pollutant.R

# problem 1
# part 1

pollutantmean <- function(directory, pollutant, id = 1:332) {
  filelist <- list.files(path = directory, pattern = ".csv",
                        full.names = TRUE)
  
  values <- numeric()
  
  for(i in id) {
    data <- read.csv(filelist[i])
    values <- c(values, data[[pollutant]]) # sulfate or nitrate
  }
  mean(values, na.rm = TRUE)
}

pollutantmean("specdata/", "nitrate", 70:72)



# part 2

complete <- function(directory, id = 1:332) {
  filelist <- list.files(path = directory, pattern = ".csv",
                         full.names = TRUE)
  # create empty vectors to later be cbind'd into a data frame
  ide <- numeric()
  nobs <- numeric()
  
  for(i in id) {
    # reads the data directory
    data <- read.csv(filelist[i])
    # id numbers chosen gets put into the vector
    ide <- c(ide, id[i])
    # finds all the values that are not NA and assigns to nobs vector
    nobs <- c(nobs, sum(!is.na(data[[2]])))
  }
  data.frame(cbind(id, nobs)) # vectors now with data, changed to DF
} 

# part 3

test