Reproducible Research Project 2
Synopsis
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.
This project involves exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database tracks characteristics of major storms and weather events in the United States, including when and where they occur, as well as estimates of any fatalities, injuries, and property damage.
The basic goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events.
The followong analysis investigates Fatalities to: - Health (injuries and fatalities) - Properties and Crops (economic consequences)
1. Across the United States, which types of events are most harmful with respect to population health?
Data Processing
#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)Exploring Columns
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"Extracting Necessary columns
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. :990.0005 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, unionTotal_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$FATALITIES),]
head(Total_injuries,5)Reshaping The data for plots
library(reshape)## Warning: package 'reshape' was built under R version 4.3.2##
## Attaching package: 'reshape'## The following object is masked from 'package:dplyr':
##
## renameNew_data<-as.data.frame(head(Total_injuries,5))
#Reshaping the dataset for plot
df<-melt(New_data, id.vars="EVTYPE")
colnames(df)## [1] "EVTYPE" "variable" "value"Results
# Create chart
ggplot(df,aes(x=reorder(EVTYPE,-value),y=value, fill=variable))+
geom_bar( stat = "identity",position="dodge")+ylab("Frequency Count")+ theme(plot.title = element_text(hjust = 0.5))+xlab("Event Type")+theme(axis.text.x = element_text(angle=45, hjust=1))+
ggtitle("Top 5 US Calamities") + theme(plot.title = element_text(hjust = 0.5))
- The bar chart clearly shows that tornadoes are the primary cause of
injuries and fatalities resulting from natural disasters in the US.
2. Which types of events have the greatest economic consequences in US?
Filtering DATA
unique(storm_event$PROPDMGEXP)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-" "1" "8"unique(storm_event$CROPDMGEXP)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"# Map property damage alphanumeric exponents to numeric values.
storm_event$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$CROPDMGEXP_numberPreparing Dataset for plotting
TotalCost<-storm_event %>% group_by(EVTYPE) %>% summarise(PropCost = sum(PropCost),
CropCost = sum(CropCost), total_cost = sum(PropCost) + sum(CropCost))
TotalCost<-TotalCost[order(-TotalCost$total_cost),]New_cost<-as.data.frame(head(TotalCost,5))
df_cost<-melt(New_cost, id.vars="EVTYPE")
colnames(df_cost)## [1] "EVTYPE" "variable" "value"Results
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))
-In the United States, floods cause the most financial damage from
natural disasters, with hurricanes or typhoons coming in a close
second.