Synopsis

In the following analysis, we have shown what NOAA Events cause the most amount of damage in terms of both Population (injuries and fatalities) and Economic (crop and property). We will be utilizing data provided by the U.S. National Oceanic and Atmospheric Administration’s (NOAA) Storm Database. This data measures January 1950 to November 2011.

The resulting analysis found that tornadoes caused both the most Population and Economic damages.

Data Processing

## for plotting
library(ggplot2)
library(gridExtra)

First, read in the data and observe the structure.

storms <- read.csv('repdata_data_StormData.csv.bz2')

str(storms)
## '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 ...

We are interested in answering the question of what types of events are most harmful with respect to both population and economic impact.

We will start with the impact on population.

Population Damage

We can see from the variables present in the provided data that population health is measured in both injuries and fatalities, which we will combine into a single variable for ease of use.

## initial variable creation
storms$Pop_Damage <- storms$FATALITIES + storms$INJURIES

After which, we will group by individual Event Type.

## sum this metric by event type.
population_damage <- aggregate(storms$Pop_Damage, by = list(storms$EVTYPE), sum) 

## now rename the resulting columns
colnames(population_damage)[1] <- 'EVTYPE'
colnames(population_damage)[2] <- 'Damage'


To get an initial read on the damage sources, we will examine the total available EVTYPEs in our data.

There are a total of

length(unique(storms$EVTYPE))
## [1] 985

unique disaster types present.


As we can see, there are far too many individual events to display cleanly on a single chart, so we will limit to the top 10.

 ## order by damage desc and limit
top_dmg_pop <- population_damage[order(population_damage$Damage, decreasing = T),][1:10,]

 ## create result plots, will arrange in a grid in the Results section.
bar_pop <- ggplot(data = top_dmg_pop, aes(x = EVTYPE)) + geom_bar(aes(y = Damage),stat = 'identity', fill = '#423f61') + coord_flip()
table_pop <- tableGrob(top_dmg_pop)

Economic Damage

We will now complete an analogous measurement for economic damage. Similar to the above analysis, we will start by creating a variable equal to the sum of both Property and Crop damage.

storms$econ_dmg <- storms$CROPDMG + storms$PROPDMG


And group by each EVTYPE.

## aggregate
econ_dmg <- aggregate(storms$econ_dmg, by = list(storms$EVTYPE), sum)

## rename columns for usage.
colnames(econ_dmg)[1] <- 'EVTYPE'
colnames(econ_dmg)[2] <- 'Damage'


The data has not changed, so we will not recount the total number of EVTYPEs present. Our next step will be to create our plot grid.

 ## order by damage desc and limit
top_econ_dmg <- econ_dmg[order(econ_dmg$Damage, decreasing = T),][1:10,]

 ## create result plots, will arrange in a grid in the Results section.
bar_econ <- ggplot(data = top_econ_dmg, aes(x = EVTYPE)) + geom_bar(aes(y = Damage),stat = 'identity', fill = '#81a193') + coord_flip()
table_econ <- tableGrob(top_econ_dmg)

Results

Population Damage

grid.arrange(bar_pop, table_pop, ncol = 2)


As we can see from the bar chart and the table in the single figure above, tornadoes are the most destructive by a long shot when it comes to population damage.

Economic Impact

grid.arrange(bar_econ, table_econ, ncol = 2)


We again see from the single figure that tornadoes are the largest cause of damage.