storm_analysis

Load the Data

# Update the path to where your file is located if needed
storm_data <- read.csv(bzfile("C:/Users/User/Downloads/repdata_data_StormData.csv.bz2"))

1. Most Harmful Events to Population Health

# Summarize fatalities and injuries by event type
health_impact <- storm_data %>%
  group_by(EVTYPE) %>%
  summarise(
    fatalities = sum(FATALITIES, na.rm = TRUE),
    injuries = sum(INJURIES, na.rm = TRUE),
    total = fatalities + injuries
  ) %>%
  arrange(desc(total))

# Show top 10
head(health_impact, 10)

## # A tibble: 10 × 4
##    EVTYPE            fatalities 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
##  7 FLASH FLOOD              978     1777  2755
##  8 ICE STORM                 89     1975  2064
##  9 THUNDERSTORM WIND        133     1488  1621
## 10 WINTER STORM             206     1321  1527

# Plot the top 10 events impacting health
top_health <- head(health_impact, 10)

ggplot(top_health, aes(x = reorder(EVTYPE, total), y = total)) +
  geom_bar(stat = "identity", fill = "tomato") +
  coord_flip() +
  labs(
    title = "Top 10 Events Harmful to Population Health",
    x = "Event Type",
    y = "Total Injuries + Fatalities"
  )

# Plot the top 10 events by fatalities
top_fatalities <- health_impact %>% arrange(desc(fatalities)) %>% head(10)

ggplot(top_fatalities, aes(x = reorder(EVTYPE, fatalities), y = fatalities)) +
  geom_bar(stat = "identity", fill = "darkred") +
  coord_flip() +
  labs(
    title = "Top 10 Events by Fatalities",
    x = "Event Type",
    y = "Number of Fatalities"
  )

2. Events with Greatest Economic Consequences

economic_impact <- storm_data %>%
  group_by(EVTYPE) %>%
  summarise(
    property = sum(PROPDMG, na.rm = TRUE),
    crop = sum(CROPDMG, na.rm = TRUE),
    total = property + crop
  ) %>%
  arrange(desc(total))

head(economic_impact, 10)

## # A tibble: 10 × 4
##    EVTYPE             property    crop    total
##    <chr>                 <dbl>   <dbl>    <dbl>
##  1 TORNADO            3212258. 100019. 3312277.
##  2 FLASH FLOOD        1420125. 179200. 1599325.
##  3 TSTM WIND          1335966. 109203. 1445168.
##  4 HAIL                688693. 579596. 1268290.
##  5 FLOOD               899938. 168038. 1067976.
##  6 THUNDERSTORM WIND   876844.  66791.  943636.
##  7 LIGHTNING           603352.   3581.  606932.
##  8 THUNDERSTORM WINDS  446293.  18685.  464978.
##  9 HIGH WIND           324732.  17283.  342015.
## 10 WINTER STORM        132721.   1979.  134700.

# Plot the top 10 events with greatest economic impact
top_economic <- head(economic_impact, 10)

ggplot(top_economic, aes(x = reorder(EVTYPE, total), y = total)) +
  geom_bar(stat = "identity", fill = "steelblue") +
  coord_flip() +
  labs(
    title = "Top 10 Events with Greatest Economic Impact",
    x = "Event Type",
    y = "Total Property + Crop Damage"
  )

Conclusion

• The most harmful event types to human health are identified using total fatalities and injuries.
• The events with the highest economic consequences are determined by the sum of property and crop damage.

You can refine this analysis by normalizing values or cleaning the EVTYPE names further.