rprofile.R

# To source this file into an environment to avoid cluttering the global workspace, put this in Rprofile:
# my.env <- new.env(); sys.source("C:/PathTo/THIS_FILE.r", my.env); attach(my.env)

#-----------------------------------------------------------------------
#     Load packages, set options and cwd, set up database connection
#-----------------------------------------------------------------------

## Load packages
library(RPostgreSQL)
library(grid)
library(ggplot2)
library(reshape2)
library(directlabels)
library(plyr)
library(scales)
library(lubridate)

# db.driver <- dbDriver('PostgreSQL') 
# db.host <-'odc_dw_prod'
# db.username <-'foo'
# db.password <- 'bar'
# db.name <- 'gp_production'  
# greenplum <- dbConnect(db.driver, host=db.host, user=db.username, password=db.password, dbname=db.name)


## Sets the working directory to C:/R
working.directory <- "/hernamesbarbara/Workspace/R"
setwd(working.directory)
message("\n******************************************************************************************")
message(paste("Set working directory to", working.directory), sep=" ")
message("\n******************************************************************************************")

## Don't show those silly significanct stars
#options(show.signif.stars=FALSE)

## dont convert strings to factor by default (e.g. in read.csv)
options(stringsAsFactors=F)

## Hard code the US repository for CRAN so it doesn't ask me every time.
r <- getOption("repos")             
r["CRAN"] <- "http://cran.us.r-project.org"
options(repos = r)
rm(r)


#-----------------------------------------------------------------------
#                             Functions
#-----------------------------------------------------------------------

## Transpose a numeric data frame with ID in first column
ix.transpose <- function(d) {
  row.names(d) <- d[[1]]
  d[[1]] <- NULL
  d <- as.data.frame(t(d))
  d$id <- row.names(d)
  d <- cbind(d[ncol(d)], d[-ncol(d)])
  row.names(d) <- NULL
  d
}

## Convert selected columns of a data frame to factor variables
factorize.columns <- function(d, ...) lapply(d, function(x) factor(x, ...)) 

## Returns names(df) in single column, numbered matrix format.
n <- function(df) matrix(names(df)) 

## Single character shortcuts for summary() and head().
s <- base::summary
h <- utils::head

## ht==headtail, i.e., show the first and last 10 items of an object
ht <- function(d) rbind(head(d,10),tail(d,10))

## Show the first 5 rows and first 5 columns of a data frame or matrix
hh <- function(d) d[1:5,1:5]

## Open current directory on mac
mac.o <- function(...) system("open .")

## Takes a dataframe and a column name, and moves that column to the front of the DF.
column.front <- function(d=dataframe, colname="colname") {
  index <- match(colname, names(d))
  cbind(d[index],d[-index])
}

read.file <- function(f) {
  q <- readLines(f, warn=F)
  return (paste(q, collapse='\n'))
}

## Multiplot utility function for ggplot viewports

# Multiple plot function
#
# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)
# - cols:   Number of columns in layout
# - layout: A matrix specifying the layout. If present, 'cols' is ignored.
#
# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),
# then plot 1 will go in the upper left, 2 will go in the upper right, and
# 3 will go all the way across the bottom.
#
multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {
  require(grid)
  
  # Make a list from the ... arguments and plotlist
  plots <- c(list(...), plotlist)
  
  numPlots = length(plots)
  
  # If layout is NULL, then use 'cols' to determine layout
  if (is.null(layout)) {
    # Make the panel
    # ncol: Number of columns of plots
    # nrow: Number of rows needed, calculated from # of cols
    layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),
                     ncol = cols, nrow = ceiling(numPlots/cols))
  }
  
  if (numPlots==1) {
    print(plots[[1]])
    
  } else {
    # Set up the page
    grid.newpage()
    pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))
    
    # Make each plot, in the correct location
    for (i in 1:numPlots) {
      # Get the i,j matrix positions of the regions that contain this subplot
      matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))
      
      print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,
                                      layout.pos.col = matchidx$col))
    }
  }
}

# Did you make it this far?
message("\n******************************\nSuccessfully loaded Rprofile.r\n******************************")