Synposis: This analysis is done to identify health and economic problems faced by municipalities/communities across United States during natural catastrophes like storm, wildfire etc.. by answering the below two questions:

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

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

library(tidyr)
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)

Data Processing

storm_data <- read.csv('repdata_data_StormData.csv.bz2',header = TRUE)
names(storm_data)
##  [1] "STATE__"    "BGN_DATE"   "BGN_TIME"   "TIME_ZONE"  "COUNTY"    
##  [6] "COUNTYNAME" "STATE"      "EVTYPE"     "BGN_RANGE"  "BGN_AZI"   
## [11] "BGN_LOCATI" "END_DATE"   "END_TIME"   "COUNTY_END" "COUNTYENDN"
## [16] "END_RANGE"  "END_AZI"    "END_LOCATI" "LENGTH"     "WIDTH"     
## [21] "F"          "MAG"        "FATALITIES" "INJURIES"   "PROPDMG"   
## [26] "PROPDMGEXP" "CROPDMG"    "CROPDMGEXP" "WFO"        "STATEOFFIC"
## [31] "ZONENAMES"  "LATITUDE"   "LONGITUDE"  "LATITUDE_E" "LONGITUDE_"
## [36] "REMARKS"    "REFNUM"

Analysing Harmful Events

Categorising fatalities and injuries under one column and their values in another column

gather_data <- gather(most_harmful_data,type,value,FATALITIES:INJURIES)

print(gather_data)
## # A tibble: 20 × 3
##    EVTYPE            type       value
##    <chr>             <chr>      <dbl>
##  1 TORNADO           FATALITIES  5633
##  2 EXCESSIVE HEAT    FATALITIES  1903
##  3 TSTM WIND         FATALITIES   504
##  4 FLOOD             FATALITIES   470
##  5 LIGHTNING         FATALITIES   816
##  6 HEAT              FATALITIES   937
##  7 FLASH FLOOD       FATALITIES   978
##  8 ICE STORM         FATALITIES    89
##  9 THUNDERSTORM WIND FATALITIES   133
## 10 WINTER STORM      FATALITIES   206
## 11 TORNADO           INJURIES   91346
## 12 EXCESSIVE HEAT    INJURIES    6525
## 13 TSTM WIND         INJURIES    6957
## 14 FLOOD             INJURIES    6789
## 15 LIGHTNING         INJURIES    5230
## 16 HEAT              INJURIES    2100
## 17 FLASH FLOOD       INJURIES    1777
## 18 ICE STORM         INJURIES    1975
## 19 THUNDERSTORM WIND INJURIES    1488
## 20 WINTER STORM      INJURIES    1321

Analysing Economic Consquences

Converting the crop and property damages expenses into numerical format

storm_data <- storm_data %>% mutate(CROPDMGEXP = ifelse(CROPDMGEXP == "",0,ifelse(CROPDMGEXP == "K",1000,ifelse(CROPDMGEXP== "M",1000000,ifelse(CROPDMGEXP == "B",1000000000,CROPDMGEXP)))))

storm_data$CROPDMGEXP <- as.numeric(storm_data$CROPDMGEXP)
## Warning: NAs introduced by coercion
storm_data <- storm_data %>% mutate(PROPDMGEXP = ifelse(PROPDMGEXP == "",0,ifelse(PROPDMGEXP == "K",1000,ifelse(PROPDMGEXP== "M",1000000,ifelse(PROPDMGEXP == "B",1000000000,PROPDMGEXP)))))

storm_data$PROPDMGEXP <- as.numeric(storm_data$PROPDMGEXP)
## Warning: NAs introduced by coercion
storm_data$PROPDMGVALUE <- storm_data$PROPDMG*storm_data$PROPDMGEXP
storm_data$CROPDMGVALUE <- storm_data$CROPDMG*storm_data$CROPDMGEXP

Grouping and summarising crop and property damage expenses

economy_data <- storm_data %>% group_by(EVTYPE) %>% summarize(PROPDMGVALUE=sum(PROPDMGVALUE),CROPDMGVALUE = sum(CROPDMGVALUE)) %>% arrange(desc(PROPDMGVALUE+CROPDMGVALUE))

Extracting the top 10 economic losses and plotting

most_economy_loss <- economy_data[1:10,]

economy_gather_data <- gather(most_economy_loss,type,value,PROPDMGVALUE:CROPDMGVALUE)

ggplot(economy_gather_data,aes(y=reorder(EVTYPE,-value),x=value,fill=type)) + geom_bar(stat="identity") + xlab("Count of crop/property damage") + ylab("Events") + ggtitle("Economic Harmful Events")

Results:

Based on the data analysis,the below results were inferred.

1. Tornado is the most harmful event with respect to the health.

2. Flood has the greatest economic consequences.