Data Preprocessing

storm.data = read.csv(bzfile(“StormData.csv.bz2”), header = TRUE)

We need only 4 Columns

reduced.storm.data <- storm.data[,c(“EVTYPE”,“FATALITIES”,“INJURIES”,“PROPDMG”)]

Normalization

reduced.storm.data\(EVTYPE<- gsub("^HEAT\)“,”EXCESSIVE HEAT“,reduced.storm.data$EVTYPE)

reduced.storm.data\(EVTYPE <- gsub("^TSTMWIND\)“,”THUNDERSTORM WIND“, reduced.storm.data$EVTYPE)

reduced.storm.data\(EVTYPE <- gsub("^THUNDERSTORM WIND\)“,”THUNDERSTORM WINDS“, reduced.storm.data$EVTYPE)

Aggregate data on fatalties and find which events are the top 10 causes of fatalities

age.fatalities.data <- aggregate(reduced.storm.data\(FATALITIES,by = list(reduced.storm.data\)EVTYPE), FUN = sum,na.rm = T)

colnames(age.fatalities.data) = c(“event.type”, “fatality.total”)

fatalities.sorted <- age.fatalities.data[order(-age.fatalities.data$fatality.total),]

top.fatalities <- fatalities.sorted[1:10,]

top.fatalities\(event.type <- factor( top.fatalities\)event.type, levels=top.fatalities$event.type, ordered=TRUE)

Now will do same for Injuries

age.injuries.data <- aggregate(reduced.storm.data\(INJURIES,by = list(reduced.storm.data\)EVTYPE), FUN = sum,na.rm = T)

colnames(age.injuries.data) = c(“event.type”, “injury.total”)

injuries.sorted <- age.injuries.data[order(-age.injuries.data$injury.total),]

top.injuries <- fatalities.sorted[1:10,]

top.injuries\(event.type <- factor( top.injuries\)event.type, levels=top.injuries$event.type, ordered=TRUE) ## Now will do same forPropert damage

agg.prop.dmg.data <- aggregate( reduced.storm.data\(PROPDMG, by=list(reduced.storm.data\)EVTYPE), FUN=sum, na.rm=TRUE) colnames(agg.prop.dmg.data) = c(“event.type”, “prop.dmg.total”) prop.dmg.sorted <- agg.prop.dmg.data[order(-agg.prop.dmg.data$prop.dmg.total),] top.prop.dmg <- prop.dmg.sorted[1:10,] top.prop.dmg\(event.type <- factor( top.prop.dmg\)event.type, levels=top.prop.dmg$event.type, ordered=TRUE)

Plot for fatalities

library(ggplot2) ggplot(data=top.fatalities, aes(x=event.type, y=fatality.total)) + geom_bar(stat=“identity”) + xlab(“Event type”) + ylab(“Total fatalities”) + ggtitle(“Fatalities By Event Type”) + theme(axis.text.x = element_text(angle = 45, hjust = 1)) ## Plot for Injuries

ggplot(data=top.injuries, aes(x=event.type, y=injury.total)) + geom_bar(stat=“identity”) + xlab(“Event type”) + ylab(“Total injuries”) + ggtitle(“Injuries By Event Type”) + theme(axis.text.x = element_text(angle = 45, hjust = 1))

Plot for propert Damage

ggplot(data=top.prop.dmg, aes(x=event.type, y=prop.dmg.total)) + geom_bar(stat=“identity”) + xlab(“Event type”) + ylab(“Total property damage”) + ggtitle(“Property Damage By Event Type”) + theme(axis.text.x = element_text(angle = 45, hjust = 1),echo = TRUE)