In this project, we analyze the storm database taken from the U.S. National Oceanic and Atmospheric Administration (NOAA). We estimate the fatalities, injuries, property damage, and crop damage for each type of event (e.g., Flood, Typhoon, Tornado, Hail, Hurricane, etc.). Our goal is to determine which event is most harmful to US population (health) and which event has the largest economic consequences. Our analysis on Fatalities and Injuries conclude that Tornado is the most harmful event in respect to the US health (population). On the other hand, based on the Property and Cost damage, we conclude that Flood has the greatest economic consequences to the US.
Storms and other severe weather events can cause both public health and economic problems for communities and municipalities. Many severe events can result in fatalities, injuries, and property damage, and preventing such outcomes to the extent possible is a key concern.
This project involves exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database tracks characteristics of major storms and weather events in the United States, including when and where they occur, as well as estimates of any fatalities, injuries, and property damage.
The data for this assignment come in the form of a comma-separated-value file compressed via the bzip2 algorithm to reduce its size.
There is also some documentation of the database available. Here you will find how some of the variables are constructed/defined.
National Weather Service Storm Data Documentation National Climatic Data Center Storm Events FAQ The events in the database start in the year 1950 and end in November 2011. In the earlier years of the database there are generally fewer events recorded, most likely due to a lack of good records. More recent years should be considered more complete.
The data analysis address the following questions:
library(data.table)
library(ggplot2)First, we read the data by using read.csv:
data <- read.csv("repdata-data-StormData.csv.bz2", header = TRUE, sep=",")Use colnames to check the column names:
colnames(data)We are only interested in the column related to health and economic impacts. Therefore, only the following columns are needed and we can remove the rest.
EVTYPE FATALITIES INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
selection <- c('EVTYPE', 'FATALITIES', 'INJURIES', 'PROPDMG', 'PROPDMGEXP', 'CROPDMG', 'CROPDMGEXP')
data <- data[, selection]
summary(data)We also only need to use the data where fatalities, injuries, or damages occured.
data <- as.data.table(data)
data <- data[(EVTYPE != "?" & (INJURIES > 0 | FATALITIES > 0 | PROPDMG > 0 | CROPDMG > 0)),
c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")]We need to convert the exponent values from K, M, B to 1000, 1000000, and 1000000000.
cols <- c("PROPDMGEXP", "CROPDMGEXP")
data[, (cols) := c(lapply(.SD, toupper)), .SDcols = cols]
PROPDMGKey <- c("\"\"" = 10^0,
"-" = 10^0, "+" = 10^0, "0" = 10^0, "1" = 10^1, "2" = 10^2, "3" = 10^3,
"4" = 10^4, "5" = 10^5, "6" = 10^6, "7" = 10^7, "8" = 10^8, "9" = 10^9,
"H" = 10^2, "K" = 10^3, "M" = 10^6, "B" = 10^9)
CROPDMGKey <- c("\"\"" = 10^0, "?" = 10^0, "0" = 10^0, "K" = 10^3, "M" = 10^6, "B" = 10^9)
data[, PROPDMGEXP := PROPDMGKey[as.character(data[,PROPDMGEXP])]]
data[is.na(PROPDMGEXP), PROPDMGEXP := 10^0 ]
data[, CROPDMGEXP := CROPDMGKey[as.character(data[,CROPDMGEXP])] ]
data[is.na(CROPDMGEXP), CROPDMGEXP := 10^0 ]Combining the coefficient (mantissa) and exponent part of Property and Crop Damage.
data <- data[, .(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, PROPCOST = PROPDMG * PROPDMGEXP, CROPDMG, CROPDMGEXP, CROPCOST = CROPDMG * CROPDMGEXP)]In order to know the health impact, we estimate the total of Fatalities and Injuries for each event.
Health_Impact <- data[, .(FATALITIES = sum(FATALITIES), INJURIES = sum(INJURIES), TOTAL_HEALTH_IMPACTS = sum(FATALITIES) + sum(INJURIES)), by = .(EVTYPE)]
Health_Impact <- Health_Impact[order(-TOTAL_HEALTH_IMPACTS), ]
Health_Impact <- Health_Impact[1:10, ]
head(Health_Impact, 10)In order to know the economic impact, we estimate the total of Property Cost and Crop Cost for each event.
Eco_Impact <- data[, .(PROPCOST = sum(PROPCOST), CROPCOST = sum(CROPCOST), TOTAL_ECO_IMPACTS = sum(PROPCOST) + sum(CROPCOST)), by = .(EVTYPE)]
Eco_Impact <- Eco_Impact[order(-TOTAL_ECO_IMPACTS), ]
Eco_Impact <- Eco_Impact[1:10, ]
head(Eco_Impact, 10)We generate histogram to find the top 10 weather events that are most harmful to US population.
Health_Consequences <- melt(Health_Impact, id.vars = "EVTYPE", variable.name = "Fatalities_or_Injuries")
ggplot(Health_Consequences, aes(x = reorder(EVTYPE, -value), y = value)) +
geom_bar(stat = "identity", aes(fill = Fatalities_or_Injuries), position = "dodge") +
ylab("Total Injuries/Fatalities") +
xlab("Event Type") +
theme(axis.text.x = element_text(angle=45, hjust=1)) +
ggtitle("Top 10 US Weather Events that are Most Harmful to Population") +
theme(plot.title = element_text(hjust = 0.5))We generate histogram to find the top 10 weather events that have largest cost to US economy.
Eco_Consequences <- melt(Eco_Impact, id.vars = "EVTYPE", variable.name = "Damage_Type")
ggplot(Eco_Consequences, aes(x = reorder(EVTYPE, -value), y = value/1e9)) +
geom_bar(stat = "identity", aes(fill = Damage_Type), position = "dodge") +
ylab("Cost/Damage (in billion USD)") +
xlab("Event Type") +
theme(axis.text.x = element_text(angle=45, hjust=1)) +
ggtitle("Top 10 US Weather Events that have the Greatest Economic consequences") +
theme(plot.title = element_text(hjust = 0.5))