StormData NOAA Reproducible Research
Synopsis
This is the week 4 Reproducible research project for Johns Hopkins Data Science Specialization.
This project asks you to do an analysis on the NOAA sotrm Database. This database tracks major storm and weather events in the United States. This database lets you know when and where they occur, fatalities, injuries, and property damages.
Questions that need to be answered
- 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?
Libraries for analysis
library(knitr)
library(R.utils)## Loading required package: R.oo## Loading required package: R.methodsS3## R.methodsS3 v1.8.1 (2020-08-26 16:20:06 UTC) successfully loaded. See ?R.methodsS3 for help.## R.oo v1.24.0 (2020-08-26 16:11:58 UTC) successfully loaded. See ?R.oo for help.##
## Attaching package: 'R.oo'## The following object is masked from 'package:R.methodsS3':
##
## throw## The following objects are masked from 'package:methods':
##
## getClasses, getMethods## The following objects are masked from 'package:base':
##
## attach, detach, load, save## R.utils v2.10.1 (2020-08-26 22:50:31 UTC) 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, nullfile, parse,
## warningslibrary(plyr)
library(lattice)Data Processing
urlData <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FMain_data.csv.bz2"temp <- tempfile()
##Performing the download
if(!file.exists("/stormData.csv.bz2")){
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2", destfile="./stormData.csv.bz2")
}
##Uncompressing the file
if(!file.exists("stormdata.csv"))
{
bunzip2("stormData.csv.bz2","stormdata.csv",remove=F)
}
# DP1.3 loading the data & reading the file
storm <- read.csv("stormdata.csv",header=TRUE,sep=",")
summary(storm)## STATE__ BGN_DATE BGN_TIME TIME_ZONE
## Min. : 1.0 Length:902297 Length:902297 Length:902297
## 1st Qu.:19.0 Class :character Class :character Class :character
## Median :30.0 Mode :character Mode :character Mode :character
## Mean :31.2
## 3rd Qu.:45.0
## Max. :95.0
##
## COUNTY COUNTYNAME STATE EVTYPE
## Min. : 0.0 Length:902297 Length:902297 Length:902297
## 1st Qu.: 31.0 Class :character Class :character Class :character
## Median : 75.0 Mode :character Mode :character Mode :character
## Mean :100.6
## 3rd Qu.:131.0
## Max. :873.0
##
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE
## Min. : 0.000 Length:902297 Length:902297 Length:902297
## 1st Qu.: 0.000 Class :character Class :character Class :character
## Median : 0.000 Mode :character Mode :character Mode :character
## Mean : 1.484
## 3rd Qu.: 1.000
## Max. :3749.000
##
## END_TIME COUNTY_END COUNTYENDN END_RANGE
## Length:902297 Min. :0 Mode:logical Min. : 0.0000
## Class :character 1st Qu.:0 NA's:902297 1st Qu.: 0.0000
## Mode :character Median :0 Median : 0.0000
## Mean :0 Mean : 0.9862
## 3rd Qu.:0 3rd Qu.: 0.0000
## Max. :0 Max. :925.0000
##
## END_AZI END_LOCATI LENGTH WIDTH
## Length:902297 Length:902297 Min. : 0.0000 Min. : 0.000
## Class :character Class :character 1st Qu.: 0.0000 1st Qu.: 0.000
## Mode :character Mode :character Median : 0.0000 Median : 0.000
## Mean : 0.2301 Mean : 7.503
## 3rd Qu.: 0.0000 3rd Qu.: 0.000
## Max. :2315.0000 Max. :4400.000
##
## F MAG FATALITIES INJURIES
## Min. :0.0 Min. : 0.0 Min. : 0.0000 Min. : 0.0000
## 1st Qu.:0.0 1st Qu.: 0.0 1st Qu.: 0.0000 1st Qu.: 0.0000
## Median :1.0 Median : 50.0 Median : 0.0000 Median : 0.0000
## Mean :0.9 Mean : 46.9 Mean : 0.0168 Mean : 0.1557
## 3rd Qu.:1.0 3rd Qu.: 75.0 3rd Qu.: 0.0000 3rd Qu.: 0.0000
## Max. :5.0 Max. :22000.0 Max. :583.0000 Max. :1700.0000
## NA's :843563
## PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## Min. : 0.00 Length:902297 Min. : 0.000 Length:902297
## 1st Qu.: 0.00 Class :character 1st Qu.: 0.000 Class :character
## Median : 0.00 Mode :character Median : 0.000 Mode :character
## Mean : 12.06 Mean : 1.527
## 3rd Qu.: 0.50 3rd Qu.: 0.000
## Max. :5000.00 Max. :990.000
##
## WFO STATEOFFIC ZONENAMES LATITUDE
## Length:902297 Length:902297 Length:902297 Min. : 0
## Class :character Class :character Class :character 1st Qu.:2802
## Mode :character Mode :character Mode :character Median :3540
## Mean :2875
## 3rd Qu.:4019
## Max. :9706
## NA's :47
## LONGITUDE LATITUDE_E LONGITUDE_ REMARKS
## Min. :-14451 Min. : 0 Min. :-14455 Length:902297
## 1st Qu.: 7247 1st Qu.: 0 1st Qu.: 0 Class :character
## Median : 8707 Median : 0 Median : 0 Mode :character
## Mean : 6940 Mean :1452 Mean : 3509
## 3rd Qu.: 9605 3rd Qu.:3549 3rd Qu.: 8735
## Max. : 17124 Max. :9706 Max. :106220
## NA's :40
## REFNUM
## Min. : 1
## 1st Qu.:225575
## Median :451149
## Mean :451149
## 3rd Qu.:676723
## Max. :902297
## Results
Question 1
variables<-c("EVTYPE","FATALITIES","INJURIES","PROPDMG", "PROPDMGEXP","CROPDMG","CROPDMGEXP")
strmdata<-storm[variables]Fatalities <- aggregate(FATALITIES ~ EVTYPE, data = strmdata, FUN = sum)
top10Fatalities <- Fatalities[order(-Fatalities$FATALITIES), ][1:10, ]
top10Fatalities## EVTYPE FATALITIES
## 834 TORNADO 5633
## 130 EXCESSIVE HEAT 1903
## 153 FLASH FLOOD 978
## 275 HEAT 937
## 464 LIGHTNING 816
## 856 TSTM WIND 504
## 170 FLOOD 470
## 585 RIP CURRENT 368
## 359 HIGH WIND 248
## 19 AVALANCHE 224Aggregate the top 10 injuries by the event type
Injuries <- aggregate(INJURIES ~ EVTYPE, data = strmdata, FUN = sum)
top10Injuries <- Injuries[order(-Injuries$INJURIES), ][1:10, ]
top10Injuries ## EVTYPE INJURIES
## 834 TORNADO 91346
## 856 TSTM WIND 6957
## 170 FLOOD 6789
## 130 EXCESSIVE HEAT 6525
## 464 LIGHTNING 5230
## 275 HEAT 2100
## 427 ICE STORM 1975
## 153 FLASH FLOOD 1777
## 760 THUNDERSTORM WIND 1488
## 244 HAIL 1361Question 1 Plot
par(mfrow=c(1,2),mar=c(10,3,3,2))
barplot(top10Fatalities$FATALITIES,names.arg=top10Fatalities$EVTYPE,las=2,col="red",ylab="fatalities",main="Top 10 fatalities")
barplot(top10Injuries$INJURIES,names.arg=top10Injuries$EVTYPE,las=2,col="sky blue",ylab="injuries",main="Top 10 Injuries")
Question 2
Assigning the values for the property exponent
strmdata$PROPEXP[strmdata$PROPDMGEXP == "K"] <- 1000
strmdata$PROPEXP[strmdata$PROPDMGEXP == "M"] <- 1e+06
strmdata$PROPEXP[strmdata$PROPDMGEXP == ""] <- 1
strmdata$PROPEXP[strmdata$PROPDMGEXP == "B"] <- 1e+09
strmdata$PROPEXP[strmdata$PROPDMGEXP == "m"] <- 1e+06
strmdata$PROPEXP[strmdata$PROPDMGEXP == "0"] <- 1
strmdata$PROPEXP[strmdata$PROPDMGEXP == "5"] <- 1e+05
strmdata$PROPEXP[strmdata$PROPDMGEXP == "6"] <- 1e+06
strmdata$PROPEXP[strmdata$PROPDMGEXP == "4"] <- 10000
strmdata$PROPEXP[strmdata$PROPDMGEXP == "2"] <- 100
strmdata$PROPEXP[strmdata$PROPDMGEXP == "3"] <- 1000
strmdata$PROPEXP[strmdata$PROPDMGEXP == "h"] <- 100
strmdata$PROPEXP[strmdata$PROPDMGEXP == "7"] <- 1e+07
strmdata$PROPEXP[strmdata$PROPDMGEXP == "H"] <- 100
strmdata$PROPEXP[strmdata$PROPDMGEXP == "1"] <- 10
strmdata$PROPEXP[strmdata$PROPDMGEXP == "8"] <- 1e+08
strmdata$PROPEXP[strmdata$PROPDMGEXP == "+"] <- 0
strmdata$PROPEXP[strmdata$PROPDMGEXP == "-"] <- 0
strmdata$PROPEXP[strmdata$PROPDMGEXP == "?"] <- 0
strmdata$PROPDMGVAL <- strmdata$PROPDMG * strmdata$PROPEXP
unique(strmdata$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"Assigning the values for the crop
strmdata$CROPEXP[strmdata$CROPDMGEXP == "M"] <- 1e+06
strmdata$CROPEXP[strmdata$CROPDMGEXP == "K"] <- 1000
strmdata$CROPEXP[strmdata$CROPDMGEXP == "m"] <- 1e+06
strmdata$CROPEXP[strmdata$CROPDMGEXP == "B"] <- 1e+09
strmdata$CROPEXP[strmdata$CROPDMGEXP == "0"] <- 1
strmdata$CROPEXP[strmdata$CROPDMGEXP == "k"] <- 1000
strmdata$CROPEXP[strmdata$CROPDMGEXP == "2"] <- 100
strmdata$CROPEXP[strmdata$CROPDMGEXP == ""] <- 1
# Assigning '0' to invalid exponent strmdata
strmdata$CROPEXP[strmdata$CROPDMGEXP == "?"] <- 0
# calculating the crop damage
strmdata$CROPDMGVAL <- strmdata$CROPDMG * strmdata$CROPEXP
###### Property damage summary
prop <- aggregate(PROPDMGVAL~EVTYPE,data=strmdata,FUN=sum,na.rm=TRUE)
prop <- prop[with(prop,order(-PROPDMGVAL)),]
prop <- head(prop,10)
print(prop)## EVTYPE PROPDMGVAL
## 170 FLOOD 144657709807
## 411 HURRICANE/TYPHOON 69305840000
## 834 TORNADO 56947380616
## 670 STORM SURGE 43323536000
## 153 FLASH FLOOD 16822673978
## 244 HAIL 15735267513
## 402 HURRICANE 11868319010
## 848 TROPICAL STORM 7703890550
## 972 WINTER STORM 6688497251
## 359 HIGH WIND 5270046260Crop damage summary
crop <- aggregate(CROPDMGVAL~EVTYPE,data=strmdata,FUN=sum,na.rm=TRUE)
crop <- crop[with(crop,order(-CROPDMGVAL)),]
crop <- head(crop,10)
print(crop)## EVTYPE CROPDMGVAL
## 95 DROUGHT 13972566000
## 170 FLOOD 5661968450
## 590 RIVER FLOOD 5029459000
## 427 ICE STORM 5022113500
## 244 HAIL 3025954473
## 402 HURRICANE 2741910000
## 411 HURRICANE/TYPHOON 2607872800
## 153 FLASH FLOOD 1421317100
## 140 EXTREME COLD 1292973000
## 212 FROST/FREEZE 1094086000Question 2 Plot
par(mfrow=c(1,2),mar=c(11,3,3,2))
barplot(prop$PROPDMGVAL/(10^9),names.arg=prop$EVTYPE,las=2,col="gold",ylab="Prop.damage(billions)",main="Top10 Prop.Damages")
barplot(crop$CROPDMGVAL/(10^9),names.arg=crop$EVTYPE,las=2,col="orange",ylab="Crop damage(billions)",main="Top10 Crop.Damages")