#Introduction ###Public health and econimic problems are affected by a number of reasons i am now going to analysize how storms and other severe weather events play a part. Storms and severe weather conditions causes fatalities and injuries and substantial property damage. Hence to minimze damages we should analyse the given data.

###This project requires us to analyse the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database tracks when and where major storms and weather events occur in the United States, estimated of any fatalities, injuries, and property damage figures are also provided.

#Libraries:

library(dplyr)
## Warning: package 'dplyr' was built under R version 4.0.3
## 
## 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
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.0.3

#Load data

df<-read.csv("C:/Users/dsanchezc/Documents/R vp/Vp/Rvp/repdata_data_StormData.csv")
df.fatalities <- df %>% select(EVTYPE, FATALITIES) %>% group_by(EVTYPE) %>% summarise(total.fatalities = sum(FATALITIES)) %>% arrange(-total.fatalities)
## `summarise()` ungrouping output (override with `.groups` argument)
head(df.fatalities, 10)
## # A tibble: 10 x 2
##    EVTYPE         total.fatalities
##    <chr>                     <dbl>
##  1 TORNADO                    5633
##  2 EXCESSIVE HEAT             1903
##  3 FLASH FLOOD                 978
##  4 HEAT                        937
##  5 LIGHTNING                   816
##  6 TSTM WIND                   504
##  7 FLOOD                       470
##  8 RIP CURRENT                 368
##  9 HIGH WIND                   248
## 10 AVALANCHE                   224

#Across the United States, which types of events (as indicated in the EVTYPE variable) are most harmful with respect to population health?

###Fatalities

df.fatalities <- df %>% select(EVTYPE, FATALITIES) %>% group_by(EVTYPE) %>% summarise(total.fatalities = sum(FATALITIES)) %>% arrange(-total.fatalities)
## `summarise()` ungrouping output (override with `.groups` argument)
head(df.fatalities, 10)
## # A tibble: 10 x 2
##    EVTYPE         total.fatalities
##    <chr>                     <dbl>
##  1 TORNADO                    5633
##  2 EXCESSIVE HEAT             1903
##  3 FLASH FLOOD                 978
##  4 HEAT                        937
##  5 LIGHTNING                   816
##  6 TSTM WIND                   504
##  7 FLOOD                       470
##  8 RIP CURRENT                 368
##  9 HIGH WIND                   248
## 10 AVALANCHE                   224

###Injures

df.injuries <- df %>% select(EVTYPE, INJURIES) %>% group_by(EVTYPE) %>% summarise(total.injuries = sum(INJURIES)) %>% arrange(-total.injuries)
## `summarise()` ungrouping output (override with `.groups` argument)
head(df.injuries, 10)
## # A tibble: 10 x 2
##    EVTYPE            total.injuries
##    <chr>                      <dbl>
##  1 TORNADO                    91346
##  2 TSTM WIND                   6957
##  3 FLOOD                       6789
##  4 EXCESSIVE HEAT              6525
##  5 LIGHTNING                   5230
##  6 HEAT                        2100
##  7 ICE STORM                   1975
##  8 FLASH FLOOD                 1777
##  9 THUNDERSTORM WIND           1488
## 10 HAIL                        1361

#Across the United States, which types of events have the greatest economic consequences? ###Economic variables (PROPDMG,CROPDMG,PROPDMGEXP,CROPDMGEXP) calculate the total damage:

df.damage <- df %>% select(EVTYPE, PROPDMG,PROPDMGEXP,CROPDMG,CROPDMGEXP)
Symbol <- sort(unique(as.character(df.damage$PROPDMGEXP)))
Multiplier <- c(0,0,0,1,10,10,10,10,10,10,10,10,10,10^9,10^2,10^2,10^3,10^6,10^6)
convert.Multiplier <- data.frame(Symbol, Multiplier)
df.damage$Prop.Multiplier <- convert.Multiplier$Multiplier[match(df.damage$PROPDMGEXP, convert.Multiplier$Symbol)]
df.damage$Crop.Multiplier <- convert.Multiplier$Multiplier[match(df.damage$CROPDMGEXP, convert.Multiplier$Symbol)]
df.damage <- df.damage %>% mutate(PROPDMG = PROPDMG*Prop.Multiplier) %>% mutate(CROPDMG = CROPDMG*Crop.Multiplier) %>% mutate(TOTAL.DMG = PROPDMG+CROPDMG)
df.damage.total <- df.damage %>% group_by(EVTYPE) %>% summarize(TOTAL.DMG.EVTYPE = sum(TOTAL.DMG))%>% arrange(-TOTAL.DMG.EVTYPE) 
## `summarise()` ungrouping output (override with `.groups` argument)
head(df.damage.total,10)
## # A tibble: 10 x 2
##    EVTYPE            TOTAL.DMG.EVTYPE
##    <chr>                        <dbl>
##  1 FLOOD                 150319678250
##  2 HURRICANE/TYPHOON      71913712800
##  3 TORNADO                57352117607
##  4 STORM SURGE            43323541000
##  5 FLASH FLOOD            17562132111
##  6 DROUGHT                15018672000
##  7 HURRICANE              14610229010
##  8 RIVER FLOOD            10148404500
##  9 ICE STORM               8967041810
## 10 TROPICAL STORM          8382236550

#Results ###Top 10 events with the highest total fatalities and injuries

g <- ggplot(df.fatalities[1:10,], aes(x=reorder(EVTYPE, -total.fatalities), y=total.fatalities))+geom_bar(stat="identity") + theme(axis.text.x = element_text(angle=90, vjust=0.5, hjust=1))+ggtitle("Top 10 Events with Highest Total Fatalities") +labs(x="EVENT TYPE", y="Total Fatalities")
g

###Event type

g <- ggplot(df.injuries[1:10,], aes(x=reorder(EVTYPE, -total.injuries), y=total.injuries))+geom_bar(stat="identity") + theme(axis.text.x = element_text(angle=90, vjust=0.5, hjust=1))+ggtitle("Top 10 Events with Highest Total Injuries") +labs(x="EVENT TYPE", y="Total Injuries")
g

###Economic impact

g <- ggplot(df.damage.total[1:10,], aes(x=reorder(EVTYPE, -TOTAL.DMG.EVTYPE), y=TOTAL.DMG.EVTYPE))+geom_bar(stat="identity") + theme(axis.text.x = element_text(angle=90, vjust=0.5, hjust=1))+ggtitle("Top 10 Events with Highest Economic Impact") +labs(x="EVENT TYPE", y="Total Economic Impact ($USD)")

g