Analysis of storms data across the United States and impact on population health and economic activity
The objective ot the analysis is to assess the effects of severe weather events on both population and economy in the US using the NOAA Storm Database. The NOAA Storm Database contains the records of events for the time period between 1950 and November 2011.
Two sets of analysis have been carried out to find out the most harmful severe weather events with respect to:
Load and explore the data
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, union
# Download the dataset
url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
f <- file.path(getwd(), "data.csv.bz2")
if (!file.exists("data.csv.bz2")) {
download.file(url = urlData, destfile = "data.csv.bz2");
}
# Read the dataset
storm <- read.table("data.csv.bz2", header = TRUE, sep = ",", quote = "\"")
# Let's take a look at the summary and structure of the dataset
head(storm)
## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE EVTYPE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL TORNADO
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL TORNADO
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL TORNADO
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL TORNADO
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL TORNADO
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL TORNADO
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END COUNTYENDN
## 1 0 0 NA
## 2 0 0 NA
## 3 0 0 NA
## 4 0 0 NA
## 5 0 0 NA
## 6 0 0 NA
## END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES INJURIES PROPDMG
## 1 0 14.0 100 3 0 0 15 25.0
## 2 0 2.0 150 2 0 0 0 2.5
## 3 0 0.1 123 2 0 0 2 25.0
## 4 0 0.0 100 2 0 0 2 2.5
## 5 0 0.0 150 2 0 0 2 2.5
## 6 0 1.5 177 2 0 0 6 2.5
## PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES LATITUDE LONGITUDE
## 1 K 0 3040 8812
## 2 K 0 3042 8755
## 3 K 0 3340 8742
## 4 K 0 3458 8626
## 5 K 0 3412 8642
## 6 K 0 3450 8748
## LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3051 8806 1
## 2 0 0 2
## 3 0 0 3
## 4 0 0 4
## 5 0 0 5
## 6 0 0 6
str(storm)
## '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 ...
Subset the data to include only those variables that are required for the analysis. In the next step, create new variables for cost of property damage and cost of crop damage
library(dplyr)
# Subset the dataset to only keep the parameters of interest.Only keep columns with health related or property related impact. Ignore any observations where event type or property damage, crop damage and fatalities or injuries are not reported.
storm_subset <- storm %>%
select(c(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)) %>%
filter((EVTYPE != "" | FATALITIES > 0 | INJURIES > 0 | PROPDMG > 0 | PROPDMGEXP > 0 | CROPDMG> 0 | CROPDMGEXP > 0 ))
# Create new columns with total cost related to property / crop damages and convert to correct format
storm_subset$PROPDMG_COST <- case_when(storm_subset$PROPDMGEXP == "-" ~ storm_subset$PROPDMG * 10^0,
storm_subset$PROPDMGEXP == "+" ~ storm_subset$PROPDMG * 10^0,
storm_subset$PROPDMGEXP == "0" ~ storm_subset$PROPDMG * 10^0,
storm_subset$PROPDMGEXP == "1" ~ storm_subset$PROPDMG * 10^1,
storm_subset$PROPDMGEXP == "2" ~ storm_subset$PROPDMG * 10^2,
storm_subset$PROPDMGEXP == "3" ~ storm_subset$PROPDMG * 10^3,
storm_subset$PROPDMGEXP == "4" ~ storm_subset$PROPDMG * 10^4,
storm_subset$PROPDMGEXP == "5" ~ storm_subset$PROPDMG * 10^5,
storm_subset$PROPDMGEXP == "6" ~ storm_subset$PROPDMG * 10^6,
storm_subset$PROPDMGEXP == "7" ~ storm_subset$PROPDMG * 10^7,
storm_subset$PROPDMGEXP == "8" ~ storm_subset$PROPDMG * 10^8,
storm_subset$PROPDMGEXP == "h" ~ storm_subset$PROPDMG * 10^2,
storm_subset$PROPDMGEXP == "H" ~ storm_subset$PROPDMG * 10^2,
storm_subset$PROPDMGEXP == "K" ~ storm_subset$PROPDMG * 10^3,
storm_subset$PROPDMGEXP == "m" ~ storm_subset$PROPDMG * 10^6,
storm_subset$PROPDMGEXP == "M" ~ storm_subset$PROPDMG * 10^6,
storm_subset$PROPDMGEXP == "B" ~ storm_subset$PROPDMG * 10^9,
storm_subset$PROPDMGEXP == "" ~ storm_subset$PROPDMG * 10^0)
storm_subset$CROPDMG_COST <- case_when(storm_subset$CROPDMGEXP == "?" ~ storm_subset$CROPDMG * 10^0,
storm_subset$CROPDMGEXP == "0" ~ storm_subset$CROPDMG * 10^0,
storm_subset$CROPDMGEXP == "2" ~ storm_subset$CROPDMG * 10^2,
storm_subset$CROPDMGEXP == "k" ~ storm_subset$CROPDMG * 10^3,
storm_subset$CROPDMGEXP == "K" ~ storm_subset$CROPDMG * 10^3,
storm_subset$CROPDMGEXP == "m" ~ storm_subset$CROPDMG * 10^6,
storm_subset$CROPDMGEXP == "M" ~ storm_subset$CROPDMG * 10^6,
storm_subset$CROPDMGEXP == "B" ~ storm_subset$CROPDMG * 10^9,
storm_subset$CROPDMGEXP == "" ~ storm_subset$CROPDMG * 10^0)
Summarize the events by highest economic impact
library(dplyr)
# Let's look at the events with highest economic impact
storm_cost_byevent <- storm_subset %>%
group_by(EVTYPE) %>%
summarise(property = sum(PROPDMG_COST),
crop = sum(CROPDMG_COST),
total_cost = property + crop
) %>%
arrange(desc(total_cost))
head(storm_cost_byevent)
## # A tibble: 6 × 4
## EVTYPE property crop total_cost
## <chr> <dbl> <dbl> <dbl>
## 1 FLOOD 144657709807 5661968450 150319678257
## 2 HURRICANE/TYPHOON 69305840000 2607872800 71913712800
## 3 TORNADO 56947380676. 414953270 57362333946.
## 4 STORM SURGE 43323536000 5000 43323541000
## 5 DROUGHT 1046106000 13972566000 15018672000
## 6 HURRICANE 11868319010 2741910000 14610229010
Summarize the events by highest impact on the population health
library(dplyr)
# Let's look at the events which has most impact on population health - in terms of death and injuries
storm_health_byevent <- storm_subset %>%
group_by(EVTYPE) %>%
summarise(deaths = sum(FATALITIES),
injuries = sum(INJURIES),
total = deaths + injuries
) %>%
arrange(desc(total))
head(storm_health_byevent)
## # A tibble: 6 × 4
## EVTYPE deaths injuries total
## <chr> <dbl> <dbl> <dbl>
## 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
## 6 HEAT 937 2100 3037
Events that causes highest economic impact
library(dplyr)
library(tidyr)
# Convert the the economic impact data frame to a longer data frame to use in next step for creating a chart
costs_byevent <- storm_cost_byevent %>%
pivot_longer(!EVTYPE, names_to="cost_type", values_to = "damage")
head(costs_byevent)
## # A tibble: 6 × 3
## EVTYPE cost_type damage
## <chr> <chr> <dbl>
## 1 FLOOD property 144657709807
## 2 FLOOD crop 5661968450
## 3 FLOOD total_cost 150319678257
## 4 HURRICANE/TYPHOON property 69305840000
## 5 HURRICANE/TYPHOON crop 2607872800
## 6 HURRICANE/TYPHOON total_cost 71913712800
library(ggplot2)
# Create a chart to present the top 10 events with the highest economic impact
econ_plot <- ggplot(costs_byevent[1:30,], aes(x=reorder(EVTYPE, -damage), y = damage)) +
geom_bar(stat="identity", aes(fill=cost_type), width = 0.75, position = "dodge") +
xlab("Event type") +
theme(axis.text.x = element_text(angle=90, hjust=1)) +
ylab("Economic impact") +
ggtitle("Top 10 storm events in the US causing highest economic damage")
# Print the economic impact chart on the screen
econ_plot
Events that are most harmful to population health in term of deaths and injuries
library(dplyr)
library(tidyr)
# Convert the impact on population health dataframe to a longer data frame to use in next step for creating a chart
health_byevent <- storm_health_byevent %>%
pivot_longer(!EVTYPE, names_to="health_type", values_to = "value")
head(health_byevent)
## # A tibble: 6 × 3
## EVTYPE health_type value
## <chr> <chr> <dbl>
## 1 TORNADO deaths 5633
## 2 TORNADO injuries 91346
## 3 TORNADO total 96979
## 4 EXCESSIVE HEAT deaths 1903
## 5 EXCESSIVE HEAT injuries 6525
## 6 EXCESSIVE HEAT total 8428
library(ggplot2)
# Create a chart to present the top 10 events that are most harmful to population health
health_plot <- ggplot(health_byevent[1:30,], aes(x=reorder(EVTYPE, -value), y = value)) +
geom_bar(stat="identity", aes(fill=health_type), width = 0.75, position = "dodge") +
xlab("Event type") +
theme(axis.text.x = element_text(angle=90, hjust=1)) +
ylab("Count") +
ggtitle("Top 10 storm events in the US causing highest impact on population health")
# Print the population health impact chart on the screen
health_plot