Introduction:
Severe weather Phenomenon can cause both damage public health and economic sectors and assets
like crops and property. They result in fatalities, injuries, and property damage.Prevention
of these natural disasters is important in public interest.
Through this project, we explore the U.S. National Oceanic and Atmospheric
Administration’s (NOAA) storm database. The database tracks characteristics of major storms and weather events in the United States, giving data on the fatalities, injuries, and property damage.

Synopsis:

This report explores the effect of natural disasters on public health(injuries and fatalities) and
economy (Crop damage and Property damage). The report analysed the NOAA storm database
containing data on extreme climate events. The data was collected during the period from 1950 through 2011.

This analysis aids to answer the following two questions:
1) Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?
2) Across the United States, which types of events have the greatest economic consequences?

Main conclusions of the study:
1) Tornado has caused highest fatalities and injuries with more than 5600 deaths and 91400 injuries.
2) Floods have caused the most significant economic damage of more than 157 billion USD.

The data columns of interest:
* EVTYPE -> Type of event
* FATALITIES -> Number of fatalities
* INJURIES -> Number of injuries
* PROPDMG -> Amount of property damage in orders of magnitude
* PROPDMGEXP -> Order of magnitude for property damage (e.g. K for thousands)
* CROPDMG -> Amount of crop damage in orders of magnitude
* PROPDMGEXP -> Order of magnitude for crop damage (e.g. M for millions)

Loading data and reading it into data-frame storm:

setwd("/Users/kareena_610/https:/github.com/k-610z/Rep_Data-Storm-Project2")

storm <- read.csv(bzfile("StormData.csv.bz2"), sep = ",", header = TRUE, stringsAsFactors = FALSE)

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

summ_pophealthdmg<- storm %>% 
                select(EVTYPE,FATALITIES,INJURIES) %>% 
                filter(complete.cases(.)) %>% 
                group_by(EVTYPE) %>% 
                summarise(sum_fatalities=sum(FATALITIES),sum_injuries=sum(INJURIES))

summ_pophealthdmg%>% 
        select(EVTYPE, sum_fatalities,sum_injuries) %>% 
        filter(sum_fatalities==max(sum_fatalities))
## # A tibble: 1 × 3
##   EVTYPE  sum_fatalities sum_injuries
##   <chr>            <dbl>        <dbl>
## 1 TORNADO           5633        91346
summ_pophealthdmg%>% 
    select(EVTYPE, sum_fatalities,sum_injuries) %>% 
    filter(sum_injuries==max(sum_injuries))
## # A tibble: 1 × 3
##   EVTYPE  sum_fatalities sum_injuries
##   <chr>            <dbl>        <dbl>
## 1 TORNADO           5633        91346
# Summary of EVTYPE with the highest fatalities and injuries
MaxPopFat<-summ_pophealthdmg%>% 
    select(EVTYPE, sum_fatalities,sum_injuries) %>% 
    arrange(desc(sum_fatalities))
#Lets take the 10 highest fatality count events
MaxPopFat<-MaxPopFat[1:10,]
MaxPopFat # Displays result
## # A tibble: 10 × 3
##    EVTYPE         sum_fatalities sum_injuries
##    <chr>                   <dbl>        <dbl>
##  1 TORNADO                  5633        91346
##  2 EXCESSIVE HEAT           1903         6525
##  3 FLASH FLOOD               978         1777
##  4 HEAT                      937         2100
##  5 LIGHTNING                 816         5230
##  6 TSTM WIND                 504         6957
##  7 FLOOD                     470         6789
##  8 RIP CURRENT               368          232
##  9 HIGH WIND                 248         1137
## 10 AVALANCHE                 224          170
MaxPopInj<-summ_pophealthdmg%>% 
    select(EVTYPE, sum_fatalities,sum_injuries) %>% 
    arrange(desc(sum_injuries))
#Lets take the 10 highest fatality count events
MaxPopInj<-MaxPopInj[1:10,]
MaxPopInj # Displays result
## # A tibble: 10 × 3
##    EVTYPE            sum_fatalities sum_injuries
##    <chr>                      <dbl>        <dbl>
##  1 TORNADO                     5633        91346
##  2 TSTM WIND                    504         6957
##  3 FLOOD                        470         6789
##  4 EXCESSIVE HEAT              1903         6525
##  5 LIGHTNING                    816         5230
##  6 HEAT                         937         2100
##  7 ICE STORM                     89         1975
##  8 FLASH FLOOD                  978         1777
##  9 THUNDERSTORM WIND            133         1488
## 10 HAIL                          15         1361

Observation: We see that Tornado is the event causing maximum damage on public health.

Data Visualization of Total fatalities and Total Injuries caused by Severe Weather Events.

par(mfrow = c(1, 2), mar = c(15, 4, 3, 2), mgp = c(3, 1, 0), cex =1.0)
barplot(MaxPopFat$sum_fatalities, las = 3, names.arg = MaxPopFat$EVTYPE, main = "Weather Events With\n The Top 10 Highest Fatalities", ylab = "Number of Fatalities", col = "grey")
barplot(MaxPopInj$sum_injuries, las = 3, names.arg =MaxPopInj$EVTYPE , main = "Weather Events With\n The Top 10 Highest Injuries", ylab = "Number of Injuries", col = "seagreen")

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

eventsummary<- storm %>% 
    select(EVTYPE,PROPDMG,PROPDMGEXP,CROPDMG,CROPDMGEXP) %>% 
    filter(complete.cases(.))

row<-nrow(eventsummary)

Converting notation of ‘K’,‘M’,‘B’, into integers.

#Property damage expenses may be in H,K,M,B
 for (i in length(row))
 {  cropval=1
    propval=1
    if(eventsummary$CROPDMGEXP[i]=="K")
    cropval=1000
    else if(eventsummary$CROPDMGEXP[i]=="M")
    cropval=1000000
    else if(eventsummary$CROPDMGEXP[i]=="B")
    cropval=1000000000 
    eventsummary$CROPDMG[i]<-eventsummary$CROPDMG[i]*cropval
   
    if(eventsummary$PROPDMGEXP[i]=="K")
        propval=1000
    else if(eventsummary$PROPDMGEXP[i]=="M")
        propval=1000000
    else if(eventsummary$PROPDMGEXP[i]=="B")
        propval=1000000000 
    eventsummary$PROPDMG[i]<-eventsummary$PROPDMG[i]*propval
 }

Summarising the data as the highest damage to crops, to property and the total damage overall
This will be the damage to economy of United States

summary_ecodmg<- eventsummary %>% 
    select(EVTYPE,PROPDMG,CROPDMG) %>% 
    filter(complete.cases(.)) %>% 
    group_by(EVTYPE) %>% 
    summarise(sum_propdmg=sum(PROPDMG),sum_cropdmg=sum(CROPDMG))
#Event causing highest Property Damage
summary_ecodmg%>% 
    select(EVTYPE, sum_propdmg,sum_cropdmg) %>% 
    filter(sum_propdmg==max(sum_propdmg))
## # A tibble: 1 × 3
##   EVTYPE  sum_propdmg sum_cropdmg
##   <chr>         <dbl>       <dbl>
## 1 TORNADO    3237233.     100019.
#Event causing highest Crop Damage
summary_ecodmg%>% 
    select(EVTYPE, sum_propdmg,sum_cropdmg) %>% 
    filter(sum_cropdmg==max(sum_cropdmg))
## # A tibble: 1 × 3
##   EVTYPE sum_propdmg sum_cropdmg
##   <chr>        <dbl>       <dbl>
## 1 HAIL       688693.     579596.
#Summarizing data 
MaxPropDMG<-summary_ecodmg%>% 
    select(EVTYPE, sum_propdmg,sum_cropdmg) %>% 
    arrange(desc(sum_propdmg))
# Lets take the first 10 highest Property Damages:
MaxPropDMG<-MaxPropDMG[1:10,]
MaxPropDMG #Display result
## # A tibble: 10 × 3
##    EVTYPE             sum_propdmg sum_cropdmg
##    <chr>                    <dbl>       <dbl>
##  1 TORNADO               3237233.     100019.
##  2 FLASH FLOOD           1420125.     179200.
##  3 TSTM WIND             1335966.     109203.
##  4 FLOOD                  899938.     168038.
##  5 THUNDERSTORM WIND      876844.      66791.
##  6 HAIL                   688693.     579596.
##  7 LIGHTNING              603352.       3581.
##  8 THUNDERSTORM WINDS     446293.      18685.
##  9 HIGH WIND              324732.      17283.
## 10 WINTER STORM           132721.       1979.
MaxCropDMG<-summary_ecodmg%>% 
    select(EVTYPE, sum_propdmg,sum_cropdmg) %>% 
    arrange(desc(sum_cropdmg))
# Lets take the first 10 highest Crop damages:
MaxCropDMG<-MaxCropDMG[1:10,]
MaxCropDMG#Display result
## # A tibble: 10 × 3
##    EVTYPE             sum_propdmg sum_cropdmg
##    <chr>                    <dbl>       <dbl>
##  1 HAIL                   688693.     579596.
##  2 FLASH FLOOD           1420125.     179200.
##  3 FLOOD                  899938.     168038.
##  4 TSTM WIND             1335966.     109203.
##  5 TORNADO               3237233.     100019.
##  6 THUNDERSTORM WIND      876844.      66791.
##  7 DROUGHT                  4099.      33899.
##  8 THUNDERSTORM WINDS     446293.      18685.
##  9 HIGH WIND              324732.      17283.
## 10 HEAVY RAIN              50842.      11123.

Observation: We see that property damage is highest in Tornado but crop damage is highest in Hail

Adding both the damages to choose one event that causes the highest damage to both properties and crops
Then we will compute the 10 events corresponding to highest total Economic Damage

MaxTotEcoDMG<-summary_ecodmg %>% 
    select(EVTYPE, sum_propdmg,sum_cropdmg) %>% 
    group_by(EVTYPE) %>% 
    summarize(tot_ecodmg=sum_propdmg+sum_cropdmg) %>% 
    arrange(desc(tot_ecodmg))
MaxTotEcoDMG<-MaxTotEcoDMG[1:10, ]
MaxTotEcoDMG#Display result
## # A tibble: 10 × 2
##    EVTYPE             tot_ecodmg
##    <chr>                   <dbl>
##  1 TORNADO              3337252.
##  2 FLASH FLOOD          1599325.
##  3 TSTM WIND            1445168.
##  4 HAIL                 1268290.
##  5 FLOOD                1067976.
##  6 THUNDERSTORM WIND     943636.
##  7 LIGHTNING             606932.
##  8 THUNDERSTORM WINDS    464978.
##  9 HIGH WIND             342015.
## 10 WINTER STORM          134700.

Observation:

If we add up all the data, the highest economical damage is by

1)Tornado
2)Flash Flood

Data Visualization of Total Property Damages, Total Crop Damages and Total Economic Damages caused by these Severe Weather Events

par(mfrow = c(1, 3), mar = c(15, 4, 3, 2), mgp = c(3, 1, 0), cex =0.6)
barplot(MaxPropDMG$sum_propdmg/(10^6), las = 3, names.arg = MaxPropDMG$EVTYPE , main = "Top 10 Events with\n Greatest Property Damages", ylab = "Cost of damages ($ million)", col = "lightblue")
barplot(MaxCropDMG$sum_cropdmg/(10^6), las = 3, names.arg = MaxCropDMG$EVTYPE , main = "Top 10 Events With\n Greatest Crop Damages", ylab = "Cost of damages ($ million)", col = "lightgreen")
barplot(MaxTotEcoDMG$tot_ecodmg/(10^6), las = 3, names.arg = MaxTotEcoDMG$EVTYPE, main = "Top 10 Events With\n Greatest Economic Damages", ylab = "Cost of damages ($ million)", col = "lightpink")

Results:

1)Tornado is the event causing maximum damage on public health.
2.1)Property damage is highest in Tornado but crop damage is highest in Hail.
2.2)If we add up all the data, the highest economical damage is by
Tornado
Flash Flood