Human consequences of weather events in USA
Italo López
2023-02-08
Synopsis
In this document we present the health and economic consequences of weather events in the USA. We do so using the NOAA Storm Database, by presenting plots and statistics related with weather events
Data Processing
The data was download from the NOAA Storm Database in a bzip2 file and then decompressed in R
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2",destfile = "data.bz2")
data <- read.csv(bzfile("data.bz2"))
head(data)## 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 6colnames(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"ncol(data)## [1] 37str(data)## '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 ...summary(data)## 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
## Results
Most damaging weather events for the economy
data%>%group_by(EVTYPE) %>%select(EVTYPE,PROPDMG)%>%
summarise_all(funs(mean, median, min, max, sd))%>%arrange(desc(mean))## Warning: `funs()` was deprecated in dplyr 0.8.0.
## Please use a list of either functions or lambdas:
##
## # Simple named list:
## list(mean = mean, median = median)
##
## # Auto named with `tibble::lst()`:
## tibble::lst(mean, median)
##
## # Using lambdas
## list(~ mean(., trim = .2), ~ median(., na.rm = TRUE))
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was generated.## # A tibble: 985 x 6
## EVTYPE mean median min max sd
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 "COASTAL EROSION" 766 766 766 766 NA
## 2 "HEAVY RAIN AND FLOOD" 600 600 600 600 NA
## 3 "RIVER AND STREAM FLOOD" 600 600 400 800 283.
## 4 "Landslump" 570 570 570 570 NA
## 5 "BLIZZARD/WINTER STORM" 500 500 500 500 NA
## 6 "FLASH FLOOD/" 500 500 500 500 NA
## 7 "FLASH FLOODING/THUNDERSTORM WI" 500 500 500 500 NA
## 8 "FLOOD/RIVER FLOOD" 500 500 500 500 NA
## 9 "FROST\\FREEZE" 500 500 500 500 NA
## 10 "HEAVY PRECIPITATION" 500 500 500 500 NA
## # ... with 975 more rows
## # i Use `print(n = ...)` to see more rowsmost_harmful<-data%>%group_by(EVTYPE) %>%select(EVTYPE,PROPDMG)%>%
summarise_all(funs(mean, median, min, max, sd))%>%arrange(desc(mean))%>%
slice(1:4)
ggplot(data%>%select(EVTYPE,PROPDMG)%>%
filter(EVTYPE %in% c(most_harmful%>%unlist%>%as.vector())),aes(PROPDMG))+geom_histogram()+facet_grid(~EVTYPE)+labs(caption="Note: Histogram of Property Damage of the most damaging weather events")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Most damaging weather events for population health
data%>%group_by(EVTYPE) %>%select(EVTYPE,FATALITIES)%>%
summarise_all(funs(mean, median, min, max, sd))%>%arrange(desc(mean))## # A tibble: 985 x 6
## EVTYPE mean median min max sd
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 TORNADOES, TSTM WIND, HAIL 25 25 25 25 NA
## 2 COLD AND SNOW 14 14 14 14 NA
## 3 TROPICAL STORM GORDON 8 8 8 8 NA
## 4 RECORD/EXCESSIVE HEAT 5.67 0 0 17 9.81
## 5 EXTREME HEAT 4.36 0 0 57 12.4
## 6 HEAT WAVE DROUGHT 4 4 4 4 NA
## 7 HIGH WIND/SEAS 4 4 4 4 NA
## 8 MARINE MISHAP 3.5 3.5 1 6 3.54
## 9 WINTER STORMS 3.33 0 0 10 5.77
## 10 Heavy surf and wind 3 3 3 3 NA
## # ... with 975 more rows
## # i Use `print(n = ...)` to see more rowsdata%>%group_by(EVTYPE) %>%select(EVTYPE,INJURIES)%>%
summarise_all(funs(mean, median, min, max, sd))%>%arrange(desc(mean))## # A tibble: 985 x 6
## EVTYPE mean median min max sd
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Heat Wave 70 70 70 70 NA
## 2 TROPICAL STORM GORDON 43 43 43 43 NA
## 3 WILD FIRES 37.5 0 0 150 75
## 4 THUNDERSTORMW 27 27 27 27 NA
## 5 HIGH WIND AND SEAS 20 20 20 20 NA
## 6 SNOW/HIGH WINDS 18 18 2 34 22.6
## 7 GLAZE/ICE STORM 15 15 15 15 NA
## 8 HEAT WAVE DROUGHT 15 15 15 15 NA
## 9 WINTER STORM HIGH WINDS 15 15 15 15 NA
## 10 HURRICANE/TYPHOON 14.5 0 0 780 89.8
## # ... with 975 more rows
## # i Use `print(n = ...)` to see more rows