1. Pre Processing the Data

1.1 Load the data into R

setwd("~/Desktop/Data Science Specialization/data")

if(!file.exists("./data")){dir.create("./data")}
fileUrl <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
download.file(fileUrl,destfile="./data/Dataset.zip")

unzip(zipfile="./data/Dataset.zip",exdir="./data")

## Warning in unzip(zipfile = "./data/Dataset.zip", exdir = "./data"): error 1
## in extracting from zip file

storm <- read.csv("~/Desktop/Data Science Specialization/StormData.csv")

1.2 Load the required R packages

library(plyr)
library(ggplot2)
library(grid)
library(gridExtra)

2 Data Processing

2.1 Review the questions to be answered

#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?

2.2 Extract only the necessary data for this specific analysis

head(storm)

##   STATE__           BGN_DATE BGN_TIME TIME_ZONE COUNTY COUNTYNAME STATE
## 1       1  4/18/1950 0:00:00     0130       CST     97     MOBILE    AL
## 2       1  4/18/1950 0:00:00     0145       CST      3    BALDWIN    AL
## 3       1  2/20/1951 0:00:00     1600       CST     57    FAYETTE    AL
## 4       1   6/8/1951 0:00:00     0900       CST     89    MADISON    AL
## 5       1 11/15/1951 0:00:00     1500       CST     43    CULLMAN    AL
## 6       1 11/15/1951 0:00:00     2000       CST     77 LAUDERDALE    AL
##    EVTYPE BGN_RANGE BGN_AZI BGN_LOCATI END_DATE END_TIME COUNTY_END
## 1 TORNADO         0                                               0
## 2 TORNADO         0                                               0
## 3 TORNADO         0                                               0
## 4 TORNADO         0                                               0
## 5 TORNADO         0                                               0
## 6 TORNADO         0                                               0
##   COUNTYENDN END_RANGE END_AZI END_LOCATI LENGTH WIDTH F MAG FATALITIES
## 1         NA         0                      14.0   100 3   0          0
## 2         NA         0                       2.0   150 2   0          0
## 3         NA         0                       0.1   123 2   0          0
## 4         NA         0                       0.0   100 2   0          0
## 5         NA         0                       0.0   150 2   0          0
## 6         NA         0                       1.5   177 2   0          0
##   INJURIES PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP WFO STATEOFFIC ZONENAMES
## 1       15    25.0          K       0                                    
## 2        0     2.5          K       0                                    
## 3        2    25.0          K       0                                    
## 4        2     2.5          K       0                                    
## 5        2     2.5          K       0                                    
## 6        6     2.5          K       0                                    
##   LATITUDE LONGITUDE LATITUDE_E LONGITUDE_ REMARKS REFNUM
## 1     3040      8812       3051       8806              1
## 2     3042      8755          0          0              2
## 3     3340      8742          0          0              3
## 4     3458      8626          0          0              4
## 5     3412      8642          0          0              5
## 6     3450      8748          0          0              6

event <- c("EVTYPE", "FATALITIES", "INJURIES", "PROPDMG", "PROPDMGEXP", "CROPDMG", 
           "CROPDMGEXP")
data <- storm[event]

2.3 Find Property Damage

unique(data$PROPDMGEXP)

##  [1] K M   B m + 0 5 6 ? 4 2 3 h 7 H - 1 8
## Levels:  - ? + 0 1 2 3 4 5 6 7 8 B h H K m M

data$PROPEXP[data$PROPDMGEXP == "K"] <- 1000
data$PROPEXP[data$PROPDMGEXP == "M"] <- 1e+06
data$PROPEXP[data$PROPDMGEXP == ""] <- 1
data$PROPEXP[data$PROPDMGEXP == "B"] <- 1e+09
data$PROPEXP[data$PROPDMGEXP == "m"] <- 1e+06
data$PROPEXP[data$PROPDMGEXP == "0"] <- 1
data$PROPEXP[data$PROPDMGEXP == "5"] <- 1e+05
data$PROPEXP[data$PROPDMGEXP == "6"] <- 1e+06
data$PROPEXP[data$PROPDMGEXP == "4"] <- 10000
data$PROPEXP[data$PROPDMGEXP == "2"] <- 100
data$PROPEXP[data$PROPDMGEXP == "3"] <- 1000
data$PROPEXP[data$PROPDMGEXP == "h"] <- 100
data$PROPEXP[data$PROPDMGEXP == "7"] <- 1e+07
data$PROPEXP[data$PROPDMGEXP == "H"] <- 100
data$PROPEXP[data$PROPDMGEXP == "1"] <- 10
data$PROPEXP[data$PROPDMGEXP == "8"] <- 1e+08

data$PROPEXP[data$PROPDMGEXP == "+"] <- 0
data$PROPEXP[data$PROPDMGEXP == "-"] <- 0
data$PROPEXP[data$PROPDMGEXP == "?"] <- 0

data$PROPDMGVAL <- data$PROPDMG * data$PROPEXP

2.4 Find crop damage

unique(data$CROPDMGEXP)

## [1]   M K m B ? 0 k 2
## Levels:  ? 0 2 B k K m M

data$CROPEXP[data$CROPDMGEXP == "M"] <- 1e+06
data$CROPEXP[data$CROPDMGEXP == "K"] <- 1000
data$CROPEXP[data$CROPDMGEXP == "m"] <- 1e+06
data$CROPEXP[data$CROPDMGEXP == "B"] <- 1e+09
data$CROPEXP[data$CROPDMGEXP == "0"] <- 1
data$CROPEXP[data$CROPDMGEXP == "k"] <- 1000
data$CROPEXP[data$CROPDMGEXP == "2"] <- 100
data$CROPEXP[data$CROPDMGEXP == ""] <- 1

data$CROPEXP[data$CROPDMGEXP == "?"] <- 0

data$CROPDMGVAL <- data$CROPDMG * data$CROPEXP

2.5 Total the data by event

fatal <- aggregate(FATALITIES ~ EVTYPE, data, FUN = sum)
injury <- aggregate(INJURIES ~ EVTYPE, data, FUN = sum)
propdmg <- aggregate(PROPDMGVAL ~ EVTYPE, data, FUN = sum)
cropdmg <- aggregate(CROPDMGVAL ~ EVTYPE, data, FUN = sum)

2.6 Find and plot events with the highest events and fatalities (e.g., most harmful)

fatal8 <- fatal[order(-fatal$FATALITIES), ][1:8, ]

injury8 <- injury[order(-injury$INJURIES), ][1:8, ]
par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(fatal8$FATALITIES, las = 3, names.arg = fatal8$EVTYPE, main = "Events with Highest Fatalities", 
        ylab = "Number of fatalities", col = "blue")
barplot(injury8$INJURIES, las = 3, names.arg = injury8$EVTYPE, main = "Events with Highest Injuries", 
        ylab = "Number of injuries", col = "blue")

2.7 Find and plot events with highest property damage

propdmg8 <- propdmg[order(-propdmg$PROPDMGVAL), ][1:8, ]

cropdmg8 <- cropdmg[order(-cropdmg$CROPDMGVAL), ][1:8, ]
par(mfrow = c(1, 2), mar = c(12, 4, 3, 2), mgp = c(3, 1, 0), cex = 0.8)
barplot(propdmg8$PROPDMGVAL/(10^9), las = 3, names.arg = propdmg8$EVTYPE, 
        main = "Events with Highest Property Damages", ylab = "Damage Cost ($ billions)", 
        col = "blue")
barplot(cropdmg8$CROPDMGVAL/(10^9), las = 3, names.arg = cropdmg8$EVTYPE, 
        main = "Events With Highest Crop Damages", ylab = "Damage Cost ($ billions)", 
        col = "blue")

Results

# The weather events that were the most harmful were analyzed using fatalities and injuries as a proxy to "harmfulness." We discovered that Tornados by far cause the most fatalities *and* injuries compared to other weather events. Excessive heat and flash floods caused the second and third most fatalities, respectively. TSTM Wind and floods caused the second and third most injuries, respectively.
# The economic consequences of these weather events was analuzed using property damages and crop damages as a proxy to "economic consequence." Floods caused the most property damage, followed by hurricanes/typhoons and tornados. Droughts caused the most crop damage, followed by floods and riverfloods.
# Overall, tornados appear to be the most harmful weather event, and floods (considering property and crop damages together) appear to have the most *negative* economic consequences.