Reproducible Research Project 2
1. Synopsis
The basic goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events.
The following analysis investigates Fatalities to:
- Health (injuries and fatalities)
- Properties and Crops (economic consequences)
2. Across the United States, which types of events are most harmful with respect to population health?
2.1. Data Processing
First, Download and extract raw data.
#importing library for plot
library(ggplot2)
Url<-"https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
#Downloading the Data
download.file(Url,destfile = "storm_data.csv")
storm_data<-read.csv("storm_data.csv")
head(storm_data)2.2. Examining Column Names
colnames(storm_data)## [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"2.3. Data Subsetting
Extracting Relevant columns that contributes to the events.
storm_event<-storm_data[, c("BGN_DATE", "EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")]
summary(storm_event)## BGN_DATE EVTYPE FATALITIES INJURIES
## Length:902297 Length:902297 Min. : 0.0000 Min. : 0.0000
## Class :character Class :character 1st Qu.: 0.0000 1st Qu.: 0.0000
## Mode :character Mode :character Median : 0.0000 Median : 0.0000
## Mean : 0.0168 Mean : 0.1557
## 3rd Qu.: 0.0000 3rd Qu.: 0.0000
## Max. :583.0000 Max. :1700.0000
## 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. :990.0002.4. Events that contributes to most injuries and Fatalities
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# Calculating Total Fatalities and Injuries
Total_injuries<-storm_event %>% group_by(EVTYPE) %>% summarise(FATALITIES = sum(FATALITIES),
INJURIES = sum(INJURIES), totals = sum(FATALITIES) + sum(INJURIES))
Total_injuries<-Total_injuries[order(-Total_injuries$FATALITIES),]
head(Total_injuries,5)2.5. Melting/reshaping data so that it is easier to put in bar graph format
Getting the top 5 rows in descending order.
library(reshape)## Warning: package 'reshape' was built under R version 4.3.2##
## Attaching package: 'reshape'## The following object is masked from 'package:dplyr':
##
## renameNew_data<-as.data.frame(head(Total_injuries,5))
#Reshaping the dataset for plot
df<-melt(New_data, id.vars="EVTYPE")
colnames(df)## [1] "EVTYPE" "variable" "value"2.6. Results
# Create chart
ggplot(df,aes(x=reorder(EVTYPE,-value),y=value, fill=variable))+
geom_bar( stat = "identity",position="dodge")+ylab("Frequency Count")+ theme(plot.title = element_text(hjust = 0.5))+xlab("Event Type")+theme(axis.text.x = element_text(angle=45, hjust=1))+
ggtitle("Top 5 US Calamities") + theme(plot.title = element_text(hjust = 0.5))
3. Which types of events have the greatest economic consequences in US?
unique(storm_event$PROPDMGEXP)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-" "1" "8"unique(storm_event$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"3.1. Subset the dataset on the parameters of interest.
Converting Exponent Columns into Actual Values.
# Map property damage alphanumeric exponents to numeric values.
storm_event$PROPDMGEXP_number <- recode(storm_event$PROPDMGEXP,
" " = 10^0,
"-" = 10^0,
"+" = 10^0,
"0" = 10^0,
"1" = 10^1,
"2" = 10^2,
"3" = 10^3,
"4" = 10^4,
"5" = 10^5,
"6" = 10^6,
"7" = 10^7,
"8" = 10^8,
"9" = 10^9,
"H" = 10^2,
"K" = 10^3,
"M" = 10^6,
"B" = 10^9,
.default = 10^0)
# Map crop damage alphanumeric exponents to numeric values
storm_event$CROPDMGEXP_number <- recode(storm_event$CROPDMGEXP,
" " = 10^0,
"?" = 10^0,
"0" = 10^0,
"K" = 10^3,
"M" = 10^6,
"B" = 10^9,
.default = 10^0)
#Cost of Damaged Property and Crop
storm_event$PropCost<-storm_event$PROPDMG * storm_event$PROPDMGEXP_number
storm_event$CropCost<-storm_event$CROPDMG * storm_event$CROPDMGEXP_number3.2. Events that contributes to Population Health
Calculating total cost of health consequences.
#Calculating Total Property and Crop Cost
TotalCost<-storm_event %>% group_by(EVTYPE) %>% summarise(PropCost = sum(PropCost),
CropCost = sum(CropCost), total_cost = sum(PropCost) + sum(CropCost))
TotalCost<-TotalCost[order(-TotalCost$total_cost),]3.3. Melting data so that it is easier to put in bar graph format
New_cost<-as.data.frame(head(TotalCost,5))
df_cost<-melt(New_cost, id.vars="EVTYPE")
colnames(df_cost)## [1] "EVTYPE" "variable" "value"3.4. Results
# Create chart
ggplot(df_cost,aes(x=reorder(EVTYPE,-value),y=value, fill=variable))+
geom_bar( stat = "identity",position="dodge")+ylab("Frequency Count")+ theme(plot.title = element_text(hjust = 0.5))+xlab("Event Type")+theme(axis.text.x = element_text(angle=45, hjust=1)) + ggtitle("Top 5 US Storm Events causing Economic Consequences")+
theme(plot.title = element_text(hjust = 0.5))