aaronsaunders

fp = open("file.txt")
data = fp.read().decode("utf-8-sig").encode("utf-8")

aaronsaunders

p1 <- pw + geom_point() + facet_grid(.~g, scales='fixed') + coord_equal() +   
      stat_smooth(method='lm')
p2 <- px + geom_point() + facet_grid(.~g, scales='fixed') + coord_equal() + 
      stat_smooth(method='lm')
p3 <- pz + geom_point() + facet_grid(.~g, scales='fixed') + coord_equal() +   
      stat_smooth(method='lm')

grid.arrange(p1, p2, p3, ncol=1)

aaronsaunders

# create new MarinerNames field that contains only the name of Mariners
# players (plagarized from Winston Chang's R Graphics Cookbook Recipe 5.11)
outfield$MarinerNames = outfield$Name
idx = (outfield$Team.x == "Mariners")
outfield$MarinerNames[!idx] = NA
# create a new table, taking a subset that has only the Mariners players
Mariners = subset(outfield, Team.x == "Mariners")
# add the names of the UZR stars to outfield$Table2 sort the table by
# wRAA, then add the names of the top 4 wRAA stars
outfield$wRAAstars = outfield$Name

aaronsaunders

dat <- data.frame(x = rnorm(10), y = rnorm(10), label = letters[1:10])

#Create a subset of data that you want to label. Here we label points a - e
labeled.dat <- dat[dat$label %in% letters[1:5] ,]

ggplot(dat, aes(x,y)) + geom_point() +
  geom_text(data = labeled.dat, aes(x,y, label = label), hjust = 2)

#Or add a separate layer for each point you want to label.
ggplot(dat, aes(x,y)) + geom_point() +

aaronsaunders

# Recently I wanted to recreate  assocplot  using  ggplot2. In the end I propose a simple way to visualize data arranged two-way tables using geom_tile.
#
# I used Titanic data set as an example combining age and sex dimensions to get two-way data.
#
# I plot residuals of Chi-squared test (like in assocplot) on the left and probability of survival on the right. A nice feature of geom_tile is that nicely highlights missing data (children were not crew members). Here is a code generating the plots:

library(ggplot2)
library(grid)
library(reshape2)

aaronsaunders

colSums( x, na.rm= FALSE, dims= 1)
rowSums( x, na.rm= FALSE, dims= 1)
colMeans(x, na.rm= FALSE, dims= 1)
rowMeans(x, na.rm= FALSE, dims= 1)
rowsum(x, group, reorder= TRUE)    # finds row sums for each level of a grouping variable
apply(X, MARGIN, FUN, ...)         # applies the function (FUN) to either rows (1) or columns (2) on object X
apply(x, 1, min)                   # finds the minimum for each row
apply(x, 2, max)                   # finds the maximum for each column
col.max(x)                         # another way to find which column has the maximum value for each row 
which.min(x)

aaronsaunders

install.packages("Hmisc",dependencies=TRUE)
update.packages()
q()

setwd()
getwd()
ls()           # lists objects
rm(object)     # deletes an object

library(RColorBrewer)  # load ColorBrewer palettes

aaronsaunders

#
# Steve Pittard - [email protected], 03/19/12
# Code to illustrate motivations for using apply function
#
# See www.bimcore.emory.edu/bbseries for slides and code downloads
#
# References include:
# http://statland.org/R/R/Rpulse2.htm , http://www.cyclismo.org/tutorial/R/tables.html#manipulations
# http://nsaunders.wordpress.com/2010/08/20/a-brief-introduction-to-apply-in-r/
# 

aaronsaunders

# run a quick demonstration
install.packages("Hmisc",dependencies=TRUE)
update.packages()
library("Hmisc")
mydata<-spss.get("http://www.rci.rutgers.edu/~rwomack/R/vermont.sav",use.value.labels=TRUE)
head(mydata)
tail(mydata)
summary(mydata)
attach(mydata)
hist(AGEP)

aaronsaunders

library(lattice)

my.wines <- read.csv("http://www.bimcore.emory.edu/wine.csv", header=TRUE)

# Look at the correlations

library(gclus)
my.abs     <- abs(cor(my.wines))
my.colors  <- dmat.color(my.abs)
my.ordered <- order.single(cor(my.wines))