Project 2
2024-04-12
1. Synopsis
This project aims to analyze the NOAA Storm Database and explore the effects of storms and weather events on both population and economy.
This analysis explores which types of events are most harmful on: - Health (injuries and fatalities) - Property and crops (economic consequences)
2. Data Processing
2.1 Loading data
#install.packages("dplyr")
library(dplyr)
# Download dataset
url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
dataset <- "storm_data.csv"
file <- paste("./", dataset, ".bz2", sep="")
download.file(url, destfile = file, method = "curl")# Read dataset
df <- read.csv("./storm_data.csv.bz2")
head(df)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE EVTYPE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL TORNADO
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL TORNADO
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL TORNADO
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL TORNADO
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL TORNADO
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL TORNADO
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END COUNTYENDN
## 1 0 0 NA
## 2 0 0 NA
## 3 0 0 NA
## 4 0 0 NA
## 5 0 0 NA
## 6 0 0 NA
## END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES INJURIES PROPDMG
## 1 0 14.0 100 3 0 0 15 25.0
## 2 0 2.0 150 2 0 0 0 2.5
## 3 0 0.1 123 2 0 0 2 25.0
## 4 0 0.0 100 2 0 0 2 2.5
## 5 0 0.0 150 2 0 0 2 2.5
## 6 0 1.5 177 2 0 0 6 2.5
## PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES LATITUDE LONGITUDE
## 1 K 0 3040 8812
## 2 K 0 3042 8755
## 3 K 0 3340 8742
## 4 K 0 3458 8626
## 5 K 0 3412 8642
## 6 K 0 3450 8748
## LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3051 8806 1
## 2 0 0 2
## 3 0 0 3
## 4 0 0 4
## 5 0 0 5
## 6 0 0 62.2 Variables available
colnames(df)## [1] "STATE__" "BGN_DATE" "BGN_TIME" "TIME_ZONE" "COUNTY"
## [6] "COUNTYNAME" "STATE" "EVTYPE" "BGN_RANGE" "BGN_AZI"
## [11] "BGN_LOCATI" "END_DATE" "END_TIME" "COUNTY_END" "COUNTYENDN"
## [16] "END_RANGE" "END_AZI" "END_LOCATI" "LENGTH" "WIDTH"
## [21] "F" "MAG" "FATALITIES" "INJURIES" "PROPDMG"
## [26] "PROPDMGEXP" "CROPDMG" "CROPDMGEXP" "WFO" "STATEOFFIC"
## [31] "ZONENAMES" "LATITUDE" "LONGITUDE" "LATITUDE_E" "LONGITUDE_"
## [36] "REMARKS" "REFNUM"2.3 Filtering variables
Selecting only variables of interest. Additionally, we are filtering the rows with data available.
cols <- c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP",
"CROPDMG", "CROPDMGEXP")
df <- df %>%
select(cols) %>%
filter(EVTYPE != "?" & (INJURIES > 0 | FATALITIES > 0 | PROPDMG > 0 | CROPDMG > 0))## Warning: Using an external vector in selections was deprecated in tidyselect 1.1.0.
## ℹ Please use `all_of()` or `any_of()` instead.
## # Was:
## data %>% select(cols)
##
## # Now:
## data %>% select(all_of(cols))
##
## See <https://tidyselect.r-lib.org/reference/faq-external-vector.html>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.2.4 Converting numbers
Cleaning up the PROPDMGEXP and CROPDMGEXP columns to facilitate their use in calculating property and crop costs.
# Change all damage exponents to uppercase
cols <- c("PROPDMGEXP", "CROPDMGEXP")
df <- df %>%
mutate(across(all_of(cols), toupper))
# Map property damage alphanumeric exponents to numeric values
prop_dmg_key <- c("\"\"" = 10^0,
"-" = 10^0,
"+" = 10^0,
"0" = 10^0,
"1" = 10^1,
"2" = 10^2,
"3" = 10^3,
"4" = 10^4,
"5" = 10^5,
"6" = 10^6,
"7" = 10^7,
"8" = 10^8,
"9" = 10^9,
"H" = 10^2,
"K" = 10^3,
"M" = 10^6,
"B" = 10^9)
# Map crop damage alphanumeric exponents to numeric values
crop_dmg_key <- c("\"\"" = 10^0,
"?" = 10^0,
"0" = 10^0,
"K" = 10^3,
"M" = 10^6,
"B" = 10^9)
df <- df %>%
mutate(PROPDMGEXP = prop_dmg_key[as.character(PROPDMGEXP)]) %>%
mutate(PROPDMGEXP = ifelse(is.na(PROPDMGEXP), 10^0, PROPDMGEXP)) %>%
mutate(CROPDMGEXP = crop_dmg_key[as.character(CROPDMGEXP)]) %>%
mutate(CROPDMGEXP = ifelse(is.na(CROPDMGEXP), 10^0, CROPDMGEXP))2.5 Calculating economic costs
df <- df %>%
mutate(prop_cost = PROPDMG * PROPDMGEXP,
crop_cost = CROPDMG * CROPDMGEXP) %>%
select(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, prop_cost,
CROPDMG, CROPDMGEXP, crop_cost)2.6 Calculating total cost by event
total_cost <- df %>%
group_by(EVTYPE) %>%
summarise(prop_cost = sum(prop_cost),
crop_cost = sum(crop_cost),
total_cost = sum(prop_cost) + sum(crop_cost)) %>%
arrange(desc(total_cost)) %>%
slice_head(n = 10)
head(total_cost)## # A tibble: 6 × 4
## EVTYPE prop_cost crop_cost total_cost
## <chr> <dbl> <dbl> <dbl>
## 1 FLOOD 144657709807 5661968450 150319678257
## 2 HURRICANE/TYPHOON 69305840000 2607872800 71913712800
## 3 TORNADO 56947380676. 414953270 57362333946.
## 4 STORM SURGE 43323536000 5000 43323541000
## 5 HAIL 15735267513. 3025954473 18761221986.
## 6 FLASH FLOOD 16822673978. 1421317100 18243991078.2.7 Calculating total fatalities and injuries by event
total_injuries <- df %>%
group_by(EVTYPE) %>%
summarise(FATALITIES = sum(FATALITIES),
INJURIES = sum(INJURIES),
totals = sum(FATALITIES) + sum(INJURIES)) %>%
arrange(desc(FATALITIES)) %>%
slice_head(n = 10)
head(total_injuries)## # A tibble: 6 × 4
## EVTYPE FATALITIES INJURIES totals
## <chr> <dbl> <dbl> <dbl>
## 1 TORNADO 5633 91346 96979
## 2 EXCESSIVE HEAT 1903 6525 8428
## 3 FLASH FLOOD 978 1777 2755
## 4 HEAT 937 2100 3037
## 5 LIGHTNING 816 5230 6046
## 6 TSTM WIND 504 6957 74613. Results
3.1 Which types of events are most harmful to population health?
#install.packages('tidyr')
library(tidyr)
df_harmful <- total_injuries %>%
pivot_longer(cols = c("FATALITIES", "INJURIES"),
names_to = "type",
values_to = "count")
head(df_harmful)## # A tibble: 6 × 4
## EVTYPE totals type count
## <chr> <dbl> <chr> <dbl>
## 1 TORNADO 96979 FATALITIES 5633
## 2 TORNADO 96979 INJURIES 91346
## 3 EXCESSIVE HEAT 8428 FATALITIES 1903
## 4 EXCESSIVE HEAT 8428 INJURIES 6525
## 5 FLASH FLOOD 2755 FATALITIES 978
## 6 FLASH FLOOD 2755 INJURIES 1777library("ggplot2")
# Create chart
health_chart <- ggplot(df_harmful, aes(x=reorder(EVTYPE, -count), y=count))
# Plot data as bar chart
health_chart = health_chart + geom_bar(stat="identity", aes(fill=type), position="dodge")
# Format y-axis scale and set y-axis label
health_chart = health_chart + ylab("Frequency Count")
# Set x-axis label
health_chart = health_chart + xlab("Event Type")
# Rotate x-axis tick labels
health_chart = health_chart + theme(axis.text.x = element_text(angle=45, hjust=1))
# Set chart title and center it
health_chart = health_chart + ggtitle("Top 10 US Killers") + theme(plot.title = element_text(hjust = 0.5))
health_chart
3.2 Which types of events have the greatest economic consequences?
df_econ <- total_cost %>%
pivot_longer(cols = c("prop_cost", "crop_cost"),
names_to = "damage_type",
values_to = "cost")
head(df_econ)## # A tibble: 6 × 4
## EVTYPE total_cost damage_type cost
## <chr> <dbl> <chr> <dbl>
## 1 FLOOD 150319678257 prop_cost 144657709807
## 2 FLOOD 150319678257 crop_cost 5661968450
## 3 HURRICANE/TYPHOON 71913712800 prop_cost 69305840000
## 4 HURRICANE/TYPHOON 71913712800 crop_cost 2607872800
## 5 TORNADO 57362333946. prop_cost 56947380676.
## 6 TORNADO 57362333946. crop_cost 414953270# Create chart
econ_chart <- ggplot(df_econ, aes(x=reorder(EVTYPE, -cost), y=cost))
# Plot data as bar chart
econ_chart = econ_chart + geom_bar(stat="identity", aes(fill=damage_type), position="dodge")
# Format y-axis scale and set y-axis label
econ_chart = econ_chart + ylab("Cost")
# Set x-axis label
econ_chart = econ_chart + xlab("Event Type")
# Rotate x-axis tick labels
econ_chart = econ_chart + theme(axis.text.x = element_text(angle=45, hjust=1))
# Set chart title and center it
econ_chart = econ_chart + ggtitle("Top Events causing Economic Consequences") + theme(plot.title = element_text(hjust = 0.5))
econ_chart