Reproducible Research Course Project 2 – Severe Weather Analysis based on NOAA Storm Database
Yihao Yang
7/19/2020
Synopsis
This document is for the Coursera course: Reproducible Research Project 2.
After setting up the R environments and loading raw data, some data preprocessing was done for later exploitative plotting. And then two questions was addressed via plotting:
- Across the United States, which types of events are most harmful with respect to population health?
- Across the United States, which types of events have the greatest economic consequences?
Data Processing
Loading libraries.
library(dplyr)
library(stringr)
library(ggplot2)
library(reshape2)Read raw CSV file containing the data into the cache and examine the data.
data <- read.csv("repdata_data_StormData.csv.bz2")
str(data)## '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 ...Cleaning up the data$EVTYPE
- List the most common events
data$EVTYPE <- str_to_lower(data$EVTYPE)
word_counts <- table(str_to_lower(data$EVTYPE))
word_counts <- sort(word_counts,decreasing = TRUE)
head(word_counts,n=50)##
## hail tstm wind thunderstorm wind
## 288661 219942 82564
## tornado flash flood flood
## 60652 54277 25327
## thunderstorm winds high wind lightning
## 20843 20214 15754
## heavy snow heavy rain winter storm
## 15708 11742 11433
## winter weather funnel cloud marine tstm wind
## 7045 6844 6175
## marine thunderstorm wind waterspout strong wind
## 5812 3796 3569
## urban/sml stream fld wildfire blizzard
## 3392 2761 2719
## drought ice storm excessive heat
## 2488 2006 1678
## high winds wild/forest fire frost/freeze
## 1533 1457 1343
## dense fog winter weather/mix tstm wind/hail
## 1293 1104 1028
## extreme cold/wind chill heat high surf
## 1002 767 734
## tropical storm flash flooding extreme cold
## 690 682 657
## coastal flood lake-effect snow flood/flash flood
## 656 636 625
## snow landslide cold/wind chill
## 617 600 539
## fog rip current marine hail
## 538 470 442
## dust storm avalanche wind
## 427 386 346
## rip currents storm surge
## 304 261- Tidy up
data$EVTYPE
common_envs = c("hail","wind","tornado","flood","lightning","snow","rain","storm")
envtype_backup <- data$EVTYPE
data$EVTYPE <- "other"
for (env in common_envs){
data$EVTYPE[str_detect(envtype_backup,paste0("(",env,")"))] <- env
}
table(data$EVTYPE)##
## flood hail lightning other rain snow storm tornado
## 82690 289270 15762 44018 12238 17639 124624 60700
## wind
## 255356Data processing for exploring severe weather’s effect on population health.
data.health <- select(data,EVTYPE,FATALITIES,INJURIES)
data.health.sum <- summarise(group_by(data.health,EVTYPE),
FATALITIES = sum(FATALITIES,na.rm = TRUE),
INJURIES = sum(INJURIES,na.rm = TRUE))
data.health.sum <- melt(data.health.sum,id.vars = "EVTYPE")Data processing for exploring severe weather’s effect on economy.
data$PROPDMGEXP <- str_to_lower(data$PROPDMGEXP)
data$CROPDMGEXP <- str_to_lower(data$CROPDMGEXP)
table(data$PROPDMGEXP)##
## - ? + 0 1 2 3 4 5 6
## 465934 1 8 5 216 25 13 4 4 28 4
## 7 8 b h k m
## 5 1 40 7 424665 11337table(data$CROPDMGEXP)##
## ? 0 2 b k m
## 618413 7 19 1 9 281853 1995Ignore messy labels except k,m,b
data.econ <- select(data,EVTYPE,PROPDMG,CROPDMG)
mgexps <- c("k"=3,"m"=6,"b"=9)
for (mgexp in names(mgexps)){
idx_prop <- (data$PROPDMGEXP == mgexp)
idx_crop <- (data$CROPDMGEXP == mgexp)
data.econ$PROPDMG[idx_prop] <- data.econ$PROPDMG[idx_prop] * (10^mgexps[[mgexp]])
data.econ$CROPDMG[idx_crop] <- data.econ$CROPDMG[idx_crop] * (10^mgexps[[mgexp]])
}
data.econ <- melt(data.econ,id.vars = "EVTYPE")
head(data.econ)## EVTYPE variable value
## 1 tornado PROPDMG 25000
## 2 tornado PROPDMG 2500
## 3 tornado PROPDMG 25000
## 4 tornado PROPDMG 2500
## 5 tornado PROPDMG 2500
## 6 tornado PROPDMG 2500Results
Across the United States, which types of events are most harmful with respect to population health?
According to following graph, tornado is the most harmful type of events with respect to population health.
ggplot(data = data.health.sum,aes(x=EVTYPE,y=value,fill=variable)) +
geom_bar(stat="identity") +
xlab("event type") + ylab("total number of casualties") +
ggtitle("Total Casualties by Different Severe Weathers")
Across the United States, which types of events have the greatest economic consequences?
According to the following graph, flood has the greatest economic consequences.
ggplot(data=data.econ,aes(x=EVTYPE,y=value,fill=variable)) +
geom_bar(stat="identity") + xlab("event type") + ylab("damage value") +
ggtitle("Severe Weather Damage on Properties(PROPDMG) and Crops(CROPDMG)")