# Commands that generated the results of Section 2.1 of
# "The Portfolio Probe User's Manual"
#
# These commands demonstrate the static random portfolio method 
# of performance measurement
#
# This depends on functions listed in 'pprobe_functions01.R'
# The data are created in 'pprobe_R_data01.txt'
#
# The functions that create the graphs are in 'pprobe_graphFun01.R'
# If you want hardcopies of the graphs, then you need to start a
# graphics device (like 'pdf') and do 'dev.off()' after the graphs
# are created.




# things to CHANGE, possibly

PP_LOC <- ".." 





# initial setup

if(!exists("us.pricemat")) attach(paste(PP_LOC, "us.pricemat.rda", sep="/"))
if(!exists("us.macdmat")) attach(paste(PP_LOC, "us.macdmat.rda", sep="/"))




# create the starting portfolio
init.20.w10 <- trade.optimizer(us.pricemat[251,], 
	expected.return=us.macdmat[251,], port.size=20, max.weight=.1, 
	gross.value=1e6, long.only=TRUE,
	do.warn=c(novar=FALSE, utility.switch=FALSE))


# These optimizations do not involve a variance for simplicity
# Real optimizations almost certainly will, see the file
# 'pprobe_R_varCache.txt' for a method of dealing with 
# large variance matrices

# do the series of optimizations for 200% turnover
ser.20.w10.t200 <- pp.serial.opt(init.20.w10, pricemat=us.pricemat[-1:-251,], 
	alphamat=us.macdmat, frac.turnover=2/252, max.weight=.1, 
	port.size=20, do.warn=c(novar=FALSE, utility.switch=FALSE), 
	keep.port=TRUE)

# do the series of optimizations for 400% turnover
ser.20.w10.t400 <- pp.serial.opt(init.20.w10, pricemat=us.pricemat[-1:-251,], 
	alphamat=us.macdmat, frac.turnover=4/252, max.weight=.1, 
	port.size=20, do.warn=c(novar=FALSE, utility.switch=FALSE), 
	keep.port=TRUE)

# generate random portfolios that obey constraints at start of period
rp251.20.w10 <- random.portfolio(1000, us.pricemat[251,], 
	expected.return=us.macdmat[251,], port.size=20, max.weight=.1, 
	gross.value=1e6, long.only=TRUE)

# calculate returns of random portfolios for 2007
rp251.20.w10.ret07 <- pp.simpret(valuation(rp251.20.w10, 
	us.pricemat[c(251, nrow(us.pricemat)-252),], collapse=TRUE))

# calculate return of optimal portfolios for 2007
serret200.07 <- ser.20.w10.t200$value[251]/ser.20.w10.t200$value[1] - 1
serret400.07 <- ser.20.w10.t400$value[251]/ser.20.w10.t400$value[1] - 1

# calculate returns of random portfolios for 2007-2008
rp251.20.w10.ret0708 <- pp.simpret(valuation(rp251.20.w10, 
	us.pricemat[c(251, nrow(us.pricemat)),], collapse=TRUE))

# calculate return of optimal portfolios for 2007-2008
serret200.0708 <- ser.20.w10.t200$value[504]/ser.20.w10.t200$value[1] - 1
serret400.0708 <- ser.20.w10.t400$value[504]/ser.20.w10.t400$value[1] - 1


# create the graphs
P.simpm07(NULL)
P.simpm0708(NULL)


# calculate percentiles

round(100 * mean(rp251.20.w10.ret07 < serret200.07))
round(100 * mean(rp251.20.w10.ret07 < serret400.07))

round(100 * mean(rp251.20.w10.ret0708 < serret200.0708))
round(100 * mean(rp251.20.w10.ret0708 < serret400.0708))