Reproducible Research Project 2

Title: Health and Economic Impacts of Hazardous Events in the US

##Synopsis The following data analysis report is about the health and economic impacts caused by various hazardous events in the United States, starting from 1950 to November, 2011. The raw data is manipulated and computed to show the TOP 10 HAZARDS and their impacts with the help of tabular data as well as graphical plots. Where on one hand TORNADOES have caused a huge impact, relatively, on human health; FLOODS have been responsible for impacting the economy by damaging property as well as crops. The data on which the analysis is done doesn’t cover accurate information due to the lack of data collection in earlier days and hence, the final results can vary from the actual scenario of the past yet matching perfectly with the provided data.

Data Processing

Importing Libraries

library(knitr)

## Warning: package 'knitr' was built under R version 4.0.3

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.0.3

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.0.3

Q-1: Across the United States, which types of events are most harmful with respect to population health?

Downloading data from the given URL and loading into variable ‘data’

url<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
#dest<-"Please enter the directory address in which you want to download the file/name of file" #(Remove beginning # to run this line)
#download.file(url,dest) #(Remove beginning # to run this line)
data<-read.csv("data.csv",header = TRUE,sep = ",")

Creating a plot of impact vs events

impact<-with(data,aggregate(FATALITIES+INJURIES~EVTYPE,data,sum))
names(impact)[2]<-"IMPACT"
topEvents<-head(impact[order(-impact$IMPACT),],10)
topEvents

##                EVTYPE IMPACT
## 834           TORNADO  96979
## 130    EXCESSIVE HEAT   8428
## 856         TSTM WIND   7461
## 170             FLOOD   7259
## 464         LIGHTNING   6046
## 275              HEAT   3037
## 153       FLASH FLOOD   2755
## 427         ICE STORM   2064
## 760 THUNDERSTORM WIND   1621
## 972      WINTER STORM   1527

evplot<-ggplot(topEvents,aes(EVTYPE,IMPACT))+geom_bar(stat = "identity")+ggtitle("Impact of harmful events on US populations health")+xlab("Event")+ylab("Impact=Fatalities+Injuries")+geom_bar(stat = "identity",col="brown",fill="red")+theme_light()+theme(axis.text.x=element_text(angle = 90, hjust=1))
evplot

Answer1: Looking at the topEvents data frame and the bar plot of Impact vs Events, we can conclude that the most harmful event has been Tornado, impacting 96,979 people in the total US population.

Results

Q-2: Across the United States, which types of events have the greatest economic consequences?

Creating a plot of economic impact vs events

#Here we need to decode and change the characters to the corresponding monetary values

ddata<-data[c(8,25:28)]
ddata$property<-factor(ddata$PROPDMGEXP,levels=c("H","K","M","B","h","m","O"))
ddata$property[is.na(data$property)] <- "O"
ddata$crops<-factor(ddata$CROPDMGEXP,levels=c("K","M","B","k","m","O"))
ddata$crops[is.na(ddata$crops)] <- "O"
ddata<- mutate(ddata,PROPERTY= 0, CROPS=0)
 
ddata$PROPERTY[ddata$property=="K"]<-1000
ddata$PROPERTY[ddata$property=="H"|ddata$property=="h"]<-100
ddata$PROPERTY[ddata$property=="M"|ddata$property=="m"]<-1e6
ddata$PROPERTY[ddata$property=="B"]<-1e9
ddata$PROPERTY[ddata$propertyr=="O"]<-1

ddata$CROPS[ddata$crops=="K"|ddata$crops=="k"]<-1000
ddata$CROPS[ddata$crops=="M"|ddata$crops=="m"]<-1e6
ddata$CROPS[ddata$crops=="B"]<-1e9
ddata$CROPS[ddata$crops=="O"]<-1

#Creating a new dataset which constitutes variables representing the property and crop damages

ddata<- mutate(ddata,pdam= PROPDMG*PROPERTY/1e6, cdam=CROPDMG*CROPS/1e6)
ddata2<-aggregate(cbind(pdam,cdam)~EVTYPE,ddata,sum,na.rm=TRUE)
ddata2<-ddata2 %>% group_by(EVTYPE) %>% summarize(pdam=sum(pdam,na.rm=TRUE),cdam=sum(cdam,na.rm=TRUE))

## `summarise()` ungrouping output (override with `.groups` argument)

ddata2<-arrange(ddata2,desc(pdam+cdam))
ddata2<-ddata2[1:10,]

#Summing up the crop and property damages and storing value in a new variable "cdam"

ddata2<-mutate(ddata2,EVTYPE,pdam,cdam,dam=pdam+cdam)
ddata2

## # A tibble: 10 x 4
##    EVTYPE               pdam      cdam     dam
##    <chr>               <dbl>     <dbl>   <dbl>
##  1 FLOOD             144658.  5662.    150320.
##  2 HURRICANE/TYPHOON  69306.  2608.     71914.
##  3 TORNADO            56937.   415.     57352.
##  4 STORM SURGE        43324.     0.005  43324.
##  5 HAIL               15732.  3026.     18758.
##  6 FLASH FLOOD        16141.  1421.     17562.
##  7 DROUGHT             1046. 13973.     15019.
##  8 HURRICANE          11868.  2742.     14610.
##  9 RIVER FLOOD         5119.  5029.     10148.
## 10 ICE STORM           3945.  5022.      8967.

#plotting cdam vs events

damplot<-ggplot(ddata2,aes(EVTYPE,dam))+geom_bar(stat="identity",col="black",fill="green")+ggtitle("Economic impact of harmful events on crops and property")+xlab("Event")+ylab("Total Damage(in Milion dollars)")+theme_light()+theme(axis.text.x = element_text(angle = 90,hjust = 1))
damplot

Answer2: Looking at the data frame ddata2 and plot of total damage(in millions) vs Events, it is clear that Floods have cause the maximum damage.