storm_data_analysis
R Markdown
#Code for reading in the dataset and/or processing the data
# Download the compressed file
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2",
"C:/Users/vidus/Downloads/repdata_data_StormData.csv.bz2")
# Read the compressed CSV file
con <- bzfile("C:/Users/vidus/Downloads/repdata_data_StormData.csv.bz2", "r")
dataset <- read.csv(con)
close(con)
# Inspect the data frame
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#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