US Storm Data Analysis on Health Harm and Property Damage

Synopsis

This analysis is based on the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. The purpose is to find out across the United States,

• which types of events are most harmful with respect to population health (fatalities and injuries), and

• which types of events have the greatest economic consequences (property damages and crop damages).

Data Processing

download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2",
              destfile = "StormData.csv.bz2")
storm <- read.csv("StormData.csv.bz2")

Results

1. Most health harmful types of events

library(dplyr)
library(scales)
sum_HARM <- storm %>%
    group_by(EVTYPE) %>%
    summarise(sum_HARM = sum(FATALITIES + INJURIES)) %>%
    arrange(desc(sum_HARM))

top10ratio_HARM <- sum(sum_HARM$sum_HARM[1:10]) / sum(sum_HARM$sum_HARM)
top10ratio_HARM

## [1] 0.8811868

Top 10 event types caused 88.1% of the whole health harm.

The list and grap of top 10 types of events:

head(sum_HARM, 10)

## # A tibble: 10 × 2
##               EVTYPE sum_HARM
##               <fctr>    <dbl>
## 1            TORNADO    96979
## 2     EXCESSIVE HEAT     8428
## 3          TSTM WIND     7461
## 4              FLOOD     7259
## 5          LIGHTNING     6046
## 6               HEAT     3037
## 7        FLASH FLOOD     2755
## 8          ICE STORM     2064
## 9  THUNDERSTORM WIND     1621
## 10      WINTER STORM     1527

library(ggplot2)
ggplot(head(sum_HARM, 10), 
       aes(x = reorder(EVTYPE, -sum_HARM), 
           y = sum_HARM,
           fill = EVTYPE)) + 
    geom_bar(stat = "identity") +
    labs(title = "Health Harms by Event Types", 
         x = "Event Type", y = "Health Harm") +
    theme(axis.text.x = element_text(size = 8, angle = 45),
          legend.position="none") +
    scale_y_continuous(labels = scientific)

2. Most economy damagable types of events

sum_DAMAGE <- storm %>%
    group_by(EVTYPE) %>%
    summarise(sum_DAMAGE = sum(PROPDMG + CROPDMG)) %>%
    arrange(desc(sum_DAMAGE))

top10ratio_DAMAGE <- sum(sum_DAMAGE$sum_DAMAGE[1:10]) / sum(sum_DAMAGE$sum_DAMAGE)
top10ratio_DAMAGE

## [1] 0.9121675

Top 10 event types caused 91.2% of the whole economic damage.

The list and grap of top 10 types of events:

head(sum_DAMAGE, 10)

## # A tibble: 10 × 2
##                EVTYPE sum_DAMAGE
##                <fctr>      <dbl>
## 1             TORNADO  3312276.7
## 2         FLASH FLOOD  1599325.1
## 3           TSTM WIND  1445168.2
## 4                HAIL  1268289.7
## 5               FLOOD  1067976.4
## 6   THUNDERSTORM WIND   943635.6
## 7           LIGHTNING   606932.4
## 8  THUNDERSTORM WINDS   464978.1
## 9           HIGH WIND   342014.8
## 10       WINTER STORM   134699.6

ggplot(head(sum_DAMAGE, 10), 
       aes(x = reorder(EVTYPE, -sum_DAMAGE), 
           y = sum_DAMAGE,
           fill = EVTYPE)) + 
    geom_bar(stat = "identity") +
    labs(title = "Economic Damages by Event Types", 
         x = "Event Type", y = "Economic Damage") +
    theme(axis.text.x = element_text(size = 8, angle = 45),
          legend.position="none") +
    scale_y_continuous(labels = scientific)