Reproducible_Research_Assign2
Marjorie Taboada
2024-04-21
library(rlang)
library(stargazer)
library(texreg)
library(lubridate)
library(tidyverse)
library(writexl)Reproducible Research Assignment 2
Synopsis
This assignment uses U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database to examine the most damaging weather events and types of events. The questions answered are:
1. What types of weather events cause the most fatalities and injuries?
2. What were the most fatal and injurious single events in the dataset?
3. What types of events have caused the largest amounts of economic (property and crop) damage?
Data Processing
#Steps: #Explore #Clean #Manipulate #Describe and summarise #Visualise #Analyse
Load file
data <- read.csv("/Users/marjo/Desktop/RStudio/repdata_data_StormData.csv")
head(data)## 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 6names(data)## [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"Subset the data set to use only the columns that we will use in the analysis
storm <- data %>%
select(c("EVTYPE","FATALITIES","INJURIES","PROPDMG","PROPDMGEXP","CROPDMG","CROPDMGEXP")) %>%
rename_all(tolower)
str(storm)## 'data.frame': 902297 obs. of 7 variables:
## $ evtype : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ fatalities: num 0 0 0 0 0 0 0 0 1 0 ...
## $ injuries : num 15 0 2 2 2 6 1 0 14 0 ...
## $ propdmg : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ propdmgexp: chr "K" "K" "K" "K" ...
## $ cropdmg : num 0 0 0 0 0 0 0 0 0 0 ...
## $ cropdmgexp: chr "" "" "" "" ...Now our data set has 902,297 rows and 7 colums. This is a brief description of each variable:
#evtype : storm event type
#fatalities: amount of fatalities per event
#injuries : amount of injuries per event
#propdmg : property damage amount
#propdmgexp: property damage in exponents
#cropdmg : crop damage amount
#cropdmgexp: crop damage in exponents
Converting propdmgexp and cropdmgexp variables to characters:
storm$propdmgexp <- as.character(storm$propdmgexp)
storm$cropdmgexp <- as.character(storm$cropdmgexp)First Analysis: Sum of fatalities and injuries
first_analysis <-
storm %>% select(evtype, fatalities, injuries) %>%
group_by(evtype) %>%
summarize(fatalities = sum(fatalities), injuries = sum(injuries), .groups='drop') %>%
arrange(desc(fatalities), desc(injuries)) %>%
slice(1:10) %>%
gather(key = type, value = value, fatalities, injuries)Result: 1. Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Answer: Tornadoes have the highest impact on the population, causing a higher number of fatalities and injuries.
ggplot(data=first_analysis, aes(reorder(evtype, -value), value, fill=type)) +
geom_bar(position = "dodge", stat="identity", width=0.8) +
labs(x="Event Type", y="Count") +
theme_minimal() + # Clean and modern look
theme(axis.text.x = element_text(angle = 20, vjust=0.7, size=10, color="black"),
axis.text.y = element_text(size=10, color="black"),
plot.title = element_text(hjust = 0.5, size=14, color="black", face="bold"),
legend.position = "top",
legend.title = element_text(size=10, color="black"),
legend.text = element_text(size=10, color="black")) +
ggtitle("Total Number of Fatalities and Injuries") +
scale_fill_manual(values=c("steelblue", "seagreen")) # Custom color palette
Second Analysis: Type of events and economic consequences
#Function to calculate cost
cost <- function(x) {
if (x == "H")
1E-4
else if (x == "K")
1E-3
else if (x == "M")
1
else if (x == "B")
1E3
else
1-6
}
second_analysis <-
storm %>% select("evtype", "propdmg", "propdmgexp", "cropdmg", "cropdmgexp") %>%
mutate(prop_dmg = propdmg*sapply(propdmgexp, FUN = cost), crop_dmg = cropdmg*sapply(cropdmgexp, FUN = cost), .keep="unused") %>%
group_by(evtype) %>%
summarize(property = sum(prop_dmg), crop = sum(crop_dmg), .groups='drop') %>%
arrange(desc(property), desc(crop)) %>%
slice(1:10) %>%
gather(key = type, value = value, property, crop)Result: 2. Across the United States, which types of events have the greatest economic consequences?
Answer: Floods and hurricanes have the highest property and crop damage costs, resulting in higher economic consequences.
ggplot(data=second_analysis, aes(reorder(evtype, -value), value, fill=type)) +
geom_bar(position = "dodge", stat="identity", width=0.7) +
labs(x="Event Type", y="Count (millions)",
title="Total Cost of Property and Crop Damage") +
theme_minimal() + # Clean and modern look
theme(axis.text.x = element_text(angle=25, vjust=0.5, hjust=0.7, size=10, color="black"),
axis.text.y = element_text(size=10, color="black"),
plot.title = element_text(hjust=0.5, size=14, color="black", face="bold"),
legend.position = "top",
legend.title = element_text(size=10, color="black"),
legend.text = element_text(size=10, color="black")) +
scale_fill_manual(values=c("steelblue", "slategray")) # Custom color palette
Conclusion
#In light of the analysis, efforts should focus on enhancing safety and public health by investing in improved infrastructure and early warning systems to address tornado risks. Additionally, funding should be allocated to support innovation and the development of advanced systems and infrastructure for managing hurricanes and typhoons, with the aim of safeguarding properties and crops to minimize potential damage.