pollutantmean.R

# Import file for data loading
source("dataloader.R")

# function

pollutantmean <- function(directory, pollutant, id = 1:332) {
        ## 'directory' is a character vector of length 1 indicating
        ## the location of the CSV files
        
        ## 'pollutant' is a character vector of length 1 indicating
        ## the name of the pollutant for which we will calculate the
        ## mean; either "sulfate" or "nitrate".
        
        ## 'id' is an integer vector indicating the monitor ID numbers
        ## to be used
        
        ## Return the mean of the pollutant across all monitors list
        ## in the 'id' vector (ignoring NA values)
        
        files = sprintf("%s/%03d.csv", directory, id)
        data.list = lapply(files, read.csv, header=T)
        data.df = do.call(what="rbind",
                          args=data.list)
        mean(data.df[[pollutant]], na.rm = T)
}