ReproduceIBLE Research

Load packages used in this analysis.

if (!require(ggplot2)) {
    install.packages("ggplot2")
    library(ggplot2)
}

xtable package

if (!require(xtable)) {
    install.packages("xtable")
    library(xtable, warn.conflicts = FALSE)
}

Load Data

Download the data by given link

setwd("~/repos/coursera/data-science-specialization-github-assignments/reproducible-research-course-project-2")
stormDataFileURL <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
stormDataFile <- "data/storm-data.csv.bz2"
if (!file.exists('data')) {
    dir.create('data')
}
if (!file.exists(stormDataFile)) {
    download.file(url = stormDataFileURL, destfile = stormDataFile)
}
stormData <- read.csv(stormDataFile, sep = ",", header = TRUE)
stopifnot(file.size(stormDataFile) == 49177144) 
stopifnot(dim(stormData) == c(902297,37))

Clean Date Data

Format date variables

stormDataTidy$DATE_START <- as.Date(stormDataTidy$BGN_DATE, format = "%m/%d/%Y")
stormDataTidy$DATE_END <- as.Date(stormDataTidy$END_DATE, format = "%m/%d/%Y")
stormDataTidy$YEAR <- as.integer(format(stormDataTidy$DATE_START, "%Y"))
stormDataTidy$DURATION <- as.numeric(stormDataTidy$DATE_END - stormDataTidy$DATE_START)/3600

Summarize Data

Summarized dataset of health impact data (fatalities + injuries). Sorting.

healthImpactData <- aggregate(x = list(HEALTH_IMPACT = stormDataTidy$FATALITIES + stormDataTidy$INJURIES), 
                                  by = list(EVENT_TYPE = stormDataTidy$EVTYPE), 
                                  FUN = sum,
                                  na.rm = TRUE)
healthImpactData <- healthImpactData[order(healthImpactData$HEALTH_IMPACT, decreasing = TRUE),]

Summarized dataset of damage impact costs (property damage + crop damage). Sorting in descending order by damage cost.

damageCostImpactData <- aggregate(x = list(DAMAGE_IMPACT = stormDataTidy$PROP_COST + stormDataTidy$CROP_COST), 
                                  by = list(EVENT_TYPE = stormDataTidy$EVTYPE), 
                                  FUN = sum,
                                  na.rm = TRUE)
damageCostImpactData <- damageCostImpactData[order(damageCostImpactData$DAMAGE_IMPACT, decreasing = TRUE),]

Results

Q1.) Event Types Most Harmful to Population Health

print(xtable(head(healthImpactData, 10),
             caption = "Top 10 Weather Events Most Harmful to Population Health"),
             caption.placement = 'top',
             type = "html",
             include.rownames = FALSE,
             html.table.attributes='class="table-bordered", width="100%"')

healthImpactChart <- ggplot(head(healthImpactData, 10),
                            aes(x = reorder(EVENT_TYPE, HEALTH_IMPACT), y = HEALTH_IMPACT, fill = EVENT_TYPE)) +
                            coord_flip() +
                            geom_bar(stat = "identity") + 
                            xlab("Event Type") +
                            ylab("Total Fatalities and Injures") +
                            theme(plot.title = element_text(size = 14, hjust = 0.5)) +
                            ggtitle("Top 10 Weather Events Most Harmful to\nPopulation Health")
print(healthImpactChart)

Q2.) Event Types with Greatest Economic Consequences

print(xtable(head(damageCostImpactData, 10),
             caption = "Top 10 Weather Events with Greatest Economic Consequences"),
             caption.placement = 'top',
             type = "html",
             include.rownames = FALSE,
             html.table.attributes='class="table-bordered", width="100%"')

damageCostImpactChart <- ggplot(head(damageCostImpactData, 10),
                            aes(x = reorder(EVENT_TYPE, DAMAGE_IMPACT), y = DAMAGE_IMPACT, fill = EVENT_TYPE)) +
                            coord_flip() +
                            geom_bar(stat = "identity") + 
                            xlab("Event Type") +
                            ylab("Total Property / Crop Damage Cost\n(in Billions)") +
                            theme(plot.title = element_text(size = 14, hjust = 0.5)) +
                            ggtitle("Top 10 Weather Events with\nGreatest Economic Consequences")
print(damageCostImpactChart)