Reproducible Research Course Project 2
Mohamed Elashri
4/5/2020
Synopsis
To explore the NOAA Storm Database and answer some basic questions about severe weather events. This report explores U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database (1950-2011). We identify top 20 events which had the most harmful effects on human population and also pin point top 20 events leading to greatest economic consequences.
Data Processing
first let us import the important packages that we are going to use in this analysis
library(plyr)
library(ggplot2)
library(scales)Loading the data
let us read the storm data and store it in data frame format.
data <- bzfile("repdata_data_StormData.csv.bz2")
sd <- read.csv(data)
dim(sd)## [1] 902297 37Let us now check data labels
names(sd)## [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"clean/process the data
now let us subset our data
data_1 <- sd[,c(8, 23, 24)]
data_1[,1] <- as.character(data_1[,1])
aggdata <- aggregate(data_1[,2:3], by=list(data_1$EVTYPE), FUN=sum, na.rm=T)
names(aggdata)[1] <- "EVTYPE"
od <- aggdata[order(-aggdata[,2], -aggdata[,3]), ]
head(od, n=10)## EVTYPE FATALITIES INJURIES
## 834 TORNADO 5633 91346
## 130 EXCESSIVE HEAT 1903 6525
## 153 FLASH FLOOD 978 1777
## 275 HEAT 937 2100
## 464 LIGHTNING 816 5230
## 856 TSTM WIND 504 6957
## 170 FLOOD 470 6789
## 585 RIP CURRENT 368 232
## 359 HIGH WIND 248 1137
## 19 AVALANCHE 224 170Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
now we Plot the top 20 events responsible for human fatalities
od <- aggdata[order(-aggdata[,2]), ]
names(od)[1] <- "EVTYPE"
topf <- head(od, n=20)
ggplot(data=topf, aes(x=EVTYPE, y=log10(FATALITIES))) + geom_bar(stat = "identity", fill="#140303", colour="black") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + ggtitle("Top 20 US Events causing FATALITIES") + labs(y=expression(log[10](FATALITIES)), x="US NOAA Event Type") 
now let us Plot the top 20 events responsible for human injuries
od <- aggdata[order(-aggdata[,3]), ]
names(od)[1] <- "EVTYPE"
topi <- head(od, n=20)ggplot(data=topi, aes(x=EVTYPE, y=log10(INJURIES))) + geom_bar(stat = "identity", fill="#140303", colour="black") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + ggtitle("Top 20 US NOAA Events causing INJURIES") + labs(y=expression(log[10](INJURIES)), x="US NOAA Event Type") 
Top Events that causes the maximum harm to the human population health are:
intersect(topf[,1], topi[,1])## [1] "TORNADO" "EXCESSIVE HEAT" "FLASH FLOOD"
## [4] "HEAT" "LIGHTNING" "TSTM WIND"
## [7] "FLOOD" "HIGH WIND" "WINTER STORM"
## [10] "THUNDERSTORM WIND" "HEAVY SNOW" "BLIZZARD"Across the United States, which types of events have the greatest economic consequences?
first let us get the new subset
new <- sd[,c(8,25,26,27,28)]let us now extract the unique exponents in property damage and crop damage
unique((new[,3]))## [1] K M B m + 0 5 6 ? 4 2 3 h 7 H - 1 8
## Levels: - ? + 0 1 2 3 4 5 6 7 8 B h H K m Mnow lets do the exponents conversion
new[,3] <- toupper(new[,3])
new[,5] <- toupper(new[,5])expval <- function(x, exp = "") {
switch(exp, `-` = x * -1, `?` = x, `+` = x, `1` = x, `2` = x * (10^2), `3` = x *
(10^3), `4` = x * (10^4), `5` = x * (10^5), `6` = x * (10^6), `7` = x *
(10^7), `8` = x * (10^8), H = x * 100, K = x * 1000, M = x * 1e+06,
B = x * 1e+09, x)
}
any <- aggregate(new[,c(2,4)], by=list(new$EVTYPE, new$PROPDMGEXP, new$CROPDMGEXP), FUN=sum, na.rm=T)
## lets remove rows with 0 values
nan = any[apply(any[c(4,5)], 1, function(row) any(row != 0 )), ]Now if we have an event, we want to calculate total dollar it will cost with combining both crob and property damage it causes
nr <- nrow(nan)
total <- numeric()
for (i in 1:nr) {
val <- expval(nan[i,4], nan[i,2])
val <- val + expval(nan[i,5], nan[i,3])
total <- append(total, val)
}
length(total)## [1] 874now lets get those events
head(total)## [1] 132 4 7 54 10 3check this events ID in our original data
nan$TOTALDMG <- total
names(nan)[1] <- "EVTYPE"
head(nan)## EVTYPE Group.2 Group.3 PROPDMG CROPDMG TOTALDMG
## 131 FLASH FLOOD 132 0 132
## 135 FLASH FLOODING 4 0 4
## 139 FLOOD 7 0 7
## 195 HAIL 54 0 54
## 253 HEAVY SNOW SQUALLS 10 0 10
## 294 HIGH WINDS 3 0 3let us analysis the unique events based on their damage
damage <- aggregate(nan$TOTALDMG, by=list(nan$EVTYPE), FUN=sum, na.rm=T)
names(damage) <- c("EVTYPE", "TOTALDMG")
head(damage)## EVTYPE TOTALDMG
## 1 HIGH SURF ADVISORY 200000
## 2 FLASH FLOOD 50000
## 3 TSTM WIND 8100000
## 4 TSTM WIND (G45) 8000
## 5 ? 5000
## 6 AGRICULTURAL FREEZE 28820000make them in order
damage <- damage[order(-damage[,2]), ]
head(damage)## EVTYPE TOTALDMG
## 72 FLOOD 150319678257
## 197 HURRICANE/TYPHOON 71913712800
## 354 TORNADO 57362333947
## 299 STORM SURGE 43323541000
## 116 HAIL 18761221986
## 59 FLASH FLOOD 18243991079now we plot the top 20 events that causes maximum damage to economic
plot <- head(damage, n=20)
ggplot(data=plot, aes(x=EVTYPE, y=TOTALDMG/1e+9)) + geom_bar(stat = "identity", fill="#140303", colour="black") + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + ggtitle("Top 20 US NOAA Events in economical damage") + labs(y="Economic Damage ", x=" Event Type")
Results
From the plots we can use them to answer our two question in a direct way.
- what are the top Events causing harm to human population health ?
intersect(topf[,1], topi[,1])## [1] "TORNADO" "EXCESSIVE HEAT" "FLASH FLOOD"
## [4] "HEAT" "LIGHTNING" "TSTM WIND"
## [7] "FLOOD" "HIGH WIND" "WINTER STORM"
## [10] "THUNDERSTORM WIND" "HEAVY SNOW" "BLIZZARD"- what are the top Events causing damage in terms of economic value ?
head(damage, n=20L)## EVTYPE TOTALDMG
## 72 FLOOD 150319678257
## 197 HURRICANE/TYPHOON 71913712800
## 354 TORNADO 57362333947
## 299 STORM SURGE 43323541000
## 116 HAIL 18761221986
## 59 FLASH FLOOD 18243991079
## 39 DROUGHT 15018672000
## 189 HURRICANE 14610229010
## 262 RIVER FLOOD 10148404500
## 206 ICE STORM 8967041360
## 363 TROPICAL STORM 8382236550
## 424 WINTER STORM 6715441251
## 174 HIGH WIND 5908617565
## 414 WILDFIRE 5060586800
## 369 TSTM WIND 5038935845
## 300 STORM SURGE/TIDE 4642038000
## 313 THUNDERSTORM WIND 3897965522
## 195 HURRICANE OPAL 3191846000
## 412 WILD/FOREST FIRE 3108626330
## 142 HEAVY RAIN/SEVERE WEATHER 2500000000We can see that the Tornado events are the most dangerous on human life and flood is the most dangerous in terms on economic value loss.