Created
March 16, 2014 01:31
-
-
Save dmarx/9577136 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(TTR) | |
GetClosePrices=function(stocks, from=20090206, to=20140206){ | |
# Returns a dataframe whose columns correspond to | |
# the prices of stocks in the input parameter. | |
# | |
# stocks: A character vector of ticker symbols | |
# from/to: Dates in YYYYMMDD format, from < to. | |
df = xts() | |
symbols=c() | |
for(sym in stocks){ | |
print(sym) | |
#prices = getYahooData(sym, from, to)$Close | |
#df = tryCatch({ | |
tryCatch({ | |
data = getYahooData(sym, from, to) | |
prices = data$Close | |
if(length(prices)>0){ | |
df=merge(df, prices) | |
symbols=c(symbols, sym)} | |
#print(length(symbols)) | |
#print(dim(df)) | |
#merge(df, prices) | |
}, | |
error=function(cond) { | |
print(paste("Error encountered retrieving symbol:",sym)) | |
print(cond) | |
#df | |
}, | |
warning=function(cond) { | |
print(paste("Warning encountered retrieving symbol:",sym)) | |
print(cond) | |
#df | |
}#, | |
#finally=df | |
) | |
if(length(symbols)!=dim(df)[2]){ | |
print("PROBLEMO!!") | |
return(NULL) | |
} | |
#df = merge(df, prices, join='inner') # drop missing days | |
} | |
print(length(symbols)) | |
print(dim(df)) | |
colnames(df) = symbols #stocks | |
df | |
} | |
WeekYear <- function(x, format="%Y-%m-%d"){ | |
# from http://grokbase.com/t/r/r-help/124yxpntwm/r-extracting-week-number-starting-from-a-specific-date | |
as.integer(format(strptime(x, format=format), "%Y%W")) | |
} | |
Calc_r_ji = function(stocks){ | |
wy = WeekYear(index(stocks)) | |
unq_wy = unique(wy) | |
# Extract the first trading day from each week | |
# There's probably a better way to do this... | |
firstday_ix = c() | |
for(d in unq_wy){ | |
first = which(wy==d)[1] | |
firstday_ix = c(firstday_ix, first) | |
} | |
# coerce to dataframe to allow for subtraction as I have it | |
# in the r_ji calculation | |
d_ji = data.frame(stocks[firstday_ix]) | |
n=nrow(d_ji) | |
r_ji = (d_ji[-1,] - d_ji[-n,])/d_ji[-n,] | |
r_ji | |
} | |
GetStats=function(stock_names=all_stocknames2 | |
,start_date=20120206 | |
,end_date=20140206){ | |
prices = GetClosePrices(stock_names, start_date, end_date) | |
# Trim stocks down only those that have the most days in common. | |
# This method assumes that all rows that are NA are in common, which | |
# won't strictly be true, so the end number of rows will be somewhat | |
# less than the anticipated total, but this will still give us a lot | |
# of data to work with. | |
colnas = lapply(prices, function(x)sum(is.na(x))) | |
colnas = sapply(colnas, c) | |
num_na = as.integer(names(which(table(colnas) == max(table(colnas))))) | |
prices = prices[,colnas==num_na] | |
prices = na.omit(prices) | |
r_ji = Calc_r_ji(prices) | |
mu = colMeans(r_ji, na.rm=TRUE) | |
sigma = cov(r_ji, use="pairwise.complete.obs") | |
list(mu=mu, sigma=sigma, r_ji=r_ji, prices=prices) | |
} | |
stockData = GetStats() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment