Exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database

library(tidyverse)

## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr

## Conflicts with tidy packages ----------------------------------------------

## filter(): dplyr, stats
## lag():    dplyr, stats

stormdata_file_path <-"repdata%2Fdata%2FStormData.csv.bz2"
#stormdata_file_path <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
stormdata <- read_csv(stormdata_file_path)

## Parsed with column specification:
## cols(
##   .default = col_character(),
##   STATE__ = col_double(),
##   COUNTY = col_double(),
##   BGN_RANGE = col_double(),
##   COUNTY_END = col_double(),
##   END_RANGE = col_double(),
##   LENGTH = col_double(),
##   WIDTH = col_double(),
##   F = col_integer(),
##   MAG = col_double(),
##   FATALITIES = col_double(),
##   INJURIES = col_double(),
##   PROPDMG = col_double(),
##   CROPDMG = col_double(),
##   LATITUDE = col_double(),
##   LONGITUDE = col_double(),
##   LATITUDE_E = col_double(),
##   LONGITUDE_ = col_double(),
##   REFNUM = col_double()
## )

## See spec(...) for full column specifications.

Synopsis

Storms and other severe weather events can cause both public health and economic problems for communities and municipalities. Many severe events can result in fatalities, injuries, and property damage, and preventing such outcomes to the extent possible is a key concern.

This project involves exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database tracks characteristics of major storms and weather events in the United States, including when and where they occur, as well as estimates of any fatalities, injuries, and property damage.

Data Processing

1 - Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

# simple group tbl by EVTYPE
grouped_events <- stormdata %>% 
          group_by(EVTYPE)

events_most_harmful <- grouped_events  %>% 
          summarise(FATALITIES = sum(FATALITIES), INJURIES = sum(INJURIES)) %>%
          arrange(desc(INJURIES + FATALITIES))

2 - Across the United States, which types of events have the greatest economic consequences?

# I have to factor magnitude letters
grouped_events$propFactor<-factor(grouped_events$PROPDMGEXP,levels=c("H","K","M","B","h","m","O"))
grouped_events$propFactor[is.na(grouped_events$propFactor)] <- "O"
grouped_events$cropFactor<-factor(grouped_events$CROPDMGEXP,levels=c("K","M","B","k","m","O"))
grouped_events$cropFactor[is.na(grouped_events$cropFactor)] <- "O"

grouped_events <- grouped_events %>% mutate(PROP= 0, CROP=0)

grouped_events$PROP[grouped_events$propFactor=="K"]<-1000
grouped_events$PROP[grouped_events$propFactor=="H"|grouped_events$propFactor=="h"]<-100
grouped_events$PROP[grouped_events$propFactor=="M"|grouped_events$propFactor=="m"]<-1e6
grouped_events$PROP[grouped_events$propFactor=="B"]<-1e9
grouped_events$PROP[grouped_events$propFactor=="O"]<-1

grouped_events$CROP[grouped_events$cropFactor=="K"|grouped_events$cropFactor=="k"]<-1000
grouped_events$CROP[grouped_events$cropFactor=="M"|grouped_events$cropFactor=="m"]<-1e6
grouped_events$CROP[grouped_events$cropFactor=="B"]<-1e9
grouped_events$CROP[grouped_events$cropFactor=="O"]<-1


grouped_events <- grouped_events %>% mutate(PROPdmgVal= PROPDMG*PROP/1e6, CROPdmgVal=CROPDMG*CROP/1e6)

# Sum it product of PROPdmg and CROPdmg by EVTYPE
events_economic_consequences <- grouped_events %>%
     summarize(PROPdmgVal=sum(PROPdmgVal,na.rm=TRUE),CROPdmgVal=sum(CROPdmgVal,na.rm=TRUE))
events_economic_consequences<-arrange(events_economic_consequences,desc(PROPdmgVal+CROPdmgVal))
events_economic_consequences<-events_economic_consequences[1:10,]

Results

A2 <- head(events_most_harmful, 10)

library(reshape2)

## 
## Attaching package: 'reshape2'

## The following object is masked from 'package:tidyr':
## 
##     smiths

A3 <- melt(A2, id.var="EVTYPE")
ggplot(A3, aes(x = reorder(EVTYPE, value, sum), y = value, fill = variable)) + 
   coord_flip() +
  geom_bar(stat = "identity") + xlab("Storm Type") + ylab("Casualties") + labs(title = expression("Disaster Casualties"))

A4 <- melt(events_economic_consequences, id.var="EVTYPE")
ggplot(A4, aes(x = reorder(EVTYPE, value, sum), y = value, fill = variable)) + 
  coord_flip() + 
# theme(legend.position = "top") 
  geom_bar(stat = "identity") + xlab("Storm Type") + ylab("Damage Million") + labs(title = expression("Disaster Economic Impact"))