The Negative Consequences of Weather Events on Health and Economics in U.S.
Somaya AlGabry
23/02/2021
Packages:
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)
library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionlibrary(RColorBrewer)Synposis:
The weather events have great harm on health and economics. They was the cause in a lot of deaths and injuries, and cost the country billions of dollars. After the analysis the most fetal event types were: excessive heat, tornado and flash flood. These three events resulted in more than 4000 deaths from 1996 to 2011. While tornado, flood and excessive heat were the most injurious. Regarding the economic consequences, Hurricane was the most dangerous on properties. It cost more than 15 billion dollars in the period 1996-2011. Drought was the most dangerous on crops and it cost more than 3 billion dollars in the same period.
Data Loading:
filename <- "repdata%2Fdata%2FStormData.csv.bz2"
fileURL <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
if (!file.exists(filename)){
download.file(fileURL, filename)
}
if (!file.exists("repdata%2Fdata%2FStormData.csv")) {
unzip(filename)
}
data <- read.csv("repdata%2Fdata%2FStormData.csv")Data Exploration:
str(data)## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : chr "4/18/1950 0:00:00" "4/18/1950 0:00:00" "2/20/1951 0:00:00" "6/8/1951 0:00:00" ...
## $ BGN_TIME : chr "0130" "0145" "1600" "0900" ...
## $ TIME_ZONE : chr "CST" "CST" "CST" "CST" ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: chr "MOBILE" "BALDWIN" "FAYETTE" "MADISON" ...
## $ STATE : chr "AL" "AL" "AL" "AL" ...
## $ EVTYPE : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : chr "" "" "" "" ...
## $ BGN_LOCATI: chr "" "" "" "" ...
## $ END_DATE : chr "" "" "" "" ...
## $ END_TIME : chr "" "" "" "" ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : chr "" "" "" "" ...
## $ END_LOCATI: chr "" "" "" "" ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ FATALITIES: num 0 0 0 0 0 0 0 0 1 0 ...
## $ INJURIES : num 15 0 2 2 2 6 1 0 14 0 ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ PROPDMGEXP: chr "K" "K" "K" "K" ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: chr "" "" "" "" ...
## $ WFO : chr "" "" "" "" ...
## $ STATEOFFIC: chr "" "" "" "" ...
## $ ZONENAMES : chr "" "" "" "" ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : chr "" "" "" "" ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ...data$DATE <- as.POSIXct(data$BGN_DATE, format="%m/%d/%Y %H:%M:%OS")
length(unique(data$EVTYPE))## [1] 985Data Processing:
The reference to understand the data and variables is here
- From the exploratory analysis we noticed that all the earlier events are Tornado type. When we referred to NOAA, we found that only Tornadoes was recorded in the first 5 years. From 1955-1996 only Tornadoes, Thunderstorm Winds and Hails were recorded. After that all event types were recorded. So to make the analysis fair and meaningful, we will only consider the data recorded 1996 and after. Now I am going to subset the data:
subdata <- subset(data, DATE >= as.Date("1996-01-01") )
dim(subdata)## [1] 653530 38- The questions needed in the analysis are related to the harm on population health (fetalities and injuries) and the economical damages (to properities and crops) according to event type. So, I am going to subset the variables I need to answer the questions from the original data in order to make the cleaning and analysis faster.
The variables needed are:
EVTYPE :Event type.
FATALITIES .
INJURIES .
PROPDMG : Properity damage.
PROPDMGEXP : Properity damage exponent.
CROPDMG : Crop damage.
CROPDMGEXP : Crop damage exponent.
I will make two subsets, one for the variables related to health harm, and the other for the variables related to the economic damage.
healthVar <- c("EVTYPE", "FATALITIES", "INJURIES")
healthdata <- subdata[, healthVar]
ecoVar <- c("EVTYPE", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")
ecodata <- subdata[, ecoVar]
length(unique(subdata$EVTYPE))## [1] 516- The most challenging mess! According to NOAA, Event types are 48. But in our subset there is 516 Event types! most of them are typos. Now we are going to try solving this.
healthdata$EVTYPE <- tolower(healthdata$EVTYPE)
healthdata$EVTYPE <- gsub(" ", "", healthdata$EVTYPE)
healthdata <- healthdata[!grepl("[Ss]ummary",healthdata$EVTYPE),]
healthdata$EVTYPE <- gsub("marinetstm", "marinethunderstormwind", healthdata$EVTYPE)
healthdata$EVTYPE[grep("tstm", healthdata$EVTYPE)] = "thunderstormwind"
healthdata <- healthdata[!grepl("non",healthdata$EVTYPE),]
healthdata <- healthdata[!grepl("minor",healthdata$EVTYPE),]
healthdata <- healthdata[!grepl("record",healthdata$EVTYPE),]
healthdata$EVTYPE <- gsub("temperature[s]", "", healthdata$EVTYPE)
healthdata <- healthdata[!grepl("temperature",healthdata$EVTYPE),]
healthdata$EVTYPE <- gsub("/", "", healthdata$EVTYPE)
healthdata$EVTYPE[grep("extreme", healthdata$EVTYPE)] = "extremecoldwindchill"
healthdata$EVTYPE[grep("urban", healthdata$EVTYPE)] = "flood"
healthdata$EVTYPE[grep("sml", healthdata$EVTYPE)] = "flood"
healthdata <- healthdata[!grepl("dry",healthdata$EVTYPE),]
healthdata$EVTYPE[grep("surf", healthdata$EVTYPE)] = "highsurf"
healthdata$EVTYPE[grep("marinethunderstormwind", healthdata$EVTYPE)] = "marinetstm"
healthdata$EVTYPE[grep("thunderstormwind", healthdata$EVTYPE)] = "tstm"
healthdata$EVTYPE[grep("thunderstorm[s]", healthdata$EVTYPE)] = "tstm"
healthdata$EVTYPE[grep("marinehail", healthdata$EVTYPE)] = "marinehal"
healthdata$EVTYPE[grep("marinehighwind", healthdata$EVTYPE)] = "marinehghwnd"
healthdata$EVTYPE[grep("marinestrongwind", healthdata$EVTYPE)] = "marinestrngwnd"
healthdata <- healthdata[!grepl("marineaccident",healthdata$EVTYPE),]
healthdata$EVTYPE <- gsub("gust[y|s]", "strong", healthdata$EVTYPE)
healthdata$EVTYPE[grep("strongwind", healthdata$EVTYPE)] = "strongwnd"
healthdata$EVTYPE[grep("windstrong", healthdata$EVTYPE)] = "strongwnd"
healthdata$EVTYPE[grep("highwind", healthdata$EVTYPE)] = "highwnd"
healthdata$EVTYPE[grep("extremecoldwindchill", healthdata$EVTYPE)] = "extremecoldwndchill"
healthdata$EVTYPE[grep("windchill", healthdata$EVTYPE)] = "coldwndchill"
healthdata$EVTYPE[grep("heavyrain", healthdata$EVTYPE)] = "heavyrain"
healthdata$EVTYPE[grep("hail", healthdata$EVTYPE)] = "hail"
healthdata <- healthdata[!grepl("wind",healthdata$EVTYPE),]
healthdata$EVTYPE[grep("effectsnow", healthdata$EVTYPE)] = "lakeeffectsnw"
healthdata$EVTYPE[grep("snow", healthdata$EVTYPE)] = "heavysnow"
healthdata$EVTYPE[grep("coast", healthdata$EVTYPE)] = "coastalflood"
healthdata$EVTYPE[grep("cst", healthdata$EVTYPE)] = "coastalflood"
healthdata$EVTYPE[grep("flashflood", healthdata$EVTYPE)] = "flashflood"
healthdata$EVTYPE[grep("riverflood", healthdata$EVTYPE)] = "coastalflood"
healthdata$EVTYPE[grep("tidalflood", healthdata$EVTYPE)] = "coastalflood"
healthdata$EVTYPE[grep("streetflood", healthdata$EVTYPE)] = "flood"
healthdata <- healthdata[!grepl("wet",healthdata$EVTYPE),]
healthdata$EVTYPE[grep("freezingfog", healthdata$EVTYPE)] = "frezingfog"
healthdata$EVTYPE[grep("freez", healthdata$EVTYPE)] = "freeze"
healthdata$EVTYPE[grep("erosion", healthdata$EVTYPE)] = "coastalflood"
healthdata$EVTYPE[grep("icy", healthdata$EVTYPE)] = "heavysnow"
healthdata$EVTYPE[grep("rain", healthdata$EVTYPE)] = "heavyrain"
healthdata$EVTYPE[grep("icejam", healthdata$EVTYPE)] = "flashflood"
healthdata$EVTYPE[grep("ice", healthdata$EVTYPE)] = "icestorm"
healthdata$EVTYPE[grep("extremecold", healthdata$EVTYPE)] = "extremecldwndchill"
healthdata$EVTYPE[grep("exessivecold", healthdata$EVTYPE)] = "extremecldwndchill"
healthdata$EVTYPE[grep("cold", healthdata$EVTYPE)] = "coldwndchill"
healthdata$EVTYPE[grep("frost", healthdata$EVTYPE)] = "freeze"
healthdata$EVTYPE[grep("winterstorm", healthdata$EVTYPE)] = "wnterstorm"
healthdata$EVTYPE[grep("winter", healthdata$EVTYPE)] = "winterweather"
healthdata$EVTYPE[grep("wintr", healthdata$EVTYPE)] = "winterweather"
healthdata <- healthdata[!grepl("land",healthdata$EVTYPE),]
healthdata$EVTYPE[grep("hurricane", healthdata$EVTYPE)] = "hurricane"
healthdata$EVTYPE[grep("burst", healthdata$EVTYPE)] = "tstm"
healthdata$EVTYPE[grep("heatwave", healthdata$EVTYPE)] = "heat"
healthdata$EVTYPE[grep("excessiveheat", healthdata$EVTYPE)] = "excessiveheat"
healthdata$EVTYPE[grep("stormsurge", healthdata$EVTYPE)] = "stormsurge"
healthdata$EVTYPE[grep("sleet", healthdata$EVTYPE)] = "sleet"
healthdata$EVTYPE[grep("((hot)|(warm))weather", healthdata$EVTYPE)] = "heat"
healthdata$EVTYPE[grep("duststorm", healthdata$EVTYPE)] = "dststorm"
healthdata$EVTYPE[grep("dust", healthdata$EVTYPE)] = "dustdevil"
healthdata$EVTYPE[grep("volcanicash", healthdata$EVTYPE)] = "volcanicash"
healthdata$EVTYPE <- gsub("tstm", "thunderstorm", healthdata$EVTYPE)
healthdata$EVTYPE[grep("hypotherm", healthdata$EVTYPE)] = "winterweather"
healthdata$EVTYPE[grep("hypertherm", healthdata$EVTYPE)] = "heat"
healthdata$EVTYPE[grep("funnel", healthdata$EVTYPE)] = "funnelcloud"
healthdata$EVTYPE[grep("spout", healthdata$EVTYPE)] = "waterspout"
healthdata$EVTYPE[grep("typhoon", healthdata$EVTYPE)] = "hurricane"
healthdata$EVTYPE[grep("highswell", healthdata$EVTYPE)] = "highsurf"
healthdata$EVTYPE[grep("(hot)|(warm)", healthdata$EVTYPE)] = "heat"
healthdata$EVTYPE[grep("densefog", healthdata$EVTYPE)] = "densefog"
healthdata$EVTYPE[grep("fire", healthdata$EVTYPE)] = "wildfire"
healthdata$EVTYPE[grep("sea", healthdata$EVTYPE)] = "highsurf"
healthdata$EVTYPE <- gsub("vog", "fog", healthdata$EVTYPE)
healthdata$EVTYPE[grep("severethunderstorm", healthdata$EVTYPE)] = "thunderstorm"
healthdata$EVTYPE[grep("cloud", healthdata$EVTYPE)] = "funnelcloud"
healthdata$EVTYPE[grep("highwater", healthdata$EVTYPE)] = "flashflood"
healthdata$EVTYPE[grep("^wnd", healthdata$EVTYPE)] = "coldwndchill"
healthdata$EVTYPE[grep("wave", healthdata$EVTYPE)] = "flashflood"
healthdata$EVTYPE[grep("tornado", healthdata$EVTYPE)] = "tornado"
healthdata$EVTYPE[grep("ripcurrent", healthdata$EVTYPE)] = "ripcurrent"
healthdata <- healthdata[!grepl("(mud)|(glaze)|(precip)|(month)|(year)|(season)|(metro)|(nosevereweather)|(dam)|(tide)|(slid)|(spell)|(remnant)|(redflag)|(lights)|(drowning)",healthdata$EVTYPE),]
ecodata$EVTYPE <- tolower(ecodata$EVTYPE)
ecodata$EVTYPE <- gsub(" ", "", ecodata$EVTYPE)
ecodata <- ecodata[!grepl("[Ss]ummary",ecodata$EVTYPE),]
ecodata$EVTYPE <- gsub("marinetstm", "marinethunderstormwind", ecodata$EVTYPE)
ecodata$EVTYPE[grep("tstm", ecodata$EVTYPE)] = "thunderstormwind"
ecodata <- ecodata[!grepl("non",ecodata$EVTYPE),]
ecodata <- ecodata[!grepl("minor",ecodata$EVTYPE),]
ecodata <- ecodata[!grepl("record",ecodata$EVTYPE),]
ecodata$EVTYPE <- gsub("temperature[s]", "", ecodata$EVTYPE)
ecodata <- ecodata[!grepl("temperature",ecodata$EVTYPE),]
ecodata$EVTYPE <- gsub("/", "", ecodata$EVTYPE)
ecodata$EVTYPE[grep("extreme", ecodata$EVTYPE)] = "extremecoldwindchill"
ecodata$EVTYPE[grep("urban", ecodata$EVTYPE)] = "flood"
ecodata$EVTYPE[grep("sml", ecodata$EVTYPE)] = "flood"
ecodata <- ecodata[!grepl("dry",ecodata$EVTYPE),]
ecodata$EVTYPE[grep("surf", ecodata$EVTYPE)] = "highsurf"
ecodata$EVTYPE[grep("marinethunderstormwind", ecodata$EVTYPE)] = "marinetstm"
ecodata$EVTYPE[grep("thunderstormwind", ecodata$EVTYPE)] = "tstm"
ecodata$EVTYPE[grep("thunderstorm[s]", ecodata$EVTYPE)] = "tstm"
ecodata$EVTYPE[grep("marinehail", ecodata$EVTYPE)] = "marinehal"
ecodata$EVTYPE[grep("marinehighwind", ecodata$EVTYPE)] = "marinehghwnd"
ecodata$EVTYPE[grep("marinestrongwind", ecodata$EVTYPE)] = "marinestrngwnd"
ecodata <- ecodata[!grepl("marineaccident",ecodata$EVTYPE),]
ecodata$EVTYPE <- gsub("gust[y|s]", "strong", ecodata$EVTYPE)
ecodata$EVTYPE[grep("strongwind", ecodata$EVTYPE)] = "strongwnd"
ecodata$EVTYPE[grep("windstrong", ecodata$EVTYPE)] = "strongwnd"
ecodata$EVTYPE[grep("highwind", ecodata$EVTYPE)] = "highwnd"
ecodata$EVTYPE[grep("extremecoldwindchill", ecodata$EVTYPE)] = "extremecoldwndchill"
ecodata$EVTYPE[grep("windchill", ecodata$EVTYPE)] = "coldwndchill"
ecodata$EVTYPE[grep("heavyrain", ecodata$EVTYPE)] = "heavyrain"
ecodata$EVTYPE[grep("hail", ecodata$EVTYPE)] = "hail"
ecodata <- ecodata[!grepl("wind",ecodata$EVTYPE),]
ecodata$EVTYPE[grep("effectsnow", ecodata$EVTYPE)] = "lakeeffectsnw"
ecodata$EVTYPE[grep("snow", ecodata$EVTYPE)] = "heavysnow"
ecodata$EVTYPE[grep("coast", ecodata$EVTYPE)] = "coastalflood"
ecodata$EVTYPE[grep("cst", ecodata$EVTYPE)] = "coastalflood"
ecodata$EVTYPE[grep("flashflood", ecodata$EVTYPE)] = "flashflood"
ecodata$EVTYPE[grep("riverflood", ecodata$EVTYPE)] = "coastalflood"
ecodata$EVTYPE[grep("tidalflood", ecodata$EVTYPE)] = "coastalflood"
ecodata$EVTYPE[grep("streetflood", ecodata$EVTYPE)] = "flood"
ecodata <- ecodata[!grepl("wet",ecodata$EVTYPE),]
ecodata$EVTYPE[grep("freezingfog", ecodata$EVTYPE)] = "frezingfog"
ecodata$EVTYPE[grep("freez", ecodata$EVTYPE)] = "freeze"
ecodata$EVTYPE[grep("erosion", ecodata$EVTYPE)] = "coastalflood"
ecodata$EVTYPE[grep("icy", ecodata$EVTYPE)] = "heavysnow"
ecodata$EVTYPE[grep("rain", ecodata$EVTYPE)] = "heavyrain"
ecodata$EVTYPE[grep("icejam", ecodata$EVTYPE)] = "flashflood"
ecodata$EVTYPE[grep("ice", ecodata$EVTYPE)] = "icestorm"
ecodata$EVTYPE[grep("extremecold", ecodata$EVTYPE)] = "extremecldwndchill"
ecodata$EVTYPE[grep("exessivecold", ecodata$EVTYPE)] = "extremecldwndchill"
ecodata$EVTYPE[grep("cold", ecodata$EVTYPE)] = "coldwndchill"
ecodata$EVTYPE[grep("frost", ecodata$EVTYPE)] = "freeze"
ecodata$EVTYPE[grep("winterstorm", ecodata$EVTYPE)] = "wnterstorm"
ecodata$EVTYPE[grep("winter", ecodata$EVTYPE)] = "winterweather"
ecodata$EVTYPE[grep("wintr", ecodata$EVTYPE)] = "winterweather"
ecodata <- ecodata[!grepl("land",ecodata$EVTYPE),]
ecodata$EVTYPE[grep("hurricane", ecodata$EVTYPE)] = "hurricane"
ecodata$EVTYPE[grep("burst", ecodata$EVTYPE)] = "tstm"
ecodata$EVTYPE[grep("heatwave", ecodata$EVTYPE)] = "heat"
ecodata$EVTYPE[grep("excessiveheat", ecodata$EVTYPE)] = "excessiveheat"
ecodata$EVTYPE[grep("stormsurge", ecodata$EVTYPE)] = "stormsurge"
ecodata$EVTYPE[grep("sleet", ecodata$EVTYPE)] = "sleet"
ecodata$EVTYPE[grep("((hot)|(warm))weather", ecodata$EVTYPE)] = "heat"
ecodata$EVTYPE[grep("duststorm", ecodata$EVTYPE)] = "dststorm"
ecodata$EVTYPE[grep("dust", ecodata$EVTYPE)] = "dustdevil"
ecodata$EVTYPE[grep("volcanicash", ecodata$EVTYPE)] = "volcanicash"
ecodata$EVTYPE <- gsub("tstm", "thunderstorm", ecodata$EVTYPE)
ecodata$EVTYPE[grep("hypotherm", ecodata$EVTYPE)] = "winterweather"
ecodata$EVTYPE[grep("hypertherm", ecodata$EVTYPE)] = "heat"
ecodata$EVTYPE[grep("funnel", ecodata$EVTYPE)] = "funnelcloud"
ecodata$EVTYPE[grep("spout", ecodata$EVTYPE)] = "waterspout"
ecodata$EVTYPE[grep("typhoon", ecodata$EVTYPE)] = "hurricane"
ecodata$EVTYPE[grep("highswell", ecodata$EVTYPE)] = "highsurf"
ecodata$EVTYPE[grep("(hot)|(warm)", ecodata$EVTYPE)] = "heat"
ecodata$EVTYPE[grep("densefog", ecodata$EVTYPE)] = "densefog"
ecodata$EVTYPE[grep("fire", ecodata$EVTYPE)] = "wildfire"
ecodata$EVTYPE[grep("sea", ecodata$EVTYPE)] = "highsurf"
ecodata$EVTYPE <- gsub("vog", "fog", ecodata$EVTYPE)
ecodata$EVTYPE[grep("severethunderstorm", ecodata$EVTYPE)] = "thunderstorm"
ecodata$EVTYPE[grep("cloud", ecodata$EVTYPE)] = "funnelcloud"
ecodata$EVTYPE[grep("highwater", ecodata$EVTYPE)] = "flashflood"
ecodata$EVTYPE[grep("^wnd", ecodata$EVTYPE)] = "coldwndchill"
ecodata$EVTYPE[grep("wave", ecodata$EVTYPE)] = "flashflood"
ecodata$EVTYPE[grep("tornado", ecodata$EVTYPE)] = "tornado"
ecodata$EVTYPE[grep("ripcurrent", ecodata$EVTYPE)] = "ripcurrent"
ecodata <- ecodata[!grepl("(mud)|(glaze)|(precip)|(month)|(year)|(season)|(metro)|(nosevereweather)|(dam)|(tide)|(slid)|(spell)|(remnant)|(redflag)|(lights)|(drowning)",ecodata$EVTYPE),]
length(unique(ecodata$EVTYPE))## [1] 49- Managing the exponential values:
unique(ecodata$PROPDMGEXP)## [1] "K" "" "M" "B" "0"ecodata$PROPDMGEXP <- gsub("K", 1000, ecodata$PROPDMGEXP)
ecodata$PROPDMGEXP <- gsub("M", 1000000, ecodata$PROPDMGEXP)
ecodata$PROPDMGEXP <- gsub("B", 1000000000, ecodata$PROPDMGEXP)
ecodata$PROPDMGEXP[ecodata$PROPDMGEXP==""] = 0
ecodata$PROPDMGEXP <- as.numeric(ecodata$PROPDMGEXP)
unique(ecodata$CROPDMGEXP)## [1] "K" "" "M" "B"ecodata$CROPDMGEXP <- gsub("K", 1000, ecodata$CROPDMGEXP)
ecodata$CROPDMGEXP <- gsub("M", 1000000, ecodata$CROPDMGEXP)
ecodata$CROPDMGEXP <- gsub("B", 1000000000, ecodata$CROPDMGEXP)
ecodata$CROPDMGEXP[ecodata$CROPDMGEXP == ""] = 0
ecodata$CROPDMGEXP <- as.numeric(ecodata$CROPDMGEXP)
ecodatasum <- summarise(ecodata, EVTYPE, PROPDMG= PROPDMG + PROPDMGEXP, CROPDMG = CROPDMG + CROPDMGEXP)Results:
health2 <- healthdata %>% group_by(EVTYPE) %>%
summarise(totalfetalities = sum(FATALITIES) ,totalinjuries= sum(INJURIES)) %>%
arrange(desc(totalfetalities))## `summarise()` ungrouping output (override with `.groups` argument)#these are the most 10 fetal events:
fetal <- head(health2, 10)
rename <- c("Excessive Heat", "Tornado", "Flash Flood", "Lightening", "Rip Current", "Flood", "Thunderstorm", "Extreme Cold Wind Chill", "Heat", "High Wind")
fetal$EVTYPE = rename
fetal## # A tibble: 10 x 3
## EVTYPE totalfetalities totalinjuries
## <chr> <dbl> <dbl>
## 1 Excessive Heat 1797 6391
## 2 Tornado 1511 20667
## 3 Flash Flood 890 1676
## 4 Lightening 651 4141
## 5 Rip Current 542 503
## 6 Flood 442 6837
## 7 Thunderstorm 379 5130
## 8 Extreme Cold Wind Chill 257 108
## 9 Heat 238 1311
## 10 High Wind 235 1083#and these are the most 10 injurious events:
health3 <- arrange(health2, desc(totalinjuries))
injury <- head(health3, 10)
rename2 <- c("Tornado", "Flood", "Excessive Heat", "Thunderstorm", "Lightening", "Flash Flood", "Wild Fire", "Hurricane", "Heat", "Winter Storm")
injury$EVTYPE= rename2
injury## # A tibble: 10 x 3
## EVTYPE totalfetalities totalinjuries
## <chr> <dbl> <dbl>
## 1 Tornado 1511 20667
## 2 Flood 442 6837
## 3 Excessive Heat 1797 6391
## 4 Thunderstorm 379 5130
## 5 Lightening 651 4141
## 6 Flash Flood 890 1676
## 7 Wild Fire 87 1458
## 8 Hurricane 125 1328
## 9 Heat 238 1311
## 10 Winter Storm 191 1292col1 <- brewer.pal(49, "Spectral")
par(mfrow=c(1,2))
pie(health2$totalfetalities, c("Excessive Heat", "Tornado", "Flash Flood", "Lightening", "Rip Current", "Flood", "Thunderstorm") ,
col = col1, main = "Fetalities")
pie(health3$totalinjuries, c("Tornado", "Flood", "Excessive Heat", "Thunderstorm", "Lightening"), col= col1, main = "Injuries")
mtext( "The Most Harmful Events on Population Health",side = 1, outer = TRUE, cex = 1, line = -2)
eco1 <- ecodatasum %>% group_by(EVTYPE) %>%
summarise(totalPROPDMG= sum(PROPDMG), totalCROPDMG= sum(CROPDMG))## `summarise()` ungrouping output (override with `.groups` argument)eco2 <- arrange(eco1, desc(totalPROPDMG))
propdmg <- head(eco2, 10)
rename3 <- c("Hurricane/Typhoon", "Flood", "Tornado", "Storm Surge", "Flash Flood", "Wild Fire", "Hail", "High Wind", "Tropical Storm", "Thunderstorm")
propdmg$EVTYPE = rename3
eco3 <- arrange(eco1, desc(totalCROPDMG))
cropdmg <- head(eco3, 10)
rename4 <- c("Drought", "Hurricane/Typhoon", "Hail", "Flood", "Thunderstorm", "Flash Flood", "Tornado", "Freeze", "High wind", "Heavy Rain")
cropdmg$EVTYPE = rename4
#Here is the highest 10 event types regarding the cost of properity damage:
propdmg## # A tibble: 10 x 3
## EVTYPE totalPROPDMG totalCROPDMG
## <chr> <dbl> <dbl>
## 1 Hurricane/Typhoon 15125084227. 1059057463.
## 2 Flood 6436917989. 326469620.
## 3 Tornado 4495242878. 84368128.
## 4 Storm Surge 3043292041. 143855
## 5 Flash Flood 2421912628. 194400067.
## 6 Wild Fire 2222172315. 29816549.
## 7 Hail 1834771387. 596026071.
## 8 High Wind 1308033616. 57469268.
## 9 Tropical Storm 1104501808. 30395264.
## 10 Thunderstorm 943942945. 311069130.ggplot(propdmg, aes(reorder(EVTYPE, totalPROPDMG), totalPROPDMG / 1000000000, fill= EVTYPE))+
geom_bar(stat="identity") +
coord_flip() +
theme(legend.position = "none") +
xlab("Event Types") +
ylab("Total cost of properity damage in billion dollars")
#and here is the highest 10 regarding the cost of crop damage:
cropdmg## # A tibble: 10 x 3
## EVTYPE totalPROPDMG totalCROPDMG
## <chr> <dbl> <dbl>
## 1 Drought 30381094. 3137405294.
## 2 Hurricane/Typhoon 15125084227. 1059057463.
## 3 Hail 1834771387. 596026071.
## 4 Flood 6436917989. 326469620.
## 5 Thunderstorm 943942945. 311069130.
## 6 Flash Flood 2421912628. 194400067.
## 7 Tornado 4495242878. 84368128.
## 8 Freeze 8057375. 78985113.
## 9 High wind 1308033616. 57469268.
## 10 Heavy Rain 61712303. 52268238.ggplot(cropdmg, aes(reorder(EVTYPE, totalCROPDMG), totalCROPDMG / 1000000000 , fill= EVTYPE))+
geom_bar(stat="identity") +
coord_flip() +
theme(legend.position = "none") +
xlab("Event Types") +
ylab("Total cost of crop damage in billion dollars")