Reproducible research Project 2
Vishal Soni
29/05/2021
#Code for reading in the dataset and/or processing the data
dataset <-download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2","./storm_dataset")
dataset <- read.csv(bzfile("storm_dataset"))
head(dataset)## 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 6str(dataset)## '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 ...names(dataset)## [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"#1) Across the United States, which types of events (as indicated in the EVTYPE #variable) are most harmful with respect to population health?
#for Events we have to compare with 2 health problems i.e injuries and fatalities
#We have to aggregate both one by one the compare
#a) aggregating EVTYPE wrt injuries
total_injuries <- aggregate(INJURIES~EVTYPE, dataset, sum)
total_injuries <- arrange(total_injuries, desc(INJURIES))
total_injuries <- total_injuries[1:20, ]
total_injuries## EVTYPE INJURIES
## 1 TORNADO 91346
## 2 TSTM WIND 6957
## 3 FLOOD 6789
## 4 EXCESSIVE HEAT 6525
## 5 LIGHTNING 5230
## 6 HEAT 2100
## 7 ICE STORM 1975
## 8 FLASH FLOOD 1777
## 9 THUNDERSTORM WIND 1488
## 10 HAIL 1361
## 11 WINTER STORM 1321
## 12 HURRICANE/TYPHOON 1275
## 13 HIGH WIND 1137
## 14 HEAVY SNOW 1021
## 15 WILDFIRE 911
## 16 THUNDERSTORM WINDS 908
## 17 BLIZZARD 805
## 18 FOG 734
## 19 WILD/FOREST FIRE 545
## 20 DUST STORM 440#b) aggregating EVTYPE wrt fatalities
total_fatalities <- aggregate(FATALITIES~EVTYPE,dataset, sum)
total_fatalities <- arrange(total_fatalities, desc(FATALITIES))
total_fatalities <- total_fatalities[1:20, ]
total_fatalities## EVTYPE FATALITIES
## 1 TORNADO 5633
## 2 EXCESSIVE HEAT 1903
## 3 FLASH FLOOD 978
## 4 HEAT 937
## 5 LIGHTNING 816
## 6 TSTM WIND 504
## 7 FLOOD 470
## 8 RIP CURRENT 368
## 9 HIGH WIND 248
## 10 AVALANCHE 224
## 11 WINTER STORM 206
## 12 RIP CURRENTS 204
## 13 HEAT WAVE 172
## 14 EXTREME COLD 160
## 15 THUNDERSTORM WIND 133
## 16 HEAVY SNOW 127
## 17 EXTREME COLD/WIND CHILL 125
## 18 STRONG WIND 103
## 19 BLIZZARD 101
## 20 HIGH SURF 101#c) ploting
par(mfrow = c(1, 2), mar = c(15, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(total_fatalities$FATALITIES, las = 3, names.arg = total_fatalities$EVTYPE, main = "Weather Events With\n The Top 10 Highest Fatalities", ylab = "Number of Fatalities", col = total_fatalities$FATALITIES)
#OR ##########Creating double bar graphs
#d) merging both
totals<- merge(total_fatalities, total_injuries, by.x = "EVTYPE", by.y = "EVTYPE")
totals<-arrange(totals,desc(FATALITIES+INJURIES))
bad_stuff <- melt(totals, id.vars="EVTYPE", variable.name = "bad_thing")
tail(bad_stuff, 5)## EVTYPE bad_thing value
## 20 THUNDERSTORM WIND INJURIES 1488
## 21 WINTER STORM INJURIES 1321
## 22 HIGH WIND INJURIES 1137
## 23 HEAVY SNOW INJURIES 1021
## 24 BLIZZARD INJURIES 805#e) ploting
# Create chart
healthChart <- ggplot(bad_stuff, aes(x=reorder(EVTYPE, -value), y=value))
# Plot data as bar chart
healthChart = healthChart + geom_bar(stat="identity", aes(fill=bad_thing), position="dodge")
# Set x-axis label
healthChart = healthChart + xlab("Event Type")
# Rotate x-axis tick labels
healthChart = healthChart + theme(axis.text.x = element_text(angle=45, hjust=1))
# Set chart title and center it
healthChart = healthChart + ggtitle("Top 10 US Killers") + theme(plot.title = element_text(hjust = 0.5))
healthChart
#2. Across the United States, which types of events have the greatest economic #consequences?
we have property Damage and crop damage
#a) Aggregate Data for Property Damage
propdmg <- aggregate(PROPDMG ~ EVTYPE, data = dataset, FUN = sum)
propdmg <- propdmg[order(propdmg$PROPDMG, decreasing = TRUE), ]
# 10 most harmful causes of injuries
propdmgMax <- propdmg[1:10, ]
print(propdmgMax)## EVTYPE PROPDMG
## 834 TORNADO 3212258.2
## 153 FLASH FLOOD 1420124.6
## 856 TSTM WIND 1335965.6
## 170 FLOOD 899938.5
## 760 THUNDERSTORM WIND 876844.2
## 244 HAIL 688693.4
## 464 LIGHTNING 603351.8
## 786 THUNDERSTORM WINDS 446293.2
## 359 HIGH WIND 324731.6
## 972 WINTER STORM 132720.6#b) Aggregate Data for Crop Damage
cropdmg <- aggregate(CROPDMG ~ EVTYPE, data = dataset, FUN = sum)
cropdmg <- cropdmg[order(cropdmg$CROPDMG, decreasing = TRUE), ]
# 10 most harmful causes of injuries
cropdmgMax <- cropdmg[1:10, ]
print(cropdmgMax)## EVTYPE CROPDMG
## 244 HAIL 579596.28
## 153 FLASH FLOOD 179200.46
## 170 FLOOD 168037.88
## 856 TSTM WIND 109202.60
## 834 TORNADO 100018.52
## 760 THUNDERSTORM WIND 66791.45
## 95 DROUGHT 33898.62
## 786 THUNDERSTORM WINDS 18684.93
## 359 HIGH WIND 17283.21
## 290 HEAVY RAIN 11122.80#c)ploting
par(mfrow = c(1, 2), mar = c(15, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(propdmgMax$PROPDMG, las = 3, names.arg = propdmgMax$EVTYPE,
main = "Top 10 Events with\n Greatest Property Damages",
ylab = "Number of Injuries", col = propdmgMax$PROPDMG)
barplot(cropdmgMax$CROPDMG, las = 3, names.arg = cropdmgMax$EVTYPE,
main = "Top 10 Events with\n Greatest Crop Damages",
ylab = "Number of Injuries", col = cropdmgMax$CROPDMG)
MAKING DOUBLE BAR GRAPH
#d)merging both
totalDamage<- merge(propdmgMax,cropdmgMax,by.x = "EVTYPE", by.y = "EVTYPE")
totalDamage<-arrange(totalDamage,desc(PROPDMG + CROPDMG))
top_10_damages <- melt(totalDamage, id.vars="EVTYPE", variable.name = "Damage_Types")
head(top_10_damages, 5)## EVTYPE Damage_Types value
## 1 TORNADO PROPDMG 3212258.2
## 2 FLASH FLOOD PROPDMG 1420124.6
## 3 TSTM WIND PROPDMG 1335965.6
## 4 HAIL PROPDMG 688693.4
## 5 FLOOD PROPDMG 899938.5#e)ploting
# Create chart
DamageChart <- ggplot(top_10_damages, aes(x=reorder(EVTYPE, -value/100000), y=value/100000))
# Plot data as bar chart
DamageChart = DamageChart + geom_bar(stat="identity", aes(fill=Damage_Types), position="dodge")
# Set x-axis label
DamageChart = DamageChart + xlab("Event Type") +ylab("Cost of damage in $(billions)")
# Rotate x-axis tick labels
DamageChart = DamageChart + theme(axis.text.x = element_text(angle=45, hjust=1))
# Set chart title and center it
DamageChart = DamageChart + ggtitle("Top 10 greatest economic consequences") + theme(plot.title = element_text(hjust = 0.5))
DamageChart
MAKING TRIPLE BAR GRAPH
#f)merging both and melting
#merging both
totalDamage<- merge(propdmgMax,cropdmgMax,by.x = "EVTYPE", by.y = "EVTYPE")
totalDamage$TOTALDMG <- totalDamage$PROPDMG + totalDamage$CROPDMG
totalDamage<-arrange(totalDamage,desc(TOTALDMG))
#totalDamage<-totalDamage[,c(totalDamage$EVTYPE,round(totalDamage$PROPDMG),round(totalDamage$CROPDMG),round(totalDamage$TOTALDMG))]
top_10_damages <- melt(totalDamage, id.vars="EVTYPE", variable.name = "Damage_Types")
tail(top_10_damages, 5)## EVTYPE Damage_Types value
## 20 HAIL TOTALDMG 1268289.7
## 21 FLOOD TOTALDMG 1067976.4
## 22 THUNDERSTORM WIND TOTALDMG 943635.6
## 23 THUNDERSTORM WINDS TOTALDMG 464978.1
## 24 HIGH WIND TOTALDMG 342014.8#g)ploting
# Create chart
DamageChart <- ggplot(top_10_damages, aes(x=reorder(EVTYPE, -value/1000), y=value/1000),fill=Damage_Types)
# Plot data as bar chart
DamageChart = DamageChart + geom_bar(stat="identity", aes(fill=Damage_Types), position="dodge")
# Set x-axis label
DamageChart = DamageChart + xlab("Event Type") + ylab("Cost of damage in $(billions)")
# Rotate x-axis tick labels
DamageChart = DamageChart + theme(axis.text.x = element_text(angle=45, hjust=1))
# Set chart title and center it
DamageChart = DamageChart + ggtitle("Top 10 greatest economic consequences") + theme(plot.title = element_text(hjust = 0.5))
DamageChart
Assignment
The basic goal of this assignment is to explore the NOAA Storm Database and answer some basic questions about severe weather events. Use of the NOAA Storm Database is to be used to address the questions below and I need to show the code for your entire analysis. The analysis can consist of tables, figures, or other summaries by using R to support the analysis.
Synopsis
The NOAA 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. This project looks at severe weather events can cause both public health and economic problems.
Questions: This data analysis must address the following questions :
- Question 1: Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health ?
- Question 2: Across the United States, which types of events have the greatest economic consequences ?
Results: Based on analysis of aggregate human and economic impacts seen with the data by storm event types :
- Findings on Question 1: Tornado’s by far cause the most fatalities and injuries, by far the most signifcant harm to public health.
- Excessive heat and flash flooding are second and third leading causes of fatalities.
- Tornados cause by far more human injuries. Thunderstorm related events (Wind, Lightning, Flooding) combine to be a signficant injury contributor as well.
- Findings on Question 2: Floods cause the most significant total damage (property and crop.)
- While property damage is most significant with flooding, Hurricanes/Typhoons, and Tornados, and Storm Surge are also strong contributors to property damage as well
- Crop damage occurs with flooding, but drought events are the most significant cause of economic harm crops. For crops flooding, ice storms, and hail are also noted contributors to economic harm.