Synopsis

Severe weather in the United States impacts lives and causes economy damage every year. This analysis will show the most significant types of severe weather events that adversely affect population health and cause economic damage beween 1950 and 2011.

This analysis explores the NOAA storm database of severe weather reports between 1950 and November 2011. It will answer two questions:
1. Which type of weather events cause the greatest number of weather related fatalities
2. Which type of weather events cause the greatest economical damage

Data Processing

This section contains R steps to download the data, import it into R and calculate results.

R Library Calls

library(plyr)
## Warning: package 'plyr' was built under R version 3.1.2
library(knitr)
library(RCurl)
## Warning: package 'RCurl' was built under R version 3.1.2
## Loading required package: bitops

Source Data

Data for this analysis can be found at: https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2

National Weather Service Storm Data Documentation

National Climatic Data Center Storm Events FAQ

R Code to Download Zip File to working directory.

 fileUrl <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
 destfilepath <- paste(getwd(),"/stormdata2.csv.bz2",sep="")

 if (!file.exists(destfilepath)){
      download.file(fileUrl, destfile=destfilepath) 
 }

Data import and calculations

R Code to Read in data from working directory.

 stormdata <- read.csv(bzfile(destfilepath), fill=TRUE)

Sample data rows

head(stormdata, n=3)
##   STATE__          BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE
## 1       1 4/18/1950 0:00:00     0130       CST     97     MOBILE    AL
## 2       1 4/18/1950 0:00:00     0145       CST      3    BALDWIN    AL
## 3       1 2/20/1951 0:00:00     1600       CST     57    FAYETTE    AL
##    EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 1 TORNADO         0                                               0
## 2 TORNADO         0                                               0
## 3 TORNADO         0                                               0
##   COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES
## 1         NA         0                      14.0   100 3   0          0
## 2         NA         0                       2.0   150 2   0          0
## 3         NA         0                       0.1   123 2   0          0
##   INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES
## 1       15    25.0          K       0                                    
## 2        0     2.5          K       0                                    
## 3        2    25.0          K       0                                    
##   LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1     3040      8812       3051       8806              1
## 2     3042      8755          0          0              2
## 3     3340      8742          0          0              3

Summarizing the Data

PubHealthDamage <- ddply(stormdata, c("EVTYPE"),summarize,Fatalities=sum(FATALITIES))
PubHealthDamage <- PubHealthDamage[order(-PubHealthDamage["Fatalities"]),]
Top10FatalTypes <- PubHealthDamage[1:10,]

EconDamage <- ddply(stormdata, c("EVTYPE"),summarize,PropDmg=sum(PROPDMG))
EconDamage <- EconDamage[order(-EconDamage["PropDmg"]),]
Top10EconDmgTypes <- EconDamage[1:10,]

Results

To understand the impact on public health, the number of fatalities related to the weather event was calculated. The Top 10 events causing the most fatalities shows Tornados cause the most weather related events. Tornados caused 5,633 fatalities over the 61 years of data tracked by NOAA.

par(mar=c(4,4,2,1))
par(oma=c(4,2,0,0))
PHPlot <- barplot(Top10FatalTypes$Fatalities, names.arg = Top10FatalTypes$EVTYPE, main="Top 10 Severe Weather Events Causing Most Fatalities",ylim=c(0,500+max(Top10FatalTypes$Fatalities)),las=2,col=c("red"))
text(PHPlot, Top10FatalTypes$Fatalities, labels=prettyNum(round(Top10FatalTypes$Fatalities),big.mark=","), pos=3, col="black")

dev.off()
## null device 
##           1

To understand the impact on the economy, the measure of property damage related to the weather event was calculated. The Top 10 events causing the most damage shows tornados also cause the most weather related property damage. Tornados caused $3.2M in property damage over the 61 years of data tracked by NOAA.

par(mar=c(4,4,2,1))
par(oma=c(8,2,0,0))

EDPlot <- barplot(Top10EconDmgTypes$PropDmg, names.arg = Top10EconDmgTypes$EVTYPE, main="Top 10 Severe Weather Events Causing Most Property Damage",ylim=c(0,500000+max(Top10EconDmgTypes$PropDmg)),las=2,col=c("blue"))

dev.off()
## null device 
##           1