# ---- Load data ----
## Covid-19 Data
load(url("https://pols2580.paultesta.org/files/data/covid.rda"))
## Presidential Election Data
load(url("https://pols2580.paultesta.org/files/data/pres_df.rda"))
# ---- Recode Covid Data ----
territories <- c(
"American Samoa",
"Guam",
"Northern Mariana Islands",
"Puerto Rico",
"Virgin Islands"
)
# Filter out Territories and create state variable
covid_us <- covid %>%
filter(!administrative_area_level_2 %in% territories)%>%
mutate(
state = administrative_area_level_2
)
# Calculate new cases, new cases per capita, and 7-day average
covid_us %>%
dplyr::group_by(state) %>%
mutate(
new_cases = confirmed - lag(confirmed),
new_cases_pc = new_cases / population *100000,
new_cases_pc_7day = zoo::rollmean(new_cases_pc,
k = 7,
align = "right",
fill=NA )
) -> covid_us
# Recode facemask policy
covid_us %>%
mutate(
# Recode facial_coverings to create face_masks
face_masks = case_when(
facial_coverings == 0 ~ "No policy",
abs(facial_coverings) == 1 ~ "Recommended",
abs(facial_coverings) == 2 ~ "Some requirements",
abs(facial_coverings) == 3 ~ "Required shared places",
abs(facial_coverings) == 4 ~ "Required all times",
),
# Turn face_masks into a factor with ordered policy levels
face_masks = factor(face_masks,
levels = c("No policy","Recommended",
"Some requirements",
"Required shared places",
"Required all times")
)
) -> covid_us
# Create year-month and percent vaccinated variables
covid_us %>%
mutate(
year = year(date),
month = month(date),
year_month = paste(year,
str_pad(month, width = 2, pad=0),
sep = "-"),
percent_vaccinated = people_fully_vaccinated/population*100
) -> covid_us
# Recode Deaths
covid_us %>%
dplyr::group_by(state) %>%
mutate(
new_deaths = deaths - lag(deaths),
new_deaths_pc = new_deaths / population *100000,
new_deaths_pc_7day = zoo::rollmean(new_deaths_pc,
k = 7,
align = "right",
fill=NA ),
new_deaths_pc_14day = zoo::rollmean(new_deaths_pc,
k = 14,
align = "right",
fill=NA )
) -> covid_us
# ---- Recode Presidential Election Data ----
# Transform Presidential Election data
pres_df %>%
mutate(
year_election = year,
state = str_to_title(state),
# Fix DC
state = ifelse(state == "District Of Columbia", "District of Columbia", state)
) %>%
filter(party_simplified %in% c("DEMOCRAT","REPUBLICAN"))%>%
filter(year == 2020) %>%
select(state, state_po, year_election, party_simplified, candidatevotes, totalvotes
) %>%
pivot_wider(names_from = party_simplified,
values_from = candidatevotes) %>%
mutate(
dem_voteshare = DEMOCRAT/totalvotes*100,
rep_voteshare = REPUBLICAN/totalvotes*100,
winner = forcats::fct_rev(factor(ifelse(rep_voteshare > dem_voteshare,"Trump","Biden")))
) -> pres2020_df
# ---- Merge Data ----
dim(covid_us)
