Reproducible Research Project 2

Synopsis

This project analyzes the U.S. National Oceanic and Atmospheric Administration (NOAA) storm database to identify the most harmful weather events in terms of population health and economic consequences.

Data Processing

# Load data
data <- read.csv("Reproducible Research/repdata_data_StormData1.csv")

# Convert EVTYPE to uppercase
data$EVTYPE <- toupper(data$EVTYPE)

Results

Harmful events to population health

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

health <- data %>%
  group_by(EVTYPE) %>%
  summarise(injuries = sum(INJURIES), fatalities = sum(FATALITIES)) %>%
  arrange(desc(injuries + fatalities)) %>%
  head(10)

## `summarise()` ungrouping output (override with `.groups` argument)

health

## # A tibble: 10 x 3
##    EVTYPE            injuries fatalities
##    <chr>                <dbl>      <dbl>
##  1 TORNADO              91346       5633
##  2 EXCESSIVE HEAT        6525       1903
##  3 TSTM WIND             6957        504
##  4 FLOOD                 6789        470
##  5 LIGHTNING             5230        816
##  6 HEAT                  2100        937
##  7 FLASH FLOOD           1777        978
##  8 ICE STORM             1975         89
##  9 THUNDERSTORM WIND     1488        133
## 10 WINTER STORM          1321        206

Economic consequences

data$PROPDMGEXP <- as.character(data$PROPDMGEXP)

data$PROPDMGEXP[data$PROPDMGEXP == "K"] <- 1000
data$PROPDMGEXP[data$PROPDMGEXP == "M"] <- 1e6
data$PROPDMGEXP[data$PROPDMGEXP == "B"] <- 1e9

data$PROPDMGEXP <- as.numeric(data$PROPDMGEXP)

## Warning: NAs introduced by coercion

data$PROPDMG[is.na(data$PROPDMGEXP)] <- 0

data$TOTALDMG <- data$PROPDMG * data$PROPDMGEXP

econ <- data %>%
  group_by(EVTYPE) %>%
  summarise(damage = sum(TOTALDMG)) %>%
  arrange(desc(damage)) %>%
  head(10)

## `summarise()` ungrouping output (override with `.groups` argument)

econ

## # A tibble: 10 x 2
##    EVTYPE                         damage
##    <chr>                           <dbl>
##  1 TORNADOES, TSTM WIND, HAIL 1600000000
##  2 WILD FIRES                  624100000
##  3 HAILSTORM                   241000000
##  4 HIGH WINDS/COLD             110500000
##  5 MAJOR FLOOD                 105000000
##  6 HURRICANE OPAL/HIGH WINDS   100000000
##  7 WINTER STORM HIGH WINDS      60000000
##  8 HURRICANE EMILY              50000000
##  9 EROSION/CSTL FLOOD           16200000
## 10 COASTAL  FLOODING/EROSION    15000000