Synopsis

The aim of this research work is to analyse the impact of storm towards population health and economic consequences in US. The data is obtained from the US NOAA Storm Database. This work has two specific research questions:

Data Preparation

Loading required libraries

library(data.table)
library(ggplot2)
library(R.utils)

Downloading and loading dataset into stormData variable. The data is downloaded from here.

download.file("http://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2", "repdata-data-StormData.csv.bz2")
bunzip2("repdata-data-StormData.csv.bz2")
stormData <- read.csv("repdata-data-StormData.csv")
stormData<-data.table(stormData)

Results

In this section, two detailed analysis works are reported.

Analysis 1: Which types of events are most harmful with respect to population health?

In the first analysis work, the top 5 event types that are most harmful to US population health are listed and ploted.

Data preparation: Extracting the appropriate columns.

The original dataset was transformed by subsetting data with relevant columns only. The columns are “EVTYPE”, “FATALITIES”, and “INJURIES”. After that, a new table named “dt.event.health” is created to capture the total fatalities, injuries grouped by the event type.

stormData.event.health<-stormData[,list(EVTYPE,FATALITIES,INJURIES)]
dt.event.health<-stormData.event.health[,list(sum(FATALITIES),sum(INJURIES),sum(FATALITIES)+ sum(INJURIES)),by=list(EVTYPE)]
setnames(dt.event.health,"V1","Total.Fatalities")
setnames(dt.event.health,"V2","Total.Injuries")
setnames(dt.event.health,"V3","Total")

Order the dataset according to “Total” decreasing

dt.event.health<-dt.event.health[order(-rank(Total))]

Displaying the top 5 events

head(dt.event.health,5)
##            EVTYPE Total.Fatalities Total.Injuries Total
## 1:        TORNADO             5633          91346 96979
## 2: EXCESSIVE HEAT             1903           6525  8428
## 3:      TSTM WIND              504           6957  7461
## 4:          FLOOD              470           6789  7259
## 5:      LIGHTNING              816           5230  6046

Plotting the top 5 events using ggplot

ggplot(data = dt.event.health[1:5], aes(x = EVTYPE, y= Total, fill=EVTYPE)) +
     geom_bar(stat="identity") +
     labs(x = "Event Type", y = "Count", color = "Event Type", fill="Event Type", title="Top 5 Events with Hightest Impact to Population Health in US") +
     theme_bw()

The graph above shows that tornado has been the main event that greatly impact the health of US population. The second event is excessive heat, while lightning has ranked the 5th position.

Analysis 2: Which types of events have the greatest economic consequences?

In this analysis work, the top 5 event types that are most harmful to US economic are listed and ploted.

Data preparation: Extracting the appropriate columns.

stormData.event.eco<-stormData[,list(EVTYPE,PROPDMG,CROPDMG)]
dt.event.eco<-stormData.event.eco[,list(sum(PROPDMG),sum(CROPDMG),sum(PROPDMG)+ sum(CROPDMG)),by=list(EVTYPE)]
setnames(dt.event.eco,"V1","Total.Property")
setnames(dt.event.eco,"V2","Total.Crop")
setnames(dt.event.eco,"V3","Total")
dt.event.eco<-dt.event.eco[order(-rank(Total))]

Order the dataset according to “Total” decreasing

dt.event.health<-dt.event.health[order(-rank(Total))]

Displaying the top 5 events

head(dt.event.eco,5)
##         EVTYPE Total.Property Total.Crop   Total
## 1:     TORNADO      3212258.2   100018.5 3312277
## 2: FLASH FLOOD      1420124.6   179200.5 1599325
## 3:   TSTM WIND      1335965.6   109202.6 1445168
## 4:        HAIL       688693.4   579596.3 1268290
## 5:       FLOOD       899938.5   168037.9 1067976

Plotting the top 5 events using ggplot

ggplot(data = dt.event.eco[1:5], aes(x = EVTYPE, y= Total, fill=EVTYPE)) +
  geom_bar(stat="identity") +
  labs(x = "Event Type", y = "Count", color = "Event Type", fill="Event Type", title="Top 5 Events with Hightest Economic Consequences in US") +
  theme_bw()

The graph above shows the top 5 events with hightest economic consequences in US. Tornado has again reported to be the main event with highest economic consequences in US. Like many countries, flash flood is one of the major problems to a nation’s economy.