Which Applied Epi training is this question referring to?
Live intro course, final exercise using R markdown
Provide an overview of your problem
I’d like to create a dynamic in-line code for the section under header: Weekly epidemic curve by city, which will dynamically update the month (or week) where cases have peaked.
I’m thinking the first step would be to get the week or month/year with the most number of cases, then pipe that into an in-line code. However, I’m at a loss how to start this process. Should I create a new table with the number of cases per week or month? Or can I somehow use the weekly_breaks df that we created for the epi curve?
I’d also like to create a dynamic in-line code for the section under header: Cumulative case incidence by city, which will dynamically update the city with the highest incidence rate in the sentence.
For this part, I was already able to include the actual number of cases using the max(city_table$inc_per_10k). However I don’t know how to “call” the actual name of the city (in this case, College Park) with the highest number of cases.
I will start answering your second question. You can extract the value in the City column with the highest incidence using this line city_table$city[which.max(city_table$inc_per_10k)]. This will give you the name of the city with highest value in the inc_per_10k column.
The first question is more complex because identifying peaks using code is not as simple as identifying them visually. A possible solution would be to create a summarized data frame grouped by months and extract the names of the n months with the highest number of cases, similar to what we did in the second question, the problem is, in this case, if n is 2, the selected months would be either December 2020 and January 2021, which can be interpreted as the same peak, not two peaks.
Therefore, before developing a solution that automatically identifies the peaks of a time series, the ideal would be to define what we would like to call a peak, and this will depend on the data set we have.