Tornadoes are the most devasting weather event in the Unites States

Synopsis

The analysis was conducted by using the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database contains characteristics of major storms and weather events in the United States, and holds estimates about casualties, injuries and damages. In the following report, we compile the 10 most harmful events for each of these 3 categories, and conclude that tornado are in the lead for every one. Hence, tornadoes constitute a hazard on the safety of citizens and economy.

Data Processing

Loading the raw data and loading the libraries. The data was first downloaded from the link : ” https://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2” and stored in the working directory. The raw data was then read with the read_csv R function. No manipulation of the data was done by that point.

Results

Health Damages

Sorting the top 10 weather events causing fatalities

top_10_fatalities <- repdata_data_StormData_csv %>% 
  group_by(EVTYPE) %>% 
  summarise(total_fatalities = sum(FATALITIES, na.rm = T)) %>% 
  arrange(desc(total_fatalities)) %>% 
  head(10)

Plotting them on a histogram

ggplot(top_10_fatalities, aes(x = reorder(EVTYPE, -total_fatalities), 
  y = total_fatalities)) + 
  geom_bar(stat = "identity", fill = "red") + 
  labs(x = "Event Type", y = "Total Fatalities", 
       title = "Top 10 Weather Events by Fatalities") + 
  theme_minimal(base_size = 15) + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) 

Tornado is by far the event that causes the most casualties

The same is done for injuries

top_10_injuries <- repdata_data_StormData_csv %>% 
  group_by(EVTYPE) %>% 
  summarise(total_injuries = sum(INJURIES)) %>% 
  arrange(desc(total_injuries)) %>% 
  head(10)

ggplot(top_10_injuries, aes(x = reorder(EVTYPE, -total_injuries), 
                              y = total_injuries)) + 
  geom_bar(stat = "identity", fill = "blue") + 
  labs(x = "Event Type", y = "Total Injuries", 
       title = "Top 10 Weather Events by Injuries") + 
  theme_minimal(base_size = 15) + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) 

Tornado takes the lead by far.

Economic Damages

We also look at the total property damage that each type of weather event causes

top_10_eco_dmg <- repdata_data_StormData_csv %>% 
  group_by(EVTYPE) %>% 
  summarise(total_eco_dmg = sum(PROPDMG)) %>% 
  arrange(desc(total_eco_dmg)) %>% 
  head(10)

ggplot(top_10_eco_dmg, aes(x = reorder(EVTYPE, -total_eco_dmg),
                           y = total_eco_dmg)) + 
  geom_bar(stat = "identity", fill = "lightgreen") + 
  labs(x = "Event Type", y = "Total Economic Damage in USD", 
  title = "Top 10 Weather Events by Economic Damage") + 
  theme_minimal(base_size = 15) + 
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Tornadoes cause the most property damages in the United States.