Storm Data Analysis
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.
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.
What is this analysis about?
The basic goal of this analysis is to explore the NOAA Storm Database and answer some basic questions about severe weather events. You must use the database to answer the questions below and show the code for your entire analysis.
Questions
Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Across the United States, which types of events have the greatest economic consequences?
Data Processing
library(ggplot2)
library(knitr)
library(dplyr)##
## Attaching package: 'dplyr'
##
## The following object is masked from 'package:stats':
##
## filter
##
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(grid)
library(gridExtra)opts_chunk$set(cache = TRUE)download.file('http://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2', 'StormData.csv.bz2')raw_data <- read.csv(bzfile("StormData.csv.bz2"))names(raw_data)## [1] "STATE__" "BGN_DATE" "BGN_TIME" "TIME_ZONE" "COUNTY"
## [6] "COUNTYNAME" "STATE" "EVTYPE" "BGN_RANGE" "BGN_AZI"
## [11] "BGN_LOCATI" "END_DATE" "END_TIME" "COUNTY_END" "COUNTYENDN"
## [16] "END_RANGE" "END_AZI" "END_LOCATI" "LENGTH" "WIDTH"
## [21] "F" "MAG" "FATALITIES" "INJURIES" "PROPDMG"
## [26] "PROPDMGEXP" "CROPDMG" "CROPDMGEXP" "WFO" "STATEOFFIC"
## [31] "ZONENAMES" "LATITUDE" "LONGITUDE" "LATITUDE_E" "LONGITUDE_"
## [36] "REMARKS" "REFNUM"head(raw_data)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE
## 1 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL
## 2 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL
## 3 1 2/20/1951 0:00:00 1600 CST 57 FAYETTE AL
## 4 1 6/8/1951 0:00:00 0900 CST 89 MADISON AL
## 5 1 11/15/1951 0:00:00 1500 CST 43 CULLMAN AL
## 6 1 11/15/1951 0:00:00 2000 CST 77 LAUDERDALE AL
## EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 1 TORNADO 0 0
## 2 TORNADO 0 0
## 3 TORNADO 0 0
## 4 TORNADO 0 0
## 5 TORNADO 0 0
## 6 TORNADO 0 0
## COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES
## 1 NA 0 14.0 100 3 0 0
## 2 NA 0 2.0 150 2 0 0
## 3 NA 0 0.1 123 2 0 0
## 4 NA 0 0.0 100 2 0 0
## 5 NA 0 0.0 150 2 0 0
## 6 NA 0 1.5 177 2 0 0
## INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES
## 1 15 25.0 K 0
## 2 0 2.5 K 0
## 3 2 25.0 K 0
## 4 2 2.5 K 0
## 5 2 2.5 K 0
## 6 6 2.5 K 0
## LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1 3040 8812 3051 8806 1
## 2 3042 8755 0 0 2
## 3 3340 8742 0 0 3
## 4 3458 8626 0 0 4
## 5 3412 8642 0 0 5
## 6 3450 8748 0 0 6fatal_inj <- aggregate(cbind(FATALITIES, INJURIES) ~ EVTYPE, data = raw_data, sum)# clean property damage column
prop_damage <-subset(raw_data, raw_data$PROPDMGEXP %in% c('B','M','m','K'))
# keep only EVTYPE, PROPDMG and PROPDMGEXP
prop_damage <- select(prop_damage,c(EVTYPE,PROPDMG,PROPDMGEXP))
# covert PROPDMGEXP into characters
prop_damage$PROPDMGEXP <- as.character(prop_damage$PROPDMGEXP)
#Using PROPDMGEXP and PROPDMG add andother field that calculates the real amount of damage
prop <- mutate(prop_damage, prop_cost = ifelse(PROPDMGEXP == 'K' , PROPDMG*1000,
ifelse(PROPDMGEXP %in% c('M','m') , PROPDMG*1000000,
ifelse(PROPDMGEXP == 'B' , PROPDMG*1000000000,0))))
# sum for each event type
prop_damage_by_event <- aggregate(prop_cost ~ EVTYPE, data = prop, sum)
# sort
prop_sorted <- arrange(prop_damage_by_event, -prop_cost)top_prop_sorted <- head(prop_sorted, 20)# clean dataset for only crop damage
crop <-subset(raw_data, raw_data$CROPDMGEXP %in% c('B','M','m','K','k'))
# create new df only using EVTYPE,CROPDMG,CROPDMGEXP
crop <- select(crop,c(EVTYPE,CROPDMG,CROPDMGEXP))
# convert CROPDMGEXP into characters
crop$CROPDMGEXP <- as.character(crop$CROPDMGEXP)
# create "cost" column with damage cost in dollars (not thousands, millions or bilions)
crop <- mutate(crop, crop_cost = ifelse(CROPDMGEXP %in% c('K','k') , CROPDMG*1000,
ifelse(CROPDMGEXP %in% c('M','m') , CROPDMG*1000000,
ifelse(CROPDMGEXP == 'B' , CROPDMG*1000000000,0))))
# sum for each event type
crop_damage_by_event <- aggregate(crop_cost ~ EVTYPE, data = crop, sum)
# sort
crop_sorted <- arrange(crop_damage_by_event, -crop_cost)top_crop_sorted <- head(crop_sorted, 20)
top_crop_sorted## EVTYPE crop_cost
## 1 DROUGHT 13972566000
## 2 FLOOD 5661968450
## 3 RIVER FLOOD 5029459000
## 4 ICE STORM 5022113500
## 5 HAIL 3025954450
## 6 HURRICANE 2741910000
## 7 HURRICANE/TYPHOON 2607872800
## 8 FLASH FLOOD 1421317100
## 9 EXTREME COLD 1292973000
## 10 FROST/FREEZE 1094086000
## 11 HEAVY RAIN 733399800
## 12 TROPICAL STORM 678346000
## 13 HIGH WIND 638571300
## 14 TSTM WIND 554007350
## 15 EXCESSIVE HEAT 492402000
## 16 FREEZE 446225000
## 17 TORNADO 414953110
## 18 THUNDERSTORM WIND 414843050
## 19 HEAT 401461500
## 20 WILDFIRE 295472800# merge datasets by EVTYPE. Dataset sizes are different so there are will be NA's after merging
merged <- merge(crop_sorted, prop_sorted, by = 'EVTYPE', all = TRUE)
# convert NA's into 0
merged$prop_cost[is.na(merged$prop_cost)] <- 0
merged <- mutate(merged, TOTAL = prop_cost + crop_cost)
merged <- arrange(merged, -TOTAL)
# top 20 destractive events
h_merged <- head(merged,20)Results
- Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
Most harmful types of events in US for population
head(fatal_inj, 30)## EVTYPE FATALITIES INJURIES
## 1 ? 0 0
## 2 ABNORMALLY DRY 0 0
## 3 ABNORMALLY WET 0 0
## 4 ABNORMAL WARMTH 0 0
## 5 ACCUMULATED SNOWFALL 0 0
## 6 AGRICULTURAL FREEZE 0 0
## 7 APACHE COUNTY 0 0
## 8 ASTRONOMICAL HIGH TIDE 0 0
## 9 ASTRONOMICAL LOW TIDE 0 0
## 10 AVALANCE 1 0
## 11 AVALANCHE 224 170
## 12 BEACH EROSIN 0 0
## 13 Beach Erosion 0 0
## 14 BEACH EROSION 0 0
## 15 BEACH EROSION/COASTAL FLOOD 0 0
## 16 BEACH FLOOD 0 0
## 17 BELOW NORMAL PRECIPITATION 0 0
## 18 BITTER WIND CHILL 0 0
## 19 BITTER WIND CHILL TEMPERATURES 0 0
## 20 Black Ice 0 0
## 21 BLACK ICE 1 24
## 22 BLIZZARD 101 805
## 23 BLIZZARD AND EXTREME WIND CHIL 0 0
## 24 BLIZZARD AND HEAVY SNOW 0 0
## 25 BLIZZARD/FREEZING RAIN 0 0
## 26 BLIZZARD/HEAVY SNOW 0 0
## 27 BLIZZARD/HIGH WIND 0 0
## 28 Blizzard Summary 0 0
## 29 BLIZZARD WEATHER 0 0
## 30 BLIZZARD/WINTER STORM 0 0# sort FATALITIES from most destractive and take top 20
fatal_inj <- arrange(fatal_inj, -FATALITIES)
h_fatal_inj <- head(fatal_inj, 20)
# sort EVTYPE from most destractive to less destactive in fatalities
fatal_levels <- h_fatal_inj$EVTYPE
h_fatal_inj$EVTYPE <- factor(h_fatal_inj$EVTYPE, levels = fatal_levels)
# create plot 1
p1 <- ggplot(h_fatal_inj, aes(EVTYPE, FATALITIES)) +
geom_point(color = 'blue', size = 4) +
theme(axis.text.x = element_text(angle = 30, hjust = 1))
# sort INJURIES from most destractive and take top 20
fatal_inj <- arrange(fatal_inj, -INJURIES)
h_fatal_inj <- head(fatal_inj, 20)
# sort EVTYPE from most destractive to less destactive in injuries
inj_levels <- h_fatal_inj$EVTYPE
h_fatal_inj$EVTYPE <- factor(h_fatal_inj$EVTYPE, levels = inj_levels)
# create plot 2
p2 <- ggplot(h_fatal_inj, aes(EVTYPE, INJURIES)) +
geom_point(color = 'green', size = 4) +
theme(axis.text.x = element_text(angle = 30, hjust = 1))
# combine two plots in one figure
grid.arrange(p1, p2, ncol = 1, main = "Top-20 destractive events in US")
- Across the United States, which types of events have the greatest economic consequences?
Most harmful types of events in US for property and crop
top_prop_sorted## EVTYPE prop_cost
## 1 FLOOD 144657709800
## 2 HURRICANE/TYPHOON 69305840000
## 3 TORNADO 56937160480
## 4 STORM SURGE 43323536000
## 5 FLASH FLOOD 16140811510
## 6 HAIL 15732266720
## 7 HURRICANE 11868319010
## 8 TROPICAL STORM 7703890550
## 9 WINTER STORM 6688497250
## 10 HIGH WIND 5270046260
## 11 RIVER FLOOD 5118945500
## 12 WILDFIRE 4765114000
## 13 STORM SURGE/TIDE 4641188000
## 14 TSTM WIND 4484928440
## 15 ICE STORM 3944927810
## 16 THUNDERSTORM WIND 3483121140
## 17 HURRICANE OPAL 3172846000
## 18 WILD/FOREST FIRE 3001829500
## 19 HEAVY RAIN/SEVERE WEATHER 2500000000
## 20 THUNDERSTORM WINDS 1735952850top_crop_sorted## EVTYPE crop_cost
## 1 DROUGHT 13972566000
## 2 FLOOD 5661968450
## 3 RIVER FLOOD 5029459000
## 4 ICE STORM 5022113500
## 5 HAIL 3025954450
## 6 HURRICANE 2741910000
## 7 HURRICANE/TYPHOON 2607872800
## 8 FLASH FLOOD 1421317100
## 9 EXTREME COLD 1292973000
## 10 FROST/FREEZE 1094086000
## 11 HEAVY RAIN 733399800
## 12 TROPICAL STORM 678346000
## 13 HIGH WIND 638571300
## 14 TSTM WIND 554007350
## 15 EXCESSIVE HEAT 492402000
## 16 FREEZE 446225000
## 17 TORNADO 414953110
## 18 THUNDERSTORM WIND 414843050
## 19 HEAT 401461500
## 20 WILDFIRE 295472800h_merged## EVTYPE crop_cost prop_cost TOTAL
## 1 FLOOD 5661968450 144657709800 150319678250
## 2 HURRICANE/TYPHOON 2607872800 69305840000 71913712800
## 3 TORNADO 414953110 56937160480 57352113590
## 4 STORM SURGE 5000 43323536000 43323541000
## 5 HAIL 3025954450 15732266720 18758221170
## 6 FLASH FLOOD 1421317100 16140811510 17562128610
## 7 DROUGHT 13972566000 1046106000 15018672000
## 8 HURRICANE 2741910000 11868319010 14610229010
## 9 RIVER FLOOD 5029459000 5118945500 10148404500
## 10 ICE STORM 5022113500 3944927810 8967041310
## 11 TROPICAL STORM 678346000 7703890550 8382236550
## 12 WINTER STORM 26944000 6688497250 6715441250
## 13 HIGH WIND 638571300 5270046260 5908617560
## 14 WILDFIRE 295472800 4765114000 5060586800
## 15 TSTM WIND 554007350 4484928440 5038935790
## 16 STORM SURGE/TIDE 850000 4641188000 4642038000
## 17 THUNDERSTORM WIND 414843050 3483121140 3897964190
## 18 HURRICANE OPAL 19000000 3172846000 3191846000
## 19 WILD/FOREST FIRE 106796830 3001829500 3108626330
## 20 THUNDERSTORM WINDS 190654700 1735952850 1926607550# create levels for plot
crop_prop_levels <- h_merged$EVTYPE
h_merged$EVTYPE <- factor(h_merged$EVTYPE, levels = crop_prop_levels)
ggplot(h_merged, aes(EVTYPE, TOTAL)) +
geom_point(color = 'red', size = 4) +
theme(axis.text.x = element_text(angle = 30, hjust = 1))