Storm Analysis Coursera Project 2 for Reproducible Research

Analysis of Severe Weather Events Impact on Public Health and Economy in the United States

This project look at the NOAA Storm Database (1950 - 2011) to identify the types of severe weather events that are most harmful to population health and have the greatest economic consequences. The analysis includes data processing steps, results with visualizations, and a discussion of the findings.

Data Processing

First, load packages.

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Download file

url_data <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"

data_path <- file.path("data","StormData.csv.bz2")

if (!dir.exists("data")) {
     dir.create("data")   
} 

download.file(url_data, data_path)

Import data to R

# Readr package automatically unzip bz2

raw_data <- read_csv(data_path)

## Rows: 902297 Columns: 37
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (18): BGN_DATE, BGN_TIME, TIME_ZONE, COUNTYNAME, STATE, EVTYPE, BGN_AZI,...
## dbl (18): STATE__, COUNTY, BGN_RANGE, COUNTY_END, END_RANGE, LENGTH, WIDTH, ...
## lgl  (1): COUNTYENDN
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Transform and clean data

# Convert date columns

data <- raw_data |> 
        mutate(BGN_DATE = strptime(BGN_DATE, format = "%m/%d/%Y %H:%M:%S")) 
        
# Filter relevant columns
data <- data |> 
  select(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)

# Handle missing values
data <- na.omit(data)

# Creating a function to convert exponent symbols to numeric values

convert_exponent <- function(exp) {
  if (sum(exp %in% c("K", "k"))) {
    return(1e3)
  } else if (sum(exp %in% c("M", "m"))) {
    return(1e6)
  } else if (sum(exp %in% c("B", "b"))) {
    return(1e9)
  } else if (sum(exp %in% c("H", "h"))) {
    return(1e2)
  } else if (sum(exp %in% c("", "+", "-", "?", "0"))) {
    return(1)
  } else {
    return(as.numeric(exp))
  }
}

# Create relevant variables

data <- data |> 
        mutate(numPROPDMGEXP = convert_exponent(PROPDMGEXP),
               numCROPDMGEXP = convert_exponent(CROPDMGEXP),
               totalPROPDMGE = numPROPDMGEXP * PROPDMG,
               totalCROPDMGE = numCROPDMGEXP * CROPDMG,
               totalEconomicDmg = totalPROPDMGE + totalCROPDMGE)

Results

Most Harmful Events to Population Health (Fatalities)

# Aggregate data by event type
health_impact <- data  |> 
  group_by(EVTYPE)  |> 
  summarize(Total_Fatalities = sum(FATALITIES), Total_Injuries = sum(INJURIES))  |> 
  arrange(desc(Total_Fatalities))

# Plot the results
ggplot(health_impact[1:10, ], aes(x = reorder(EVTYPE, -Total_Fatalities), y = Total_Fatalities)) +
  geom_bar(stat = "identity") +
  labs(title = "Top 10 Most Harmful Events to Population Health (Fatalities)",
       x = "Event Type", y = "Total Fatalities") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Most Harmful Events to Population Health (Injuries)

# Plot the results

health_impact <- data  |> 
  group_by(EVTYPE)  |> 
  summarize(Total_Fatalities = sum(FATALITIES), Total_Injuries = sum(INJURIES))  |> 
  arrange(desc(Total_Injuries))

ggplot(health_impact[1:10, ], aes(x = reorder(EVTYPE, -Total_Injuries), y = Total_Injuries)) +
  geom_bar(stat = "identity") +
  labs(title = "Top 10 Most Harmful Events to Population Health (Injuries)",
       x = "Event Type", y = "Total Injuries") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Events with Greatest Economic Consequences

economic_impact <- data %>%
  group_by(EVTYPE) %>%
  summarize(Total_Economic_Damage = sum(totalEconomicDmg)) %>%
  arrange(desc(Total_Economic_Damage))

# Plot the results
ggplot(economic_impact[1:10, ], aes(x = reorder(EVTYPE, -Total_Economic_Damage), y = Total_Economic_Damage)) +
  geom_bar(stat = "identity") +
  labs(title = "Top 10 Events with Greatest Economic Consequences",
       x = "Event Type", y = "Total Economic Damage (in dollars)") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Conclusions

As we see, Tornado is the most harmful weather event. It is important that authorities help to solve this situation.