Storm Data Analysis for Peer-graded Assignment
Caitlin
2022-12-25
Background of this analysis
This is data analysis regarding how stroms and other severe weather events can cause both public health and economic problems. The dataset used in this analysis is fromm the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database, covering data from 1950 to November 2011.
library(ggplot2)
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, unionlibrary(tidyr)
# load data and have an overview
url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(url, "stormdata.csv.bz2")
df_storm <- read.csv("stormdata.csv.bz2")
str(df_storm)## '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 ...head(df_storm)## 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 6Data processing
You can also embed plots, for example:
sum(is.na(df_storm$EVTYPE))## [1] 0sum(is.na(df_storm$STATE))## [1] 0sum(is.na(df_storm$FATALITIES))## [1] 0sum(is.na(df_storm$INJURIES))## [1] 0sum(is.na(df_storm))## [1] 1745947df_storm1 <- df_storm %>% select(c("EVTYPE","FATALITIES","INJURIES","PROPDMG","PROPDMGEXP","CROPDMG","CROPDMGEXP")) %>% rename_all(tolower)
str(df_storm1 )## 'data.frame': 902297 obs. of 7 variables:
## $ evtype : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ 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 "" "" "" "" ...df_health <- df_storm1 %>% select(evtype, fatalities, injuries) %>% group_by(evtype) %>% summarize(fatalities = sum(fatalities), injuries = sum(injuries)) %>% arrange(desc(fatalities),desc(injuries)) %>% slice(1:10) %>% gather(key = type, value = value, fatalities, injuries)
str(df_health)## tibble [20 × 3] (S3: tbl_df/tbl/data.frame)
## $ evtype: chr [1:20] "TORNADO" "EXCESSIVE HEAT" "FLASH FLOOD" "HEAT" ...
## $ type : chr [1:20] "fatalities" "fatalities" "fatalities" "fatalities" ...
## $ value : num [1:20] 5633 1903 978 937 816 ...unique(df_storm1$propdmgexp)## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "?" "4" "2" "3" "h" "7" "H" "-" "1" "8"unique(df_storm1$cropdmgexp)## [1] "" "M" "K" "m" "B" "?" "0" "k" "2"cost <- function(x) {
if (x == "H")
1E-4
else if (x == "K")
1E-3
else if (x == "M")
1
else if (x == "B")
1E3
else
1-6
}
df_economic <- df_storm1 %>% select(evtype, propdmg, propdmgexp, cropdmg,cropdmgexp) %>%
mutate(prop_dmg = propdmg*sapply(propdmgexp, FUN = cost), crop_dmg = cropdmg*sapply(cropdmgexp, FUN = cost),.keep = "unused") %>% group_by(evtype) %>% summarize(property = sum(prop_dmg), crop = sum(crop_dmg), .groups='drop') %>% arrange(desc(property), desc(crop)) %>% slice(1:10) %>% gather(key = type, value = value, property, crop)
str(df_economic)## tibble [20 × 3] (S3: tbl_df/tbl/data.frame)
## $ evtype: chr [1:20] "FLOOD" "HURRICANE/TYPHOON" "TORNADO" "STORM SURGE" ...
## $ type : chr [1:20] "property" "property" "property" "property" ...
## $ value : num [1:20] 144623 69306 55375 43324 14089 ...Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the plot. ##
Plot the results to answer below two questions
1.Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
2.Across the United States, which types of events have the greatest economic consequences?
ggplot(data = df_health, aes(reorder(evtype, -value), value, fill = type))+
geom_bar(position = "dodge", stat = "identity") +
labs(x = "Event Type", y = "Count")+ theme_bw() +
theme(axis.text.x = element_text(angle = 20, vjust = 0.7)) +
ggtitle("Total Number of Fatalities and Injuries of top 10 storm event types") +
scale_fill_manual(values = c("purple", "blue"))
ggplot(data=df_economic, aes(reorder(evtype, -value), value, fill=type)) +
geom_bar(position = "dodge", stat="identity") +
labs(x="Event Type", y="Count (millions)") +
theme_bw() +
theme(axis.text.x = element_text(angle = 25, vjust=0.5)) +
ggtitle("Total Cost of Property and Crop Damage by top 10 storm event types") +
scale_fill_manual(values=c("darkgreen", "grey"))
Conclusion
To sum up, tornado is the most impactful event to human health. More resources should be arranged to prevent tornado to guarantee the public health. Flood and hurricane/typhoon cause the most damage to economy espesially for property. The government should better system and infrastructure to protect property and crop.