gistfile1.txt

# Get a list of the FTSE-100 companies
# e.g. by scraping a suitable web page
require(XML)
require(RCurl)

pagescrape = readHTMLTable(getURL('https://en.wikipedia.org/wiki/FTSE_100_Index'))
n.rows     = unlist(lapply(pagescrape,function(tab)if(!is.null(dim(tab)[1]))dim(tab)[1] else 0))   
stocktable = pagescrape[[which.max(n.rows)]] # grab biggest table on the page

stocktable$Ticker = sub('^(.*)\\.(.+)$','\\1-\\2',stocktable$Ticker) # cope with BT.A
ftse100 = sub('^(.*?)\\.?$','\\1.L',stocktable$Ticker) # add .L to all stock names

# Now grab the historical data for the ftse100 stocks
require(quantmod)
getSymbols(ftse100,auto.assign=TRUE,src='yahoo',env=.GlobalEnv,from='2015-01-01') # get historical stock data from yahoo

# Build the list of daily returns
require(TTR)
roclist = do.call(cbind,lapply(ftse100,function(x){ROC(Cl(get(x)))}))
names(roclist) = ftse100
roclist = tail(roclist, 256) # only keep last 256 days of data

#
# Some tidying up due to problems with Yahoo's data feed.
# It's a bit frightening how many stocks have missing data
#
roclist = roclist[, colSums(is.na(roclist)) < nrow(roclist)*0.1] # remove stocks with insufficient data
roclist = na.omit(roclist) # remove any days with missing data

# NB: The following arrays are daily means and variances

mean.return       = colMeans(roclist,na.rm=T)
covariance.matrix = cov(roclist,use="pairwise.complete.obs")

View(mean.return)
View(covariance.matrix)

# create a portfolio by specifying the weight for each stock
# sum(portfolio) should be 1

# The example here would be an equal-weighted portfolio of every ftse100 stock

portfolio        = rep(1/ncol(roclist),ncol(roclist))
names(portfolio) = names(roclist)

#
# Approximate yearly return and volatility of the portfolio, assuming 225 working days in year
#
return.of.portfolio     = as.numeric(t(portfolio) %*% mean.return) * 225
volatility.of.portfolio = sqrt(as.numeric(t(portfolio) %*% cov(roclist) %*% portfolio)) * sqrt(225)