Analysis of Health Impact and Economic Consequences of US Storm
Rajaram
05/07/2020
Synopsis
The goal of this project is to explore NOAA Storm Database and answer some questions regarding events. The events in database start in the year 1950 and end in November 2011.
This Project analysis address the following questions:
- Across the united states, Which type of events are most harmful with respect to population health?
- Across united states, which types of events has greatest economic consequences?
Data
The data for this analysis come in the form of comma-separated-value file compressed via the bzip2 algorithm to reduce its size.
To know about variables of the database , please see below links.
- National Weather Service Storm Data Documentation
- National Climatic Data Center Storm Events FAQ
Data Processing
a) Data Loading
Download the file from location and load this to data.table
dataurl <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
if (!file.exists("StormData.csv.bz2")) {
download.file(dataurl,destfile="StormData.csv.bz2")
}
storm <- read.csv("StormData.csv.bz2")
library(data.table)
storm <- as.data.table(storm)b) Examine the variable names and decide the variable names to keep for the analysis
names(storm)## [1] "STATE__" "BGN_DATE" "BGN_TIME" "TIME_ZONE" "COUNTY"
## [6] "COUNTYNAME" "STATE" "EVTYPE" "BGN_RANGE" "BGN_AZI"
## [11] "BGN_LOCATI" "END_DATE" "END_TIME" "COUNTY_END" "COUNTYENDN"
## [16] "END_RANGE" "END_AZI" "END_LOCATI" "LENGTH" "WIDTH"
## [21] "F" "MAG" "FATALITIES" "INJURIES" "PROPDMG"
## [26] "PROPDMGEXP" "CROPDMG" "CROPDMGEXP" "WFO" "STATEOFFIC"
## [31] "ZONENAMES" "LATITUDE" "LONGITUDE" "LATITUDE_E" "LONGITUDE_"
## [36] "REMARKS" "REFNUM"keepcols <- c("EVTYPE","INJURIES","FATALITIES","PROPDMG","PROPDMGEXP",
"CROPDMG","CROPDMGEXP")c) Data Subsetting
Subset the data where there is proper event recorded and variables used in the analysis are having more than 0.
storm <- storm[, keepcols,with=FALSE]
cols <- c("PROPDMGEXP", "CROPDMGEXP")
## changing the type from factor to character for data transformations
stormDT <- storm[, (cols) := lapply(.SD,as.character),
.SDcols = cols]
## subset data for the events and measure variables are greater than 0
stormDT <- stormDT[(EVTYPE != "?" &
(INJURIES > 0 | FATALITIES > 0 | PROPDMG > 0 | CROPDMG > 0))]d) Data Transformation
Data Transformation for Crop damage and Property damage exponential. Blank values are converted to 0, All alpha numeric notations are made in same case and converted to common notation.
table(stormDT$CROPDMGEXP)##
## ? 0 B k K m M
## 152663 6 17 7 21 99932 1 1985table(stormDT$PROPDMGEXP)##
## - + 0 2 3 4 5 6 7 B
## 11585 1 5 210 1 1 4 18 3 3 40
## h H K m M
## 1 6 231427 7 11320stormDT[CROPDMGEXP=="",CROPDMGEXP := 0]
stormDT[PROPDMGEXP=="",PROPDMGEXP := 0]
stormDT[, (cols) := c(lapply(.SD, toupper)), .SDcols = cols]
table(stormDT$CROPDMGEXP)##
## ? 0 B K M
## 6 152680 7 99953 1986table(stormDT$PROPDMGEXP)##
## - + 0 2 3 4 5 6 7 B H
## 1 5 11795 1 1 4 18 3 3 40 7
## K M
## 231427 11327cropDmgExpKey <- c("?" = 10^0,
"0" = 10^0,
"K" = 10^3,
"M" = 10^6,
"B" = 10^9)
propDmgExpKey <- c("-" = 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)
stormDT[, CROPDMGEXP := cropDmgExpKey[as.character(stormDT[,CROPDMGEXP])]]
stormDT[, PROPDMGEXP := propDmgExpKey[as.character(stormDT[,PROPDMGEXP])]]
table(stormDT$CROPDMGEXP)##
## 1 1000 1e+06 1e+09
## 152686 99953 1986 7table(stormDT$PROPDMGEXP)##
## 1 100 1000 10000 1e+05 1e+06 1e+07 1e+09
## 11801 8 231428 4 18 11330 3 40e) Calculate Cost
Cost of Property and Crop damage is calculated as follows : Cost * Cost Exp
stormDT <- stormDT[, .(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, PROPCOST = PROPDMG * PROPDMGEXP, CROPDMG, CROPDMGEXP, CROPCOST = CROPDMG * CROPDMGEXP)]f) Calculate Total Fatalaties and Injuries
In this step, total fatalaties and Injuries are calculated and Top 10 are used for results
totalhealthDT <- stormDT[, .(FATALITIES = sum(FATALITIES), INJURIES = sum(INJURIES), TOTALS = sum(FATALITIES) + sum(INJURIES)), by = .(EVTYPE)]
totalhealthDT <- totalhealthDT[order(-FATALITIES), ]
totalhealthDT <- totalhealthDT[1:10, ]
head(totalhealthDT)## EVTYPE FATALITIES INJURIES TOTALS
## 1: TORNADO 5633 91346 96979
## 2: EXCESSIVE HEAT 1903 6525 8428
## 3: FLASH FLOOD 978 1777 2755
## 4: HEAT 937 2100 3037
## 5: LIGHTNING 816 5230 6046
## 6: TSTM WIND 504 6957 7461g) Calculate Total Property and Crop Damage Cost
In this step, Total Property and Crop Damage costs are calculated and Top 10 are used for results
totalCostDT <- stormDT[, .(PROPCOST = sum(PROPCOST), CROPCOST = sum(CROPCOST), TOTALCOST = sum(PROPCOST) + sum(CROPCOST)), by = .(EVTYPE)]
totalCostDT <- totalCostDT[order(-TOTALCOST), ]
totalCostDT <- totalCostDT[1:10, ]
head(totalCostDT)## EVTYPE PROPCOST CROPCOST TOTALCOST
## 1: FLOOD 144657709807 5661968450 150319678257
## 2: HURRICANE/TYPHOON 69305840000 2607872800 71913712800
## 3: TORNADO 56947380677 414953270 57362333947
## 4: STORM SURGE 43323536000 5000 43323541000
## 5: HAIL 15735267513 3025954473 18761221986
## 6: FLASH FLOOD 16822673979 1421317100 18243991079Results
Events that are most harmful with respect to population health
melting data for plot reprsentation
health_consequences <- melt(totalhealthDT, id.vars="EVTYPE", variable.name = "HEALTHTYPE")
head(health_consequences)## EVTYPE HEALTHTYPE value
## 1: TORNADO FATALITIES 5633
## 2: EXCESSIVE HEAT FATALITIES 1903
## 3: FLASH FLOOD FATALITIES 978
## 4: HEAT FATALITIES 937
## 5: LIGHTNING FATALITIES 816
## 6: TSTM WIND FATALITIES 504library(ggplot2)
ggplot(health_consequences, aes(x=reorder(EVTYPE,value), y=value))+
geom_bar(stat="identity",aes(fill=HEALTHTYPE),position="dodge")+
labs(title="Top 10 Event Types for Fatalaties/Injuries",x="Event Type", y="Number of Health Consequences")+
coord_flip()
Events that have greatest economic consequences
melting data for plot reprsentation
econ_consequences <- melt(totalCostDT, id.vars="EVTYPE", variable.name = "DAMAGETYPE")
econ_consequences[, DAMAGETYPE := ordered(DAMAGETYPE, levels = c("CROPCOST","PROPCOST","TOTALCOST"))]
head(econ_consequences)## EVTYPE DAMAGETYPE value
## 1: FLOOD PROPCOST 144657709807
## 2: HURRICANE/TYPHOON PROPCOST 69305840000
## 3: TORNADO PROPCOST 56947380677
## 4: STORM SURGE PROPCOST 43323536000
## 5: HAIL PROPCOST 15735267513
## 6: FLASH FLOOD PROPCOST 16822673979library(ggplot2)
options(scipen=999)
ggplot(econ_consequences, aes(x=reorder(EVTYPE,value), y=value))+
geom_bar(stat="identity",aes(fill=DAMAGETYPE),position="dodge")+
labs(title="Top 10 Event Types impacts economy",x="Event Type", y="Cost of Impact")+
coord_flip()
options(scipen=0)