The zip file contains 332 comma-separated-value (CSV) files containing pollution monitoring data for fine particulate matter (PM) air pollution at 332 locations in the United States. Each file contains data from a single monitor and the ID number for each monitor is contained in the file name. For example, data for monitor 200 is contained in th…

complete.R

## Write a function that reads a directory full of files and reports the number of completely observed cases in each data file.
## The function should return a data frame where the first column is the name of the file and the second column is the number
## of complete cases. A prototype of this function follows
 
complete <- function(directory, id = 1:332) {
    ## 'directory' is a character vector of length 1 indicating
    ## the location of the CSV files
    ## 'id' is an integer vector indicating the monitor ID numbers
    ## to be used
    ## Return a data frame of the form:
    ## id nobs
    ## 1 117
    ## 2 1041
    ## ...
    ## where 'id' is the monitor ID number and 'nobs' is the
    ## number of complete cases

    comp <- data.frame(id=numeric(), nobs=numeric())

    for (i in id) {
        filename <- obsFileName(directory, i)
        data <- read.csv(filename)
        comp <- rbind(comp, data.frame(id=i, nobs=nrow(data[complete.cases(data), ])))
    }
    
    comp
}

corr.R

## Write a function that takes a directory of data files and a threshold
## for complete cases and calculates the correlation between sulfate and
## nitrate for monitor locations where the number of completely observed
## cases (on all variables) is greater than the threshold. The function
## should return a vector of correlations for the monitors that meet the
## threshold requirement. If no monitors meet the threshold requirement,
## then the function should return a numeric vector of length 0.

corr <- function(directory, threshold = 0) {
    ## 'directory' is a character vector of length 1 indicating
    ## the location of the CSV files
    ## 'threshold' is a numeric vector of length 1 indicating the
    ## number of completely observed observations (on all
    ## variables) required to compute the correlation between
    ## nitrate and sulfate; the default is 0
    ## Return a numeric vector of correlations

    source("complete.R")
    source("obsFileName.R")
    observations <- complete(directory, 1:332)
    sulfate <- numeric()
    nitrate <- numeric()
    result <- numeric()
    
    for (i in observations$id[observations$nobs > threshold]) {
        filename <- obsFileName(directory, i)
        data <- read.csv(filename)
        result <- c(result, cor(data$sulfate, data$nitrate, use="complete.obs"))
    }
     
    result
}

obsFileName.R

## Return relative path to csv file by detector number

obsFileName <- function(directory, obs) {
    if (obs<10) {
        filename = paste(directory, "/","00", obs, ".csv", sep="")
    } else if (obs >= 10 && obs < 100) {
        filename = paste(directory, "/", "0", obs, ".csv", sep="")
    } else {
        filename = paste(directory, "/", obs, ".csv", sep="")
    }
}

pollutantmean.R

## Write a function named 'pollutantmean' that calculates the mean of a pollutant
## (sulfate or nitrate) across a specified list of monitors. The function
## 'pollutantmean' takes three arguments: 'directory', 'pollutant', and 'id'.
## Given a vector monitor ID numbers, 'pollutantmean' reads that monitors'
## particulate matter data from the directory specified in the 'directory' argument
## and returns the mean of the pollutant across all of the monitors,
## ignoring any missing values coded as NA
 
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)

    source("obsFileName.R")
    allData <- numeric()
    
    for (i in id) {
        filename <- obsFileName(directory, i)
 
        data <- read.csv(filename)
        
        if (pollutant == "sulfate") {
            allData <- c(allData, data$sulfate)
        } else if (pollutant == "nitrate") {
            allData <- c(allData, data$nitrate)
        }
    }
    
    mean(allData, na.rm=TRUE)
}