# Statistical abstract of Affy Annotations file
# efg, 22 June 2005

filename <- file.choose()
cat(filename, "\n")
d <- read.csv(filename, as.is=TRUE)

# ID info
cat("\n")
print(d[1,2:4])
cat("\n")

N <- ncol(d)
dbstats <- data.frame(name=names(d),
                    MinLength=rep(NA,N), MaxLength=rep(NA,N),
                    UniqueCount=rep(NA,N),
                    MissingCount=rep(NA,N))

for (i in 1:ncol(d))
{
  dbstats$MinLength[i]    <- min( nchar(  d[[i]] ) )
  dbstats$MaxLength[i]    <- max( nchar(  d[[i]] ) )
  dbstats$UniqueCount[i]  <- length( unique( d[[i]] ) )
  dbstats$MissingCount[i] <- sum( d[[i]] == "---"  )  # Affy "missing"
}

print(dbstats)