stevenworthington

library(ggplot2)
library(plyr)
data(mpg)

# create a data frame with averages and standard deviations
hwy.means <- ddply(mpg, c("class", "year"), summarize,  hwy.avg = mean(hwy), hwy.sd = sd(hwy))

# barplot with values over bars
ggplot(hwy.means) + 
    geom_bar(aes(class, hwy.avg, fill = factor(year)), position = "dodge", colour = "black", size = 0.3) +

stevenworthington

# example of how to concatenate lots of variables into a formula without typing them out

# example from the High School and Beyond data set
hsb_df <- read.table("http://www.ats.ucla.edu/stat/R/notes/hs0.csv", header = TRUE, sep = ",")

# create the formula using variables from columns 4:8 and 10:11 as predictors
hsb_form <- formula( paste(c("math ~ 1", colnames(hsb_df[, c(4:8, 10:11)])), collapse = " + ") ) 

# fit the model
fit1 <- lm(hsb_form, data = hsb_df)

stevenworthington

# ipak function: install and load multiple R packages.
# check to see if packages are installed. Install them if they are not, then load them into the R session.

ipak <- function(pkg){
    new.pkg <- pkg[!(pkg %in% installed.packages()[, "Package"])]
    if (length(new.pkg)) 
        install.packages(new.pkg, dependencies = TRUE)
    sapply(pkg, require, character.only = TRUE)
}

stevenworthington

# ===============================================================================
# Name               : centroid_perm
# Original author    : Steven Worthington (sworthington@iq.harvard.edu)
# Affiliation        : IQSS, Harvard University
# Date (mm/dd/yyyy)  : 06/14/2012 
# Version            : v0.8
# Aim                : exact permutation test for group differences
# ===============================================================================

# Goal:

stevenworthington

# example of calculating K-medoids using the uncentered
# correlation metric as a measure of distance


# 0) load data
data(mtcars)


# 1) create a distance matrix using the "cosine of the angle" method (aka, uncentered correlation)

stevenworthington

# Note: requires loading the "socsub" data frame (not a bundled R dataset)


# ------------------------------------------------------------------------------------
# pairwise comparisons including interactions


# use lm model to get design matrix
model1 <- lm(agro.rec.tot ~ sex*ageclass + loggrpmem, offset = logtimeage, data = socsub)

stevenworthington

# list with character vectors
text <- list(a = "all day I play @sworth with R",
             b = "all night I play @sworth with R")

# extract letters after "@" in a single character vector
sub("^.*@(\\w+).*", "\\1", text$a) 

# extract letters after "@" in a list of character vectors
gsub("^.*@(\\w+).*", "\\1", text)

stevenworthington

library(sp)
library(maptools)

# get North Carolina shape data
NC <- readShapePoly(system.file("shapes/sids.shp", package = "maptools")[1],
          IDvar = "FIPSNO", proj4string = CRS("+proj=longlat +ellps=clrk66"))

# plot polygons
plot(NC, border = "blue", axes = TRUE, las = 1)

stevenworthington

# set working directory
dir_path <-  "path_to_text_files"
setwd(dir_path)

# create vector of filenames
filenames <- list.files(dir_path)

# read in files to a list
docList <- lapply(filenames, scan, what = "character", sep = "\n")

stevenworthington

x <- c(
	'knitr', #  A general-purpose package for dynamic report generation in R.
# 'sqldf', # For running SQL statements on R data frames, optimized for convenience.
	'randomForest', # Classification and regression based on a forest of trees using random inputs.
	'arm', # R functions for processing lm, glm, svy.glm, mer and polr outputs.
	'ggplot2', # An implementation of the Grammar of Graphics.
	'gridExtra', # misc. high-level Grid functions
	'plyr', # Tools for splitting, applying and combining data.
	'tree', # Classification and regression trees.
	'gbm', # Generalized Boosted Regression Models