Reproducible Research - Peer Assessment 2
Saul G.
June 18, 2015
The Impact of Storms and Other Severe Weather Events in Public Health and Economic Problems for Communities and Municipalities
Synopsis
In this report we aim to describe the relationship between the storms and other severe weather events on both public health and economic problems for communities and municipalities. The study utilizes the U.S National Oceanic and Atmospheric Administration’s (NOAA) storm database.
Data Processing
Here we are going to download the data.
For information about the variables: - National Weather Service Storm (Data Documentation)[https://d396qusza40orc.cloudfront.net/repdata%2Fpeer2_doc%2Fpd01016005curr.pdf] - National Climatic Data Center Storm Events (FAQ)[https://d396qusza40orc.cloudfront.net/repdata%2Fpeer2_doc%2FNCDC%20Storm%20Events-FAQ%20Page.pdf]
Load Data
# Download the data for Mac or Windows
archiveFile<-"storm.csv.bz2"
if (!file.exists(archiveFile)){
fileUrl<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
if(Sys.info()["sysname"]=="Darwin"){
download.file(url=fileUrl, destfile=archiveFile, method="curl")
} else {
download.file(url=fileUrl, destfile=archiveFile)
}
}
#Decompress the csv.bz2 file
# Load data
storm <- read.csv("./storm.csv",header=TRUE,stringsAsFactors=FALSE)
#Install: install.packages("gridExtra")
#Look at the data
head(storm)## 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
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE 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
## 4 TORNADO 0 0
## 5 TORNADO 0 0
## 6 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
## 4 NA 0 0.0 100 2 0 0
## 5 NA 0 0.0 150 2 0 0
## 6 NA 0 1.5 177 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
## 4 2 2.5 K 0
## 5 2 2.5 K 0
## 6 6 2.5 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
## 4 3458 8626 0 0 4
## 5 3412 8642 0 0 5
## 6 3450 8748 0 0 6For this study we will only be utilizing the following variables: EVTYPE , FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP
# Subset these variables from the dataset
mydatacol<-c("EVTYPE","FATALITIES","INJURIES","PROPDMG","PROPDMGEXP","CROPDMG",
"CROPDMGEXP")
mydata<-storm[mydatacol]
head(mydata)## EVTYPE FATALITIES INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## 1 TORNADO 0 15 25.0 K 0
## 2 TORNADO 0 0 2.5 K 0
## 3 TORNADO 0 2 25.0 K 0
## 4 TORNADO 0 2 2.5 K 0
## 5 TORNADO 0 2 2.5 K 0
## 6 TORNADO 0 6 2.5 K 0Preparing the Property Damage data
First lets explore our data
unique(mydata$PROPDMGEXP)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-"
## [18] "1" "8"unique(mydata$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"# Translate the property and crop exponent data to numerical
#PROPERTY
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="K"]<-1e+03
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="M"]<-1e+06
mydata$PROPDMGEXP[mydata$PROPDMGEXP==""]<-1
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="B"]<-1e+09
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="m"]<-1e+06
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="0"]<-1
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="5"]<-1e+05
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="6"]<-1e+06
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="4"]<-1e+04
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="2"]<-1e+02
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="3"]<-1e+03
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="h"]<-1e+2
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="7"]<-1e+07
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="H"]<-1e+02
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="1"]<-1e+01
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="8"]<-1e+08
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="+"]<-0
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="?"]<-0
mydata$PROPDMGEXP[mydata$PROPDMGEXP=="-"]<-0
#CROP
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="M"]<-1e+06
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="K"]<-1e+03
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="m"]<-1e+06
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="B"]<-1e+09
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="0"]<-1
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="k"]<-1e+06
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="2"]<-1e+09
mydata$CROPDMGEXP[mydata$CROPDMGEXP==""]<-1
mydata$CROPDMGEXP[mydata$CROPDMGEXP=="?"]<-0
#Convert column PROPDMGEXP and CROPDMGEXP to number
mydata$PROPDMGEXP<-sapply(mydata$PROPDMGEXP,as.numeric)
mydata$CROPDMGEXP<-sapply(mydata$CROPDMGEXP,as.numeric)
#Multiply by PROPDMG to get the value of each event
mydata$PROPDMGTOTAL<-mydata$PROPDMGEXP*mydata$PROPDMG
mydata$CROPDMGTOTAL<-mydata$CROPDMGEXP*mydata$CROPDMG
#Order Data Frame
mydata<-data.frame(EVTYPE=mydata$EVTYPE,
FATALITIES=mydata$FATALITIES,
INJURIES=mydata$INJURIES,
PROPDMG=mydata$PROPDMG,
PROPDMGEXP=mydata$PROPDMGEXP,
PROPDMGTOTAL=mydata$PROPDMGTOTAL,
CROPDMG=mydata$CROPDMG,
CROPDMGEXP=mydata$CROPDMGEXP,
CROPDMGTOTAL=mydata$CROPDMGTOTAL)
head(mydata)## EVTYPE FATALITIES INJURIES PROPDMG PROPDMGEXP PROPDMGTOTAL CROPDMG
## 1 TORNADO 0 15 25.0 1000 25000 0
## 2 TORNADO 0 0 2.5 1000 2500 0
## 3 TORNADO 0 2 25.0 1000 25000 0
## 4 TORNADO 0 2 2.5 1000 2500 0
## 5 TORNADO 0 2 2.5 1000 2500 0
## 6 TORNADO 0 6 2.5 1000 2500 0
## CROPDMGEXP CROPDMGTOTAL
## 1 1 0
## 2 1 0
## 3 1 0
## 4 1 0
## 5 1 0
## 6 1 0Sum data by Event Type
aggFatalities<-aggregate(FATALITIES~EVTYPE,data=mydata,FUN=sum)
aggINJURIES<-aggregate(INJURIES~EVTYPE,data=mydata,FUN=sum)
aggPROPDMG<-aggregate(PROPDMGTOTAL~EVTYPE,data=mydata,FUN=sum)
aggCROPDMG<-aggregate(CROPDMGTOTAL~EVTYPE,data=mydata,FUN=sum)Sort data and retrieve the top 10 events
fatalities10<-head(aggFatalities[order(aggFatalities$FATALITIES,decreasing=TRUE),],n=10)
injuries10<-head(aggINJURIES[order(aggINJURIES$INJURIES,decreasing=TRUE),],n=10)
property10<-head(aggPROPDMG[order(aggPROPDMG$PROPDMGTOTAL,decreasing=TRUE),] , n=10)
crop10<-head(aggCROPDMG[order(aggCROPDMG$CROPDMGTOTAL,decreasing=TRUE),] ,n=10)Results
library(ggplot2)## Warning: package 'ggplot2' was built under R version 3.1.3library(grid)
library(gridExtra)Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
gfatalities<-ggplot(fatalities10,aes(reorder(EVTYPE,-FATALITIES),FATALITIES))+
geom_bar(stat="identity", fill="blue")+
theme_bw() + theme(axis.text.x = element_text(angle = 90, hjust = 1))+
labs(x="Event Type", y="Fatalities") + labs(title="Number of Fatalities")
ginjuries<- ggplot(injuries10, aes(reorder(EVTYPE, -INJURIES),INJURIES)) +
geom_bar(stat="identity", fill="blue") +
theme_bw() + theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
labs(x="Event Type", y="Injuries") + labs(title= "Number of Injuries")
#Show results
grid.arrange(gfatalities,ginjuries, nrow=1)
####Across the United States, which types of events have the greatest economic consequences?
gproperties<-ggplot(property10,aes(reorder(EVTYPE,-PROPDMGTOTAL),PROPDMGTOTAL))+
geom_bar(stat="identity", fill="blue")+
theme_bw() + theme(axis.text.x = element_text(angle = 90, hjust = 1))+
labs(x="Event Type", y="Damage") +
labs(title="Number of Damage in Properties")
gcrop<-ggplot(crop10,aes(reorder(EVTYPE,-CROPDMGTOTAL),CROPDMGTOTAL))+
geom_bar(stat="identity", fill="blue")+
theme_bw() + theme(axis.text.x = element_text(angle = 90, hjust = 1))+
labs(x="Event Type", y="Damage") +
labs(title="Number of Damage in Crops")
#Show results
grid.arrange(gproperties,gcrop, nrow=1)