Analysis of Severe Weather Events in the United States

Introduction

This report analyzes storm data to identify the events most harmful to public health and with the greatest economic impacts.

Load 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

library(ggplot2)

file_path <- "repdata_data_StormData.csv"  # Atualizar com o caminho correto
data <- read.csv(file_path, stringsAsFactors = FALSE)

Normalize economic damage values

convert_damage <- function(dmg, exp) {
  exp_factors <- c("K" = 1e3, "M" = 1e6, "B" = 1e9)
  
  exp <- toupper(trimws(ifelse(is.na(exp) | exp == "", "0", exp)))
  factor <- ifelse(exp %in% names(exp_factors), exp_factors[exp], 1)
  
  return(as.numeric(dmg) * factor)
}

data <- data %>%
  mutate(
    PROPDMG_TOTAL = mapply(convert_damage, PROPDMG, PROPDMGEXP),
    CROPDMG_TOTAL = mapply(convert_damage, CROPDMG, CROPDMGEXP)
  )

Question 1: Events most harmful to public health

damage_health <- data %>%
  group_by(EVTYPE) %>%
  summarise(
    Total_Fatalities = sum(FATALITIES, na.rm = TRUE),
    Total_Injuries = sum(INJURIES, na.rm = TRUE),
    Total_Health_Damage = Total_Fatalities + Total_Injuries
  ) %>%
  arrange(desc(Total_Health_Damage))

print(head(damage_health, 10))  # Top 10 eventos mais prejudiciais

## # A tibble: 10 × 4
##    EVTYPE            Total_Fatalities Total_Injuries Total_Health_Damage
##    <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

Question 2: Events with the greatest economic impact

damage_economic <- data %>%
  group_by(EVTYPE) %>%
  summarise(
    Total_Prop_Damage = sum(PROPDMG_TOTAL, na.rm = TRUE),
    Total_Crop_Damage = sum(CROPDMG_TOTAL, na.rm = TRUE),
    Total_Economic_Damage = Total_Prop_Damage + Total_Crop_Damage
  ) %>%
  arrange(desc(Total_Economic_Damage))

Graphics

Top 10 most damaging events for public health

grafico1 <- ggplot(head(damage_health, 10), aes(x = reorder(EVTYPE, -Total_Health_Damage), y = Total_Health_Damage, fill = EVTYPE)) +
  geom_bar(stat = "identity") +
  coord_flip() +
  labs(title = "Top 10 most damaging events for public healtha",
       x = "Event Type", y = "Public Health Damage (Fatalities + Injuries)") +
  theme_minimal() +
  theme(legend.position = "none")

print(grafico1)

Top 10 events with the greatest economic impact

grafico2 <- ggplot(head(damage_economic, 10), aes(x = reorder(EVTYPE, -Total_Economic_Damage), 
                                      y = Total_Economic_Damage, fill = EVTYPE)) +
  geom_bar(stat = "identity") +
  coord_flip() +
  labs(title = "Top 10 events with the greatest economic impact ",
       x = "Type of Event", y = "Total Economic Damages (USD)") +
  theme_minimal() +
  theme(legend.position = "none")

print(grafico2)