Storm Data Analysis from 1950-2011

Impact of Severe whether Events On Public Health and Economy

Synopsis

In this report, the goal is to analyze the impact of different weather events on public health and economy based on the storm database collected from the U.S. National Oceanic and Atmospheric Administration’s (NOAA) from 1950 - 2011. The data used will be estimates of fatalities, injuries, property and crop damage to decide which types of event are most harmful to the population health and economy. From these data, we found that high temperatures and tornado are most harmful with respect to population health, while flood, drought, and hurricane/typhoon have the greatest economic impacts.

Step1: Loading R packages required for Analysis and Loading storm data

library(ggplot2)
library(gridExtra)
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

storm<-read.csv("repdata-data-StormData.csv",header = TRUE)

Step2: Data cleaning

storm$CROPDMGEXP<-toupper(storm$CROPDMGEXP)
storm$PROPDMGEXP<-toupper(storm$PROPDMGEXP)


storm$PROPDMGEXP[storm$PROPDMGEXP == "B"]<-9
storm$PROPDMGEXP[storm$PROPDMGEXP == "M"]<-6
storm$PROPDMGEXP[storm$PROPDMGEXP == "K"]<-3
storm$PROPDMGEXP[storm$PROPDMGEXP == "H"]<-2
storm$PROPDMGEXP[storm$PROPDMGEXP == ""]<-0
storm$PROPDMGEXP[storm$PROPDMGEXP == "-"]<-0
storm$PROPDMGEXP[storm$PROPDMGEXP == "?"]<-0
storm$PROPDMGEXP[storm$PROPDMGEXP == "+"]<-0

storm$CROPDMGEXP[storm$CROPDMGEXP == "B"]<-9
storm$CROPDMGEXP[storm$CROPDMGEXP == "M"]<-6
storm$CROPDMGEXP[storm$CROPDMGEXP == "K"]<-3
storm$CROPDMGEXP[storm$CROPDMGEXP == "?"]<-0
storm$CROPDMGEXP[storm$CROPDMGEXP == ""]<-0

storm$PROPDMGEXP<-as.numeric(storm$PROPDMGEXP)
storm$CROPDMGEXP<-as.numeric(storm$CROPDMGEXP)

storm$PROPDMG<-storm$PROPDMG*(10^storm$PROPDMGEXP)
storm$CROPDMG<-storm$CROPDMG*(10^storm$CROPDMGEXP)

Step3: Data processing for summarising the data per wheather events

storm1grp <- group_by(storm,EVTYPE) 

storm1 <- summarise(storm1grp,tot_fat = sum(FATALITIES,na.rm=T),
          tot_inj = sum(INJURIES,na.rm=T),
          tot_PROPDMG=sum(PROPDMG,na.rm=T),
          tot_CROPDMG=sum(CROPDMG,na.rm=T))

storm_fat<-storm1[order(-storm1$tot_fat),c(1,2)]
storm_inj<-storm1[order(-storm1$tot_inj),c(1,3)]
storm_PROPDMG<-storm1[order(-storm1$tot_PROPDMG),c(1,4)]
storm_CROPDMG<-storm1[order(-storm1$tot_CROPDMG),c(1,5)]

Step 4: Plotting data and Results

Top 10 Wheather Responsible for Fatalities

storm_fat[1:10,]

## Source: local data frame [10 x 2]
## 
##            EVTYPE tot_fat
##            (fctr)   (dbl)
## 1         TORNADO    5633
## 2  EXCESSIVE HEAT    1903
## 3     FLASH FLOOD     978
## 4            HEAT     937
## 5       LIGHTNING     816
## 6       TSTM WIND     504
## 7           FLOOD     470
## 8     RIP CURRENT     368
## 9       HIGH WIND     248
## 10      AVALANCHE     224

Top 10 Wheather Events Responsible for injuries

storm_inj[1:10,]

## Source: local data frame [10 x 2]
## 
##               EVTYPE tot_inj
##               (fctr)   (dbl)
## 1            TORNADO   91346
## 2          TSTM WIND    6957
## 3              FLOOD    6789
## 4     EXCESSIVE HEAT    6525
## 5          LIGHTNING    5230
## 6               HEAT    2100
## 7          ICE STORM    1975
## 8        FLASH FLOOD    1777
## 9  THUNDERSTORM WIND    1488
## 10              HAIL    1361

plot1<-ggplot(data=storm_fat[1:10,], aes(x=EVTYPE, y=tot_fat)) +
  geom_bar(stat="identity", fill="steelblue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) + 
  xlab("Weather Type") + 
  ylab("Number Of Fatalities") + 
  ggtitle("Top 10 Calamities in Terms of Fatalities\n Events in the U.S.\n from 1995 - 2011")


plot2<-ggplot(data=storm_inj[1:10,], aes(x=EVTYPE, y=tot_inj)) +
  geom_bar(stat="identity", fill="steelblue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) + 
  xlab("Weather Type") + 
  ylab("Number Of Injuries") + 
  ggtitle("Top 10 Calamities in Terms of Injuries\n Events in the U.S.\n from 1995 - 2011")

grid.arrange(plot1,plot2,ncol=2)

Top 10 Wheather Events Responsible for Property Damage

storm_PROPDMG[1:10,]

## Source: local data frame [10 x 2]
## 
##               EVTYPE  tot_PROPDMG
##               (fctr)        (dbl)
## 1              FLOOD 144657709807
## 2  HURRICANE/TYPHOON  69305840000
## 3            TORNADO  56947380677
## 4        STORM SURGE  43323536000
## 5        FLASH FLOOD  16822673979
## 6               HAIL  15735267513
## 7          HURRICANE  11868319010
## 8     TROPICAL STORM   7703890550
## 9       WINTER STORM   6688497251
## 10         HIGH WIND   5270046295

Top 10 Wheather Events Responsible for Crop Damage

storm_CROPDMG[1:10,]

## Source: local data frame [10 x 2]
## 
##               EVTYPE tot_CROPDMG
##               (fctr)       (dbl)
## 1            DROUGHT 13972566000
## 2              FLOOD  5661968450
## 3        RIVER FLOOD  5029459000
## 4          ICE STORM  5022113500
## 5               HAIL  3025954473
## 6          HURRICANE  2741910000
## 7  HURRICANE/TYPHOON  2607872800
## 8        FLASH FLOOD  1421317100
## 9       EXTREME COLD  1292973000
## 10      FROST/FREEZE  1094086000

plot3<-ggplot(data=storm_PROPDMG[1:10,], aes(x=EVTYPE, y=tot_PROPDMG)) +
  geom_bar(stat="identity", fill="steelblue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) + 
  xlab("Weather Type") + 
  ylab("Total Property Damage") + 
  ggtitle("Top 10 Calamities in Terms of Property Damage\n Events in the U.S.\n from 1995 - 2011")

plot4<-ggplot(data=storm_CROPDMG[1:10,], aes(x=EVTYPE, y=tot_CROPDMG)) +
  geom_bar(stat="identity", fill="steelblue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) + 
  xlab("Weather Type") + 
  ylab("Total Crop Damage") + 
  ggtitle("Top 10 Calamities in Terms of Crop Damage\n Events in the U.S.\n from 1995 - 2011")

grid.arrange(plot3,plot4,ncol=2)