Data Analysis of the Health and Economic Impacts of US Storms
1: Introduction
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.
2: Synopsis
The basic goal of This project involves exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) Storm Database and explore the effects of severe weather events on both population and economy. The database covers the time period between 1950 and November 2011.
The following analysis investigates which types of severe weather events are most harmful on:
1. Health (injuries and fatalities)
2. Property and crops (economic consequences)- Prerequisites: Download The Zip file and set working directory where the files are placed.
3: Data Processing
library("data.table")
library("ggplot2")
storm_data_frame <- read.csv("StormData.csv.bz2")
storm_data_table <- as.data.table(storm_data_frame)
colnames(storm_data_table)## [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"cols2Remove <- colnames(storm_data_table[, !c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")])
storm_data_table[, c(cols2Remove) := NULL]
storm_data_table <- storm_data_table[(EVTYPE != "?" & (INJURIES > 0 | FATALITIES > 0 | PROPDMG > 0 | CROPDMG > 0)), c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP") ]
cols <- c("PROPDMGEXP", "CROPDMGEXP")
storm_data_table[, (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)
storm_data_table[, PROPDMGEXP := propDmgKey[as.character(storm_data_table[,PROPDMGEXP])]]
storm_data_table[is.na(PROPDMGEXP), PROPDMGEXP := 10^0 ]
storm_data_table[, CROPDMGEXP := cropDmgKey[as.character(storm_data_table[,CROPDMGEXP])] ]
storm_data_table[is.na(CROPDMGEXP), CROPDMGEXP := 10^0 ]
storm_data_table <- storm_data_table[, .(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, propCost = PROPDMG * PROPDMGEXP, CROPDMG, CROPDMGEXP, cropCost = CROPDMG * CROPDMGEXP)]
totalCostDT <- storm_data_table[, .(propCost = sum(propCost), cropCost = sum(cropCost), Total_Cost = sum(propCost) + sum(cropCost)), by = .(EVTYPE)]
totalCostDT <- totalCostDT[order(-Total_Cost), ]
totalCostDT <- totalCostDT[1:10, ]
head(totalCostDT, 5)## EVTYPE propCost cropCost Total_Cost
## 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 18761221986totalInjuriesDT <- storm_data_table[, .(FATALITIES = sum(FATALITIES), INJURIES = sum(INJURIES), totals = sum(FATALITIES) + sum(INJURIES)), by = .(EVTYPE)]
totalInjuriesDT <- totalInjuriesDT[order(-FATALITIES), ]
totalInjuriesDT <- totalInjuriesDT[1:10, ]
head(totalInjuriesDT, 5)## 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 60464: Results
bad_stuff <- melt(totalInjuriesDT, id.vars="EVTYPE", variable.name = "bad_thing")
head(bad_stuff, 5)## EVTYPE bad_thing value
## 1: TORNADO FATALITIES 5633
## 2: EXCESSIVE HEAT FATALITIES 1903
## 3: FLASH FLOOD FATALITIES 978
## 4: HEAT FATALITIES 937
## 5: LIGHTNING FATALITIES 816healthChart <- ggplot(bad_stuff, aes(x=reorder(EVTYPE, -value), y=value))
healthChart = healthChart + geom_bar(stat="identity", aes(fill=bad_thing), position="dodge")
healthChart = healthChart + ylab("Frequency Count")
healthChart = healthChart + xlab("Event Type")
healthChart = healthChart + theme(axis.text.x = element_text(angle=45, hjust=1))
healthChart = healthChart + ggtitle("Top 10 US Killers") + theme(plot.title = element_text(hjust = 0.5))
healthChart
econ_consequences <- melt(totalCostDT, id.vars="EVTYPE", variable.name = "Damage_Type")
head(econ_consequences, 5)## EVTYPE Damage_Type value
## 1: FLOOD propCost 144657709807
## 2: HURRICANE/TYPHOON propCost 69305840000
## 3: TORNADO propCost 56947380677
## 4: STORM SURGE propCost 43323536000
## 5: HAIL propCost 15735267513econChart <- ggplot(econ_consequences, aes(x=reorder(EVTYPE, -value), y=value))
econChart = econChart + geom_bar(stat="identity", aes(fill=Damage_Type), position="dodge")
econChart = econChart + ylab("Cost (dollars)")
econChart = econChart + xlab("Event Type")
econChart = econChart + theme(axis.text.x = element_text(angle=45, hjust=1))
econChart = econChart + ggtitle("Top 10 US Storm Events causing Economic Consequences") + theme(plot.title = element_text(hjust = 0.5))
econChart