source.R

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 3.2.3

### Reading the csv file
storm.data <- read.csv("stormData.csv")



### Normalize all the data and selecting only the required columns
reduced.storm.data <- 
                storm.data[,c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG")]

reduced.storm.data$EVTYPE <- 
                gsub("^HEAT$", "EXCESSIVE HEAT", reduced.storm.data$EVTYPE)
reduced.storm.data$EVTYPE <- 
                gsub("^TSTM WIND$", "THUNDERSTORM WIND", reduced.storm.data$EVTYPE)
reduced.storm.data$EVTYPE <- 
                gsub("^THUNDERSTORM WIND$", "THUNDERSTORM WINDS", reduced.storm.data$EVTYPE)

### For FATALITIES we aggregate and find the top 10 among them.

agg.fatalities.data <-
                aggregate(
                                reduced.storm.data$FATALITIES, 
                                by=list(reduced.storm.data$EVTYPE), FUN=sum, na.rm=TRUE)
colnames(agg.fatalities.data) = c("event.type", "fatality.total")
fatalities.sorted <- 
                agg.fatalities.data[order(-agg.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)
###We repeat the same for INJURIES

agg.injuries.data <-
                aggregate(
                                reduced.storm.data$INJURIES, 
                                by=list(reduced.storm.data$EVTYPE), FUN=sum, na.rm=TRUE)
colnames(agg.injuries.data) = c("event.type", "injury.total")
injuries.sorted <- agg.injuries.data[order(-agg.injuries.data$injury.total),] 
top.injuries <- injuries.sorted[1:10,]
top.injuries$event.type <- 
                factor(
                                top.injuries$event.type, levels=top.injuries$event.type, 
                                ordered=TRUE)

### and also for property 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)

## Pictorial Representaion of the same

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))

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))

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))

## Tornado caused maximum damage