------------------------------

n8thangreen

## ----setup, include=FALSE------------------------------------------------
knitr::opts_chunk$set(echo = TRUE)

## ---- eval=T,echo=T------------------------------------------------------
a <- 1
b <- 2
c <- -1
d <- 2

# Check if two values are the same. Note the difference between