Problem Statement:

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.

This report consists in analyzing the NOAA storm database containing data on extreme climate events. This data was collected during the period from 1950 through 2011. The purpose of this analysis is 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?

Basic Packages Used :

echo = TRUE           # Always make code visible
options(scipen = 1)   # Turn off scientific notations for numbers
library(grid)
library(ggplot2)
library(plyr)
library(dplyr)

require(gridExtra)

storm <- read.csv("/Users/repdata_data_StormData.csv",sep = ",",header = TRUE, stringsAsFactors = FALSE)
dim(storm)

## [1] 902297     37

Data Extraction from the text (Text Analysis)

events <- c("Astronomical Low Tide", "Avalanche", "Blizzard", "Coastal Flood", "Cold/Wind Chill", "Debris Flow", "Dense Fog", "Dense Smoke", "Drought", "Dust Devil", "Dust Storm", "Excessive Heat", "Extreme cold/Wind Chill", "Flash Flood", "Flood", "Freezing", "Frost/Freeze", "Funnel Cloud", "Hail", "Heat", "Heavy Rain", "Heavy Snow", "High Surf", "High Wind", "Hurricane/Typhoon", "Ice Storm", "Lakeshore Flood", "Lake-Effect Snow", "Lightning", "Marine Hail", "Marine High Wind", "Marine Strong Wind", "Marine Thunderstorm Wind", "Rip Current", "Seiche", "Sleet", "Storm Tide", "Strong Wind", "Thunderstorm Wind", "Tornado", "Tropical Depression", "Tropical Storm", "Tsunami", "Volcanic Ash", "Waterspout", "Wildfire", "Winter Storm", "Winter Weather")  

Using Regex function 😆 (To be precise of the text from the dataset)

events_regex <- c("Astronomical Low Tide|Low Tide", "Avalanche", "Blizzard", "Coastal Flood", "Cold/Wind Chill", "Debris Flow", "Dense Fog", "Dense Smoke", "Drought", "Dust Devil", "Dust Storm", "Excessive Heat", "Extreme cold/Wind Chill|Extreme Cold|Wind Chill", "Flash Flood", "Flood", "Freezing", "Frost/Freeze|Frost|Freeze", "Funnel Cloud", "Hail", "Heat", "Heavy Rain", "Heavy Snow", "High Surf", "High Wind", "Hurricane/Typhoon|Hurricane|Typhoon", "Ice Storm", "Lakeshore Flood", "Lake-Effect Snow", "Lightning", "Marine Hail", "Marine High Wind", "Marine Strong Wind", "Marine Thunderstorm Wind|Marine tstm Wind", "Rip Current", "Seiche", "Sleet", "Storm Tide", "Strong Wind", "Thunderstorm Wind|tstm wind", "Tornado", "Tropical Depression", "Tropical Storm", "Tsunami", "Volcanic Ash", "Waterspout", "Wildfire", "Winter Storm", "Winter Weather")  

Extracting rows into corresponding events :

• 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)

options(scipen = 999)  # force fixed notation of numbers instead of scientific
cleandata <- data.frame(EVTYPE = character(0), FATALITIES = numeric(0), INJURIES = numeric(0), PROPDMG = numeric(0), PROPDMGEXP = character(0), CROPDMG = numeric(0), CROPDMGEXP = character(0))  
for (i in 1:length(events)) {
    rows <- storm[grep(events_regex[i], ignore.case = TRUE, storm$EVTYPE), ]
    rows <- rows[, c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", "CROPDMGEXP")]
    CLEANNAME <- c(rep(events[i], nrow(rows)))
    rows <- cbind(rows, CLEANNAME)
    cleandata <- rbind(cleandata, rows)
}

# convert letter exponents to integers
cleandata[(cleandata$PROPDMGEXP == "K" | cleandata$PROPDMGEXP == "k"), ]$PROPDMGEXP <- 3
cleandata[(cleandata$PROPDMGEXP == "M" | cleandata$PROPDMGEXP == "m"), ]$PROPDMGEXP <- 6
cleandata[(cleandata$PROPDMGEXP == "B" | cleandata$PROPDMGEXP == "b"), ]$PROPDMGEXP <- 9
cleandata[(cleandata$CROPDMGEXP == "K" | cleandata$CROPDMGEXP == "k"), ]$CROPDMGEXP <- 3
cleandata[(cleandata$CROPDMGEXP == "M" | cleandata$CROPDMGEXP == "m"), ]$CROPDMGEXP <- 6
cleandata[(cleandata$CROPDMGEXP == "B" | cleandata$CROPDMGEXP == "b"), ]$CROPDMGEXP <- 9

fatalities <- aggregate(FATALITIES ~ CLEANNAME, data = cleandata, FUN = sum)
fatalities <- fatalities[order(fatalities$FATALITIES, decreasing = TRUE), ]
# 10 most harmful causes of fatalities
MaxFatalities <- fatalities[1:10, ]
print(MaxFatalities) 

##                  CLEANNAME FATALITIES
## 38                 Tornado       5661
## 19                    Heat       3138
## 11          Excessive Heat       1922
## 14                   Flood       1525
## 13             Flash Flood       1035
## 28               Lightning        817
## 37       Thunderstorm Wind        753
## 33             Rip Current        577
## 12 Extreme cold/Wind Chill        382
## 23               High Wind        299

injuries <- aggregate(INJURIES ~ CLEANNAME, data = cleandata, FUN = sum)
injuries <- injuries[order(injuries$INJURIES, decreasing = TRUE), ]
# 10 most harmful causes of injuries
MaxInjuries <- injuries[1:10, ]
print(MaxInjuries)

##            CLEANNAME INJURIES
## 38           Tornado    91407
## 37 Thunderstorm Wind     9493
## 19              Heat     9224
## 14             Flood     8604
## 11    Excessive Heat     6525
## 28         Lightning     5232
## 25         Ice Storm     1992
## 13       Flash Flood     1802
## 23         High Wind     1523
## 18              Hail     1467

par(mfrow = c(1, 2), mar = c(15, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(MaxFatalities$FATALITIES, las = 3, names.arg = MaxFatalities$CLEANNAME, main = "Weather Events With\n The Top 10 Highest Fatalities", ylab = "Number of Fatalities", col = "grey")
barplot(MaxInjuries$INJURIES, las = 3, names.arg = MaxInjuries$CLEANNAME, main = "Weather Events With\n The Top 10 Highest Injuries", ylab = "Number of Injuries", col = "grey")