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.

Data

The data for this assignment come in the form of a comma-separated-value file compressed via the bzip2 algorithm to reduce its size. You can download the file from the course web site.

More documentation can be found here and here

The 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.

Downloading and reading the data into R

We shall download and read the file from the site repository.

if (!"StormData.csv.bz2" %in% dir("./")) {
  print("Downloading file, please wait....")
        download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2","datafile.csv.bz2")
}


if(!'StormData' %in% ls()){
  StormData <- read.csv("StormData.csv.bz2", header = TRUE, sep = ",")
}

Data processing

names(StormData)
##  [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"

The data contains 902297 observations and 37 variables. The questions regarding this assignment regards the economic and human and economic consequences. We shall therefore only require the following variables to answer these question. They reduce the dimensions of the data for us:

# New dataframe for manipulation:

conseReal <- StormData[, c(8,23:28)]

We can now do some data processing on the new dataframe

# Transform the exponentials that read "-", "+" and "?" to read "0" exponential.

rm <- c("B", "h", "H", "K", "m", "M")
conseReal$PROPDMGEXP <- ifelse(conseReal$PROPDMGEXP %in% rm,  as.character(conseReal$PROPDMGEXP), "NONE")
conseReal$CROPDMGEXP <- ifelse(conseReal$CROPDMGEXP %in% rm,  as.character(conseReal$CROPDMGEXP), "NONE")

# We shall multiply the exponential colum with the damage column

conseReal$PROPDMG <- conseReal$PROPDMG * (10^9 * (conseReal$PROPDMGEXP == "B") + 
10^6 *(conseReal$PROPDMGEXP %in% c("m", "M")) + 
10^3 * (conseReal$PROPDMGEXP %in% c("k", "K")) + 
100 * (conseReal$PROPDMGEXP %in% c("h", "H")))

conseReal$CROPDMG <- conseReal$CROPDMG * (10^9 * (conseReal$CROPDMGEXP == "B") + 10^6 *(conseReal$CROPDMGEXP %in% c("m", "M")) + 10^3 * (conseReal$CROPDMGEXP %in% c("k", "K")) + 100 * (conseReal$CROPDMGEXP %in% c("h", "H")))


# we then combine the tow columns with total damage costs
conseReal$PROPandCROP <- conseReal$PROPDMG + conseReal$CROPDMG

# Combine the fatalities and the injuries columns

conseReal$FandI <- conseReal$FATALITIES + conseReal$INJURIES

Results

Questions:

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

DeathAndInjuries <- aggregate(FandI ~ EVTYPE, data = conseReal, FUN = sum)
DeathAndInjuries <- DeathAndInjuries[order(DeathAndInjuries$FandI, decreasing = TRUE),]
# TOP 15 causes of Fatality and Injuries
MaxHumanHarm <- DeathAndInjuries[1:15, ]
print(MaxHumanHarm)  
##                EVTYPE FandI
## 830           TORNADO 96979
## 123    EXCESSIVE HEAT  8428
## 854         TSTM WIND  7461
## 164             FLOOD  7259
## 452         LIGHTNING  6046
## 269              HEAT  3037
## 147       FLASH FLOOD  2755
## 424         ICE STORM  2064
## 759 THUNDERSTORM WIND  1621
## 972      WINTER STORM  1527
## 354         HIGH WIND  1385
## 238              HAIL  1376
## 406 HURRICANE/TYPHOON  1339
## 304        HEAVY SNOW  1148
## 953          WILDFIRE   986

Figure 1

barplot(sort(by(MaxHumanHarm$FandI, MaxHumanHarm$EVTYPE, sum), decreasing=T)[15:1], horiz=T, las=1, cex.names=0.7, xlab="Total Fatalities and Injuries Per Event Type")
 mtext("Total Fatalities and Injuries By Event Type (top 15)", side=3, line=1, cex=1, at=30000, font=2)

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

Destruction <- aggregate(PROPandCROP/10e9 ~ EVTYPE, data = conseReal, FUN = sum)
Destruction <- Destruction[order(Destruction$PROPandCROP, decreasing = TRUE),]
# TOP 15 Total Cost of Damage by Event Type (Billion of Dollars)
MaxDestruction <- Destruction[1:15, ]
print(MaxDestruction)  
##                EVTYPE PROPandCROP/1e+10
## 164             FLOOD        15.0319678
## 406 HURRICANE/TYPHOON         7.1913713
## 830           TORNADO         5.7352114
## 666       STORM SURGE         4.3323541
## 238              HAIL         1.8757805
## 147       FLASH FLOOD         1.7562129
## 88            DROUGHT         1.5018672
## 397         HURRICANE         1.4610229
## 586       RIVER FLOOD         1.0148404
## 424         ICE STORM         0.8967041
## 844    TROPICAL STORM         0.8382237
## 972      WINTER STORM         0.6715441
## 354         HIGH WIND         0.5908618
## 953          WILDFIRE         0.5060587
## 854         TSTM WIND         0.5038936

Figure 2

barplot(sort(by(MaxDestruction$PROPandCROP, MaxDestruction$EVTYPE, sum), decreasing=T)[15:1], horiz=T, las=1, cex.names=0.7, xlab="Total Cost of Destruction Per Event Type")
 mtext("Total Cost of Destruction By Event Type (Billions of $)", side=3, line=1, cex=1, at=30000, font=2)

Conclusion

tornado Injured and Killed most people in the USA than any other weather event under the period between 1950 and end in November 2011. However floods caused the most destruction to property and crops within the same period.