Weather events effects in public health and economy analysis

Synopsis

This document its aimed to analyse U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database to help government or municipal manager who might be responsible for preparing for severe weather events and will need to prioritize resources for different types of events.

We will find most human harmful and economic damage for type of event

Data processing

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, union

if(!file.exists("./stormData.csv.bz2")){
    download.file("https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2", destfile = "./stormData.csv.bz2")
}
## data
stormData <- read.csv("stormData.csv.bz2")

# Convert letters in numbers to find economic damage
stormData$PROPDMGEXP <- as.character(stormData$PROPDMGEXP)
stormData$PROPDMGEXP[stormData$PROPDMGEXP == "K"] <- 1000
stormData$PROPDMGEXP[stormData$PROPDMGEXP == "M"] <- 1e+06
stormData$PROPDMGEXP[stormData$PROPDMGEXP == "B"] <- 1e+09
stormData$PROPDMGEXP <- as.numeric(stormData$PROPDMGEXP)

## Warning: NAs introduced by coercion

stormData$CROPDMGEXP <- as.character(stormData$CROPDMGEXP)
stormData$CROPDMGEXP[stormData$CROPDMGEXP == "K"] <- 1000
stormData$CROPDMGEXP[stormData$CROPDMGEXP == "M"] <- 1e+06
stormData$CROPDMGEXP[stormData$CROPDMGEXP == "B"] <- 1e+09
stormData$CROPDMGEXP <- as.numeric(stormData$CROPDMGEXP)

## Warning: NAs introduced by coercion

## We will use dplyr
stormTable <- tbl_df(stormData)

Human harmful analysis

## group data by event type
humanDamage <-stormTable %>% select(EVTYPE,FATALITIES,INJURIES) %>% filter (INJURIES > 0) %>%group_by(EVTYPE)
summarize(humanDamage, TOTAL_FATALITIES =sum(FATALITIES),  TOTAL_INJURIES = sum(INJURIES)) %>% arrange(desc(TOTAL_FATALITIES))

## Source: local data frame [158 x 3]
## 
##            EVTYPE TOTAL_FATALITIES TOTAL_INJURIES
##            (fctr)            (dbl)          (dbl)
## 1         TORNADO             5227          91346
## 2  EXCESSIVE HEAT              402           6525
## 3       LIGHTNING              283           5230
## 4       TSTM WIND              199           6957
## 5     FLASH FLOOD              171           1777
## 6           FLOOD              104           6789
## 7       HIGH WIND              102           1137
## 8    WINTER STORM               85           1321
## 9            HEAT               73           2100
## 10       WILDFIRE               55            911
## ..            ...              ...            ...

As we can see the most harmful human event is TORNADOS (They ara at top of previouse list)

Let’s see where dose the Tornados are concetrated.

tornados <- select(stormTable,EVTYPE,LATITUDE,LONGITUDE,INJURIES) %>% filter(EVTYPE == 'TORNADO', LATITUDE !=0,LONGITUDE !=0)
plot(-tornados$LONGITUDE,tornados$LATITUDE,col= rgb(0,0,0,0.1) ,main = "TORNADO AREAS")

On the east part of US there are more tornados

Economic Damage Analysis

## group data by event type
economicDamage <-stormTable %>% select(EVTYPE,PROPDMGEXP,CROPDMGEXP) %>% filter (!is.na(PROPDMGEXP),!is.na(CROPDMGEXP)) %>%group_by(EVTYPE)

economicDamage <- mutate(economicDamage,TOTAL_ECONOMIC_DAMAGE = PROPDMGEXP+CROPDMGEXP)
summarize(economicDamage, TOTAL_DAMAGE =sum(TOTAL_ECONOMIC_DAMAGE)) %>% arrange(desc(TOTAL_DAMAGE))

## Source: local data frame [124 x 2]
## 
##               EVTYPE TOTAL_DAMAGE
##               (fctr)        (dbl)
## 1  HURRICANE/TYPHOON   7042017000
## 2              FLOOD   5267850000
## 3            TORNADO   3891885000
## 4          HURRICANE   3083050000
## 5            DROUGHT   2069731000
## 6        RIVER FLOOD   2010020000
## 7               HAIL   1937123005
## 8        FLASH FLOOD   1892396005
## 9           WILDFIRE   1117451000
## 10         ICE STORM   1070851000
## ..               ...          ...

As we see at the top of list HURRICANE/TYPHOON are the more economic damage event

Results

TORNADOS are the most dangerous events for humans counting FATALITIES and INJURIES. HURRICANE/TYPHOON are the most economic damage events