U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database is used to study impact of weather events on health and economy of the country.

The data for this assignment come in the form of a comma-separated-value file compressed via the bzip2 algorithm to reduce its size. You can download the file from the course web site:

download.file('https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2','storm.csv.bz2',method = "auto", quiet=FALSE)

1. Load the data

2. Process/transform the data (if necessary) into a format suitable for your analysis

my_data <- read.csv("storm.csv.bz2")

Health variables:

• FATALITIES
• INJURIES

Economic variables:

• PROPDMG
• PROPDMGEXP
• CROPDMG
• CROPDMGEXP

Events - target variable:

• EVTYPE

vars <- c( "EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")
data <- my_data[, vars]

Checking for NA values

sum(is.na(data$FATALITIES))
sum(is.na(data$INJURIES))
sum(is.na(data$PROPDMG))
sum(is.na(data$CROPDMG))
sum(is.na(data$PROPDMGEXP))
sum(is.na(data$CROPDMGEXP))

Divide the hold data set into the groups

• Hail
• Heat
• Flood
• Wind
• Storm
• Snow
• Tornado
• Winter
• Rain

data$EVENT <- "OTHER"
data$EVENT[grep("HAIL", data$EVTYPE, ignore.case = TRUE)] <- "HAIL"
data$EVENT[grep("HEAT", data$EVTYPE, ignore.case = TRUE)] <- "HEAT"
data$EVENT[grep("FLOOD", data$EVTYPE, ignore.case = TRUE)] <- "FLOOD"
data$EVENT[grep("WIND", data$EVTYPE, ignore.case = TRUE)] <- "WIND"
data$EVENT[grep("STORM", data$EVTYPE, ignore.case = TRUE)] <- "STORM"
data$EVENT[grep("SNOW", data$EVTYPE, ignore.case = TRUE)] <- "SNOW"
data$EVENT[grep("TORNADO", data$EVTYPE, ignore.case = TRUE)] <- "TORNADO"
data$EVENT[grep("WINTER", data$EVTYPE, ignore.case = TRUE)] <- "WINTER"
data$EVENT[grep("RAIN", data$EVTYPE, ignore.case = TRUE)] <- "RAIN"
data$PROPDMGEXP <- as.character(data$PROPDMGEXP)

If any NA replace it with 0

data$PROPDMGEXP[is.na(data$PROPDMGEXP)] <- 0

data$PROPDMGEXP[!grepl("K|M|B", data$PROPDMGEXP, ignore.case = TRUE)] <- 0

Convert character to numeric for analysis

data$PROPDMGEXP[grep("K", data$PROPDMGEXP, ignore.case = TRUE)] <- "3"
data$PROPDMGEXP[grep("M", data$PROPDMGEXP, ignore.case = TRUE)] <- "6"
data$PROPDMGEXP[grep("B", data$PROPDMGEXP, ignore.case = TRUE)] <- "9"
data$PROPDMGEXP <- as.numeric(as.character(data$PROPDMGEXP))
data$property.damage <- data$PROPDMG * 10^data$PROPDMGEXP

Same preprocessing of data (CROPDMGEXP)

data$CROPDMGEXP <- as.character(data$CROPDMGEXP)
data$CROPDMGEXP[is.na(data$CROPDMGEXP)] <- 0
data$CROPDMGEXP[!grepl("K|M|B", data$CROPDMGEXP, ignore.case = TRUE)] <- 0
data$CROPDMGEXP[grep("K", data$CROPDMGEXP, ignore.case = TRUE)] <- "3"
data$CROPDMGEXP[grep("M", data$CROPDMGEXP, ignore.case = TRUE)] <- "6"
data$CROPDMGEXP[grep("B", data$CROPDMGEXP, ignore.case = TRUE)] <- "9"
data$CROPDMGEXP <- as.numeric(as.character(data$CROPDMGEXP))
data$crop.damage <- data$CROPDMG * 10^data$CROPDMGEXP

Plot top 10 reason for Death and Injury

Death <- aggregate(data$FATALITIES, by = list(data$EVENT), FUN = sum)
colnames(Death) <- c("EVENT", "Death")
Death <- Death[order(Death$Death, decreasing = TRUE),][1:10,]

INJURIES <- aggregate(data$INJURIES, by = list(data$EVENT), FUN = sum)
colnames(INJURIES) <- c("EVENT", "INJURIES")
INJURIES <- INJURIES[order(INJURIES$INJURIES, decreasing = TRUE),][1:10,]

Two types of damage property and crop which would be plotted

Property <- aggregate(data$property.damage, by = list(data$EVENT), FUN = sum)
colnames(Property) <- c("EVENT", "Property")
Property <- Property[order(Property$Property, decreasing = TRUE),][1:10,]

C <- aggregate(data$crop.damage, by = list(data$EVTYPE), FUN = sum)
colnames(C) <- c("EVENT", "Crop")
C <- C[order(C$Crop, decreasing = TRUE),][1:10,]