The basic goal of this document was to explore the NOAA Storm Database and answer some basic questions about severe weather events using analysis that can consist of tables, figures, or other summaries and show all the code in R to support the analysis.
for this analysis i decide to use the following packages for organize, analyse and visualize the results of my analysis.
library(rio)
library(dplyr)
library(tibble)
library(ggplot2)
library(gridExtra)
In this part of my code i decide to use de library rio for load the dataset in R.
For this i used the function import() as we can see in the next code line.
data <- import("./data/repdata_data_StormData.csv")
For respond the question of which events were most harmful with respect to population health, we try to analyse in two different ways.
- Looking for the total of Injuries in United States.
- Looking for the total of Fatalities in United States
and compare how was the behavior foe each of them.
harmful <- data %>%
select(EVTYPE,INJURIES, FATALITIES) %>%
group_by(EVTYPE) %>%
summarise(INJURIES=sum(INJURIES), FATALITIES= sum(FATALITIES))
harmful <- arrange(harmful, desc(FATALITIES), desc(INJURIES))
harmful_top <- head(harmful,10)
as_tibble(harmful_top)
## # A tibble: 10 × 3
## EVTYPE INJURIES FATALITIES
## <chr> <dbl> <dbl>
## 1 TORNADO 91346 5633
## 2 EXCESSIVE HEAT 6525 1903
## 3 FLASH FLOOD 1777 978
## 4 HEAT 2100 937
## 5 LIGHTNING 5230 816
## 6 TSTM WIND 6957 504
## 7 FLOOD 6789 470
## 8 RIP CURRENT 232 368
## 9 HIGH WIND 1137 248
## 10 AVALANCHE 170 224
showing that Tornado is the most harmful event for injuries and fatalities in United States in that period or time
p1 <- harmful %>%
filter(INJURIES >= 1100L & INJURIES <= 91346L) %>%
ggplot() +
aes(x = reorder(EVTYPE, INJURIES) , y = INJURIES) +
geom_col(fill = "#112446") +
theme_minimal()+
coord_flip()
p2 <- harmful %>%
filter(FATALITIES >= 224L & FATALITIES <= 5633L) %>%
ggplot() +
aes(x = reorder(EVTYPE, FATALITIES), y = FATALITIES) +
geom_col(fill = "orange") +
theme_minimal()+
coord_flip()
grid.arrange(p1, p2, ncol = 1)
Finally for see which of the events was the one that generate the biggest economic consequence, we replicate the last process but using the variables EVTYPE, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP.
For this first i decide to multiply the variables PROPDMG and CROPDMG for their respective exponential for see the complete number group by each event and them add the grouped values to find the total cost for each event and create a new column for tehe total of the cost of the cost calculated and see wich is the total cost for each event.
cost <- data %>%
select(EVTYPE, PROPDMG, PROPDMGEXP, CROPDMG, CROPDMGEXP) %>%
mutate(PROPDMG_final = case_when(PROPDMGEXP == "K" ~ PROPDMG * 1000,
PROPDMGEXP == "M" ~ PROPDMG * 1000000,
PROPDMGEXP == "B" ~ PROPDMG * 1000000000,
TRUE~0)) %>%
mutate(CROPDMG_final = case_when(CROPDMGEXP == "K" ~ CROPDMG * 1000,
CROPDMGEXP == "M" ~ CROPDMG * 1000000,
CROPDMGEXP == "B" ~ CROPDMG * 1000000000,
TRUE~0))
cost_final <- cost %>%
select(EVTYPE, PROPDMG_final, CROPDMG_final) %>%
group_by(EVTYPE) %>%
summarise(PROPDMG_final = sum(PROPDMG_final), PROPDMG_final = sum(CROPDMG_final))
cost_final$final_cost <- cost_final$PROPDMG_final + cost_final$PROPDMG_final
cost_final %>%
filter(final_cost >= 967610099 & final_cost <= 289315419600) %>%
ggplot() +
aes(x = reorder(EVTYPE, final_cost), y = final_cost) +
geom_col(fill = "#112446") +
coord_flip() +
theme_minimal()
This
analysis found that the event that generate more economic damages in
unite states was drought following by
flood