#page(describe(pbc), multi=T)
datadensity(pbc)
nac <- naclus(pbc)
plot(nac)
naplot(nac)
plot(varclus(~.,data=diabetes))

x <- c(1,2,6,NA)
x <- impute(x)
x
is.imputed(x)
attributes(x)
describe(x)

x <- runif(100)
smean.cl.normal(x)
smean.cl.boot(x)
smean.sd(x)
smean.sdl(x)

binconf(6, 10, .01)

bpower(.1, .2, n=500)
bpower.sim(.1, .2, n=500)

spearman2(glyhb ~ age + gender + frame,
  data=diabetes, p=2)

s <- summary(glyhb ~ age + chol + gender +
  frame, data=diabetes)
options(digits=3)
s # same print(s)
plot(s)
s <- summary(glyhb ~ age + chol + gender +
  frame, data=diabetes,
  fun=smean.cl.boot)
s
plot(s, which=1:3, pch=c('.','[',']'))
show.pch()

s <- summary(drug ~ age + platelet + chol +
 spiders + edema,data=pbc)
options(width=100)
#page(s)
plot(s)

hist.data.frame(pbc)
#attach(pbc)
ecdf(albumin)
ecdf(albumin,q=c(.25,.5,.75))
ecdf(albumin,group=drug)
ecdf(diabetes,group=diabetes$gender,
 col=1:2, label.curve=F)
ecdf(albumin, datadensity='rug')
ecdf(albumin, datadensity='density')
scat1d(albumin)

attach(titanic3)
plsmo(age, survived, group=sex,
  col=1:2, datadensity=T)

ecdf(~age|pclass,groups=sex,q=.5)
bwplot(pclass~age|sex)
bwplot(sex~age|pclass)

bwplot(sex ~ age | pclass,
  panel=panel.bpplot)

set.seed(13)
x <- rnorm(1000)
g <- sample(1:6, 1000, replace=T)
x[g==1][1:20] <- rnorm(20)+3   # contaminate 20 x's for group 1

# default trellis box plot
bwplot(g ~ x)

# box-percentile plot with data density (rug plot)
bwplot(g ~ x, panel=panel.bpplot, probs=seq(.01,.49,by=.01), datadensity=T)
# add ,scat1d.opts=list(tfrac=1) to make all tick marks the same size
# when a group has > 125 observations

# small dot for means, show only .05,.125,.25,.375,.625,.75,.875,.95 quantiles
bwplot(g ~ x, panel=panel.bpplot, cex=.3)

# suppress means and reference lines for lower and upper quartiles
bwplot(g ~ x, panel=panel.bpplot, probs=c(.025,.1,.25), means=F, qref=F)

# continuous plot up until quartiles ("Tootsie Roll plot")
bwplot(g ~ x, panel=panel.bpplot, probs=seq(.01,.25,by=.01))

# start at quartiles then make it continuous ("coffin plot")
bwplot(g ~ x, panel=panel.bpplot, probs=seq(.25,.49,by=.01))

# same as previous but add a spike to give 0.95 interval
bwplot(g ~ x, panel=panel.bpplot, probs=c(.025,seq(.25,.49,by=.01)))

# decile plot with reference lines at outer quintiles and median
bwplot(g ~ x, panel=panel.bpplot, probs=c(.1,.2,.3,.4), qref=c(.5,.2,.8))

# default plot with tick marks showing all observations outside the outer
# box (.05 and .95 quantiles), with very small ticks
bwplot(g ~ x, panel=panel.bpplot, nout=.05, scat1d.opts=list(frac=.01))

# show 5 smallest and 5 largest observations
bwplot(g ~ x, panel=panel.bpplot, nout=5)

# Use a scat1d option (preserve=T) to ensure that the right peak extends 
# to the same position as the extreme scat1d

bwplot(~x , panel=panel.bpplot, probs=seq(.00,.5,by=.001), 
       datadensity=T, scat1d.opt=list(preserve=T))

# attach(diabetes)
label(chol)
xYplot(chol ~ age, groups=gender, type='p')
Key()
xYplot(chol ~ age|location, groups=gender, type='p')
Key()
?xYplot

dfr <- expand.grid(month=1:12, continent=c('Europe','USA'), 
                   sex=c('female','male'))
attach(dfr)
set.seed(13)
y <- month/10 + 1*(sex=='female') + 2*(continent=='Europe') + 
  runif(48,-.15,.15)
lower <- y - runif(48,.05,.15)
upper <- y + runif(48,.05,.15)

xYplot(Cbind(y,lower,upper) ~ month,subset=sex=='male'&continent=='USA')
# add ,label.curves=F to suppress use of labcurve to label curves where farthest apart

xYplot(Cbind(y,lower,upper) ~ month|continent,subset=sex=='male')
xYplot(Cbind(y,lower,upper) ~ month|continent,groups=sex); Key()
xYplot(Cbind(y,lower,upper) ~ month,groups=sex,subset=continent=='Europe')
xYplot(Cbind(y,lower,upper) ~ month,groups=sex,subset=continent=='Europe',keys='lines')
# keys='lines' causes labcurve to draw a legend where the panel is most empty


s <- summarize(y, llist(month,year), smean.cl.boot)
s
xYplot(Cbind(y, Lower, Upper) ~ month | year, data=s)

xYplot(glyhb ~ chol|gender,
 method=smean.cl.normal)

Dotplot(month ~ Cbind(y, Lower, Upper) | year, data=s) 
# or Cbind(...), groups=year, data=s

# Display a 5-number (5-quantile) summary (2 intervals, dot=median)
# Note that summarize produces a matrix for y, and Cbind(y) trusts the
# first column to be the point estimate (here the median)
s <- summarize(y, llist(month,year), quantile,
               probs=c(.5,.05,.25,.75,.95), type='matrix')
Dotplot(month ~ Cbind(y) | year, data=s)
# Use factor(year) to make actual years appear in conditioning title strips
dim(s)
names(s)
dim(s$y)