Synopsis

This data analysis report is written to show the efects of storms and other severe weather events on public health and its economic cost using the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. The main questions in this report targetted are: the types of weather events are the most harmful to the public health and types of weather events are the most costly economically.

Data Processing

Downloading data:

Download the data from the U.S. National Oceanic and Atmospheric Administration’s (NOAA) website:

if(!file.exists("repdata-data-StormData.csv")) {
        tempfile <- tempfile()
        download.file("https://d396qusza40orc.cloudfront.net/repdata/data/repdata-data-StormData.csv.bz2",destfile = tempfile)
        unzip(tempfile)
        unlink(tempfile)
}

Reading the data:

stormData<-read.csv("./repdata-data-StormData.csv", header=TRUE, stringsAsFactors=FALSE) 
dim(stormData)
## [1] 902297     37
head(stormData)
##   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
(echo = TRUE)
## [1] TRUE
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"
(echo = TRUE)
## [1] TRUE
str(stormData)
## '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 ...
(echo = TRUE)
## [1] TRUE
summary(stormData)
##     STATE__       BGN_DATE           BGN_TIME          TIME_ZONE        
##  Min.   : 1.0   Length:902297      Length:902297      Length:902297     
##  1st Qu.:19.0   Class :character   Class :character   Class :character  
##  Median :30.0   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :31.2                                                           
##  3rd Qu.:45.0                                                           
##  Max.   :95.0                                                           
##                                                                         
##      COUNTY       COUNTYNAME           STATE              EVTYPE         
##  Min.   :  0.0   Length:902297      Length:902297      Length:902297     
##  1st Qu.: 31.0   Class :character   Class :character   Class :character  
##  Median : 75.0   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :100.6                                                           
##  3rd Qu.:131.0                                                           
##  Max.   :873.0                                                           
##                                                                          
##    BGN_RANGE          BGN_AZI           BGN_LOCATI          END_DATE        
##  Min.   :   0.000   Length:902297      Length:902297      Length:902297     
##  1st Qu.:   0.000   Class :character   Class :character   Class :character  
##  Median :   0.000   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :   1.484                                                           
##  3rd Qu.:   1.000                                                           
##  Max.   :3749.000                                                           
##                                                                             
##    END_TIME           COUNTY_END COUNTYENDN       END_RANGE       
##  Length:902297      Min.   :0    Mode:logical   Min.   :  0.0000  
##  Class :character   1st Qu.:0    NA's:902297    1st Qu.:  0.0000  
##  Mode  :character   Median :0                   Median :  0.0000  
##                     Mean   :0                   Mean   :  0.9862  
##                     3rd Qu.:0                   3rd Qu.:  0.0000  
##                     Max.   :0                   Max.   :925.0000  
##                                                                   
##    END_AZI           END_LOCATI            LENGTH              WIDTH         
##  Length:902297      Length:902297      Min.   :   0.0000   Min.   :   0.000  
##  Class :character   Class :character   1st Qu.:   0.0000   1st Qu.:   0.000  
##  Mode  :character   Mode  :character   Median :   0.0000   Median :   0.000  
##                                        Mean   :   0.2301   Mean   :   7.503  
##                                        3rd Qu.:   0.0000   3rd Qu.:   0.000  
##                                        Max.   :2315.0000   Max.   :4400.000  
##                                                                              
##        F               MAG            FATALITIES          INJURIES        
##  Min.   :0.0      Min.   :    0.0   Min.   :  0.0000   Min.   :   0.0000  
##  1st Qu.:0.0      1st Qu.:    0.0   1st Qu.:  0.0000   1st Qu.:   0.0000  
##  Median :1.0      Median :   50.0   Median :  0.0000   Median :   0.0000  
##  Mean   :0.9      Mean   :   46.9   Mean   :  0.0168   Mean   :   0.1557  
##  3rd Qu.:1.0      3rd Qu.:   75.0   3rd Qu.:  0.0000   3rd Qu.:   0.0000  
##  Max.   :5.0      Max.   :22000.0   Max.   :583.0000   Max.   :1700.0000  
##  NA's   :843563                                                           
##     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.   :990.000                     
##                                                                           
##      WFO             STATEOFFIC         ZONENAMES            LATITUDE   
##  Length:902297      Length:902297      Length:902297      Min.   :   0  
##  Class :character   Class :character   Class :character   1st Qu.:2802  
##  Mode  :character   Mode  :character   Mode  :character   Median :3540  
##                                                           Mean   :2875  
##                                                           3rd Qu.:4019  
##                                                           Max.   :9706  
##                                                           NA's   :47    
##    LONGITUDE        LATITUDE_E     LONGITUDE_       REMARKS         
##  Min.   :-14451   Min.   :   0   Min.   :-14455   Length:902297     
##  1st Qu.:  7247   1st Qu.:   0   1st Qu.:     0   Class :character  
##  Median :  8707   Median :   0   Median :     0   Mode  :character  
##  Mean   :  6940   Mean   :1452   Mean   :  3509                     
##  3rd Qu.:  9605   3rd Qu.:3549   3rd Qu.:  8735                     
##  Max.   : 17124   Max.   :9706   Max.   :106220                     
##                   NA's   :40                                        
##      REFNUM      
##  Min.   :     1  
##  1st Qu.:225575  
##  Median :451149  
##  Mean   :451149  
##  3rd Qu.:676723  
##  Max.   :902297  
## 
(echo = TRUE)
## [1] TRUE
fields<-c("EVTYPE","FATALITIES","INJURIES","PROPDMG", "PROPDMGEXP","CROPDMG","CROPDMGEXP")
working<-stormData[fields]

(echo = TRUE)
## [1] TRUE
fatalities <- aggregate(FATALITIES ~ EVTYPE, data = working, FUN = sum)
injuries <- aggregate(INJURIES ~ EVTYPE, data = working, FUN = sum)

fatalities10 <- fatalities[order(-fatalities$FATALITIES),][1:10, ]
injuries10 <- injuries[order(-injuries$INJURIES),][1:10, ]

(echo = TRUE)
## [1] TRUE
unique(working$PROPDMGEXP)
##  [1] "K" "M" ""  "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-" "1" "8"
(echo = TRUE)
## [1] TRUE
unique(working$CROPDMGEXP)
## [1] ""  "M" "K" "m" "B" "?" "0" "k" "2"
(echo = TRUE)
## [1] TRUE
unique(working$PROPDMGEXP)
##  [1] "K" "M" ""  "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-" "1" "8"
(echo = TRUE)
## [1] TRUE
unique(working$CROPDMGEXP)
## [1] ""  "M" "K" "m" "B" "?" "0" "k" "2"
(echo = TRUE)
## [1] TRUE
working$PROPEXP[working$PROPDMGEXP ==  "K"    ]  <-    1000
working$PROPEXP[working$PROPDMGEXP == "M"     ]   <-  1000000
working$PROPEXP[working$PROPDMGEXP == ""      ]   <-  1
working$PROPEXP[working$PROPDMGEXP == "B"     ]   <-  1000000000
working$PROPEXP[working$PROPDMGEXP == "m"     ]   <-  1000000
working$PROPEXP[working$PROPDMGEXP == "+"     ]   <-  0
working$PROPEXP[working$PROPDMGEXP == "0"     ]   <-  1
working$PROPEXP[working$PROPDMGEXP == "5"     ]   <-  100000
working$PROPEXP[working$PROPDMGEXP == "6"     ]   <-  1000000
working$PROPEXP[working$PROPDMGEXP == "?"     ]   <-  0
working$PROPEXP[working$PROPDMGEXP == "4"     ]   <-  10000
working$PROPEXP[working$PROPDMGEXP == "2"     ]   <-  100
working$PROPEXP[working$PROPDMGEXP == "3"     ]   <-  1000
working$PROPEXP[working$PROPDMGEXP == "h"     ]   <-  100
working$PROPEXP[working$PROPDMGEXP == "7"     ]   <-  10000000
working$PROPEXP[working$PROPDMGEXP == "H"     ]   <-  100
working$PROPEXP[working$PROPDMGEXP == "-"     ]   <-  0
working$PROPEXP[working$PROPDMGEXP == "1"     ]   <-  10
working$PROPEXP[working$PROPDMGEXP == "8"     ]   <-  100000000


working$CROPEXP[working$CROPDMGEXP ==  ""     ]   <-  1
working$CROPEXP[working$CROPDMGEXP == "M"     ]   <-  1000000
working$CROPEXP[working$CROPDMGEXP == "K"     ]   <-  1000
working$CROPEXP[working$CROPDMGEXP == "m"     ]   <-  1000000000
working$CROPEXP[working$CROPDMGEXP == "B"     ]   <-  1000000
working$CROPEXP[working$CROPDMGEXP == "?"     ]   <-  0
working$CROPEXP[working$CROPDMGEXP == "0"     ]   <-  1
working$CROPEXP[working$CROPDMGEXP == "k"     ]   <-  1000
working$CROPEXP[working$CROPDMGEXP == "2"     ]   <-  100

working$PROPDMGVAL <- working$PROPDMG * working$PROPEXP
working$CROPDMGVAL <- working$CROPDMG * working$CROPEXP

working$ALLDMGVAL <- working$PROPDMGVAL + working$CROPDMGVAL

(echo = TRUE)
## [1] TRUE

Results

Types of events that are the most harmful with respect to population health:

par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), las=3,cex = 0.8)
barplot(fatalities10$FATALITIES, names.arg=fatalities10$EVTYPE,col="blue",ylab="Fatalities", main="Top 10 Events with HighestFatalities")
barplot(injuries10$INJURIES, names.arg=injuries10$EVTYPE,col="yellow", ylab="Injuries", main="Top 10 Events with Highest Injuries")

(echo = TRUE)
## [1] TRUE
prop_crop_dmg <- aggregate(ALLDMGVAL ~ EVTYPE, data = working, FUN = sum)
prop_crop_dmg_10<-prop_crop_dmg[order(-prop_crop_dmg$ALLDMGVAL), ][1:10,]

(echo = TRUE)
## [1] TRUE

The 10 top types of events that have the greatest economic consequences:

par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), las=3,cex = 0.8, cex.main = 0.9)

barplot((prop_crop_dmg_10$ALLDMGVAL)/(1*1000000000), names.arg=prop_crop_dmg_10$EVTYPE, col="green", ylab="Property Damage ($ billions)", main="Top 10 Events of Highest Property/Crop Damage")

(echo = TRUE)
## [1] TRUE

Conclusion:

From the hitograms; Top 10 Events with Highest Fatalities , Top 10 Events with Highest Injuries , Top 10 Events of Highest Property/Crop Damage can be seen that the most fatalities and injuries are caused by tornados and the most property and crop damage is caused by floods.