project

knitr::opts_chunk$set(echo = TRUE, warning = FALSE, message = FALSE)
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(tidyr)
library(ggplot2)

url  <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
file <- "repdata_data_StormData.csv.bz2"
if (!file.exists(file)) download.file(url, file, mode = "wb")

storm <- read.csv(file, stringsAsFactors = FALSE)
dim(storm)

## [1] 902297     37

storm <- storm %>%
  select(EVTYPE, FATALITIES, INJURIES,
         PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP)

exp_map <- c("H" = 1e2, "K" = 1e3, "M" = 1e6, "B" = 1e9,
             setNames(10^(0:8), as.character(0:8)))

convert_exp <- function(x) {
  m <- exp_map[toupper(trimws(as.character(x)))]
  m[is.na(m)] <- 1          # simbol tak dikenal/kosong -> pengali 1
  as.numeric(m)
}

storm <- storm %>%
  mutate(PROP_USD = PROPDMG * convert_exp(PROPDMGEXP),
         CROP_USD = CROPDMG * convert_exp(CROPDMGEXP))

storm <- storm %>%
  mutate(EVTYPE = toupper(trimws(EVTYPE)),
         EVENT = case_when(
           grepl("TSTM|THUNDERSTORM", EVTYPE)      ~ "THUNDERSTORM WIND",
           grepl("TORNADO", EVTYPE)                ~ "TORNADO",
           grepl("FLASH FLOOD", EVTYPE)            ~ "FLASH FLOOD",
           grepl("FLOOD", EVTYPE)                  ~ "FLOOD",
           grepl("HURRICANE|TYPHOON", EVTYPE)      ~ "HURRICANE/TYPHOON",
           grepl("HEAT", EVTYPE)                   ~ "HEAT",
           grepl("WILD.*FIRE", EVTYPE)             ~ "WILDFIRE",
           grepl("STORM SURGE", EVTYPE)            ~ "STORM SURGE",
           grepl("^HAIL", EVTYPE)                  ~ "HAIL",
           grepl("LIGHTNING", EVTYPE)              ~ "LIGHTNING",
           grepl("RIP CURRENT", EVTYPE)            ~ "RIP CURRENT",
           grepl("WINTER STORM", EVTYPE)           ~ "WINTER STORM",
           grepl("BLIZZARD", EVTYPE)               ~ "BLIZZARD",
           TRUE                                    ~ EVTYPE))

health <- storm %>%
  group_by(EVENT) %>%
  summarise(Fatalities = sum(FATALITIES),
            Injuries   = sum(INJURIES),
            Total      = Fatalities + Injuries) %>%
  arrange(desc(Total)) %>%
  slice_head(n = 10)
health

## # A tibble: 10 × 4
##    EVENT             Fatalities Injuries Total
##    <chr>                  <dbl>    <dbl> <dbl>
##  1 TORNADO                 5636    91407 97043
##  2 HEAT                    3138     9224 12362
##  3 THUNDERSTORM WIND        754     9544 10298
##  4 FLOOD                    490     6802  7292
##  5 LIGHTNING                817     5231  6048
##  6 FLASH FLOOD             1035     1802  2837
##  7 ICE STORM                 89     1975  2064
##  8 WILDFIRE                  90     1606  1696
##  9 WINTER STORM             217     1353  1570
## 10 HURRICANE/TYPHOON        135     1333  1468

health_long <- health %>%
  select(EVENT, Fatalities, Injuries) %>%
  pivot_longer(-EVENT, names_to = "Type", values_to = "Count")

ggplot(health_long, aes(x = reorder(EVENT, Count), y = Count, fill = Type)) +
  geom_col(show.legend = FALSE) +
  coord_flip() +
  facet_wrap(~ Type, scales = "free_x") +
  labs(x = "Event type", y = "Total count",
       title = "Most Harmful Events to Population Health")

Figure 1: Top 10 weather events by total fatalities and injuries in the U.S. (1950-2011). Left panel shows fatalities, right panel shows injuries.

econ <- storm %>%
  group_by(EVENT) %>%
  summarise(Property = sum(PROP_USD) / 1e9,
            Crop     = sum(CROP_USD) / 1e9,
            Total    = Property + Crop) %>%
  arrange(desc(Total)) %>%
  slice_head(n = 10)
econ

## # A tibble: 10 × 4
##    EVENT             Property      Crop  Total
##    <chr>                <dbl>     <dbl>  <dbl>
##  1 FLOOD               151.   10.8      161.  
##  2 HURRICANE/TYPHOON    85.4   5.52      90.9 
##  3 TORNADO              57.0   0.415     57.4 
##  4 STORM SURGE          48.0   0.000855  48.0 
##  5 FLASH FLOOD          17.6   1.53      19.1 
##  6 HAIL                 16.0   3.03      19.0 
##  7 DROUGHT               1.05 14.0       15.0 
##  8 THUNDERSTORM WIND    12.8   1.27      14.1 
##  9 ICE STORM             3.94  5.02       8.97
## 10 WILDFIRE              8.49  0.403      8.89

econ_long <- econ %>%
  select(EVENT, Property, Crop) %>%
  pivot_longer(-EVENT, names_to = "Damage", values_to = "Billions")

ggplot(econ_long, aes(x = reorder(EVENT, Billions, sum), y = Billions, fill = Damage)) +
  geom_col() +
  coord_flip() +
  labs(x = "Event type", y = "Damage (billion USD)",
       title = "Events with the Greatest Economic Consequences")

Figure 2: Top 10 weather events by total economic damage (billions USD), split into property and crop damage, 1950-2011.

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)

##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.

project

Moses Walker Sitorus

2026-10-27

R Markdown

Including Plots