Coursera Reproducible Research Assignment 2
Victor Callejas Fuentes
1/28/2020
Exploring the NOAA Storm Database : Weather events which causes the most economic and health impact.
The main goal of this research is to answer the following questions: 1. Across the United States, which types of events are most harmful with respect to population health? 2. Across the United States, which types of events have the greatest economic consequences? ### Synopsis
Data processing
Required libraries
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, unionlibrary(ggplot2)Data Acquisition
# READ DATA FROM CSV
storm <- read.csv("repdata_data_StormData.csv")
#Print dimensions and variables
sprintf("Dimensions of storm: Observations %s, Variables %s",nrow(storm),ncol(storm))## [1] "Dimensions of storm: Observations 902297, Variables 37"names(storm)## [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"#CLEANING DATA
#Type of events
typeof(storm$EVTYPE)## [1] "integer"diffEVTYPE <- unique(storm$EVTYPE)
length(diffEVTYPE)## [1] 985The number of different type of events is greater than the documentation says so we need to make the following transformation:
event_types <- tolower(storm$EVTYPE)
event_types <- gsub("[[:blank:][:punct:]+]", " ", event_types)
length(unique(event_types))## [1] 874Now the number of different events is as the documentation says. So update the data.
storm$EVTYPE <- event_typesResults
As the number of different events is too big, we are only to consider the top 10. #### Question 1: Across the United States, which types of events are most harmful with respect to population health?
Fatalities <- aggregate(FATALITIES ~ EVTYPE, data=storm, sum)
Injuries <- aggregate(INJURIES ~ EVTYPE, data=storm, sum)
# Get Top 10
FatalitiesTop10 <- head(Fatalities[order(Fatalities$FATALITIES, decreasing = TRUE),],10)
InjuriesTop10 <- head(Injuries[order(Injuries$INJURIES, decreasing = TRUE),],10)
# Make plots
p1 <- ggplot(FatalitiesTop10,
aes(x=reorder(EVTYPE, FATALITIES), y=FATALITIES, fill=FATALITIES)) +
geom_bar(stat="identity") +
coord_flip() +
ylab("Total number of FATALITIES") +
xlab("Event type") +
theme(legend.position="none")
p2 <- ggplot(InjuriesTop10,
aes(x=reorder(EVTYPE, INJURIES), y=INJURIES, fill=INJURIES)) +
geom_bar(stat="identity") +
coord_flip() +
ylab("Total number of injuries") +
xlab("Event type") +
theme(legend.position="none")
#Print plots
print(p1)
print(p2)
Tornadoes cause most number of deaths and injuries among all event types by far.
Across the United States, which types of events have the greatest economic consequences?
The exponents in letter format must be converted to numeric and applied.
# Function to translate the exponent:
exp_transform <- function(e) {
# h -> hundred, k -> thousand, m -> million, b -> billion
if (e %in% c('h', 'H'))
return(2)
else if (e %in% c('k', 'K'))
return(3)
else if (e %in% c('m', 'M'))
return(6)
else if (e %in% c('b', 'B'))
return(9)
else if (!is.na(as.numeric(e))) # if a digit
return(as.numeric(e))
else if (e %in% c('', '-', '?', '+'))
return(1)
else {
stop("Invalid exponent value.")
}
}
prop_dmg_exp <- sapply(storm$PROPDMGEXP, FUN=exp_transform)
storm$PROPDMG_incl_exp <- storm$PROPDMG * (10 ** prop_dmg_exp)
crop_dmg_exp <- sapply(storm$CROPDMGEXP, FUN=exp_transform)
storm$CROPDMG_incl_exp <- storm$CROPDMG * (10 ** crop_dmg_exp)Aggregate data, get Top 10 and plot
# Aggregate data
PROPDMG_incl_exp_per_evt <- aggregate(PROPDMG_incl_exp ~ EVTYPE, data=storm, sum)
CROPDMG_incl_exp_per_evt <- aggregate(CROPDMG_incl_exp ~ EVTYPE, data=storm, sum)
# Get Top 10
PROPDMG_Top10 <- head(PROPDMG_incl_exp_per_evt[order(PROPDMG_incl_exp_per_evt$PROPDMG_incl_exp, decreasing = TRUE),],10)
PROPDMG_Top10## EVTYPE PROPDMG_incl_exp
## 138 flash flood 6.820237e+13
## 697 thunderstorm winds 2.086532e+13
## 741 tornado 1.078951e+12
## 209 hail 3.157558e+11
## 410 lightning 1.729433e+11
## 154 flood 1.446577e+11
## 366 hurricane typhoon 6.930584e+10
## 166 flooding 5.920826e+10
## 585 storm surge 4.332354e+10
## 270 heavy snow 1.793259e+10CROPDMG_Top10 <- head(CROPDMG_incl_exp_per_evt[order(CROPDMG_incl_exp_per_evt$CROPDMG_incl_exp, decreasing = TRUE),],10)
CROPDMG_Top10## EVTYPE CROPDMG_incl_exp
## 84 drought 13972566000
## 154 flood 5661968450
## 519 river flood 5029459000
## 382 ice storm 5022113500
## 209 hail 3025974480
## 357 hurricane 2741910000
## 366 hurricane typhoon 2607872800
## 138 flash flood 1421317100
## 125 extreme cold 1312973000
## 185 frost freeze 1094186000# Make plots
p3 <- ggplot(data=PROPDMG_Top10,
aes(x=reorder(EVTYPE, PROPDMG_incl_exp), y=PROPDMG_incl_exp, fill=PROPDMG_incl_exp)) +
geom_bar(stat="identity") +
coord_flip() +
ylab("Total number of property damage") +
xlab("Event type") +
theme(legend.position="none")
p4 <- ggplot(data=CROPDMG_Top10,
aes(x=reorder(EVTYPE, CROPDMG_incl_exp), y=CROPDMG_incl_exp, fill=CROPDMG_incl_exp)) +
geom_bar(stat="identity") +
coord_flip() +
ylab("Total number of crop damage") +
xlab("Event type") +
theme(legend.position="none")
#Print plots
print(p3)
print(p4)
Flash floods and thunderstorm winds cost the largest property damages. The most severe weather event in terms of crop damage is drought.