Analysis of weather

Introduction

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

The data for this assignment come in the form of a comma-separated-value file compressed via the bzip2 algorithm to reduce its size. You can download the file from the course web site:

Questions

We will be focusing en answering: the following questions:

Across the United States, which types of events (EVTYPE variable) are most harmful with respect to population health?
Across the United States, which types of events have the greatest economic consequences?

so let’s begin…

Load libraries

library(tidyverse)

## -- Attaching packages ------------------------------------------------------ tidyverse 1.3.0 --

## v ggplot2 3.2.1     v purrr   0.3.4
## v tibble  3.0.1     v dplyr   0.8.3
## v tidyr   1.0.2     v stringr 1.4.0
## v readr   1.3.1     v forcats 0.5.0

## -- Conflicts --------------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(gridExtra)

## 
## Attaching package: 'gridExtra'

## The following object is masked from 'package:dplyr':
## 
##     combine

Download and read data

Note: we will be working in our current directory, but you can change it if you desired.

# first clean the environment and setup the working directory
rm(list= ls())

# now download file
if (!file.exists("repdata_data_StormData.csv.bz2")) {
  fileURL <- 'https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2'
  download.file(fileURL, destfile='repdata_data_StormData.csv.bz2', method = 'curl')
}
#noaaDF
df_raw <- read.csv(bzfile('repdata_data_StormData.csv.bz2'),header=TRUE, stringsAsFactors = FALSE)

Results

it’s important focusing in the main question " which type of events are most harmful to population health? " to do this we will be working with 2 variables:

Fatalities and
Injuries

# preparing our sub dataset
harmful_event<- select(df_raw, EVTYPE,FATALITIES,INJURIES) %>% 
  group_by(EVTYPE) %>% summarize(FATALITIES=sum(FATALITIES, na.rm = TRUE), 
                                 INJURIES = sum(INJURIES,na.rm = TRUE)) %>% ungroup() %>% 
  filter(FATALITIES>0 | INJURIES>0 )

We have the top five fatality event:

harmful_event %>% select(EVTYPE, FATALITIES) %>% arrange(desc(FATALITIES)) %>% head()

## # A tibble: 6 x 2
##   EVTYPE         FATALITIES
##   <chr>               <dbl>
## 1 TORNADO              5633
## 2 EXCESSIVE HEAT       1903
## 3 FLASH FLOOD           978
## 4 HEAT                  937
## 5 LIGHTNING             816
## 6 TSTM WIND             504

and injuries respectively:

harmful_event %>% select(EVTYPE, INJURIES) %>% arrange(desc(INJURIES)) %>% head()

## # A tibble: 6 x 2
##   EVTYPE         INJURIES
##   <chr>             <dbl>
## 1 TORNADO           91346
## 2 TSTM WIND          6957
## 3 FLOOD              6789
## 4 EXCESSIVE HEAT     6525
## 5 LIGHTNING          5230
## 6 HEAT               2100

at the same way we can show visually the top 10 of the these two variables like:

fat<-harmful_event %>% select(EVTYPE, FATALITIES) %>% 
  arrange(desc(FATALITIES)) %>% head(10) %>%
  ggplot( aes(x= reorder(EVTYPE, -FATALITIES), y=FATALITIES )) + 
  geom_bar(stat = "identity") +
  xlab("Weather Event Type") +
  ylab("Number of Fatalities") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ggtitle('Top 10 Fatalities')
  

inj<-harmful_event %>% select(EVTYPE, INJURIES) %>% 
  arrange(desc(INJURIES)) %>% head(10) %>%
  ggplot( aes(x= reorder(EVTYPE, -INJURIES), y=INJURIES )) + 
  geom_bar(stat = "identity") +
  xlab("Weather Event Type") +
  ylab("Number of Injuries") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ggtitle('Top 10 Injuries')

grid.arrange(fat, inj, nrow = 1)

Now we will work with the second question …Across the United States, which types of events have the greatest economic consequences? to do this we’ll take PROPDMG and CROPDMG columns to answer the previous question.

DMG<- select(df_raw, EVTYPE,PROPDMG,CROPDMG) %>% 
  group_by(EVTYPE) %>% summarize(PROPDMG =sum(PROPDMG , na.rm = TRUE), 
                                 CROPDMG = sum(CROPDMG ,na.rm = TRUE)) %>% ungroup() %>% 
  filter(PROPDMG>0 | CROPDMG>0 )

We have the top five Property damage:

DMG %>% select(EVTYPE, PROPDMG) %>% arrange(desc(PROPDMG)) %>% head()

## # A tibble: 6 x 2
##   EVTYPE             PROPDMG
##   <chr>                <dbl>
## 1 TORNADO           3212258.
## 2 FLASH FLOOD       1420125.
## 3 TSTM WIND         1335966.
## 4 FLOOD              899938.
## 5 THUNDERSTORM WIND  876844.
## 6 HAIL               688693.

and Crop damage respectively:

DMG %>% select(EVTYPE, CROPDMG) %>% arrange(desc(CROPDMG)) %>% head()

## # A tibble: 6 x 2
##   EVTYPE            CROPDMG
##   <chr>               <dbl>
## 1 HAIL              579596.
## 2 FLASH FLOOD       179200.
## 3 FLOOD             168038.
## 4 TSTM WIND         109203.
## 5 TORNADO           100019.
## 6 THUNDERSTORM WIND  66791.

at the same way we can show visually the top 10 of the these two variables like:

pro<-DMG %>% select(EVTYPE, PROPDMG) %>% 
  arrange(desc(PROPDMG)) %>% head(10) %>%
  ggplot( aes(x= reorder(EVTYPE, -PROPDMG), y=PROPDMG )) + 
  geom_bar(stat = "identity") +
  xlab("Weather Event Type") +
  ylab("Property Damage") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ggtitle('Top 10 Property Damage')


cro<-DMG %>% select(EVTYPE, CROPDMG) %>% 
  arrange(desc(CROPDMG)) %>% head(10) %>%
  ggplot( aes(x= reorder(EVTYPE, -CROPDMG), y=CROPDMG )) + 
  geom_bar(stat = "identity") +
  xlab("Weather Event Type") +
  ylab("Property Damage") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  ggtitle('Top 10 Crop Damage')


grid.arrange(pro, cro, nrow = 1)