1: Synopsis

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 between 1950 and November 2011. 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.

The following analysis investigates which types of severe weather events are most harmful on:

Health (injuries and fatalities)
Property and crops (economic consequences)

2: Analysis

loading the libraries that will be used in the project.

library("data.table")
library("ggplot2")

Data Loading

using the URL to download the data, then using the dataset converting it to a format that is easy to read and analyse

Data Processing

displaying the column names of the dataset

colnames(stormDT)

##  [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"

Removing the columns that are not important for the analysis, and leaving the ones that are important. Omiting all the columns except the ones mentioned.
using the entries with the fatalities and/or injuries had occurred. This is to ensure the events brought one of the impact.

# Finding columns to remove
cols2Remove <- colnames(stormDT[, !c("EVTYPE"
  , "FATALITIES"
  , "PROPDMGEXP"
  , "CROPDMG"
  , "INJURIES"
  , "PROPDMG"
  , "CROPDMGEXP")])

# Removing columns
stormDT[, c(cols2Remove) := NULL]

# Only use data where fatalities or injuries occurred.  
stormDT <- stormDT[(EVTYPE != "?" & 
             (INJURIES > 0 | FATALITIES > 0 | PROPDMG > 0 | CROPDMG > 0)), c("EVTYPE"
                                                                            , "FATALITIES"
                                                                            , "INJURIES"
                                                                            , "PROPDMG"
                                                                            , "PROPDMGEXP"
                                                                            , "CROPDMG"
                                                                            , "CROPDMGEXP") ]

From the files how variables where constructed then, reconstructing the columns from string to numeric.

# Change all damage exponents to uppercase.
cols <- c("PROPDMGEXP", "CROPDMGEXP")
stormDT[,  (cols) := c(lapply(.SD, toupper)), .SDcols = cols]

# Map property damage alphanumeric exponents to numeric values.
propDmgKey <-  c("\"\"" = 10^0,
                 "-" = 10^0, 
                 "+" = 10^0,
                 "0" = 10^0, 
                 "7" = 10^7,
                 "8" = 10^8,
                 "9" = 10^9,
                 "H" = 10^2,
                 "K" = 10^3,
                 "1" = 10^1,
                 "2" = 10^2,
                 "3" = 10^3,
                 "4" = 10^4,
                 "5" = 10^5,
                 "6" = 10^6,
                 "M" = 10^6,
                 "B" = 10^9)

# Map crop damage alphanumeric exponents to numeric values
cropDmgKey <-  c("\"\"" = 10^0,
                "?" = 10^0,
                "K" = 10^3,
                "M" = 10^6,
                "0" = 10^0,
                "B" = 10^9)

stormDT[, PROPDMGEXP := propDmgKey[as.character(stormDT[,PROPDMGEXP])]]
stormDT[is.na(PROPDMGEXP), PROPDMGEXP := 10^0 ]

stormDT[, CROPDMGEXP := cropDmgKey[as.character(stormDT[,CROPDMGEXP])] ]
stormDT[is.na(CROPDMGEXP), CROPDMGEXP := 10^0 ]

stormDT <- stormDT[, .(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, propCost = PROPDMG * PROPDMGEXP, CROPDMG, CROPDMGEXP, cropCost = CROPDMG * CROPDMGEXP)]

Resuts.

Evaluating and ordering the cost, TotalCost per each weather event

totalCostDT <- stormDT[, .(propCost = sum(propCost), cropCost = sum(cropCost), Total_Cost = sum(propCost) + sum(cropCost)), by = .(EVTYPE)]

totalCostDT <- totalCostDT[order(-Total_Cost), ]

totalCostDT <- totalCostDT[1:10, ]

head(totalCostDT, 5)

##               EVTYPE     propCost   cropCost   Total_Cost
## 1:             FLOOD 136345613417 4405175450 140750788867
## 2: HURRICANE/TYPHOON  69305840000 2607872800  71913712800
## 3:           TORNADO  46491581827  380956270  46872538097
## 4:       STORM SURGE  43323536000       5000  43323541000
## 5:       FLASH FLOOD  14829916879 1184128100  16014044979

Evaluating the total facilities and injuries per each weather event. Ordering the events too.

totalInjuriesDT <- stormDT[, .(FATALITIES = sum(FATALITIES), INJURIES = sum(INJURIES), totals = sum(FATALITIES) + sum(INJURIES)), by = .(EVTYPE)]

totalInjuriesDT <- totalInjuriesDT[order(-FATALITIES), ]

totalInjuriesDT <- totalInjuriesDT[1:10, ]

head(totalInjuriesDT, 5)

##            EVTYPE FATALITIES INJURIES totals
## 1:        TORNADO       5017    84792  89809
## 2: EXCESSIVE HEAT       1828     6324   8152
## 3:    FLASH FLOOD        864     1562   2426
## 4:           HEAT        831     1450   2281
## 5:      LIGHTNING        765     4888   5653

Visualisation of the results

Weather Events that are most harmful to the health

bad_stuff <- melt(totalInjuriesDT, id.vars="EVTYPE", variable.name = "bad_thing")
head(bad_stuff, 5)

##            EVTYPE  bad_thing value
## 1:        TORNADO FATALITIES  5017
## 2: EXCESSIVE HEAT FATALITIES  1828
## 3:    FLASH FLOOD FATALITIES   864
## 4:           HEAT FATALITIES   831
## 5:      LIGHTNING FATALITIES   765

# Create chart
healthChart <- ggplot(bad_stuff, aes(x=reorder(EVTYPE, -value), y=value))

# Plot data as bar chart
healthChart = healthChart + geom_bar(stat="identity", aes(fill=bad_thing), position="dodge")

# Format y-axis scale and set y-axis label
healthChart = healthChart + ylab("Frequency Count") 

# Set x-axis label
healthChart = healthChart + xlab("Event Type") 

# Rotate x-axis tick labels 
healthChart = healthChart + theme(axis.text.x = element_text(angle=45, hjust=1))

# Set chart title and center it
healthChart = healthChart + ggtitle("Top 10 US Killers") + theme(plot.title = element_text(hjust = 0.5))

healthChart

Cost leading to economic consequences.

econ_consequences <- melt(totalCostDT, id.vars="EVTYPE", variable.name = "Damage_Type")
head(econ_consequences, 5)

##               EVTYPE Damage_Type        value
## 1:             FLOOD    propCost 136345613417
## 2: HURRICANE/TYPHOON    propCost  69305840000
## 3:           TORNADO    propCost  46491581827
## 4:       STORM SURGE    propCost  43323536000
## 5:       FLASH FLOOD    propCost  14829916879

# Create chart
econChart <- ggplot(econ_consequences, aes(x=reorder(EVTYPE, -value), y=value))

# Plot data as bar chart
econChart = econChart + geom_bar(stat="identity", aes(fill=Damage_Type), position="dodge")

# Format y-axis scale and set y-axis label
econChart = econChart + ylab("Cost (dollars)") 

# Set x-axis label
econChart = econChart + xlab("Event Type") 

# Rotate x-axis tick labels 
econChart = econChart + theme(axis.text.x = element_text(angle=45, hjust=1))

# Set chart title and center it
econChart = econChart + ggtitle("Top 10 US Storm Events causing Economic Consequences") + theme(plot.title = element_text(hjust = 0.5))

econChart

Data Analysis to show impact of weather to health

Gloria Gabriel

2023-01-10