Synopsis: Through analyzing the data provided by the NOAA storm database, this project evaluate the severe weather types which cause great population and economic lost across the United States from 1950 to 2011. The total population lost include the fatality and injury amount. The total economic lost includes the lost caused by property damage and crop damage. The evaluation provides the result that TORNADO causes the greatest damage on both population and economics.

Data Processing:

read the file

general_table <- read.csv("repdata_data_StormData.csv")
cache = TRUE

re-arrange the dataset by types

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
grouped_df<-
    general_table %>%
    group_by(EVTYPE) %>%
    summarise(total_fatality = sum(FATALITIES), total_injuries = sum(INJURIES)) %>%
    mutate(total_population_damage = total_fatality + total_injuries) %>%
    arrange(desc(total_population_damage))

find which event has most damage on population health

weather_population<- grouped_df$EVTYPE[which.max(grouped_df$total_population_damage)]
populationDM_num <- max(grouped_df$total_population_damage)
head(grouped_df,10)
## # A tibble: 10 × 4
##    EVTYPE            total_fatality total_injuries total_population_damage
##    <chr>                      <dbl>          <dbl>                   <dbl>
##  1 TORNADO                     5633          91346                   96979
##  2 EXCESSIVE HEAT              1903           6525                    8428
##  3 TSTM WIND                    504           6957                    7461
##  4 FLOOD                        470           6789                    7259
##  5 LIGHTNING                    816           5230                    6046
##  6 HEAT                         937           2100                    3037
##  7 FLASH FLOOD                  978           1777                    2755
##  8 ICE STORM                     89           1975                    2064
##  9 THUNDERSTORM WIND            133           1488                    1621
## 10 WINTER STORM                 206           1321                    1527

From the data, we can see TORNADO cause the most population damage across the country. Including both Injuries and Fatalities, the total lost of population caused by TORNADO is 9.6979^{4}

Below is the bar chart of the population damage caused by different severe weather types. The plot only shows the non-zero values.

library(ggplot2)
library(patchwork)

non_zero_value <- grouped_df[grouped_df$total_population_damage != 0,]
plot1<-ggplot(non_zero_value, aes(x = reorder(EVTYPE, total_population_damage, decreasing=TRUE), y = total_population_damage)) +
  geom_bar(stat = "identity") +
  labs(x = "Weather Types", y = "Damage Num", title = "Severe Weather Damage on Popultaion") +
  theme_minimal() +
      theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5)) 
  
plot2<-ggplot(non_zero_value[1:10,], aes(x = reorder(EVTYPE, total_population_damage, decreasing=TRUE), y = total_population_damage)) +
  geom_bar(stat = "identity") +
  labs(x = "Weather Types", y = "Damage Num", title = "Zoomed In Plot") +
  theme_minimal() +
      theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5)) 

combined_plot<-plot1/plot2 + plot_layout(ncol=1,heights = c(1,2))
combined_plot

cache = TRUE

Find the economic lost across different weather types

library(tidyr)
value_df <- general_table %>%
    mutate(PROPDMGEXP = 
              case_when(PROPDMGEXP == "M" ~ 1e6,
                        PROPDMGEXP == "B" ~ 1e9,
                        PROPDMGEXP == "K" ~ 1e3,
                        TRUE ~ as.numeric(PROPDMGEXP))) %>%
    mutate(CROPDMGEXP = 
               case_when(CROPDMGEXP == "M" ~ 1e6,
                         CROPDMGEXP == "B" ~ 1e9,
                         CROPDMGEXP == "K" ~ 1e3,
                         TRUE ~ as.numeric(CROPDMGEXP))) %>%
    replace_na(list(PROPDMGEXP=0,CROPDMGEXP=0)) %>%
    mutate(PROPDMG_num = PROPDMG * PROPDMGEXP) %>%
    mutate(CROPDMG_num = CROPDMG * CROPDMGEXP) %>%
    group_by(EVTYPE) %>%
    summarise(total_prop_lost = sum(PROPDMG_num), total_crop_lost = sum(CROPDMG_num)) %>%
    mutate(total_econ_lost = total_prop_lost + total_crop_lost) %>%
    arrange(desc(total_econ_lost))
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `PROPDMGEXP = case_when(...)`.
## Caused by warning:
## ! NAs introduced by coercion
## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `CROPDMGEXP = case_when(...)`.
## Caused by warning:
## ! NAs introduced by coercion

Find which weather type cause the greatest economic lost

weather_econ<-value_df$EVTYPE[which.max(value_df$total_econ_lost)]
econDM_num <- max(value_df$total_econ_lost)
head(value_df,10)
## # A tibble: 10 × 4
##    EVTYPE            total_prop_lost total_crop_lost total_econ_lost
##    <chr>                       <dbl>           <dbl>           <dbl>
##  1 FLOOD               144657709800       5661968450   150319678250 
##  2 HURRICANE/TYPHOON    69305840000       2607872800    71913712800 
##  3 TORNADO              56925660991        414953110    57340614101 
##  4 STORM SURGE          43323536000             5000    43323541000 
##  5 HAIL                 15727366870       3025537450    18752904320 
##  6 FLASH FLOOD          16140812087.      1421317100    17562129187.
##  7 DROUGHT               1046106000      13972566000    15018672000 
##  8 HURRICANE            11868319010       2741910000    14610229010 
##  9 RIVER FLOOD           5118945500       5029459000    10148404500 
## 10 ICE STORM             3944927810       5022113500     8967041310

From the data, we can see FLOOD cause the most economic lost across the country. Including both Property Damage and Crop Damage, the total lost of economics caused by FLOOD is 1.5031968^{11}

Below is the bar chart of the economic lost caused by different severe weather types. The plot only shows the non-zero values.

non_zero_econvalue <-value_df[value_df$total_econ_lost !=0,]
plot3<-ggplot(non_zero_econvalue, aes(x = reorder(EVTYPE, total_econ_lost, decreasing=TRUE), y = total_econ_lost)) +
    geom_bar(stat = "identity") +
    labs(x = "Weather Types", y = "Lost Num", title = "Severe Weather Damage on Economics") +
    theme_minimal() +
    theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5))

plot4<-ggplot(non_zero_econvalue[1:10,], aes(x = reorder(EVTYPE, total_econ_lost, decreasing=TRUE), y = total_econ_lost)) +
  geom_bar(stat = "identity") +
  labs(x = "Weather Types", y = "Lost Num", title = "Zoomed In Plot") +
  theme_minimal() +
      theme(axis.text.x = element_text(angle = 45, hjust = 1, size = 5)) 

combined_plot_1<-plot3/plot4 + plot_layout(ncol=1,heights = c(1,2))
combined_plot_1

cache = TRUE

Result: From the data, we can see Tornado causes the greatest lost on population and Flood caused the greatest lost on economics through out the years in the United States. Tornado caused 9.6979^{4} of population lost and Flood caused 1.5031968^{11} of economic lost.