# Load necessary libraries
library(dplyr)
library(ggplot2)
library(lubridate)
library(scales) # For formatting numbers
# Load the storm data
storm_data <- read.csv("repdata_data_StormData.csv")
# Check the structure of the data
str(storm_data[,1:10]) # First 10 columns for brevity
## 'data.frame': 902297 obs. of 10 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 "" "" "" "" ...
summary(storm_data[,c("FATALITIES", "INJURIES", "PROPDMG", "CROPDMG")])
## FATALITIES INJURIES PROPDMG CROPDMG
## Min. : 0.0000 Min. : 0.0000 Min. : 0.00 Min. : 0.000
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.00 1st Qu.: 0.000
## Median : 0.0000 Median : 0.0000 Median : 0.00 Median : 0.000
## Mean : 0.0168 Mean : 0.1557 Mean : 12.06 Mean : 1.527
## 3rd Qu.: 0.0000 3rd Qu.: 0.0000 3rd Qu.: 0.50 3rd Qu.: 0.000
## Max. :583.0000 Max. :1700.0000 Max. :5000.00 Max. :990.000
# Function to convert damage values with exponents
convert_damage <- function(dmg, exp) {
exp <- toupper(as.character(exp))
multiplier <- case_when(
exp == "K" ~ 1000,
exp == "M" ~ 1000000,
exp == "B" ~ 1000000000,
exp %in% c("", "+", "-", "?") ~ 1,
TRUE ~ 1 # Default for unrecognized exponents
)
return(dmg * multiplier)
}
# Clean and prepare data
storm_data_clean <- storm_data %>%
# Select needed columns
select(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP) %>%
# Remove rows with missing event type
filter(!is.na(EVTYPE) & EVTYPE != "") %>%
# Standardize event types
mutate(
EVTYPE = toupper(EVTYPE),
EVTYPE = case_when(
grepl("TORNADO|TORNDAO", EVTYPE) ~ "TORNADO",
grepl("HEAT|HOT", EVTYPE) ~ "EXCESSIVE HEAT",
grepl("HURRICANE|TYPHOON", EVTYPE) ~ "HURRICANE/TYPHOON",
grepl("FLOOD|FLD", EVTYPE) ~ "FLOOD",
grepl("WIND|WND", EVTYPE) ~ "WIND",
grepl("SNOW|WINTER|ICE", EVTYPE) ~ "WINTER WEATHER",
grepl("RAIN|PRECIP", EVTYPE) ~ "HEAVY RAIN",
TRUE ~ EVTYPE
),
# Convert damage values
PROPDMG = convert_damage(PROPDMG, PROPDMGEXP),
CROPDMG = convert_damage(CROPDMG, CROPDMGEXP)
)
# Health impact analysis
health_impact <- storm_data_clean %>%
group_by(EVTYPE) %>%
summarise(
total_fatalities = sum(FATALITIES),
total_injuries = sum(INJURIES),
total_health_impact = sum(FATALITIES + INJURIES)
) %>%
arrange(desc(total_health_impact))
# Show top 10 events by health impact
health_top10 <- head(health_impact, 10)
health_top10 %>%
mutate(across(where(is.numeric), ~ format(., big.mark = ",")))
## # A tibble: 10 × 4
## EVTYPE total_fatalities total_injuries total_health_impact
## <chr> <chr> <chr> <chr>
## 1 TORNADO "5,661" "91,407" "97,068"
## 2 WIND "1,424" "11,498" "12,922"
## 3 EXCESSIVE HEAT "3,138" " 9,224" "12,362"
## 4 FLOOD "1,553" " 8,683" "10,236"
## 5 LIGHTNING " 816" " 5,230" " 6,046"
## 6 WINTER WEATHER " 538" " 5,151" " 5,689"
## 7 HURRICANE/TYPHOON " 135" " 1,333" " 1,468"
## 8 HAIL " 15" " 1,361" " 1,376"
## 9 WILDFIRE " 75" " 911" " 986"
## 10 BLIZZARD " 101" " 805" " 906"
# Economic impact analysis (in billions)
economic_impact <- storm_data_clean %>%
group_by(EVTYPE) %>%
summarise(
property_damage_billions = sum(PROPDMG) / 1000000000,
crop_damage_billions = sum(CROPDMG) / 1000000000,
total_damage_billions = (sum(PROPDMG) + sum(CROPDMG)) / 1000000000
) %>%
arrange(desc(total_damage_billions))
# Show top 10 events by economic impact
economic_top10 <- head(economic_impact, 10)
economic_top10 %>%
mutate(across(where(is.numeric), ~ paste0("$", round(., 2), "B")))
## # A tibble: 10 × 4
## EVTYPE property_damage_bill…¹ crop_damage_billions total_damage_billions
## <chr> <chr> <chr> <chr>
## 1 FLOOD $167.59B $12.39B $179.98B
## 2 HURRICANE/… $85.36B $5.52B $90.87B
## 3 TORNADO $58.59B $0.42B $59.01B
## 4 STORM SURGE $43.32B $0B $43.32B
## 5 HAIL $15.73B $3.03B $18.76B
## 6 WIND $16.04B $2.03B $18.07B
## 7 WINTER WEA… $11.7B $5.2B $16.9B
## 8 DROUGHT $1.05B $13.97B $15.02B
## 9 TROPICAL S… $7.7B $0.68B $8.38B
## 10 WILDFIRE $4.77B $0.3B $5.06B
## # ℹ abbreviated name: ¹​property_damage_billions
# Plot health impact
ggplot(health_top10,
aes(x = reorder(EVTYPE, total_health_impact),
y = total_health_impact)) +
geom_bar(stat = "identity", fill = "red", alpha = 0.8) +
geom_text(aes(label = comma(total_health_impact)),
hjust = -0.1, size = 3.5) +
coord_flip() +
scale_y_continuous(labels = comma, expand = expansion(mult = c(0, 0.1))) +
labs(x = "Event Type",
y = "Total Fatalities + Injuries",
title = "Top 10 Most Harmful Weather Events to Population Health") +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5, face = "bold"))
# Plot economic impact
ggplot(economic_top10,
aes(x = reorder(EVTYPE, total_damage_billions),
y = total_damage_billions)) +
geom_bar(stat = "identity", fill = "blue", alpha = 0.8) +
geom_text(aes(label = paste0("$", round(total_damage_billions, 1), "B")),
hjust = -0.1, size = 3.5) +
coord_flip() +
scale_y_continuous(labels = dollar_format(suffix = "B"),
expand = expansion(mult = c(0, 0.1))) +
labs(x = "Event Type",
y = "Total Damage (Billions USD)",
title = "Top 10 Most Costly Weather Events") +
theme_minimal() +
theme(plot.title = element_text(hjust = 0.5, face = "bold"))
# Save processed data
save(health_impact, economic_impact, file = "weather_analysis_results.RData")
# Key findings
cat("## Key Findings\n\n")
## ## Key Findings
cat("1. **Health Impact**: Tornadoes cause the most harm with",
format(sum(health_top10$total_health_impact[1]), big.mark = ","),
"total casualties (fatalities + injuries).\n\n")
## 1. **Health Impact**: Tornadoes cause the most harm with 97,068 total casualties (fatalities + injuries).
cat("2. **Economic Impact**: Floods are the most costly weather events causing approximately $",
round(economic_top10$total_damage_billions[1], 1),
" billion in total damage.\n\n")
## 2. **Economic Impact**: Floods are the most costly weather events causing approximately $ 180 billion in total damage.
cat("3. **Pattern**: Hydrological events (floods) and meteorological events (tornadoes, hurricanes) dominate both health and economic impact categories.")
## 3. **Pattern**: Hydrological events (floods) and meteorological events (tornadoes, hurricanes) dominate both health and economic impact categories.