Synopsis

Storms and other severe weather events have huge impact on public health and economic problems for municipalities and their inhabitants. Some of severe events can cause injuries property damage and even lead to death. This analysis present which types of events are most harmful with respect to population health and which have the greatest economic consequences.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.This report contributes by attempting to answer two questions: 1. Across the United States, which types of weather events are most harmful with respect to population health? 2. Across the United States, which types of weather events have the most severe economic consequences health?

Importing Libraries

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(ggplot2)

Download the Data Set from the Internet

link <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(url = link, destfile = "StormDatafile")
# Read the Dataset
StormData <- read.csv(bzfile("StormDatafile"),sep = ",",header=TRUE)

Data Processing

Since the property damange estimates were collected from various data sources, with different measurements thats why we first had to transform the data into a single comparable value:

table(StormData$PROPDMGEXP)

## 
##             -      ?      +      0      1      2      3      4      5      6 
## 465934      1      8      5    216     25     13      4      4     28      4 
##      7      8      B      h      H      K      m      M 
##      5      1     40      1      6 424665      7  11330

StormData$PROPDMGEXP2 <- 1
StormData$PROPDMGEXP2[which(StormData$PROPDMGEXP == "K")] <- 1000
StormData$PROPDMGEXP2[which(StormData$PROPDMGEXP == "M" | StormData$PROPDMGEXP == "m")] <- 1000000
StormData$PROPDMGEXP2[which(StormData$PROPDMGEXP == "B")] <- 1000000000

table(StormData$PROPDMGEXP2)

## 
##      1   1000  1e+06  1e+09 
## 466255 424665  11337     40

Question 1. Across the United States, which types of weather events are most harmful with respect to population health?

Plot 1: Shows Death toll Vs Event type

StormData %>%
      select(FATALITIES, EVTYPE) %>%
      group_by(EVTYPE) %>%
      summarise(SumFATALITIES = sum(FATALITIES)) %>%
      top_n(n = 8, wt = SumFATALITIES) %>%
      ggplot(aes(y = SumFATALITIES, x = reorder(x = EVTYPE, X = SumFATALITIES), fill=EVTYPE))+
      geom_bar(stat = "identity", show.legend = FALSE) +
      #geom_text(aes(label=SumFATALITIES), size = 4, hjust = 0.5, vjust = -0.1) +
      xlab(label = "") +
      ylab(label = "Death toll") +
      coord_flip() +
      theme_light()

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

Plot 2: Shows Injuries Vs Event type

StormData %>%
      select(INJURIES, EVTYPE) %>%
      group_by(EVTYPE) %>%
      summarise(SumINJURIES = sum(INJURIES)) %>%
      top_n(n = 8, wt = SumINJURIES) %>%
      ggplot(aes(y = SumINJURIES, x = reorder(x = EVTYPE, X = SumINJURIES), fill=EVTYPE))+
      geom_bar(stat = "identity", show.legend = FALSE) +
      #geom_text(aes(label=SumINJURIES), size = 4, hjust = 0.5, vjust = -0.1) +
      xlab(label = "") +
      ylab(label = "INJURIES") +
      coord_flip() +
      theme_light()

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

Question 2. Across the United States, which types of weather events have the most severe economic consequences health?

Plot: Shows Property damage estimates Vs Event type

StormData %>%
      select(PROPDMG, PROPDMGEXP2, EVTYPE) %>%
      group_by(EVTYPE) %>%
      mutate(SumPROPDMGEXP = (PROPDMG * PROPDMGEXP2)) %>%
      summarise(SumPROPDMGEXP2 = sum(SumPROPDMGEXP)) %>%
      top_n(n = 8, wt = SumPROPDMGEXP2) %>%
      ggplot(aes(y = SumPROPDMGEXP2, x = reorder(x = EVTYPE, X = SumPROPDMGEXP2), fill=EVTYPE))+
      geom_bar(stat = "identity", show.legend = FALSE) +
      #geom_text(aes(label=SumFATALITIES), size = 4, hjust = 0.5, vjust = -0.1) +
      xlab(label = "") +
      ylab(label = "Property damage estimates") +
      coord_flip() +
      theme_light()

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

Result

It is observed in above analysis that flood has the greatest economic consequences whereas Tornado is the most harmful to population health because caused the most death tolls and injuries.

Analysis of Storms and other of severe weather on population health and the economy

Shubham Nagle