US Storm Damage Data Analysis: 1996-2011
RMemmel
11/09/2020
Synopsis
This report examined NOAA data for extreme weather events in the US. Statistical data analysis (documented below) answered two questions about severe weather events:
- Which types of events are most harmful with respect to population health?
- Excessive heat and tornadoes are the deadliest weather events to occur in the US over the time period 1996 to 2011.
- During the same period, tornadoes cause the most injuries by far.
- Excessive heat and tornadoes are the deadliest weather events to occur in the US over the time period 1996 to 2011.
- Which events have the greatest economic consequences?
- In economic terms, Wind related events and ice storms caused the greatest impact in the US during the time period 1996 to 2011.
- In economic terms, Wind related events and ice storms caused the greatest impact in the US during the time period 1996 to 2011.
Data Processing
The NOAA data [47Mb] for this project is in a comma-separated-value file and can bedownload the file from here: https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2
Documentation (variables, etc) for the database is available here: https://d396qusza40orc.cloudfront.net/repdata%2Fpeer2_doc%2Fpd01016005curr.pdf
National Climatic Data Center Storm Events FAQ:
https://d396qusza40orc.cloudfront.net/repdata%2Fpeer2_doc%2FNCDC%20Storm%20Events-FAQ%20Page.pdf
Events in the database start in the year 1950 and end in November 2011. In the earlier years of the database there are generally fewer events recorded, most likely due to a lack of good records. More recent years should be considered more complete. Additionally, the data documentation reveals that the current damage categories were introduced in 1995.
Consequently, the data set used for this project will range from 1996 to 2011
- Load the libraries
library(ggplot2)
library(knitr)
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 library("gridExtra") ##
## Attaching package: 'gridExtra'## The following object is masked from 'package:dplyr':
##
## combine- Load the raw CSV file containing the data
myData<-read.csv("repdata_data_StormData.csv") # copy of data- Process/transform the data (if necessary) into a format suitable for your analysis
str(myData) # to understand what data looks like## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : chr "4/18/1950 0:00:00" "4/18/1950 0:00:00" "2/20/1951 0:00:00" "6/8/1951 0:00:00" ...
## $ BGN_TIME : chr "0130" "0145" "1600" "0900" ...
## $ TIME_ZONE : chr "CST" "CST" "CST" "CST" ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: chr "MOBILE" "BALDWIN" "FAYETTE" "MADISON" ...
## $ STATE : chr "AL" "AL" "AL" "AL" ...
## $ EVTYPE : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : chr "" "" "" "" ...
## $ BGN_LOCATI: chr "" "" "" "" ...
## $ END_DATE : chr "" "" "" "" ...
## $ END_TIME : chr "" "" "" "" ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : chr "" "" "" "" ...
## $ END_LOCATI: chr "" "" "" "" ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ 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 ...
## $ PROPDMGEXP: chr "K" "K" "K" "K" ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: chr "" "" "" "" ...
## $ WFO : chr "" "" "" "" ...
## $ STATEOFFIC: chr "" "" "" "" ...
## $ ZONENAMES : chr "" "" "" "" ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : chr "" "" "" "" ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ... head(myData)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE EVTYPE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL TORNADO
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL TORNADO
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL TORNADO
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL TORNADO
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL TORNADO
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL TORNADO
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END COUNTYENDN
## 1 0 0 NA
## 2 0 0 NA
## 3 0 0 NA
## 4 0 0 NA
## 5 0 0 NA
## 6 0 0 NA
## END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES INJURIES PROPDMG
## 1 0 14.0 100 3 0 0 15 25.0
## 2 0 2.0 150 2 0 0 0 2.5
## 3 0 0.1 123 2 0 0 2 25.0
## 4 0 0.0 100 2 0 0 2 2.5
## 5 0 0.0 150 2 0 0 2 2.5
## 6 0 1.5 177 2 0 0 6 2.5
## PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES LATITUDE LONGITUDE
## 1 K 0 3040 8812
## 2 K 0 3042 8755
## 3 K 0 3340 8742
## 4 K 0 3458 8626
## 5 K 0 3412 8642
## 6 K 0 3450 8748
## LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3051 8806 1
## 2 0 0 2
## 3 0 0 3
## 4 0 0 4
## 5 0 0 5
## 6 0 0 6- Date in BGN_DATE is stored as char, convert to Date
myData$BGN_DATE <- as.Date(myData$BGN_DATE, "%m/%d/%Y") - Filter out dates prior to 1996, since earlier EVENT data is incomplete. 902297 to 653530 obs.
myData2<-myData[myData$BGN_DATE > "1995/12/31",]- Event type has mixed upper and lower case. Change to all upper.
myData2$EVTYPE<-toupper(myData2$EVTYPE)- Breakdown data into subset to include population health and covert to factors
health <- subset(myData2, select = c(EVTYPE,FATALITIES,INJURIES ))
health$EVTYPE<-as.factor(health$EVTYPE)
# aggregate teh data by EVENT type
agg_health<-aggregate(cbind(health$FATALITIES, health$INJURIES),by=list(Category=health$EVTYPE), FUN=sum)
# sort the table so we get top 10 deadliest
deaths<-agg_health[order(-agg_health$V1),]
deathsTop <- deaths[1:10,]
# sort the table so we get top 10 most injuries
injury<-agg_health[order(-agg_health$V2),]
injuryTop <- injury[1:10,] - Breakdown data into subset to include only economic data and covert to numbers
economic <- subset(myData2, select = c(EVTYPE,PROPDMG,PROPDMGEXP, CROPDMG, CROPDMGEXP))
# convert alpha to uppercase
economic$PROPDMGEXP <-toupper(economic$PROPDMGEXP)
economic$CROPDMGEXP <-toupper(economic$CROPDMGEXP)
# convert letters to numbers so we can calc
economic$c_multi[economic$CROPDMGEXP=="K"]<-1000
economic$c_multi[economic$CROPDMGEXP=="M"]<-1000000
economic$c_multi[economic$CROPDMGEXP=="G"]<-1000000000
economic$c_multi[economic$CROPDMGEXP==""] <-0
# convert letters to numbers so we can calc
economic$p_multi[economic$PROPDMGEXP=="K"]<-1000
economic$p_multi[economic$PROPDMGEXP=="M"]<-1000000
economic$p_multi[economic$PROPDMGEXP=="G"]<-1000000000
economic$p_multi[economic$PROPDMGEXP==""] <-0- Calculate the damage
economic$cropCost<-economic$CROPDMG * economic$c_multi
economic$propCost<-economic$PROPDMG * economic$p_multi
# total damage
economic$total <- economic$cropCost + economic$propCost10 Aggregate the results
# aggregate the data by EVENT type
agg_economic<-aggregate(cbind(economic$total),by=list(Category=economic$EVTYPE), FUN=sum)
# sort the table so we get top 10 deadliest
sort_econ<-agg_economic[order(-agg_economic$V1),]
econTop <- sort_econ[1:10,]
Results
- Across the United States, these are the 10 deadliest weather events:
ggplot(deathsTop,aes(x= reorder(Category,+V1),V1)) +
geom_bar(stat = "identity",fill="red",alpha=1, colour="black",) + coord_flip() +
geom_text(aes(label=round(V1, 1)), vjust= 0.5, hjust = 1.1,
color="black", size=3) +
labs(x="Weather Event") + labs(y="Deaths") +
labs(title=paste("Top 10 Weather Events by Fatalities", "1996-2011", sep="\n"))+
theme(axis.text.x = element_text(angle = 90, hjust = 1))
- Across the United States, these 10 weather events cause the most injuries:
ggplot(injuryTop,aes(x= reorder(Category,+V2),V2)) +
geom_bar(stat = "identity",fill="blue",alpha=1, colour="black",) +
geom_text(aes(label=round(V2, 1)), vjust= 0.5, hjust = 1.1,
color="white", size=3) +
coord_flip() +
labs(x="Weather Event") + labs(y="Total Injuries") +
labs(title=paste("Top 10 Weather Events by Injuries", "1996-2011", sep="\n"))+
theme(axis.text.x = element_text(angle = 90, hjust = 1))
- Across the United States, these 10 weather event types had the greatest economic consequences from 1996 to 2011:
# change units to billions so graph is clearer
econTop$mega <- econTop$V1/1000000000
# Plot the economic impact findings
ggplot(econTop,aes(x= reorder(Category,+mega),mega)) +
geom_bar(stat = "identity",fill="lightgreen",alpha=1, colour="darkgreen",) +
geom_text(aes(label=round(mega, 2)), vjust= 0.5, hjust = 1.2,
color="darkgreen", size=3) +
coord_flip() +
labs(x="Weather Event") + labs(y="Total Damage (billions of dollars)") +
labs(title=paste("Top 10 Weather Events by Economic Impact", "1996-2011", sep="\n")) +
theme(axis.text.x = element_text(angle = 90, hjust = 1),
plot.title = element_text(hjust = 0.5))
Conclusions
Excessive heat and tornados are the deadliest weather events to occur in the US over the time period 1996 to 2011. During the same period, tornados cause the most injuries by far. In economic terms, Wind related events and ice storms caused the greatest impact.
Thanks for reviewing.