In this report we aim to investigate the impact of sever weather events on population health and economy across the United States between the years 1950 and 2011. Our goal is to identify the most harmful types of events with respect to population health, and the types of events that have the greatest economic consequences. To achive this goal, we used the U.S. National Oceanic and Atmospheric Administration's (NOAA) storm database.
Our findings show that convection, flood, and winter related weather events are respectively the most harmful types of events. On the other hand, flood, tropical cyclones, and convection related weather events have respectively the greatest economic consequences. Marine related events are the least harmful with lowest economic consequences.
This section describes how the data were loaded into R and processed for analysis.
1 - Downloading the Data:
# To avoid the Error message: 'unsupported URL scheme message' generated by
# Knitr when downloading from https
setInternet2(TRUE)
# Data file url
url <- "https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2"
# Create the directory 'data' if it doesn't exist
if (!file.exists("data")) {
dir.create("data")
}
# Download the data file
download.file(url, "data/stormData.csv.bz2")
# Record the date the file was downloaded
date_downloaded <- date()
date_downloaded
## [1] "Sun May 25 17:07:06 2014"
2 - Reading the Data:
# Opening a connection with the compressed data file
conn <- bzfile("data/stormData.csv.bz2", open = "r")
# Reading the data from the connection
data <- read.csv(conn, stringsAsFactors = FALSE, strip.white = TRUE)
# Closing the connection
close(conn)
3 - Exploring the Data:
Looking at a summary of the data using str and summary functions:
str(data)
## 'data.frame': 902297 obs. of 37 variables:
## $ STATE__ : num 1 1 1 1 1 1 1 1 1 1 ...
## $ BGN_DATE : chr "4/18/1950 0:00:00" "4/18/1950 0:00:00" "2/20/1951 0:00:00" "6/8/1951 0:00:00" ...
## $ BGN_TIME : chr "0130" "0145" "1600" "0900" ...
## $ TIME_ZONE : chr "CST" "CST" "CST" "CST" ...
## $ COUNTY : num 97 3 57 89 43 77 9 123 125 57 ...
## $ COUNTYNAME: chr "MOBILE" "BALDWIN" "FAYETTE" "MADISON" ...
## $ STATE : chr "AL" "AL" "AL" "AL" ...
## $ EVTYPE : chr "TORNADO" "TORNADO" "TORNADO" "TORNADO" ...
## $ BGN_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ BGN_AZI : chr "" "" "" "" ...
## $ BGN_LOCATI: chr "" "" "" "" ...
## $ END_DATE : chr "" "" "" "" ...
## $ END_TIME : chr "" "" "" "" ...
## $ COUNTY_END: num 0 0 0 0 0 0 0 0 0 0 ...
## $ COUNTYENDN: logi NA NA NA NA NA NA ...
## $ END_RANGE : num 0 0 0 0 0 0 0 0 0 0 ...
## $ END_AZI : chr "" "" "" "" ...
## $ END_LOCATI: chr "" "" "" "" ...
## $ LENGTH : num 14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
## $ WIDTH : num 100 150 123 100 150 177 33 33 100 100 ...
## $ F : int 3 2 2 2 2 2 2 1 3 3 ...
## $ MAG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ FATALITIES: num 0 0 0 0 0 0 0 0 1 0 ...
## $ INJURIES : num 15 0 2 2 2 6 1 0 14 0 ...
## $ PROPDMG : num 25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
## $ PROPDMGEXP: chr "K" "K" "K" "K" ...
## $ CROPDMG : num 0 0 0 0 0 0 0 0 0 0 ...
## $ CROPDMGEXP: chr "" "" "" "" ...
## $ WFO : chr "" "" "" "" ...
## $ STATEOFFIC: chr "" "" "" "" ...
## $ ZONENAMES : chr "" "" "" "" ...
## $ LATITUDE : num 3040 3042 3340 3458 3412 ...
## $ LONGITUDE : num 8812 8755 8742 8626 8642 ...
## $ LATITUDE_E: num 3051 0 0 0 0 ...
## $ LONGITUDE_: num 8806 0 0 0 0 ...
## $ REMARKS : chr "" "" "" "" ...
## $ REFNUM : num 1 2 3 4 5 6 7 8 9 10 ...
summary(data)
## STATE__ BGN_DATE BGN_TIME TIME_ZONE
## Min. : 1.0 Length:902297 Length:902297 Length:902297
## 1st Qu.:19.0 Class :character Class :character Class :character
## Median :30.0 Mode :character Mode :character Mode :character
## Mean :31.2
## 3rd Qu.:45.0
## Max. :95.0
##
## COUNTY COUNTYNAME STATE EVTYPE
## Min. : 0 Length:902297 Length:902297 Length:902297
## 1st Qu.: 31 Class :character Class :character Class :character
## Median : 75 Mode :character Mode :character Mode :character
## Mean :101
## 3rd Qu.:131
## Max. :873
##
## BGN_RANGE BGN_AZI BGN_LOCATI END_DATE
## Min. : 0 Length:902297 Length:902297 Length:902297
## 1st Qu.: 0 Class :character Class :character Class :character
## Median : 0 Mode :character Mode :character Mode :character
## Mean : 1
## 3rd Qu.: 1
## Max. :3749
##
## END_TIME COUNTY_END COUNTYENDN END_RANGE
## Length:902297 Min. :0 Mode:logical Min. : 0
## Class :character 1st Qu.:0 NA's:902297 1st Qu.: 0
## Mode :character Median :0 Median : 0
## Mean :0 Mean : 1
## 3rd Qu.:0 3rd Qu.: 0
## Max. :0 Max. :925
##
## END_AZI END_LOCATI LENGTH WIDTH
## Length:902297 Length:902297 Min. : 0.0 Min. : 0
## Class :character Class :character 1st Qu.: 0.0 1st Qu.: 0
## Mode :character Mode :character Median : 0.0 Median : 0
## Mean : 0.2 Mean : 8
## 3rd Qu.: 0.0 3rd Qu.: 0
## Max. :2315.0 Max. :4400
##
## F MAG FATALITIES INJURIES
## Min. :0 Min. : 0 Min. : 0 Min. : 0.0
## 1st Qu.:0 1st Qu.: 0 1st Qu.: 0 1st Qu.: 0.0
## Median :1 Median : 50 Median : 0 Median : 0.0
## Mean :1 Mean : 47 Mean : 0 Mean : 0.2
## 3rd Qu.:1 3rd Qu.: 75 3rd Qu.: 0 3rd Qu.: 0.0
## Max. :5 Max. :22000 Max. :583 Max. :1700.0
## NA's :843563
## PROPDMG PROPDMGEXP CROPDMG CROPDMGEXP
## Min. : 0 Length:902297 Min. : 0.0 Length:902297
## 1st Qu.: 0 Class :character 1st Qu.: 0.0 Class :character
## Median : 0 Mode :character Median : 0.0 Mode :character
## Mean : 12 Mean : 1.5
## 3rd Qu.: 0 3rd Qu.: 0.0
## Max. :5000 Max. :990.0
##
## WFO STATEOFFIC ZONENAMES LATITUDE
## Length:902297 Length:902297 Length:902297 Min. : 0
## Class :character Class :character Class :character 1st Qu.:2802
## Mode :character Mode :character Mode :character Median :3540
## Mean :2875
## 3rd Qu.:4019
## Max. :9706
## NA's :47
## LONGITUDE LATITUDE_E LONGITUDE_ REMARKS
## Min. :-14451 Min. : 0 Min. :-14455 Length:902297
## 1st Qu.: 7247 1st Qu.: 0 1st Qu.: 0 Class :character
## Median : 8707 Median : 0 Median : 0 Mode :character
## Mean : 6940 Mean :1452 Mean : 3509
## 3rd Qu.: 9605 3rd Qu.:3549 3rd Qu.: 8735
## Max. : 17124 Max. :9706 Max. :106220
## NA's :40
## REFNUM
## Min. : 1
## 1st Qu.:225575
## Median :451149
## Mean :451149
## 3rd Qu.:676723
## Max. :902297
##
4 - Selecting the Data of Interest:
We are interested in the weather events that have either fatalities, injuries, crop damage or property damage
# Number of observations in the whole data
nrow(data)
## [1] 902297
# Selecting data with fatalities, injuries, crop damage orproperty damage
reduced_data <- data[data$FATALITIES > 0 | data$INJURIES > 0 | data$PROPDMG >
0 | data$CROPDMG > 0, ]
# Number of observations in the new data set
nrow(reduced_data)
## [1] 254633
As shown above, we reduced the size of the data from 902297 to 254633 observations.
5 - Exploaring the Types of Weather Events in the Data::
# The number of unique weather events in the data (Case-sensitive)
length(unique(reduced_data$EVTYPE))
## [1] 488
# The number of unique weather events in the data (all lower case)
length(unique(tolower(reduced_data$EVTYPE)))
## [1] 447
# Converting the raw types of events to lower case
reduced_data$EVTYPE <- tolower(reduced_data$EVTYPE)
# Creating a data frame with the frequency of raw events
raw_events <- as.data.frame(table(reduced_data$EVTYPE))
# Adding names to the data frame
names(raw_events) <- c("event", "frequency")
# Ordering the data frame based on decreasing frequency
raw_events <- raw_events[order(raw_events$frequency, decreasing = TRUE), ]
# Looking at the 40 top raw events in the data
head(raw_events, n = 40)
## event frequency
## 386 tstm wind 63235
## 329 thunderstorm wind 43655
## 371 tornado 39944
## 116 hail 26130
## 65 flash flood 20967
## 233 lightning 13293
## 346 thunderstorm winds 12086
## 78 flood 10175
## 179 high wind 5522
## 319 strong wind 3372
## 441 winter storm 1508
## 151 heavy snow 1342
## 140 heavy rain 1105
## 433 wildfire 857
## 216 ice storm 708
## 419 urban/sml stream fld 702
## 54 excessive heat 698
## 187 high winds 657
## 400 tstm wind/hail 441
## 381 tropical storm 416
## 444 winter weather 407
## 276 rip current 400
## 431 wild/forest fire 388
## 74 flash flooding 302
## 82 flood/flash flood 279
## 11 avalanche 268
## 43 drought 266
## 14 blizzard 253
## 277 rip currents 241
## 133 heat 215
## 59 extreme cold 199
## 220 lake-effect snow 194
## 224 landslide 193
## 317 storm surge 177
## 22 coastal flood 168
## 230 light snow 141
## 413 urban flood 139
## 446 winter weather/mix 139
## 174 high surf 136
## 194 hurricane 129
6 - Events Types Transformation::
As shown in the previous section, the raw types of events (in reduced_data$EVTYPE) have many malformed values and overlapping types. In addition, the number of unique values is big for the purpose of this analysis. Therefore, we decided to merge the 447 types of events into 7 types of events. The new types of events are: convection, extreme temperatures, flood, marine, tropical cyclones, winter, and other.
# Add a new column to the reduced data frame to store the merged type of
# events, and assign the value 'other'
reduced_data$merged_events <- "other"
# Creating sub-events for to be merged
convection <- "lightning|tornado|thunderstorm wind|tstm wind|hail|high wind|strong wind|strong winds|thunderstorm winds|thunderstorm windss|high winds|wind|winds|gusty wind|tstm wind/hail|tstm wind (g40)|thunderstorm winds lightning|tornado f0|tornado f1|thunderstorm wind/ trees|hail 275|hailstorm|thunderstorm winds|thunderstorms wind|thundertorm winds|tstm wind|hail/winds|hail/wind|hail 175"
extreme_temperatures <- "heat|cold|extreme cold|excessive heat|warm weather|freeze|frost/freeze|cold weather|low temperature|extreme cold/wind chill"
flood <- "flash flood|flood|flash flooding|flood/flash flood|coastal flood|urban flood|lakeshore flood|flash flooding/flood|urban/small stream flood|heavy rains/flooding|flash floods|flash flood/flood|river flooding|flooding|coastal flooding|urban flooding|river flood|urban/sml stream fld"
marine <- "rip current|storm surge/tide|heavy surf/high surf|marine strong wind|marine tstm wind|marine thunderstorm wind|tsunami|coastal storm"
tropical_cyclones <- "hurricane|tropical storm|hurricane/typhoon|hurricane erin|hurricane opal"
winter <- "winter storm|ice storm|heavy snow|heavy rain|winter weather|avalanche|lake-effect snow|storm surge|light snow|winter weather/mix|lake effect snow|freezing rain/snow|damaging freeze|rain|freezing drizzle|snow freezing rain|snow squalls|heavy snow-squalls|heavy snow-squalls|heavy rains|light freezing rain|glaze|excessive snow|freezing rain|snow|frost/freeze"
# Merging the raw types of events to the 7 new types
reduced_data$merged_events[grepl(convection, reduced_data$EVTYPE)] <- "convection"
reduced_data$merged_events[grepl(extreme_temperatures, reduced_data$EVTYPE)] <- "extreme temperatures"
reduced_data$merged_events[grepl(flood, reduced_data$EVTYPE)] <- "flood"
reduced_data$merged_events[grepl(marine, reduced_data$EVTYPE)] <- "marine"
reduced_data$merged_events[grepl(tropical_cyclones, reduced_data$EVTYPE)] <- "tropical cyclones"
reduced_data$merged_events[grepl(winter, reduced_data$EVTYPE)] <- "winter"
# Converting the new types of events to a factor
reduced_data$merged_events <- as.factor(reduced_data$merged_events)
Looking at the new merged types of events:
new_events <- as.data.frame(table(reduced_data$merged_events))
# Adding names to the data frame
names(new_events) <- c("event", "frequency")
# Ordering the data frame based on decreasing frequency
new_events <- new_events[order(new_events$frequency, decreasing = TRUE), ]
# Looking at the new events
new_events
## event frequency
## 1 convection 208900
## 3 flood 33163
## 7 winter 6544
## 5 other 3005
## 2 extreme temperatures 1477
## 4 marine 899
## 6 tropical cyclones 645
7 - Exploaring the columns related to property and crop damages (PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP):
Looking at summary for PROPDMG and CROPDMG:
# summary forr PROPDMG
summary(reduced_data$PROPDMG)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 2 5 43 25 5000
# summary for CROPDMG
summary(reduced_data$CROPDMG)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 5.4 0.0 990.0
Looking at the unique values for PROPDMGEXP and CROPDMGEXP:
# Uniques valuse for PROPDMGEXP
unique(reduced_data$PROPDMGEXP)
## [1] "K" "M" "" "B" "m" "+" "0" "5" "6" "4" "h" "2" "7" "3" "H" "-"
# Uniques valuse for CROPDMGEXP
unique(reduced_data$CROPDMGEXP)
## [1] "" "M" "K" "m" "B" "?" "0" "k"
8 - Transformation for PROPDMGEXP and CROPDMGEXP:
As shown in section 6, we need to transform the PROPDMGEXP and CROPDMGEXP (to reflect the actual numerical values) in order to use them in our analysis. For this analysis, we consider four numarical values(hundred (h), thousands (k), millions (m), billions (b) ). The remaning values (e.g. “+” “0” “5”, etc.) were ignored due to their ambiguity. Then we create new columns to store the property and crop numerical values of damage.
# Convertin to lower case
reduced_data$PROPDMGEXP <- tolower(reduced_data$PROPDMGEXP)
reduced_data$CROPDMGEXP <- tolower(reduced_data$CROPDMGEXP)
# Set of valid values
valid_values <- c("h", "k", "m", "b")
# Subsetting the data to include only observations with valid values
reduced_data <- reduced_data[reduced_data$PROPDMGEXP %in% valid_values, ]
reduced_data <- reduced_data[reduced_data$CROPDMGEXP %in% valid_values, ]
# Subsetting the data to exclude observations with zero value in PROPDMG or
# CROPDMG
reduced_data <- reduced_data[reduced_data$CROPDMG != 0 | reduced_data$PROPDMG !=
0, ]
# Relacing the valid values by their numerical values
reduced_data$PROPDMGEXP <- gsub("b", 1e+09, reduced_data$PROPDMGEXP)
reduced_data$PROPDMGEXP <- gsub("m", 1e+06, reduced_data$PROPDMGEXP)
reduced_data$PROPDMGEXP <- gsub("k", 1000, reduced_data$PROPDMGEXP)
reduced_data$PROPDMGEXP <- gsub("h", 100, reduced_data$PROPDMGEXP)
reduced_data$CROPDMGEXP <- gsub("b", 1e+09, reduced_data$CROPDMGEXP)
reduced_data$CROPDMGEXP <- gsub("m", 1e+06, reduced_data$CROPDMGEXP)
reduced_data$CROPDMGEXP <- gsub("k", 1000, reduced_data$CROPDMGEXP)
reduced_data$CROPDMGEXP <- gsub("h", 100, reduced_data$CROPDMGEXP)
# Converting to numarical values
reduced_data$PROPDMGEXP <- as.numeric(reduced_data$PROPDMGEXP)
reduced_data$CROPDMGEXP <- as.numeric(reduced_data$CROPDMGEXP)
# Creating new columns to store property and crop numerical values of
# damage.
reduced_data$prob_dmg <- reduced_data$PROPDMG * reduced_data$PROPDMGEXP
# summary of property damage
summary(reduced_data$prob_dmg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00e+00 3.00e+03 1.00e+04 2.41e+06 3.50e+04 1.15e+11
reduced_data$crop_dmg <- reduced_data$CROPDMG * reduced_data$CROPDMGEXP
# summary of crop damage
summary(reduced_data$crop_dmg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0e+00 0.0e+00 0.0e+00 3.2e+05 0.0e+00 5.0e+09
# Total damage
reduced_data$total_dmg <- reduced_data$prob_dmg + reduced_data$prob_dmg
# summary of total damage
summary(reduced_data$total_dmg)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00e+00 6.00e+03 2.00e+04 4.82e+06 7.00e+04 2.30e+11
9 - Exploaring the 'FATALITIES' and 'INJURIES' columns:
Looking at summary for FATALITIES and INJURIES:
# summary for FATALITIES
summary(reduced_data$FATALITIES)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 0.02 0.00 158.00
# summary for INJURIES
summary(reduced_data$INJURIES)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 0.3 0.0 1570.0
Therefore, no transormation is required for these columns.
This section presents the results of our analysis to answer the two main questions.
1 - The Most Harmful Types of Events with Respect to Population Health (across the United States):
Aggregating injuries and fatalities over event types
# Aggregation injuries per event
injuries_per_event <- aggregate(INJURIES ~ merged_events, reduced_data, sum)
# Ordering injuries per event
injuries_per_event <- injuries_per_event[order(injuries_per_event$INJURIES,
decreasing = TRUE), ]
injuries_per_event
## merged_events INJURIES
## 1 convection 13390
## 3 flood 7104
## 7 winter 2013
## 6 tropical cyclones 1296
## 5 other 1005
## 2 extreme temperatures 519
## 4 marine 137
# Aggregation fatalities per event
fatalities_per_event <- aggregate(FATALITIES ~ merged_events, reduced_data,
sum)
# Ordering fatalities per event
fatalities_per_event <- fatalities_per_event[order(fatalities_per_event$FATALITIES,
decreasing = TRUE), ]
fatalities_per_event
## merged_events FATALITIES
## 1 convection 1186
## 3 flood 516
## 6 tropical cyclones 100
## 5 other 92
## 2 extreme temperatures 76
## 7 winter 72
## 4 marine 39
# Aggregation total health impact (injuries + fatalities) per event
total_health_per_event <- aggregate((INJURIES + FATALITIES) ~ merged_events,
reduced_data, sum)
# Ordering total health impact per event
names(total_health_per_event) <- c("merged_events", "INJURIES_plus_FATALITIES")
total_health_per_event <- total_health_per_event[order(total_health_per_event$INJURIES_plus_FATALITIES,
decreasing = TRUE), ]
total_health_per_event
## merged_events INJURIES_plus_FATALITIES
## 1 convection 14576
## 3 flood 7620
## 7 winter 2085
## 6 tropical cyclones 1396
## 5 other 1097
## 2 extreme temperatures 595
## 4 marine 176
# Adding a new column to be used for figures
injuries_per_event$health_type <- "INJURIES"
fatalities_per_event$health_type <- "FATALITIES"
names(injuries_per_event) <- c("merged_events", "count", "health_type")
names(fatalities_per_event) <- c("merged_events", "count", "health_type")
# Combining both data frames
health_impact_per_event <- rbind(injuries_per_event, fatalities_per_event)
# Loading ggplo2 package
library(ggplot2)
# Ploting the property and crop damage per event type
qplot(as.factor(merged_events), count, data = health_impact_per_event, geom = "bar",
stat = "identity", position = "dodge", fill = health_type, xlab = "Type of Event",
ylab = "Count of Casualties", main = "Impact of Sever Weather Events on Population Health in US from 1950 to 2011")
As shown from the tables and figure, the convection related weather events are the most harmful types of events with respect to population health. Flood and winter related events come in the second and third place respictively. Marine related events are the least harmful types of events with respect to population health.
2 - The Types of Events which Have the Greatest Economic Consequences (across the United States):
Aggregating Property and Crop Damage over Event Eypes
# Property damage per event type
prop_damage_per_event <- aggregate(prob_dmg ~ merged_events, reduced_data, sum)
# Ordering the property damage
prop_damage_per_event <- prop_damage_per_event[order(prop_damage_per_event$prob_dmg,
decreasing = TRUE), ]
prop_damage_per_event
## merged_events prob_dmg
## 3 flood 1.460e+11
## 6 tropical cyclones 4.004e+10
## 1 convection 3.306e+10
## 7 winter 7.225e+09
## 5 other 4.147e+09
## 4 marine 1.449e+08
## 2 extreme temperatures 1.255e+08
# Crop damage per event type
crop_damage_per_event <- aggregate(crop_dmg ~ merged_events, reduced_data, sum)
# Ordering the crop damage
crop_damage_per_event <- crop_damage_per_event[order(crop_damage_per_event$crop_dmg,
decreasing = TRUE), ]
crop_damage_per_event
## merged_events crop_dmg
## 3 flood 1.174e+10
## 7 winter 6.258e+09
## 6 tropical cyclones 5.801e+09
## 1 convection 4.260e+09
## 5 other 2.091e+09
## 2 extreme temperatures 5.037e+08
## 4 marine 7.000e+04
# Total (property + crop) damage per event type
total_damage_per_event <- aggregate((prob_dmg + crop_dmg) ~ merged_events, reduced_data,
sum)
names(total_damage_per_event) <- c("merged_events", "total_dmg")
# Ordering the crop damage
total_damage_per_event <- total_damage_per_event[order(total_damage_per_event$total_dmg,
decreasing = TRUE), ]
total_damage_per_event
## merged_events total_dmg
## 3 flood 1.578e+11
## 6 tropical cyclones 4.584e+10
## 1 convection 3.732e+10
## 7 winter 1.348e+10
## 5 other 6.238e+09
## 2 extreme temperatures 6.292e+08
## 4 marine 1.450e+08
# Adding a new column to be used for figures
prop_damage_per_event$dmg_type <- "PROPDMG"
crop_damage_per_event$dmg_type <- "CROPDMG"
names(prop_damage_per_event) <- c("merged_events", "dmg_value", "dmg_type")
names(crop_damage_per_event) <- c("merged_events", "dmg_value", "dmg_type")
# Combining both data frames
damage_per_event <- rbind(prop_damage_per_event, crop_damage_per_event)
# Ploting the property and crop damage per event type
qplot(as.factor(merged_events), dmg_value/1e+09, data = damage_per_event, geom = "bar",
stat = "identity", position = "dodge", fill = dmg_type, xlab = "Type of Event",
ylab = "Damage (in Billions of Dollars)", main = "Economic Consequences (property and crop damage) of Sever Weather Events in US from 1950 to 2011")
As shown in the figures, the flood related events have the greatest economic consequences. The tropical cyclones and convection come in the second and third places respectively. Marine related weather events have the lowest economic consequences.
# Ploting the total damage per event type
qplot(as.factor(merged_events), total_dmg/1e+09, data = total_damage_per_event,
geom = "bar", stat = "identity", position = "stack", fill = merged_events,
xlab = "Type of Event", ylab = "Damage (in Billions of Dollars)", main = "Total Economic Consequences of Sever Weather Events in US from 1950 to 2011")
