Questions

  1. Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

  2. Across the United States, which types of events have the greatest economic consequences?

Data

You can download the file from the course web site here

Data Documentation:
1. National Weather Service
2. National Climatic Data Center Storm Events

knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.0      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.1      ✔ stringr 1.4.1 
## ✔ readr   2.1.2      ✔ forcats 0.5.2
## Warning: package 'ggplot2' was built under R version 4.2.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
setwd("C:/Users/gpond/Desktop/Research Project 2")
if(!exists("storm.data")) {
    d <- read.csv(bzfile("repdata_data_StormData.csv.bz2"),header = TRUE)
}

d <- d %>% select(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)

d <- d %>% mutate(EVTYPE = toupper(EVTYPE)) %>% mutate(EVENT = if_else(grepl("WIND", EVTYPE), 'WIND',
                                                                if_else(grepl("HEAT", EVTYPE), 'HEAT',
                                                                if_else(grepl("FLOOD", EVTYPE), 'FLOOD',
                                                                if_else(grepl("HAIL", EVTYPE), 'HAIL',
                                                                if_else(grepl("STORM", EVTYPE), 'STORM',
                                                                if_else(grepl("SNOW", EVTYPE), 'SNOW',
                                                                if_else(grepl("TORNADO", EVTYPE), 'TORNADO',
                                                                if_else(grepl("WINTER", EVTYPE), 'WINTER',
                                                                if_else(grepl("RAIN", EVTYPE), 'RAIN','OTHER'))))))))))


health_event <- d %>% group_by(EVENT) %>% summarize(FATALITIES = sum(FATALITIES),
                                                        INJURIES = sum(INJURIES)) 

d$PROPDMGEXP <- as.character(d$PROPDMGEXP)
d$PROPDMGEXP[is.na(d$PROPDMGEXP)] <- 0 
d$PROPDMGEXP[!grepl("K|M|B", d$PROPDMGEXP, ignore.case = TRUE)] <- 0 
d$PROPDMGEXP[grep("K", d$PROPDMGEXP, ignore.case = TRUE)] <- "3"
d$PROPDMGEXP[grep("M", d$PROPDMGEXP, ignore.case = TRUE)] <- "6"
d$PROPDMGEXP[grep("B", d$PROPDMGEXP, ignore.case = TRUE)] <- "9"
d$PROPDMGEXP <- as.numeric(as.character(d$PROPDMGEXP))
d$property.damage <- d$PROPDMG * 10^d$PROPDMGEXP

d$CROPDMGEXP <- as.character(d$CROPDMGEXP)
d$CROPDMGEXP[is.na(d$CROPDMGEXP)] <- 0 # NA's considered as dollars
d$CROPDMGEXP[!grepl("K|M|B", d$CROPDMGEXP, ignore.case = TRUE)] <- 0 
d$CROPDMGEXP[grep("K", d$CROPDMGEXP, ignore.case = TRUE)] <- "3"
d$CROPDMGEXP[grep("M", d$CROPDMGEXP, ignore.case = TRUE)] <- "6"
d$CROPDMGEXP[grep("B", d$CROPDMGEXP, ignore.case = TRUE)] <- "9"
d$CROPDMGEXP <- as.numeric(as.character(d$CROPDMGEXP))
d$crop.damage <- d$CROPDMG * 10^d$CROPDMGEXP

sort(table(d$property.damage), decreasing = TRUE)[1:10]
## 
##      0   5000  10000   1000   2000  25000  50000   3000  20000  15000 
## 663123  31731  21787  17544  17186  17104  13596  10364   9179   8617
sort(table(d$crop.damage), decreasing = TRUE)[1:10]
## 
##      0   5000  10000  50000  1e+05   1000   2000  25000  20000  5e+05 
## 880198   4097   2349   1984   1233    956    951    830    758    721
econ_event <- d %>% group_by(EVENT) %>% summarize(Crop = sum(CROPDMGEXP),
                                                    Property = sum(PROPDMGEXP))

The Greatest Health Impact

The Greatest Health Impact comes from Tornado.

The Greatest Economic Impact?

The Greatest Economic Impact comes from Wind.