library(R.utils)
## Warning: package 'R.utils' was built under R version 3.1.2
## Loading required package: R.oo
## Warning: package 'R.oo' was built under R version 3.1.2
## Loading required package: R.methodsS3
## Warning: package 'R.methodsS3' was built under R version 3.1.2
## R.methodsS3 v1.6.1 (2014-01-04) successfully loaded. See ?R.methodsS3 for help.
## R.oo v1.18.0 (2014-02-22) successfully loaded. See ?R.oo for help.
##
## Attaching package: 'R.oo'
##
## The following objects are masked from 'package:methods':
##
## getClasses, getMethods
##
## The following objects are masked from 'package:base':
##
## attach, detach, gc, load, save
##
## R.utils v1.34.0 (2014-10-07) successfully loaded. See ?R.utils for help.
##
## Attaching package: 'R.utils'
##
## The following object is masked from 'package:utils':
##
## timestamp
##
## The following objects are masked from 'package:base':
##
## cat, commandArgs, getOption, inherits, isOpen, parse, warnings
bunzip2("./repdata-data-StormData.csv.bz2", "./repdata-data-StormData.csv", remove = FALSE)
## Error in bunzip2.default("./repdata-data-StormData.csv.bz2", "./repdata-data-StormData.csv", : File already exists: ./repdata-data-StormData.csv
# load data into R
storm <- read.csv("./repdata-data-StormData.csv")
head(storm)
## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL
## EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 1 TORNADO 0 0
## 2 TORNADO 0 0
## 3 TORNADO 0 0
## 4 TORNADO 0 0
## 5 TORNADO 0 0
## 6 TORNADO 0 0
## COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES
## 1 NA 0 14.0 100 3 0 0
## 2 NA 0 2.0 150 2 0 0
## 3 NA 0 0.1 123 2 0 0
## 4 NA 0 0.0 100 2 0 0
## 5 NA 0 0.0 150 2 0 0
## 6 NA 0 1.5 177 2 0 0
## INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES
## 1 15 25.0 K 0
## 2 0 2.5 K 0
## 3 2 25.0 K 0
## 4 2 2.5 K 0
## 5 2 2.5 K 0
## 6 6 2.5 K 0
## LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3040 8812 3051 8806 1
## 2 3042 8755 0 0 2
## 3 3340 8742 0 0 3
## 4 3458 8626 0 0 4
## 5 3412 8642 0 0 5
## 6 3450 8748 0 0 6
# subset the data to health and economic impact analysis against weather
# event
mycol <- c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG",
"CROPDMGEXP")
mydata <- storm[mycol]
# exploring the property exponent
unique(mydata$PROPDMGEXP)
## [1] K M B m + 0 5 6 ? 4 2 3 h 7 H - 1 8
## Levels: - ? + 0 1 2 3 4 5 6 7 8 B h H K m M
# Sorting the property exponent data
mydata$PROPEXP[mydata$PROPDMGEXP == "K"] <- 1000
mydata$PROPEXP[mydata$PROPDMGEXP == "M"] <- 1e+06
mydata$PROPEXP[mydata$PROPDMGEXP == ""] <- 1
mydata$PROPEXP[mydata$PROPDMGEXP == "B"] <- 1e+09
mydata$PROPEXP[mydata$PROPDMGEXP == "m"] <- 1e+06
mydata$PROPEXP[mydata$PROPDMGEXP == "0"] <- 1
mydata$PROPEXP[mydata$PROPDMGEXP == "5"] <- 1e+05
mydata$PROPEXP[mydata$PROPDMGEXP == "6"] <- 1e+06
mydata$PROPEXP[mydata$PROPDMGEXP == "4"] <- 10000
mydata$PROPEXP[mydata$PROPDMGEXP == "2"] <- 100
mydata$PROPEXP[mydata$PROPDMGEXP == "3"] <- 1000
mydata$PROPEXP[mydata$PROPDMGEXP == "h"] <- 100
mydata$PROPEXP[mydata$PROPDMGEXP == "7"] <- 1e+07
mydata$PROPEXP[mydata$PROPDMGEXP == "H"] <- 100
mydata$PROPEXP[mydata$PROPDMGEXP == "1"] <- 10
mydata$PROPEXP[mydata$PROPDMGEXP == "8"] <- 1e+08
# give 0 to invalid exponent data, so they not count in
mydata$PROPEXP[mydata$PROPDMGEXP == "+"] <- 0
mydata$PROPEXP[mydata$PROPDMGEXP == "-"] <- 0
mydata$PROPEXP[mydata$PROPDMGEXP == "?"] <- 0
# compute the property damage value
mydata$PROPDMGVAL <- mydata$PROPDMG * mydata$PROPEXP
# exploring the crop exponent data
unique(mydata$CROPDMGEXP)
## [1] M K m B ? 0 k 2
## Levels: ? 0 2 B k K m M
# Sorting the property exponent data
mydata$CROPEXP[mydata$CROPDMGEXP == "M"] <- 1e+06
mydata$CROPEXP[mydata$CROPDMGEXP == "K"] <- 1000
mydata$CROPEXP[mydata$CROPDMGEXP == "m"] <- 1e+06
mydata$CROPEXP[mydata$CROPDMGEXP == "B"] <- 1e+09
mydata$CROPEXP[mydata$CROPDMGEXP == "0"] <- 1
mydata$CROPEXP[mydata$CROPDMGEXP == "k"] <- 1000
mydata$CROPEXP[mydata$CROPDMGEXP == "2"] <- 100
mydata$CROPEXP[mydata$CROPDMGEXP == ""] <- 1
# give 0 to invalid exponent data, so they not count in
mydata$CROPEXP[mydata$CROPDMGEXP == "?"] <- 0
# compute the crop damage value
mydata$CROPDMGVAL <- mydata$CROPDMG * mydata$CROPEXP
# aggregate the data by event
fatal <- aggregate(FATALITIES ~ EVTYPE, data = mydata, FUN = sum)
injury <- aggregate(INJURIES ~ EVTYPE, data = mydata, FUN = sum)
propdmg <- aggregate(PROPDMGVAL ~ EVTYPE, data = mydata, FUN = sum)
cropdmg <- aggregate(CROPDMGVAL ~ EVTYPE, data = mydata, FUN = sum)
# get top10 event with highest fatalities
fatal10 <- fatal[order(-fatal$FATALITIES), ][1:10, ]
# get top10 event with highest injuries
injury10 <- injury[order(-injury$INJURIES), ][1:10, ]
par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(fatal10$FATALITIES, las = 3, names.arg = fatal10$EVTYPE, main = "Weather Events With The Top 10 Highest Fatalities",
ylab = "number of fatalities", col = "green")
barplot(injury10$INJURIES, las = 3, names.arg = injury10$EVTYPE, main = "Weather Events With the Top 10 Highest Injuries",
ylab = "number of injuries", col = "green")
# get top 10 events with highest property damage
propdmg10 <- propdmg[order(-propdmg$PROPDMGVAL), ][1:10, ]
# get top 10 events with highest crop damage
cropdmg10 <- cropdmg[order(-cropdmg$CROPDMGVAL), ][1:10, ]
par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(propdmg10$PROPDMGVAL/(10^9), las = 3, names.arg = propdmg10$EVTYPE,
main = "Top 10 Events with Greatest Property Damages", ylab = "Cost of damages ($ billions)",
col = "green")
barplot(cropdmg10$CROPDMGVAL/(10^9), las = 3, names.arg = cropdmg10$EVTYPE,
main = "Top 10 Events With Greatest Crop Damages", ylab = "Cost of damages ($ billions)",
col = "green")
