New Zealand MiQ covid positivity rate calculation

NZMiQ_postivity.R

library(readxl)
library(readr)
library(dplyr)
library(lubridate)
library(ggplot2)
library(ggthemes)

# arrivals from provisional daily arrivals stats NZ
# postive MiQ data from MoH case demographics

crossings <- read_excel("Downloads/20201223-daily-movements-across-nz-border-Jan-Dec-2019-2020.xlsx", 
                        sheet = "Data", col_types = c("numeric", 
                                                      "numeric", "numeric", "date", "text", 
                                                      "text", "text", "text", "text", "text", 
                                                      "text", "text", "text", "numeric"))
arrivals <- crossings %>%
  filter(travel_mode == "A") %>%
  group_by(date) %>%
  summarise(entries = sum(total_movements))

cases <- read_csv("Downloads/covid_cases_2021-01-10.csv",
col_types = cols(`Report Date` = col_date(format = "%Y-%m-%d")))
MiQ <- cases %>% filter(DHB == "Managed Isolation & Quarantine",
                        `Overseas travel` == "Yes") %>%
  count(`Report Date`) %>%
  rename(date = `Report Date`)
# on the assumption of tests on day 3 and 12
bind_rows(arrivals %>% mutate(date = date + days(3)),
          arrivals %>% mutate(date = date + days(12))) %>%
  group_by(date) %>% 
  summarise(miq_tests = sum(entries)) %>%
  filter(date >= as.Date("2020-07-01"), date < as.Date("2021-01-11")) %>%
  left_join(MiQ, by="date") %>%
  mutate(n = ifelse(is.na(n),0,n),
         positivity_rate = 100 * n/miq_tests) %>%
  ggplot(aes(x=date,y=positivity_rate, xend=date)) +
  geom_segment(yend=0) +
  ggtitle("Assuming day 3 and 12 tests, daily positivity rate for NZ MiQ") +
  theme_minimal() + geom_smooth() +
  ylab("Positive cases per 100 tests")