HW1.Q3.halatshafer

library('tidyverse')

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✔ ggplot2 3.3.6     ✔ purrr   0.3.4
## ✔ tibble  3.1.7     ✔ dplyr   1.0.9
## ✔ tidyr   1.2.0     ✔ stringr 1.4.0
## ✔ readr   2.1.2     ✔ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

UScovid <- read.csv("/Users/kylerhalat-shafer/Desktop/UVA/MSDS/STAT 6021/Day 1 - R Basics/UScovid.csv")

Part A.)

statelevel <- UScovid%>%
  filter(date == '2021-06-03')%>%
  select(-c(county,fips,date))%>%
  group_by(state)%>%
  summarize(new_cases=sum(cases),new_deaths=sum(deaths))

head(statelevel)

Part B.)

statelevel <- statelevel%>%
  mutate(death.rate = round(new_deaths/new_cases,2))

head(statelevel)

Part C.)

Case fatality is .02

statelevel%>%
  filter(state == 'Virginia')

Part D.)

Case fatality cannot be determined for Puerto Rico becasue deaths is not available.

statelevel%>%
  filter(state == 'Puerto Rico')

Part E.)

statelevel%>%
  slice_max(death.rate,n=10)

Part F.)

statelevel%>%
  slice_min(death.rate,n=10)

Part G.)

State_pop_election <- read.csv("/Users/kylerhalat-shafer/Desktop/UVA/MSDS/STAT 6021/Day 1 - R Basics/State_pop_election.csv")

State_pop_election <- State_pop_election%>%
  rename(state = State)

state_info <- statelevel %>%
  inner_join(State_pop_election, by='state')

head(state_info)

Part H.)

state_info%>%
ggplot(aes(x=new_cases, y=new_deaths, size = Population, color=Election))+ 
  geom_point(alpha  = 0.5)

## Warning: Removed 1 rows containing missing values (geom_point).

  #facet_wrap(~state)