Damage from severe weather in US
Synopsis
This project explores the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. The data was directly downloaded from the link using r, and analyzed with library “dplyr”, “tidyr”, “data.table”, “mgsu”, and ploted with ggplot2. The plots showed that tornado caused the most harm to people’s health, and floods caused the most economic loss in US from 1950 to November of 2011.
Data Processing
- Load libraries
knitr::opts_chunk$set(echo = TRUE)
library(data.table)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:data.table':
##
## between, first, last## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ggplot2)- Download file and read file, check dim and head
destfile <- "storm.csv.bz2"
if(!file.exists(destfile)){
setInternet2(TRUE)
download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2", destfile, "curl")
load("storm.csv.bz2")
}
storm <- fread("storm.csv.bz2")
dim(storm)## [1] 902297 37head(storm, 2)## STATE__ BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE EVTYPE
## 1: 1 4/18/1950 0:00:00 0130 CST 97 MOBILE AL TORNADO
## 2: 1 4/18/1950 0:00:00 0145 CST 3 BALDWIN AL TORNADO
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END COUNTYENDN
## 1: 0 0 NA
## 2: 0 0 NA
## END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES INJURIES PROPDMG
## 1: 0 14 100 3 0 0 15 25.0
## 2: 0 2 150 2 0 0 0 2.5
## PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES LATITUDE LONGITUDE
## 1: K 0 3040 8812
## 2: K 0 3042 8755
## LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1: 3051 8806 1
## 2: 0 0 2Results
Analyze events that caused most population health damage
- Subset Health Damage data, and check NA values
health_damage <- storm %>% select(EVTYPE, FATALITIES, INJURIES)
dim(health_damage)## [1] 902297 3sum(is.na(health_damage$FATALITIES))## [1] 0sum(is.na(health_damage$INJURIES))## [1] 0- Combine Fatalities and injuries number, and sorting desc to get top 5 high events
health_damage_sum <- health_damage %>% group_by(EVTYPE) %>% summarize(totalF = sum(FATALITIES), totalI = sum(INJURIES), total = sum(FATALITIES + INJURIES)) %>% arrange(desc(total))## `summarise()` ungrouping output (override with `.groups` argument)dim(health_damage_sum)## [1] 985 4health_damage_sum_top5 <- head(health_damage_sum, 5)- Plot with ggplot bargraph
ggplot(data = health_damage_sum_top5, aes(x = reorder(EVTYPE, - total), y = total, fill = interaction(total, EVTYPE))) +
geom_bar(stat = "identity") + labs(title = "Top 5 Severe Weather Envents Harming Population Health in US", x = "Events", y = "No. of death and injuries") + theme(legend.position = "none") +
theme(plot.title = element_text(hjust = 0.5))
Analyze events that casued most economic damage
- Subset Economic Damage Data
economic_damage <- storm %>% select(EVTYPE, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)
sum(is.na(economic_damage$PROPDMG))## [1] 0sum(is.na(economic_damage$PROPDMGEXP))## [1] 0sum(is.na(economic_damage$CROPDMG))## [1] 0sum(is.na(economic_damage$CROPDMGEXP))## [1] 0dim(economic_damage)## [1] 902297 5head(economic_damage)## EVTYPE PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## 1: TORNADO 25.0 K 0
## 2: TORNADO 2.5 K 0
## 3: TORNADO 25.0 K 0
## 4: TORNADO 2.5 K 0
## 5: TORNADO 2.5 K 0
## 6: TORNADO 2.5 K 0- Convert damage value to numeric for calculation
library(mgsub)
economic_damage$PROPDMGEXP <- mgsub(economic_damage$PROPDMGEXP, c("K", "M", "B"), c("1000", "1e+06", "1e+09"))
economic_damage$CROPDMGEXP <- mgsub(economic_damage$CROPDMGEXP, c("K", "M", "B"), c("1000", "1e+06", "1e+09"))
economic_damage$PROPDMGEXP <- as.numeric(economic_damage$PROPDMGEXP)## Warning: NAs introduced by coercioneconomic_damage$CROPDMGEXP <- as.numeric(economic_damage$CROPDMGEXP)## Warning: NAs introduced by coercionstr(economic_damage)## Classes 'data.table' and 'data.frame': 902297 obs. of 5 variables:
## $ EVTYPE : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ PROPDMGEXP: num 1000 1000 1000 1000 1000 1000 1000 1000 1000 1000 ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: num NA NA NA NA NA NA NA NA NA NA ...
## - attr(*, ".internal.selfref")=<externalptr>- Calculate economic damage value
library(tidyr)
economic_damage <- mutate_all(economic_damage, ~replace_na(., 0))
economic_damage <- economic_damage %>% mutate(Damage_value = PROPDMG * PROPDMGEXP + CROPDMG * CROPDMGEXP)
head(economic_damage)## EVTYPE PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP Damage_value
## 1: TORNADO 25.0 1000 0 0 25000
## 2: TORNADO 2.5 1000 0 0 2500
## 3: TORNADO 25.0 1000 0 0 25000
## 4: TORNADO 2.5 1000 0 0 2500
## 5: TORNADO 2.5 1000 0 0 2500
## 6: TORNADO 2.5 1000 0 0 2500economic_damage_top5 <- economic_damage %>% group_by(EVTYPE) %>% summarise(E_D_value = sum(Damage_value)) %>% arrange(desc(E_D_value)) %>% head(5)## `summarise()` ungrouping output (override with `.groups` argument)str(economic_damage_top5)## tibble [5 x 2] (S3: tbl_df/tbl/data.frame)
## $ EVTYPE : chr [1:5] "FLOOD" "HURRICANE/TYPHOON" "TORNADO" "STORM SURGE" ...
## $ E_D_value: num [1:5] 1.50e+11 7.19e+10 5.73e+10 4.33e+10 1.88e+10head(economic_damage_top5)## # A tibble: 5 x 2
## EVTYPE E_D_value
## <chr> <dbl>
## 1 FLOOD 150319678250
## 2 HURRICANE/TYPHOON 71913712800
## 3 TORNADO 57340614101
## 4 STORM SURGE 43323541000
## 5 HAIL 18752904320- plot with ggplot bargraph
ggplot(data = economic_damage_top5, aes(x = reorder(EVTYPE, -E_D_value), y = E_D_value, fill = interaction(E_D_value, EVTYPE))) +
geom_bar(stat = "identity") + labs(title = "Top 5 Severe Weather Envents Harming Economics in US", x = "Events", y = "Economic Damage Value") + theme(legend.position = "none") +
theme(plot.title = element_text(hjust = 0.5))