#Synopsis By using the Storm Data provided by the U.S. National Oceanic and Atmospheric Administration’s database, analyses can be computed to determine the effect of the storms on health and economic factors. The most injuries and fatalities result from tornados. The weather event that costs the most in damages is from floods.
##Data Processing This code allows the data to be loaded into R.
setwd("~/Desktop/coursera")
data_all <- read.csv("~/Desktop/coursera/repdata-data-StormData.csv")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
healthpop <- aggregate(cbind(FATALITIES,INJURIES)~EVTYPE, data = data_all, sum, na.rm = TRUE)
healthpop <- arrange(healthpop, desc(FATALITIES+INJURIES))
healthpop <- healthpop[1:10,]
healthpop
## EVTYPE FATALITIES INJURIES
## 1 TORNADO 5633 91346
## 2 EXCESSIVE HEAT 1903 6525
## 3 TSTM WIND 504 6957
## 4 FLOOD 470 6789
## 5 LIGHTNING 816 5230
## 6 HEAT 937 2100
## 7 FLASH FLOOD 978 1777
## 8 ICE STORM 89 1975
## 9 THUNDERSTORM WIND 133 1488
## 10 WINTER STORM 206 1321
Results
barplot(t(healthpop[,-1]), names.arg=healthpop$EVTYPE, col = c("blue", "pink"), las=2, main="Harmful Storm Events")
legend("topright", c("INJURIES","FATALITIES"), fill=c("blue", "pink"))
Tornados have the highest number of injuries and fatalities of all types of storms.
DMG_data <- data_all[, c(8, 25:28)]
#H=100s, K=1000s, M=millions, B=billions
DMG_data<-DMG_data %>%
mutate(PROPDMG = PROPDMG *case_when(
PROPDMGEXP == "B" ~ 10^9,
PROPDMGEXP == "K" ~ 10^3,
PROPDMGEXP == "M" ~ 10^6,
PROPDMGEXP == "H" ~ 10^2,
TRUE ~ 0
), PROPDMGEXP=NULL
)
DMG_data<-DMG_data %>%
mutate(CROPDMG = CROPDMG *case_when(
CROPDMGEXP == "B" ~ 10^9,
CROPDMGEXP == "K" ~ 10^3,
CROPDMGEXP == "M" ~ 10^6,
CROPDMGEXP == "H" ~ 10^2,
TRUE ~ 0
), CROPDMGEXP=NULL
)
PROP_CROP <- aggregate(cbind(PROPDMG,CROPDMG) ~ EVTYPE, data_all, sum, na.rm = TRUE)
PROP_CROP <- arrange(PROP_CROP, desc(PROPDMG+CROPDMG))
PROP_CROP <- PROP_CROP[1:10, ]
PROP_CROP$PROPDMG <- PROP_CROP$PROPDMG/10^9
PROP_CROP$CROPDMG <- PROP_CROP$CROPDMG/10^9
PROP_CROP
## EVTYPE PROPDMG CROPDMG
## 1 TORNADO 0.0032122582 1.000185e-04
## 2 FLASH FLOOD 0.0014201246 1.792005e-04
## 3 TSTM WIND 0.0013359656 1.092026e-04
## 4 HAIL 0.0006886934 5.795963e-04
## 5 FLOOD 0.0008999385 1.680379e-04
## 6 THUNDERSTORM WIND 0.0008768442 6.679145e-05
## 7 LIGHTNING 0.0006033518 3.580610e-06
## 8 THUNDERSTORM WINDS 0.0004462932 1.868493e-05
## 9 HIGH WIND 0.0003247316 1.728321e-05
## 10 WINTER STORM 0.0001327206 1.978990e-06
PROP_CROP_PLOT <- barplot(t(PROP_CROP[,-1]), names.arg = PROP_CROP$EVTYPE, col = c("blue", "pink"), las=2, main = "Economic Damage From Storms")
legend("topright", c("PROPERY DMG", "CROP DMG"), fill = c("blue", "pink"))
Similar to the Harmful Storm Events, tornados have the highest overall economic damage with property and crop damage costing the most amount of money.