Reproducible Research - Course Project2

Exploration of the NOAA Storm Database: In the past 60 years tornadoes are the most harmful events in United States and floods have the greatest economic consequences

Synopsis

The basic goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events. The data analysis must address the following questions:

1.Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

2.Across the United States, which types of events have the greatest economic consequences?

The results show that in the past 60 years tornados are most harmful with respect to population health and floods have the greatest economic consequences.

Data Processing

Loading libraries

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(plyr)

## Warning: package 'plyr' was built under R version 3.3.2

## -------------------------------------------------------------------------

## You have loaded plyr after dplyr - this is likely to cause problems.
## If you need functions from both plyr and dplyr, please load plyr first, then dplyr:
## library(plyr); library(dplyr)

## -------------------------------------------------------------------------

## 
## Attaching package: 'plyr'

## The following objects are masked from 'package:dplyr':
## 
##     arrange, count, desc, failwith, id, mutate, rename, summarise,
##     summarize

library(knitr)

## Warning: package 'knitr' was built under R version 3.3.2

library(ggplot2)

## Warning: package 'ggplot2' was built under R version 3.3.2

library(grid)
library(car)

## Warning: package 'car' was built under R version 3.3.2

## 
## Attaching package: 'car'

## The following object is masked from 'package:dplyr':
## 
##     recode

Downloading Data

Downloading data from the website:

fileUrl <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"

fileZip <- "repdata-data-StormData.csv.bs2"

download.file(fileUrl, fileZip, mode = "wb")

data <- read.csv("repdata-data-StormData.csv.bs2", header = TRUE, sep=",")

tidydata <- data[,c('EVTYPE','FATALITIES','INJURIES', 'PROPDMG', 'PROPDMGEXP', 'CROPDMG', 'CROPDMGEXP')]

Results

1.Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

First we order the number of casualties descending and then the six most harmful types of events are shown:

casualties <- with(data, aggregate(INJURIES + FATALITIES ~ EVTYPE, data=data, FUN = "sum"))

names(casualties)[2] <- "Totalcasualties"


# Order the number of casualties descending
ordered_casualties <- casualties[order(-casualties$Totalcasualties),]

# Just see top6 using head()
Top6 <- head(ordered_casualties)

barplot(Top6$Totalcasualties, main = "Which event caused the most harmful with respect to population health", ylab = "Total number of casualties", names.arg=Top6$EVTYPE, cex.names=0.6)

The most harmful type of events are tornados.

The following table shows the most harmful events and numbers of casualties:

Top6

##             EVTYPE Totalcasualties
## 834        TORNADO           96979
## 130 EXCESSIVE HEAT            8428
## 856      TSTM WIND            7461
## 170          FLOOD            7259
## 464      LIGHTNING            6046
## 275           HEAT            3037

2.Across the United States, which types of events have the greatest economic consequences?

To answer, we’ll need only variables: EVTYPE,PROPDMG,PROPDMGEXP,CROPDMG,ROPDMGEXP.

EconomicCons <- data[,c("EVTYPE","PROPDMG","PROPDMGEXP","CROPDMG","CROPDMGEXP")]

To get the real values of the damage, it is required to multiply the -DMG variables with the exponent variables i.e. the -DMGEXP values. CROPDMGEXP and PROPDMGEXP are showing the units in which damage is expressed: h - hundred, k - thousand, m - milion, b - bilion. Unknown values are recoded as 1.

EconomicCons$PROPDMGEXP <- as.numeric(Recode(as.character(EconomicCons$PROPDMGEXP),"'K'=10^3;'M'=10^6;''=1;'B'=10^9;'+'=1;'0'=1;'5'=10^5;'6'=10^6; '?'=1;'4'=10^4;'2'=10^2;'3'=10^3;'h'=10^2;'7'=10^7;'H'=10^2;'-'=1;'8'=10^8"))

## Warning: NAs durch Umwandlung erzeugt

## Warning: NAs introduced by coercion
EconomicCons$CROPDMGEXP <- as.numeric(Recode(as.character(EconomicCons$CROPDMGEXP),"''=1;
    'M'=10^6;'K'=10^3;'m'=10^6;'B'=10^9;'?'=1;'0'=1;
    'k'=10^3;'2'=10^2"))

The total economic damage is the sum of the property damage and crop damage after multiplying with the exponent variables. We interested only in the top ten event types for economic impact.

EconomicConsTotal <- mutate(EconomicCons, TOTALDMG = PROPDMG * PROPDMGEXP + CROPDMG * CROPDMGEXP)
EconomicConsAggr <- aggregate(EconomicConsTotal$TOTALDMG, by=list(EconomicConsTotal$EVTYPE),FUN=sum)
names(EconomicConsAggr) <- c("EVTYPE","SUMEVENTS")
Economic10 <- (EconomicConsAggr[order(EconomicConsAggr$SUMEVENTS,decreasing = TRUE),])[1:10,]
rownames(Economic10) <- NULL
barplot(Economic10$SUMEVENTS,main = "Most harmful events and economic consequences", ylab = "Damages ($)", names.arg = Economic10$EVTYPE,
        cex.axis = 0.5,cex.names = 0.5, las = 2)

The most harmful type of events are floods.

The following table shows the ten most harmful events and economic consequences in $:

Economic10

##               EVTYPE    SUMEVENTS
## 1              FLOOD 150319678257
## 2  HURRICANE/TYPHOON  71913712800
## 3        STORM SURGE  43323541000
## 4        FLASH FLOOD  18243991079
## 5            DROUGHT  15018672000
## 6          HURRICANE  14610229010
## 7        RIVER FLOOD  10148404500
## 8          ICE STORM   8967041360
## 9     TROPICAL STORM   8382236550
## 10      WINTER STORM   6715441251