repo-res2
Michael Pawlus
Friday, January 23, 2015
Analysis of Damage to Humans and Property by Weather
Questions:
Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Across the United States, which types of events have the greatest economic consequences?
SYNOPSIS
Tornadoes cause the most damage to property and humans
Hail causes the most damage to crops
DATA PROCESSING
##load the data after downloading from here: https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2
storm <- read.csv("repdata-data-StormData.csv")evaluate the format of the data
##look at overall structure
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/ 436774 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 ...##also factors in exponent groups
unique(storm$PROPDMGEXP)## [1] K M B m + 0 5 6 ? 4 2 3 h 7 H - 1 8
## Levels: - ? + 0 1 2 3 4 5 6 7 8 B h H K m Munique(storm$CROPDMGEXP)## [1] M K m B ? 0 k 2
## Levels: ? 0 2 B k K m MTransform the dollar values to complete numbers be replacing letters with corresponding string of zeroes
storm$PROPDMGEXP <- tolower(storm$PROPDMGEXP)
storm$CROPDMGEXP <- tolower(storm$CROPDMGEXP)
zeroes <- function(ex){
ex<-as.character(ex)
if (ex=="k"){
1000
}else if(ex=="m"){
1000000
}else if (ex=="b"){
1000000000
}else{
1
}
}
storm$PROPDMG<-storm$PROPDMG * zeroes(storm$PROPDMGEXP)## Warning in if (ex == "k") {: the condition has length > 1 and only the
## first element will be usedstorm$CROPDMG<-storm$CROPDMG * zeroes(storm$CROPDMGEXP)## Warning in if (ex == "k") {: the condition has length > 1 and only the
## first element will be used## Warning in if (ex == "m") {: the condition has length > 1 and only the
## first element will be used## Warning in if (ex == "b") {: the condition has length > 1 and only the
## first element will be usedRESULTS
Plot the weather most damaging to Property
pDmgByEvn <- aggregate(PROPDMG ~ EVTYPE, storm, sum)
pDmgByEvn <- pDmgByEvn[order(-pDmgByEvn$PROPDMG),]
pDmgByEvn <- pDmgByEvn[1:5,]
barplot(pDmgByEvn$PROPDMG, names.arg=pDmgByEvn$EVTYPE, cex.names =0.5, main = "Top 5: Property Damage")
Plot the weather most damaging to Crops
cDmgByEvn <- aggregate(CROPDMG ~ EVTYPE, storm, sum)
cDmgByEvn <- cDmgByEvn[order(-cDmgByEvn$CROPDMG),]
cDmgByEvn <- cDmgByEvn[1:5,]
barplot(cDmgByEvn$CROPDMG, names.arg=cDmgByEvn$EVTYPE, cex.names =0.5, main = "Top 5: Crop Damage")
Plot the weather most damaging to Humans
fatByEvn <- aggregate(FATALITIES ~ EVTYPE, storm, sum)
fatByEvn <- fatByEvn[order(-fatByEvn$FATALITIES),]
fatByEvn <- fatByEvn[1:5,]
barplot(fatByEvn$FATALITIES, names.arg=fatByEvn$FATALITIES, cex.names =0.5, main = "Top 5: Fatalities")