Synopsis

This report explores the NOAA Storm Database to determine the impact of severe weather events on public health and the economy in the United States. The analysis identifies the top event types causing the most fatalities, injuries, and economic damage.

Data Processing

# 加载必要的包
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)
library(readr)

# 下载数据
file_url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(file_url, destfile = "StormData.csv.bz2", method = "curl")

# 读取数据
storm_data <- read_csv("StormData.csv.bz2")
## Rows: 902297 Columns: 37
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (18): BGN_DATE, BGN_TIME, TIME_ZONE, COUNTYNAME, STATE, EVTYPE, BGN_AZI,...
## dbl (18): STATE__, COUNTY, BGN_RANGE, COUNTY_END, END_RANGE, LENGTH, WIDTH, ...
## lgl  (1): COUNTYENDN
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
# 查看数据结构
str(storm_data)
## spc_tbl_ [902,297 × 37] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
##  $ STATE__   : num [1:902297] 1 1 1 1 1 1 1 1 1 1 ...
##  $ BGN_DATE  : chr [1:902297] "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 [1:902297] "0130" "0145" "1600" "0900" ...
##  $ TIME_ZONE : chr [1:902297] "CST" "CST" "CST" "CST" ...
##  $ COUNTY    : num [1:902297] 97 3 57 89 43 77 9 123 125 57 ...
##  $ COUNTYNAME: chr [1:902297] "MOBILE" "BALDWIN" "FAYETTE" "MADISON" ...
##  $ STATE     : chr [1:902297] "AL" "AL" "AL" "AL" ...
##  $ EVTYPE    : chr [1:902297] "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
##  $ BGN_RANGE : num [1:902297] 0 0 0 0 0 0 0 0 0 0 ...
##  $ BGN_AZI   : chr [1:902297] NA NA NA NA ...
##  $ BGN_LOCATI: chr [1:902297] NA NA NA NA ...
##  $ END_DATE  : chr [1:902297] NA NA NA NA ...
##  $ END_TIME  : chr [1:902297] NA NA NA NA ...
##  $ COUNTY_END: num [1:902297] 0 0 0 0 0 0 0 0 0 0 ...
##  $ COUNTYENDN: logi [1:902297] NA NA NA NA NA NA ...
##  $ END_RANGE : num [1:902297] 0 0 0 0 0 0 0 0 0 0 ...
##  $ END_AZI   : chr [1:902297] NA NA NA NA ...
##  $ END_LOCATI: chr [1:902297] NA NA NA NA ...
##  $ LENGTH    : num [1:902297] 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
##  $ WIDTH     : num [1:902297] 100 150 123 100 150 177 33 33 100 100 ...
##  $ F         : num [1:902297] 3 2 2 2 2 2 2 1 3 3 ...
##  $ MAG       : num [1:902297] 0 0 0 0 0 0 0 0 0 0 ...
##  $ FATALITIES: num [1:902297] 0 0 0 0 0 0 0 0 1 0 ...
##  $ INJURIES  : num [1:902297] 15 0 2 2 2 6 1 0 14 0 ...
##  $ PROPDMG   : num [1:902297] 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
##  $ PROPDMGEXP: chr [1:902297] "K" "K" "K" "K" ...
##  $ CROPDMG   : num [1:902297] 0 0 0 0 0 0 0 0 0 0 ...
##  $ CROPDMGEXP: chr [1:902297] NA NA NA NA ...
##  $ WFO       : chr [1:902297] NA NA NA NA ...
##  $ STATEOFFIC: chr [1:902297] NA NA NA NA ...
##  $ ZONENAMES : chr [1:902297] NA NA NA NA ...
##  $ LATITUDE  : num [1:902297] 3040 3042 3340 3458 3412 ...
##  $ LONGITUDE : num [1:902297] 8812 8755 8742 8626 8642 ...
##  $ LATITUDE_E: num [1:902297] 3051 0 0 0 0 ...
##  $ LONGITUDE_: num [1:902297] 8806 0 0 0 0 ...
##  $ REMARKS   : chr [1:902297] NA NA NA NA ...
##  $ REFNUM    : num [1:902297] 1 2 3 4 5 6 7 8 9 10 ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   STATE__ = col_double(),
##   ..   BGN_DATE = col_character(),
##   ..   BGN_TIME = col_character(),
##   ..   TIME_ZONE = col_character(),
##   ..   COUNTY = col_double(),
##   ..   COUNTYNAME = col_character(),
##   ..   STATE = col_character(),
##   ..   EVTYPE = col_character(),
##   ..   BGN_RANGE = col_double(),
##   ..   BGN_AZI = col_character(),
##   ..   BGN_LOCATI = col_character(),
##   ..   END_DATE = col_character(),
##   ..   END_TIME = col_character(),
##   ..   COUNTY_END = col_double(),
##   ..   COUNTYENDN = col_logical(),
##   ..   END_RANGE = col_double(),
##   ..   END_AZI = col_character(),
##   ..   END_LOCATI = col_character(),
##   ..   LENGTH = col_double(),
##   ..   WIDTH = col_double(),
##   ..   F = col_double(),
##   ..   MAG = col_double(),
##   ..   FATALITIES = col_double(),
##   ..   INJURIES = col_double(),
##   ..   PROPDMG = col_double(),
##   ..   PROPDMGEXP = col_character(),
##   ..   CROPDMG = col_double(),
##   ..   CROPDMGEXP = col_character(),
##   ..   WFO = col_character(),
##   ..   STATEOFFIC = col_character(),
##   ..   ZONENAMES = col_character(),
##   ..   LATITUDE = col_double(),
##   ..   LONGITUDE = col_double(),
##   ..   LATITUDE_E = col_double(),
##   ..   LONGITUDE_ = col_double(),
##   ..   REMARKS = col_character(),
##   ..   REFNUM = col_double()
##   .. )
##  - attr(*, "problems")=<externalptr>
# 数据处理：计算每种事件类型对人口健康的影响
health_impact <- storm_data %>%
  group_by(EVTYPE) %>%
  summarise(
    fatalities = sum(FATALITIES, na.rm = TRUE),
    injuries = sum(INJURIES, na.rm = TRUE)
  ) %>%
  arrange(desc(fatalities))

# 打印前几种最有影响的事件
print(head(health_impact))
## # A tibble: 6 × 3
##   EVTYPE         fatalities injuries
##   <chr>               <dbl>    <dbl>
## 1 TORNADO              5633    91346
## 2 EXCESSIVE HEAT       1903     6525
## 3 FLASH FLOOD           978     1777
## 4 HEAT                  937     2100
## 5 LIGHTNING             816     5230
## 6 TSTM WIND             504     6957
# 绘制图形：前10种导致最多死亡的事件
ggplot(head(health_impact, 10), aes(x = reorder(EVTYPE, -fatalities), y = fatalities)) +
  geom_bar(stat = "identity", fill = "red") +
  coord_flip() +
  labs(title = "Top 10 Events Causing Fatalities", x = "Event Type", y = "Fatalities")