Reproducible Research - Project 2
Camille P.
Wednesday, October 22, 2014
Fatalities, Injuries & Financial Consequeces of Storms in the United States
Summary
In this report, we will analyze the impact of storm events in the United States as they effect rhe population physically and the economy. Most specifically, we will summarize which types of events have the most serious consequences on the these categories.
Data Processing
storm <- read.csv("repdata-data-StormData.csv.bz2")
str(storm)## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : Factor w/ 16335 levels "1/1/1966 0:00:00",..: 6523 6523 4242 11116 2224 2224 2260 383 3980 3980 ...
## $ BGN_TIME : Factor w/ 3608 levels "00:00:00 AM",..: 272 287 2705 1683 2584 3186 242 1683 3186 3186 ...
## $ TIME_ZONE : Factor w/ 22 levels "ADT","AKS","AST",..: 7 7 7 7 7 7 7 7 7 7 ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: Factor w/ 29601 levels "","5NM E OF MACKINAC BRIDGE TO PRESQUE ISLE LT MI",..: 13513 1873 4598 10592 4372 10094 1973 23873 24418 4598 ...
## $ STATE : Factor w/ 72 levels "AK","AL","AM",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ EVTYPE : Factor w/ 985 levels " HIGH SURF ADVISORY",..: 834 834 834 834 834 834 834 834 834 834 ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : Factor w/ 35 levels ""," N"," NW",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_LOCATI: Factor w/ 54429 levels "","- 1 N Albion",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_DATE : Factor w/ 6663 levels "","1/1/1993 0:00:00",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_TIME : Factor w/ 3647 levels ""," 0900CST",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : Factor w/ 24 levels "","E","ENE","ESE",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ END_LOCATI: Factor w/ 34506 levels "","- .5 NNW",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ 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: Factor w/ 19 levels "","-","?","+",..: 17 17 17 17 17 17 17 17 17 17 ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: Factor w/ 9 levels "","?","0","2",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ WFO : Factor w/ 542 levels ""," CI","$AC",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ STATEOFFIC: Factor w/ 250 levels "","ALABAMA, Central",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ ZONENAMES : Factor w/ 25112 levels ""," "| __truncated__,..: 1 1 1 1 1 1 1 1 1 1 ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : Factor w/ 436781 levels "","-2 at Deer Park\n",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ...#Convert the cost (PROPDMG) based on the next column value (PROPDMGEXP): "" "-" "?" "+" "0" "1" "2" "3" "4" "5" "6" "7" "8" "B" "h" "H" "K" "m" "M"
#converting to millions so those are not changed
storm$PROPDMG[storm$PROPDMGEXP == "B"] <- storm$PROPDMG[storm$PROPDMGEXP == "B"] * (10^3)
storm$PROPDMG[storm$PROPDMGEXP == "K"] <- storm$PROPDMG[storm$PROPDMGEXP == "K"] * (10^(-3))
storm$PROPDMG[storm$PROPDMGEXP == "h" | storm$PROPDMGEXP == "H"] <- storm$PROPDMG[storm$PROPDMGEXP == "h" | storm$PROPDMGEXP == "H"] * (10^(-4))
storm$PROPDMG[storm$PROPDMGEXP == "0"] <- storm$PROPDMG[storm$PROPDMGEXP == "0"] * (10^(-6))
storm$PROPDMG[storm$PROPDMGEXP == "1"] <- storm$PROPDMG[storm$PROPDMGEXP == "1"] * (10^(-5))
storm$PROPDMG[storm$PROPDMGEXP == "2"] <- storm$PROPDMG[storm$PROPDMGEXP == "2"] * (10^(-4))Summarizing Necessary Data
fatalitiesByType <- as.data.frame(sort(with(storm, tapply(FATALITIES, EVTYPE, sum, na.rm = T)), decreasing = T))
fatalitiesByType <- cbind(rownames(fatalitiesByType), fatalitiesByType)
rownames(fatalitiesByType) <- NULL
colnames(fatalitiesByType) <- c("Type", "Total")
injuriesByType <- as.data.frame(sort(with(storm, tapply(INJURIES, EVTYPE, sum, na.rm = T)), decreasing = T))
injuriesByType <- cbind(rownames(injuriesByType), injuriesByType)
rownames(injuriesByType) <- NULL
colnames(injuriesByType) = c("Type", "Total")
costByType <- as.data.frame(sort(with(storm, tapply(PROPDMG, EVTYPE, sum, na.rm = T)), decreasing = T))
costByType <- cbind(rownames(costByType), costByType)
rownames(costByType) <- NULL
colnames(costByType) <- c("Type", "Total.Costs")Top Ten Events - By Fatalty:
head(fatalitiesByType, 10)## Type Total
## 1 TORNADO 5633
## 2 EXCESSIVE HEAT 1903
## 3 FLASH FLOOD 978
## 4 HEAT 937
## 5 LIGHTNING 816
## 6 TSTM WIND 504
## 7 FLOOD 470
## 8 RIP CURRENT 368
## 9 HIGH WIND 248
## 10 AVALANCHE 224Top Ten Events - By Inury:
head(injuriesByType, 10)## Type Total
## 1 TORNADO 91346
## 2 TSTM WIND 6957
## 3 FLOOD 6789
## 4 EXCESSIVE HEAT 6525
## 5 LIGHTNING 5230
## 6 HEAT 2100
## 7 ICE STORM 1975
## 8 FLASH FLOOD 1777
## 9 THUNDERSTORM WIND 1488
## 10 HAIL 1361TOP Ten Events - By Cost:
head(costByType, 10)## Type Total.Costs
## 1 FLOOD 144665
## 2 HURRICANE/TYPHOON 69306
## 3 TORNADO 57102
## 4 STORM SURGE 43324
## 5 FLASH FLOOD 16436
## 6 HAIL 15819
## 7 HURRICANE 11868
## 8 TROPICAL STORM 7704
## 9 WINTER STORM 6688
## 10 HIGH WIND 5305Results
library(ggplot2)
top_fatalities <- head(fatalitiesByType, 10)
top_injuries <- head(injuriesByType, 10)
top_costs <- head(costByType, 10)
plot1 <- qplot(top_fatalities$Type, top_fatalities$Total, xlab = "Events", ylab = "Number of Fatalities", main = "Top 10 Weather Related Causes of Fatalities") + theme(axis.text.x = element_text(angle = 60, hjust = 1)) + geom_bar(stat = "identity", colour = "deepskyblue4", fill = "deepskyblue3")
plot2 <- qplot(top_injuries$Type, top_injuries$Total, xlab = "Events", ylab = "Number of Injuires", main = "Top 10 Weather Related Causes of Injuries") + theme(axis.text.x = element_text(angle = 60, hjust =1)) + geom_bar(stat = "identity", colour = "darkorange2", fill = "darkorange1")
plot3 <- qplot(top_costs$Type, top_costs$Total.Costs, xlab = "Events", ylab = "Costs in Millions (US Dollars)", main = "Top 10 Most Expensive Weather Events") + theme(axis.text.x = element_text(angle = 60, hjust = 1)) + geom_bar(stat = "identity", colour = "green4", fill = "green3")
plot1
plot2
plot3
