U.S. NOAA storm database Analysis
The basic goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events.
Synopsis
This report is divided into two main sections namely data processing and results. In the data processing section the url of the data set is downloaded and read into R. The data set is processed and a new variable added with the name total damages. In the results section, graphical presentations are produced to answer two basic questions. First it shows that the most harmful event with respect to population health (fatalities and injuries) across the US is Tornado. The second plot shows that the types of events with the greatest economic consequences across the US for crop and property are Hail and Tornado repectively.
1.Data Processing
1.1 Load packages
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, unionlibrary(ggplot2)
library(gridExtra)## Warning: package 'gridExtra' was built under R version 4.2.2##
## Attaching package: 'gridExtra'## The following object is masked from 'package:dplyr':
##
## combinelibrary(reshape2)## Warning: package 'reshape2' was built under R version 4.2.21.2 Load data file and process data file
url<- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
path<- setwd("C:/Users/user/Desktop/Cousera/5. Reproducible Research/Week 4/Project2")
download.file(url, "stormdata.csv", method = "curl" )
storm_data<- read.csv("stormdata.csv", header = TRUE, sep = ",")
dim(storm_data)## [1] 902297 37colnames(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"1.3 Select specific columns for data analysis
storm_data <- storm_data[ , c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "CROPDMG", "STATE", "BGN_DATE", "END_DATE")]1.4 Process data variables
storm_data$BGN_DATE <- as.POSIXct(storm_data$BGN_DATE, format="%m/%d/%Y")
storm_data$END_DATE <- as.POSIXct(storm_data$END_DATE, format="%m/%d/%Y")
storm_data$EVTYPE <- as.factor(storm_data$EVTYPE)
storm_data$STATE <- as.factor(storm_data$STATE)
summary(storm_data)## EVTYPE FATALITIES INJURIES
## HAIL :288661 Min. : 0.0000 Min. : 0.0000
## TSTM WIND :219940 1st Qu.: 0.0000 1st Qu.: 0.0000
## THUNDERSTORM WIND: 82563 Median : 0.0000 Median : 0.0000
## TORNADO : 60652 Mean : 0.0168 Mean : 0.1557
## FLASH FLOOD : 54277 3rd Qu.: 0.0000 3rd Qu.: 0.0000
## FLOOD : 25326 Max. :583.0000 Max. :1700.0000
## (Other) :170878
## PROPDMG CROPDMG STATE
## Min. : 0.00 Min. : 0.000 TX : 83728
## 1st Qu.: 0.00 1st Qu.: 0.000 KS : 53440
## Median : 0.00 Median : 0.000 OK : 46802
## Mean : 12.06 Mean : 1.527 MO : 35648
## 3rd Qu.: 0.50 3rd Qu.: 0.000 IA : 31069
## Max. :5000.00 Max. :990.000 NE : 30271
## (Other):621339
## BGN_DATE END_DATE
## Min. :1950-01-03 00:00:00.000 Min. :1986-04-10 00:00:00.00
## 1st Qu.:1995-04-20 00:00:00.000 1st Qu.:2000-09-01 00:00:00.00
## Median :2002-03-18 00:00:00.000 Median :2005-04-30 00:00:00.00
## Mean :1998-12-27 23:37:48.996 Mean :2004-09-26 04:11:27.33
## 3rd Qu.:2007-07-28 00:00:00.000 3rd Qu.:2008-08-10 00:00:00.00
## Max. :2011-11-30 00:00:00.000 Max. :2011-11-30 00:00:00.00
## NA's :2434111.5 Add new variable to dataset
storm_data$TOTALDMG <- storm_data$PROPDMG+storm_data$CROPDMG
str(storm_data)## 'data.frame': 902297 obs. of 9 variables:
## $ EVTYPE : Factor w/ 985 levels " HIGH SURF ADVISORY",..: 834 834 834 834 834 834 834 834 834 834 ...
## $ FATALITIES: num 0 0 0 0 0 0 0 0 1 0 ...
## $ INJURIES : num 15 0 2 2 2 6 1 0 14 0 ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ STATE : Factor w/ 72 levels "AK","AL","AM",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ BGN_DATE : POSIXct, format: "1950-04-18" "1950-04-18" ...
## $ END_DATE : POSIXct, format: NA NA ...
## $ TOTALDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...2. Results
2.1 fatalities
fatalities <- storm_data %>% group_by(EVTYPE) %>% summarise(totalFatalities = sum(FATALITIES)) %>% arrange(desc(totalFatalities)) %>% head(n=10)
View(fatalities)
plot1<-ggplot(fatalities, aes(x = reorder(EVTYPE, -totalFatalities), y = totalFatalities)) +
geom_bar(stat="identity", fill="red") +
ggtitle("Graph: Fatalities by type of catastrophe") +
xlab("") +
ylab("Fatalities") +
ylim(0,100000)+
theme(text=element_text(size=10),
axis.text.x = element_text(angle=90, hjust=1))2.2 Injuries
injuries <- storm_data %>% group_by(EVTYPE) %>% summarise(totalInjuries = sum(INJURIES)) %>% arrange(desc(totalInjuries)) %>% head(n=10)
View(injuries)
plot2<-ggplot(injuries, aes(x = reorder(EVTYPE, -totalInjuries), y = totalInjuries) ) +
geom_bar(stat="identity", fill="green") +
ggtitle("Graph: Injuries by type of catastrophe") +
xlab("") +
ylab("Injuries") +
ylim(0,100000)+
theme(text=element_text(size=10),
axis.text.x = element_text(angle=90, hjust=1))2.3 Set up multiple plots on a page
grid.arrange(plot1, plot2, ncol=2)
2.4 Economic impact of events
economic <- storm_data %>% select(EVTYPE, PROPDMG, CROPDMG, TOTALDMG) %>%
group_by(EVTYPE) %>%
summarise(property_damage = sum(PROPDMG)/1000000, crop_damage = sum(CROPDMG)/1000000, total_damage = sum(TOTALDMG)/1000000 ) %>%
arrange(desc(total_damage)) %>% head(n=10)2.5 Property damage
plot3<-ggplot(economic, aes(x = reorder(EVTYPE, -property_damage), y = property_damage) ) +
geom_bar(stat="identity", fill="green") +
ggtitle("Cost of Property Damage") +
xlab("Event type") +
ylab("Cost in millions") +
ylim(0,4)+
theme(text=element_text(size=10),
axis.text.x = element_text(angle=90, hjust=1))2.6 Crop damage
plot4<-ggplot(economic, aes(x = reorder(EVTYPE, -crop_damage), y = crop_damage) ) +
geom_bar(stat="identity", fill="red") +
ggtitle("Cost of Crop Damage") +
xlab("Event type") +
ylab("Cost in millions") +
ylim(0,4)+
theme(text=element_text(size=10),
axis.text.x = element_text(angle=90, hjust=1))2.7 Total Economic damage
plot5<-ggplot(economic, aes(x = reorder(EVTYPE, -total_damage), y = total_damage) ) +
geom_bar(stat="identity", fill="blue") +
ggtitle("Economic Impact of Events") +
xlab("Event type") +
ylab("Cost in millions") +
ylim(0,4)+
theme(text=element_text(size=10),
axis.text.x = element_text(angle=90, hjust=1))2.8 Set up multiple plots on a page
grid.arrange(plot3, plot4, plot5, ncol=3)