Reproducible Research: Project2
R Markdown
Date: 11-Nov-2018
Summary: Storms and other severe weather events can cause both public health and economic problems for communities and municipalities. Many severe events can result in fatalities, injuries, and property damage, and preventing such outcomes to the extent possible is a key concern.
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?
Code for reading in the dataset and/or processing the data
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2",destfile="C:/Users/sanjayx/Desktop/coursera/StormData.csv.bz2")
storms<-data.table::fread("C:/Users/sanjayx/Desktop/coursera/StormData.csv.bz2")
names(storms)## [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"dim(storms)## [1] 902297 37summary(storms)## 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
## Min. : 0.000 Length:902297 Length:902297
## 1st Qu.: 0.000 Class :character Class :character
## Median : 0.000 Mode :character Mode :character
## Mean : 1.484
## 3rd Qu.: 1.000
## Max. :3749.000
##
## END_DATE END_TIME COUNTY_END COUNTYENDN
## Length:902297 Length:902297 Min. :0 Mode:logical
## Class :character Class :character 1st Qu.:0 NA's:902297
## Mode :character Mode :character Median :0
## Mean :0
## 3rd Qu.:0
## Max. :0
##
## END_RANGE END_AZI END_LOCATI
## Min. : 0.0000 Length:902297 Length:902297
## 1st Qu.: 0.0000 Class :character Class :character
## Median : 0.0000 Mode :character Mode :character
## Mean : 0.9862
## 3rd Qu.: 0.0000
## Max. :925.0000
##
## LENGTH WIDTH F MAG
## Min. : 0.0000 Min. : 0.000 Min. :0.0 Min. : 0.0
## 1st Qu.: 0.0000 1st Qu.: 0.000 1st Qu.:0.0 1st Qu.: 0.0
## Median : 0.0000 Median : 0.000 Median :1.0 Median : 50.0
## Mean : 0.2301 Mean : 7.503 Mean :0.9 Mean : 46.9
## 3rd Qu.: 0.0000 3rd Qu.: 0.000 3rd Qu.:1.0 3rd Qu.: 75.0
## Max. :2315.0000 Max. :4400.000 Max. :5.0 Max. :22000.0
## NA's :843563
## FATALITIES INJURIES PROPDMG
## Min. : 0.0000 Min. : 0.0000 Min. : 0.00
## 1st Qu.: 0.0000 1st Qu.: 0.0000 1st Qu.: 0.00
## Median : 0.0000 Median : 0.0000 Median : 0.00
## Mean : 0.0168 Mean : 0.1557 Mean : 12.06
## 3rd Qu.: 0.0000 3rd Qu.: 0.0000 3rd Qu.: 0.50
## Max. :583.0000 Max. :1700.0000 Max. :5000.00
##
## PROPDMGEXP CROPDMG CROPDMGEXP
## Length:902297 Min. : 0.000 Length:902297
## Class :character 1st Qu.: 0.000 Class :character
## Mode :character Median : 0.000 Mode :character
## Mean : 1.527
## 3rd Qu.: 0.000
## 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
## save(storms, file="C:/Users/sanjayx/Desktop/coursera/storms.RData")1.Across the United States, which types of events (as indicated in the EVTYPEEVTYPE variable) are most harmful with respect to population health?
load(file="C:/Users/sanjayx/Desktop/coursera/storms.RData")
ok<-complete.cases(storms$EVTYPE,storms$FATALITIES)
sum(!ok) # how many are not "ok" ?## [1] 0fatality<-storms[,c("EVTYPE","FATALITIES")]
sum_fatal<-aggregate(fatality$FATALITIES,list(fatality$EVTYPE), FUN=sum,na.rm=TRUE, na.action=NULL)
sum_fatal_top_5<-head(sum_fatal[order(sum_fatal$x, decreasing=TRUE), ], 5)
barplot(sum_fatal_top_5$x,names.arg=sum_fatal_top_5$Group.1,main="Fatalities by event type",ylab ="Fatalies")
injury<-storms[,c("EVTYPE","INJURIES")]
sum_injury<-aggregate(injury$INJURIES,list(injury$EVTYPE), FUN=sum,na.rm=TRUE, na.action=NULL)
sum_injury_top_5<-head(sum_injury[order(sum_injury$x, decreasing=TRUE), ], 5)
barplot(sum_injury_top_5$x,names.arg=sum_injury_top_5$Group.1,main="Injuries by event type",ylab ="injury")
##Across the United States, which types of events have the greatest economic consequences?
unique(storms$PROPDMGEXP)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-"
## [18] "1" "8"library(plyr)
propexp<- mapvalues(storms$PROPDMGEXP, from = c("K", "M","", "B", "m", "+", "0", "5", "6", "?", "4", "2", "3", "h", "7", "H", "-", "1", "8"), to = c(10^3, 10^6, 1, 10^9, 10^6, 0,1,10^5, 10^6, 0, 10^4, 10^2, 10^3, 10^2, 10^7, 10^2, 0, 10, 10^8))
storms$PROPDMGEXP <- as.numeric(as.character(propexp))
storms$PROPDMGTOTAL <- (storms$PROPDMG * storms$PROPDMGEXP)
unique(storms$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"cropexp <- mapvalues(storms$CROPDMGEXP, from = c("","M", "K", "m", "B", "?", "0", "k","2"), to = c(1,10^6, 10^3, 10^6, 10^9, 0, 1, 10^3, 10^2))
storms$CROPDMGEXP <- as.numeric(as.character(cropexp))
storms$CROPDMGTOTAL <- (storms$CROPDMG * storms$CROPDMGEXP)
storms$TOTALDMG<-storms$PROPDMGTOTA+storms$CROPDMGTOTA
damage<-storms[,c("EVTYPE","TOTALDMG")]
sum_damage<-aggregate(damage$TOTALDMG,list(damage$EVTYPE), FUN=sum,na.rm=TRUE, na.action=NULL)
sum_damage_top_5<-head(sum_damage[order(sum_damage$x, decreasing=TRUE), ], 5)
barplot(sum_damage_top_5$x,names.arg=sum_damage_top_5$Group.1,main="Damage by event type",ylab ="Damage")