Storm and Severe Weather Event Report that Affect Public Health and Economy in the U.S. 1950 - 2011
Ozge Tugrul Sonmez
26 Ekim 2019
Synopsis
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, crop damage. In this report, severe weather events which cause poplulation injuries and fatalities in terms of number of people and also property and crop damages in terms of $ are exhibited by graphics. The most harmful weather events are given sequentially in the plots. The most harmful event in terms of population fatalities and injuries is Tornado. The most harmful event in terms of property damage is Flood and in terms of crop damage is drought.
Data Processing
setwd("C:/Users/asus/Desktop/Reproducible Research")
#Downloading Files
if(!file.exists("repdata_data_StormData.csv.bz2")){
fileUrl<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(fileUrl,destfile="./repdata_data_StormData.csv.bz2")
}
storm<-read.csv("repdata_data_StormData.csv.bz2", header=TRUE, stringsAsFactors=FALSE)
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 6#We select 7 variables and multiply PROPDMG with the numerical value of PROPDMGEXP and multiply CROPDMG with the numerical value of CROPDMGEXP.
variables<-c("EVTYPE","FATALITIES","INJURIES","PROPDMG", "PROPDMGEXP","CROPDMG","CROPDMGEXP")
storm<-storm[variables]
head(storm)## 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 0unique(storm$PROPDMGEXP)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-"
## [18] "1" "8"unique(storm$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"storm_modified<-storm%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP=="K"|PROPDMGEXP==3,10^3))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP=="M"|PROPDMGEXP=="m"|PROPDMGEXP==6,10^6))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==""|PROPDMGEXP=="+"|PROPDMGEXP==0|PROPDMGEXP=="?"|PROPDMGEXP=="-",10^0))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP=="B",10^9))%>%mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==5,10^5))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==4,10^4))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP=="h"|PROPDMGEXP=="H"|PROPDMGEXP==2,10^2))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==7,10^7))%>%mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==1,10^1))%>%
mutate(PROPDMGEXP=replace(PROPDMGEXP,PROPDMGEXP==8,10^8))%>%
mutate(CROPDMGEXP=replace(CROPDMGEXP,CROPDMGEXP==""|CROPDMGEXP==0|CROPDMGEXP=="?",10^0))%>%
mutate(CROPDMGEXP=replace(CROPDMGEXP,CROPDMGEXP=="M"|CROPDMGEXP=="m",10^6))%>%
mutate(CROPDMGEXP=replace(CROPDMGEXP,CROPDMGEXP=="k"|CROPDMGEXP=="K",10^3))%>%
mutate(CROPDMGEXP=replace(CROPDMGEXP,CROPDMGEXP=="B",10^9))%>%
mutate(CROPDMGEXP=replace(CROPDMGEXP,CROPDMGEXP==2,10^2))
head(storm_modified)## EVTYPE FATALITIES INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## 1 TORNADO 0 15 25.0 1000 0 1
## 2 TORNADO 0 0 2.5 1000 0 1
## 3 TORNADO 0 2 25.0 1000 0 1
## 4 TORNADO 0 2 2.5 1000 0 1
## 5 TORNADO 0 2 2.5 1000 0 1
## 6 TORNADO 0 6 2.5 1000 0 1storm_modified$PROPDMGEXP<-as.numeric(storm_modified$PROPDMGEXP)
storm_modified$CROPDMGEXP<-as.numeric(storm_modified$CROPDMGEXP)
storm_final<-storm_modified%>%
mutate(PROPDMG_FINAL=PROPDMG*PROPDMGEXP)%>%
mutate(CROPDMG_FINAL=CROPDMG*CROPDMGEXP)%>%
select(EVTYPE,FATALITIES,INJURIES,PROPDMG_FINAL,CROPDMG_FINAL)
head(storm_final)## EVTYPE FATALITIES INJURIES PROPDMG_FINAL CROPDMG_FINAL
## 1 TORNADO 0 15 25000 0
## 2 TORNADO 0 0 2500 0
## 3 TORNADO 0 2 25000 0
## 4 TORNADO 0 2 2500 0
## 5 TORNADO 0 2 2500 0
## 6 TORNADO 0 6 2500 0Results
1- Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
The most harmful 7 events are listed in terms of the sum of both injuries and fatalities. Also, the most 7 events are listed in terms of injuries and fatalities separately and given in bar plots.
storm_fatalities_injuries<-melt(storm_final,id.vars="EVTYPE",measure.vars=c("FATALITIES","INJURIES"))
storm_fatalities_injuries<-storm_fatalities_injuries%>%
group_by(EVTYPE,variable)%>%
summarize(total=sum(value))%>%
group_by(EVTYPE)%>%
mutate(population_total=sum(total))%>%
arrange(desc(population_total))
storm_fatalities_injuries<-head(storm_fatalities_injuries,14)
storm_fatalities_injuries## # A tibble: 14 x 4
## # Groups: EVTYPE [7]
## EVTYPE variable total population_total
## <chr> <fct> <dbl> <dbl>
## 1 TORNADO FATALITIES 5633 96979
## 2 TORNADO INJURIES 91346 96979
## 3 EXCESSIVE HEAT FATALITIES 1903 8428
## 4 EXCESSIVE HEAT INJURIES 6525 8428
## 5 TSTM WIND FATALITIES 504 7461
## 6 TSTM WIND INJURIES 6957 7461
## 7 FLOOD FATALITIES 470 7259
## 8 FLOOD INJURIES 6789 7259
## 9 LIGHTNING FATALITIES 816 6046
## 10 LIGHTNING INJURIES 5230 6046
## 11 HEAT FATALITIES 937 3037
## 12 HEAT INJURIES 2100 3037
## 13 FLASH FLOOD FATALITIES 978 2755
## 14 FLASH FLOOD INJURIES 1777 2755p1<-ggplot(data=storm_fatalities_injuries,aes(x=(reorder(EVTYPE,population_total)),y=total,fill=variable))+
geom_bar(stat="Identity",position=position_dodge(width = 0.9))+geom_text(aes(label=total), angle=0, size=2,check_overlap = TRUE)+
scale_fill_brewer(palette="Dark2")+labs(x="Event Type",y="No of People Affected",title="Most Harmful Events with Respect to Population Health")+
theme(axis.text.x = element_text(angle=45, hjust=1))
storm_fatalities<-storm_final%>%
group_by(EVTYPE)%>%
summarize(TOTAL_FATALITIES=sum(FATALITIES))%>%
arrange(desc(TOTAL_FATALITIES))%>%
top_n(7)## Selecting by TOTAL_FATALITIESstorm_fatalities## # A tibble: 7 x 2
## EVTYPE TOTAL_FATALITIES
## <chr> <dbl>
## 1 TORNADO 5633
## 2 EXCESSIVE HEAT 1903
## 3 FLASH FLOOD 978
## 4 HEAT 937
## 5 LIGHTNING 816
## 6 TSTM WIND 504
## 7 FLOOD 470p2<-ggplot(data=storm_fatalities,aes(x=(reorder(EVTYPE,TOTAL_FATALITIES)),y=TOTAL_FATALITIES,fill=EVTYPE))+geom_bar(stat="identity")+
geom_text(aes(label=TOTAL_FATALITIES), angle=0, size=2,check_overlap = TRUE)+scale_fill_brewer(palette="Spectral")+
theme(axis.text.x = element_text(angle=45, hjust=1))+labs(x="Event Type",y="No of Fatalities")
storm_injuries<-storm_final%>%
group_by(EVTYPE)%>%
summarize(TOTAL_INJURIES=sum(INJURIES))%>%
arrange(desc(TOTAL_INJURIES))%>%
top_n(7)## Selecting by TOTAL_INJURIESstorm_injuries## # A tibble: 7 x 2
## EVTYPE TOTAL_INJURIES
## <chr> <dbl>
## 1 TORNADO 91346
## 2 TSTM WIND 6957
## 3 FLOOD 6789
## 4 EXCESSIVE HEAT 6525
## 5 LIGHTNING 5230
## 6 HEAT 2100
## 7 ICE STORM 1975p3<-ggplot(data=storm_injuries,aes(x=(reorder(EVTYPE,TOTAL_INJURIES)),y=TOTAL_INJURIES,fill=EVTYPE))+geom_bar(stat="identity")+
geom_text(aes(label=TOTAL_INJURIES), angle=0, size=2,check_overlap = TRUE)+scale_fill_brewer(palette="Spectral")+
theme(axis.text.x = element_text(angle=45, hjust=1))+labs(x="Event Type",y="No of Injuries")
grid.arrange(arrangeGrob(p1,ncol=1,nrow=1),arrangeGrob(p2,p3,ncol=2),heights=c(2,1.5))
#The most harmful events in terms of total population damage are tornado, excessive heat, tstm wind, flood, lightning, heat and flash flood sequentially.
#The most harmful events in terms of fatalities are tornado, excessive heat, flash flood, heat, lightning, tstm wind and flood sequentially.
#The most harmful events in terms of injuries are tornado, tstm wind, flood, excessive heat, lightning,heat and ice storm.2- Across the United States, which types of events have the greatest economic consequences?
The most harmful 7 events for property damage (in terms of billion dollar) and crop damage (in terms of billion dollar) are given separately in bar plots.
storm_prop_crop<-melt(storm_final,id.vars="EVTYPE",measure.vars=c("PROPDMG_FINAL","CROPDMG_FINAL"))
storm_prop_crop<-storm_prop_crop%>%
group_by(EVTYPE,variable)%>%
summarize(total=sum(value)/10^9)%>%
group_by(EVTYPE)%>%
mutate(prop_and_crop_total=sum(total))%>%
arrange(desc(prop_and_crop_total))
storm_prop_crop<-head(storm_prop_crop,14)
storm_prop_crop## # A tibble: 14 x 4
## # Groups: EVTYPE [7]
## EVTYPE variable total prop_and_crop_total
## <chr> <fct> <dbl> <dbl>
## 1 FLOOD PROPDMG_FINAL 145. 150.
## 2 FLOOD CROPDMG_FINAL 5.66 150.
## 3 HURRICANE/TYPHOON PROPDMG_FINAL 69.3 71.9
## 4 HURRICANE/TYPHOON CROPDMG_FINAL 2.61 71.9
## 5 TORNADO PROPDMG_FINAL 56.9 57.4
## 6 TORNADO CROPDMG_FINAL 0.415 57.4
## 7 STORM SURGE PROPDMG_FINAL 43.3 43.3
## 8 STORM SURGE CROPDMG_FINAL 0.000005 43.3
## 9 HAIL PROPDMG_FINAL 15.7 18.8
## 10 HAIL CROPDMG_FINAL 3.03 18.8
## 11 FLASH FLOOD PROPDMG_FINAL 16.8 18.2
## 12 FLASH FLOOD CROPDMG_FINAL 1.42 18.2
## 13 DROUGHT PROPDMG_FINAL 1.05 15.0
## 14 DROUGHT CROPDMG_FINAL 14.0 15.0library(RColorBrewer)
storm_prop_dmg<-storm_final%>%
group_by(EVTYPE)%>%
summarize(TOTAL_PROP_DMG=round(sum(PROPDMG_FINAL)/10^9,1))%>%
arrange(desc(TOTAL_PROP_DMG))%>%
top_n(7)## Selecting by TOTAL_PROP_DMGp4<-ggplot(data=storm_prop_dmg,aes(x=(reorder(EVTYPE,TOTAL_PROP_DMG)),y=TOTAL_PROP_DMG,fill=EVTYPE))+geom_bar(stat="identity")+
geom_text(aes(label=TOTAL_PROP_DMG), angle=0, size=3,check_overlap = TRUE)+scale_fill_brewer(palette="Purples")+
theme(axis.text.x = element_text(angle=45, hjust=1))+labs(x="Event Type",y="Total Property Damage (billion $)",title="Most Harmful Events with Respect to Property Damage")
p4
#The most harmful events in property damage are flood, hurricane/typhoon, tornado, storm surge, flash flood, hail and hurricane sequentially.
storm_crop_dmg<-storm_final%>%
group_by(EVTYPE)%>%
summarize(TOTAL_CROP_DMG=round(sum(CROPDMG_FINAL)/10^9,2))%>%
arrange(desc(TOTAL_CROP_DMG))%>%
top_n(7)## Selecting by TOTAL_CROP_DMGp5<-ggplot(data=storm_crop_dmg,aes(x=(reorder(EVTYPE,TOTAL_CROP_DMG)),y=TOTAL_CROP_DMG,fill=EVTYPE))+geom_bar(stat="identity")+
geom_text(aes(label=TOTAL_CROP_DMG), angle=0, size=3,check_overlap = TRUE)+scale_fill_brewer(palette="Greens")+
theme(axis.text.x = element_text(angle=45, hjust=1))+labs(x="Event Type",y="Total Crop Damage (billion $)",title="Most Harmful Events with Respect to Crop Damage")
p5
#The most harmful events in crop damage are drought, flood, river flood, ice storm, hail, hurricane and hurricane/typhoon sequentially.