File_data <- "StormData.csv"
if (!file.exists(File_data)) {
download.file(Url_data, File_data, mode = "wb")
}
# reading data
Raw_data <- read.csv(file = File_data, header=TRUE, sep=",")
# subsetting by date
Main_data <- Raw_data
Main_data$BGN_DATE <- strptime(Raw_data$BGN_DATE, "%m/%d/%Y %H:%M:%S")
Main_data <- subset(Main_data, BGN_DATE > "1995-12-31")
Main_data <- subset(Main_data, select = c(EVTYPE, FATALITIES, INJURIES, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP))
#cleaning event types names
Main_data$EVTYPE <- toupper(Main_data$EVTYPE)
# eliminating zero data
Main_data <- Main_data[Main_data$FATALITIES !=0 |
Main_data$INJURIES !=0 |
Main_data$PROPDMG !=0 |
Main_data$CROPDMG !=0, ]
Health_data <- aggregate(cbind(FATALITIES, INJURIES) ~ EVTYPE, data = Main_data, FUN=sum)
Health_data$PEOPLE_LOSS <- Health_data$FATALITIES + Health_data$INJURIES
Health_data <- Health_data[order(Health_data$PEOPLE_LOSS, decreasing = TRUE), ]
Top10_events_people <- Health_data[1:10,]
knitr::kable(Top10_events_people, format = "markdown")
| 149 |
TORNADO |
1511 |
20667 |
22178 |
| 39 |
EXCESSIVE HEAT |
1797 |
6391 |
8188 |
| 48 |
FLOOD |
414 |
6758 |
7172 |
| 107 |
LIGHTNING |
651 |
4141 |
4792 |
| 153 |
TSTM WIND |
241 |
3629 |
3870 |
| 46 |
FLASH FLOOD |
887 |
1674 |
2561 |
| 146 |
THUNDERSTORM WIND |
130 |
1400 |
1530 |
| 182 |
WINTER STORM |
191 |
1292 |
1483 |
| 69 |
HEAT |
237 |
1222 |
1459 |
| 88 |
HURRICANE/TYPHOON |
64 |
1275 |
1339 |
Main_data$PROPDMGEXP <- gsub("[Hh]", "2", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- gsub("[Kk]", "3", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- gsub("[Mm]", "6", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- gsub("[Bb]", "9", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- gsub("\\+", "1", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- gsub("\\?|\\-|\\ ", "0", Main_data$PROPDMGEXP)
Main_data$PROPDMGEXP <- as.numeric(Main_data$PROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("[Hh]", "2", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("[Kk]", "3", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("[Mm]", "6", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("[Bb]", "9", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("\\+", "1", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- gsub("\\-|\\?|\\ ", "0", Main_data$CROPDMGEXP)
Main_data$CROPDMGEXP <- as.numeric(Main_data$CROPDMGEXP)
Main_data$PROPDMGEXP[is.na(Main_data$PROPDMGEXP)] <- 0
Main_data$CROPDMGEXP[is.na(Main_data$CROPDMGEXP)] <- 0
#creating total damage values
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
Main_data <- mutate(Main_data,
PROPDMGTOTAL = PROPDMG * (10 ^ PROPDMGEXP),
CROPDMGTOTAL = CROPDMG * (10 ^ CROPDMGEXP))
Economic_data <- aggregate(cbind(PROPDMGTOTAL, CROPDMGTOTAL) ~ EVTYPE, data = Main_data, FUN=sum)
Economic_data$ECONOMIC_LOSS <- Economic_data$PROPDMGTOTAL + Economic_data$CROPDMGTOTAL
Economic_data <- Economic_data[order(Economic_data$ECONOMIC_LOSS, decreasing = TRUE), ]
Top10_events_economy <- Economic_data[1:10,]
knitr::kable(Top10_events_economy, format = "markdown")
| 48 |
FLOOD |
143944833550 |
4974778400 |
148919611950 |
| 88 |
HURRICANE/TYPHOON |
69305840000 |
2607872800 |
71913712800 |
| 141 |
STORM SURGE |
43193536000 |
5000 |
43193541000 |
| 149 |
TORNADO |
24616945710 |
283425010 |
24900370720 |
| 66 |
HAIL |
14595143420 |
2476029450 |
17071172870 |
| 46 |
FLASH FLOOD |
15222203910 |
1334901700 |
16557105610 |
| 86 |
HURRICANE |
11812819010 |
2741410000 |
14554229010 |
| 32 |
DROUGHT |
1046101000 |
13367566000 |
14413667000 |
| 152 |
TROPICAL STORM |
7642475550 |
677711000 |
8320186550 |
| 83 |
HIGH WIND |
5247860360 |
633561300 |
5881421660 |
#plotting health loss
library(ggplot2)
g <- ggplot(data = Top10_events_people, aes(x = reorder(EVTYPE, PEOPLE_LOSS), y = PEOPLE_LOSS))
g <- g + geom_bar(stat = "identity", colour = "black")
g <- g + labs(title = "Total people loss in USA by weather events in 1996-2011")
g <- g + theme(plot.title = element_text(hjust = 0.5))
g <- g + labs(y = "Number of fatalities and injuries", x = "Event Type")
g <- g + coord_flip()
print(g)
#plotting economic loss
g <- ggplot(data = Top10_events_economy, aes(x = reorder(EVTYPE, ECONOMIC_LOSS), y = ECONOMIC_LOSS))
g <- g + geom_bar(stat = "identity", colour = "black")
g <- g + labs(title = "Total economic loss in USA by weather events in 1996-2011")
g <- g + theme(plot.title = element_text(hjust = 0.5))
g <- g + labs(y = "Size of property and crop loss", x = "Event Type")
g <- g + coord_flip()
print(g)
