util.R

# Download the zip file, and extract it into the work folder,
# select the rows we need, add the date time as a new column,
# and then return the data.
getData <- function() {

    # URL and files names
    fileUrl <- 'https://d396qusza40orc.cloudfront.net/exdata%2Fdata%2Fhousehold_power_consumption.zip'
    zipFile <- 'exdata-data-household_power_consumption.zip'
    destFile <- 'household_power_consumption.txt'

    # Download and unzip
    if(!file.exists(zipFile)) {
        download.file(fileUrl, zipFile, mode="wb")
    }
    if(!file.exists(destFile)) {
        unzip(zipFile, destFile)
    }

    # Define column data types
    cols <- c("character", "character", rep("numeric", 7))

    # Using sqldf to load only data we need
    if(!require('sqldf')){
        install.packages('sqldf')
    }
    library(sqldf)
    dataFrame <- read.csv(destFile, sep=";")
    sql <- "select * from dataFrame where Date='2/2/2007' or Date='1/2/2007'"
    data <- sqldf(sql)

    # Get datetime for the plot and add them to the data
    dateTime <- paste(data$Date, data$Time, sep=' ')
    dateTime <- strptime(dateTime, format = "%d/%m/%Y %H:%M:%S")
    data$DateTime <- dateTime

    # Return the data
    data
}