-a directory (no issue on that !)
-a column (nitrate||sulfate)
-a vector containing all the numbers corresponding to the names of
files to be considered for the mean calculation (from 1 to 332)).

pollutantmean<-function(directory="specdata",pollutant="nitrate", id=1:332) {
    numerator<-0    #mean numerator init
    denominator<-0  #mean denominator init
    for (i in 1:length(id)) {
        numero<-id[i]
        filenames <- sprintf("%03d.csv", numero)
        filenames <- paste("C:/Users/quent/Desktop/DSS", directory, filenames, sep="/")
        fichier<-read.csv(filenames)
        numerator<-numerator+sum(fichier[pollutant],na.rm = TRUE)
        col<-fichier[pollutant]
        denominator<-denominator+length(col[!is.na(col)])
    }
    print(numerator/denominator)
}

pollutantmean("specdata", "nitrate", 1:274)
[1] 1.73748

pollutantmean("specdata", "nitrate", 1:275)
> Error in FUN(X[[i]], ...) :
> only defined on a data frame with all numeric variables