NOAA Storm Database Analysis

library(dplyr)

## Warning: package 'dplyr' was built under R version 4.4.2

## 
## 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 4.4.2

library(readr)

## Warning: package 'readr' was built under R version 4.4.2

library(tidyr)

## Warning: package 'tidyr' was built under R version 4.4.2

# Load the data
file_path <- "C:/Users/Боби/Desktop/repdata_data_StormData.csv.bz2"
storm_data <- read.csv(file_path)

# Inspect the structure of the dataset
str(storm_data)

## '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 ...

cleaned_data <- storm_data %>%
  select(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)

Convert Damage Values

convert_exponent <- function(exp) {
  ifelse(exp %in% c("K", "k"), 1e3,
         ifelse(exp %in% c("M", "m"), 1e6,
                ifelse(exp %in% c("B", "b"), 1e9, 1)))
}

cleaned_data <- cleaned_data %>%
  mutate(
    PROPDMGEXP = convert_exponent(PROPDMGEXP),
    CROPDMGEXP = convert_exponent(CROPDMGEXP),
    PROPDMG = PROPDMG * PROPDMGEXP,
    CROPDMG = CROPDMG * CROPDMGEXP
  )

Aggregate Data

summary_data <- cleaned_data %>%
  group_by(EVTYPE) %>%
  summarise(
    total_fatalities = sum(FATALITIES, na.rm = TRUE),
    total_injuries = sum(INJURIES, na.rm = TRUE),
    total_damage = sum(PROPDMG + CROPDMG, na.rm = TRUE)
  ) %>%
  arrange(desc(total_fatalities), desc(total_injuries), desc(total_damage))

Results

Events Most Harmful to Population Health

Fatalities

top_fatalities <- summary_data %>% top_n(10, total_fatalities)
ggplot(top_fatalities, aes(x = reorder(EVTYPE, total_fatalities), y = total_fatalities)) +
  geom_bar(stat = "identity", fill = "red") +
  coord_flip() +
  labs(title = "Top 10 Events by Fatalities", x = "Event Type", y = "Total Fatalities")

Injuries

top_injuries <- summary_data %>% top_n(10, total_injuries)
ggplot(top_injuries, aes(x = reorder(EVTYPE, total_injuries), y = total_injuries)) +
  geom_bar(stat = "identity", fill = "blue") +
  coord_flip() +
  labs(title = "Top 10 Events by Injuries", x = "Event Type", y = "Total Injuries")

Events with Greatest Economic Consequences

top_damage <- summary_data %>% top_n(10, total_damage)
ggplot(top_damage, aes(x = reorder(EVTYPE, total_damage), y = total_damage)) +
  geom_bar(stat = "identity", fill = "green") +
  coord_flip() +
  labs(title = "Top 10 Events by Economic Damage", x = "Event Type", y = "Total Damage (USD)")

Conclusion

• Tornadoes, excessive heat, and flash floods are among the most harmful events to population health.
• Floods, hurricanes/typhoons, and tornadoes cause the greatest economic damage.

This analysis highlights the importance of targeted preparation and resource allocation for managing severe weather events.