Vaccinations.Rmd

---
title: "R Notebook"
output: html_notebook
---

Using [Our World in Data vaccination](https://github.com/owid/covid-19-data/tree/master/public/data/vaccinations) data. The vaccination data is at the state level.

**NB**: it might make sense to switch _all_ my data to this, though I'm not sure I have county level data for all of them.

### Citation
Mathieu, E., Ritchie, H., Ortiz-Ospina, E. _et al._ A global database of COVID-19 vaccinations. _Nat Hum Behav_ (2021). [https://doi.org/10.1038/s41562-021-01122-8](https://doi.org/10.1038/s41562-021-01122-8)

## Get The Data
```{r}
library(tidyverse)
vaccinations <- read_csv("https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/vaccinations/us_state_vaccinations.csv") %>%
  mutate(location = replace(location,location == 'New York State', 'New York'))
```

Add a new chunk by clicking the *Insert Chunk* button on the toolbar or by pressing *Cmd+Option+I*.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the *Preview* button or press *Cmd+Shift+K* to preview the HTML file). 

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike *Knit*, *Preview* does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.


### Vaccination Map by State
```{r}
library(choroplethr)
# library(choroplethrMaps)
vaccinations %>%
  filter(date == max(date)) %>%
  select(location,people_fully_vaccinated_per_hundred) %>%
  mutate(location=tolower(location)) %>%
  rename(region= location,value = people_fully_vaccinated_per_hundred) %>%
  choroplethr::state_choropleth(title="Vaccinations Rate", legend = "%", num_colors=1) 

```
### Percent of population vaccinated

```{r}

v_rate <- vaccinations %>%
  filter(date == max(date)) %>%
  select(location,people_fully_vaccinated,people_fully_vaccinated_per_hundred)

v_rate %>% filter(location %in% c('Washington','California','United States'))


```


### Vaccinations over time

Here is a comparison of percent population vaccinated by state over time. I noticed that I had to remove a few _non_ state entities, `r c('United States','Bureau of Prisons','Dept of Defense','Long Term Care','Veterans Health')`

```{r}
vaccinations %>% 
  filter( ! location %in% c('United States','Bureau of Prisons','Dept of Defense','Long Term Care','Veterans Health','Indian Health Svc')) %>%
  select(date,location,people_fully_vaccinated_per_hundred) %>%  
  ggplot(aes(x=date,y=people_fully_vaccinated_per_hundred)) + geom_line() + facet_wrap(~location)
```

Simple plots of daily vaccinations.

```{r}
vaccinations %>% 
  filter( ! location %in% c('United States','Bureau of Prisons','Dept of Defense','Long Term Care','Veterans Health','Indian Health Svc')) %>%
  select(date,location,daily_vaccinations) %>%  
  ggplot(aes(x=date,y=daily_vaccinations)) + geom_line() + facet_wrap(~location)

vaccinations %>% 
  filter( location %in% c('Washington')) %>%
  select(date,location,daily_vaccinations) %>%  
  ggplot(aes(x=date,y=daily_vaccinations)) + geom_line() + facet_wrap(~location)

vaccinations %>% 
  filter( location %in% c('United States')) %>%
  select(date,location,daily_vaccinations) %>%  
  ggplot(aes(x=date,y=daily_vaccinations)) + geom_line() + facet_wrap(~location)

```



### How does vaccination rate compare with new cases

I'm not thinking that the vaccination rate corresponds to slowing the spread of the virus...

```{r}
v_rate <- vaccinations %>%
  filter(date == max(date)) %>%
  select(location,people_fully_vaccinated,people_fully_vaccinated_per_hundred)

cases <- nytimes %>%
  filter(date == max(date)) %>%
  group_by(state) %>%
  summarise(cumulative_cases = sum(cases),population = sum(population))

state_population <- county_population %>%
  group_by(STNAME) %>%
  summarise(population=sum(POPESTIMATE2019))

df <- inner_join(v_rate,cases,c("location" = "state"))

ggplot(df,aes(x=people_fully_vaccinated_per_hundred,y=cumulative_cases)) +
    geom_point() + 
   geom_text(aes(label=location),hjust=1, vjust=1,size=2)+
  geom_smooth()+
   xlab("Percent of state fully vaccinated") + 
  ylab("Cumulative Cases")

ggplot(df,aes(x=people_fully_vaccinated,y=cumulative_cases)) +
    geom_point() + 
  geom_text(aes(label=location),hjust=1, vjust=1,size=2)+
  geom_smooth()+
  xlab("Fully vaccinated population") + 
  ylab("Cumulative Cases")

df <-inner_join(v_rate,state_cases_week_over_week,c("location"="state")) %>%
      left_join(state_population,c("location" = "STNAME"))

ggplot(df,aes(x=people_fully_vaccinated_per_hundred,y=(last_7_days_cases/population*100000))) +
  geom_point() + 
  geom_text(aes(label=location),hjust=1, vjust=1,size=2)+
  geom_smooth()+
  xlab("Percent of state fully vaccinated") + 
  ylab("Last 7 days cases per 100k population")

df %>% 
  left_join(governors,by = c("location"="State")) %>% 
  ggplot(aes(x=people_fully_vaccinated_per_hundred,y=(last_7_days_cases/population*100000))) +
    geom_point(aes(color=Party)) +  scale_color_manual(values=c("blue", "green", "red","gray")) +
    geom_text(aes(label=location),hjust=1, vjust=1,size=2)+
    geom_smooth()+
    xlab("Percent of state fully vaccinated") + 
    ylab("Last 7 days cases per 100k population")


ggplot(df,aes(x=people_fully_vaccinated_per_hundred,y=((last_7_days_cases-last_14_days_cases)/last_14_days_cases))) +
  geom_point(shape=1) + 
  geom_text(aes(label=location),hjust=1, vjust=1,size=2) +
  geom_smooth() +
  xlab("Percent of state fully vaccinated") + 
  ylab("Week over week case growth")


```