source commit: b425700

Author: actions-user

.gitignore

@@ -0,0 +1 @@
+/.quarto/

01-practical-activity-1.R

@@ -0,0 +1,71 @@
+# nolint start
+
+# Practical 1
+# Activity 1
+
+# Load packages ----------------------------------------------------------
+library(cleanepi)
+library(linelist)
+library(incidence2)
+library(tidyverse)
+
+
+# Adapt the data dictionary ----------------------------------------------
+
+# replace 'variable_name' when you have the information
+dat_dictionary <- tibble::tribble(
+  ~options,  ~values,            ~grp, ~orders,
+       "1",   "male", "variable_name",      1L,
+       "2", "female", "variable_name",      2L,
+       "M",   "male", "variable_name",      3L,
+       "F", "female", "variable_name",      4L,
+       "m",   "male", "variable_name",      5L,
+       "f", "female", "variable_name",      6L
+)
+
+dat_dictionary
+
+
+# Read raw data ----------------------------------------------------------
+dat_raw <- readr::read_csv(
+  #<COMPLETE>
+  )
+
+dat_raw
+
+
+# Clean and standardize data ---------------------------------------------
+
+# how many cleanepi functions you used to get clean data?
+dat_clean <- dat_raw %>%
+  cleanepi::#<COMPLETE>
+
+dat_clean
+
+
+# Create time span variable ----------------------------------------------
+
+# what time span unit better describe 'delay' from 'onset' to 'death'?
+dat_timespan <- dat_clean %>%
+  cleanepi::timespan(
+    #<COMPLETE>
+    #<COMPLETE>
+    #<COMPLETE>
+    span_column_name = "timespan_variable",
+    span_remainder_unit = NULL
+  ) %>%
+  # skimr::skim(timespan_variable)
+  # categorize the delay numerical variable
+  dplyr::mutate(
+    timespan_category = base::cut(
+      x = timespan_variable,
+      breaks = #<COMPLETE>, 
+      include.lowest = TRUE,
+      right = FALSE
+    )
+  )
+
+dat_timespan
+
+
+# nolint end

01-practical-activity-2.R

@@ -0,0 +1,58 @@
+# nolint start
+
+# Practical 1
+# Activity 2
+
+# Validate linelist ------------------------------------------------------
+
+# activate Error message
+linelist::lost_tags_action(action = "error")
+# linelist::lost_tags_action(action = "warning")
+
+# print tags types, names, and data to guide make_linelist
+linelist::tags_types()
+linelist::tags_names()
+dat_timespan
+
+# does the age variable pass the validation step?
+dat_validate <- dat_timespan %>% 
+  # tag variables
+  linelist::make_linelist(
+    #<COMPLETE>
+    occupation = "timespan_category" # categorical var.
+  ) %>% 
+  # validate linelist
+  linelist::#<COMPLETE> %>% 
+  # test safeguard
+  # dplyr::select(case_id, date_onset, sex)
+  # INSTEAD
+  linelist::tags_df()
+
+
+# Create incidence -------------------------------------------------------
+
+# what is the most appropriate time-aggregate (days, months) to plot?
+dat_incidence <- dat_validate %>%  
+  # transform from individual-level to time-aggregate
+  incidence2::incidence(
+    date_index = #<COMPLETE>,
+    groups = "occupation", #OR any categorical variable
+    interval = #<COMPLETE>,
+    complete_dates = TRUE
+  )
+
+
+# Plot epicurve ----------------------------------------------------------
+
+# does using arguments like 'fill', 'show_cases', 'angle', 'n_breaks' improve the plot?
+dat_incidence %>% 
+  plot(
+    fill = "occupation", #<KEEP OR DROP>
+    show_cases = TRUE, #<KEEP OR DROP>
+    angle = 45, #<KEEP OR DROP>
+    n_breaks = 5 #<KEEP OR DROP>
+  )
+
+# find plot() arguments at ?incidence2:::plot.incidence2()
+
+# nolint end

02-practical-activity-1.R

@@ -0,0 +1,79 @@
+# nolint start
+
+# Practical 2
+# Activity 1
+
+# Load packages -----------------------------------------------------------
+library(epiparameter)
+library(EpiNow2)
+library(tidyverse)
+
+
+# Read reported cases -----------------------------------------------------
+# for covid
+dat <- read_rds("paste/link/url/here/covid") %>%
+  dplyr::select(date, confirm)
+# or
+# for ebola
+dat <- read_rds("paste/link/url/here/ebola") %>%
+  dplyr::select(date, confirm = cases)
+
+
+# Define a generation time from {epiparameter} to {EpiNow2} ---------------
+
+# access a serial interval
+ebola_serialint <- epiparameter::epiparameter_db(
+  #<COMPLETE>
+)
+
+# extract parameters from {epiparameter} object
+ebola_serialint_params <- epiparameter::#<COMPLETE>
+
+# adapt {epiparameter} to {EpiNow2} distribution inferfase
+ebola_generationtime <- EpiNow2::#<COMPLETE>
+
+
+# Define the delays from infection to case report for {EpiNow2} -----------
+
+# define delay from symptom onset to case report
+ebola_reportdelay <- EpiNow2::#<COMPLETE>
+
+# define a delay from infection to symptom onset
+ebola_incubationtime <- epiparameter::epiparameter_db(
+  #<COMPLETE>
+)
+
+# incubation period: extract distribution parameters
+ebola_incubationtime_params <- epiparameter::#<COMPLETE>
+
+# incubation period: discretize and extract maximum value (p = 99%)
+ebola_incubationtime_max <- ebola_incubationtime %>% #<COMPLETE>
+
+# incubation period: adapt to {EpiNow2} distribution interface
+ebola_incubationtime_epinow <- EpiNow2::#<COMPLETE>
+
+# print required input
+ebola_generationtime
+ebola_reportdelay
+ebola_incubationtime_epinow
+
+
+# Set the number of parallel cores for {EpiNow2} --------------------------
+withr::local_options(list(mc.cores = parallel::detectCores() - 1))
+
+
+# Estimate transmission using EpiNow2::epinow() ---------------------------
+# with EpiNow2::*_opts() functions for generation time, delays, and stan.
+estimates <- EpiNow2::epinow(
+  data = dat,
+  #<COMPLETE>
+  stan = EpiNow2::stan_opts(samples = 1000, chains = 3)
+)
+
+
+# Print plot and summary table outputs ------------------------------------
+summary(estimates)
+plot(estimates)
+
+
+# nolint end

02-practical-activity-2.R

@@ -0,0 +1,64 @@
+# nolint start
+
+# Practical 2
+# Activity 2
+
+# Load packages -----------------------------------------------------------
+library(cfr)
+library(epiparameter)
+library(tidyverse)
+
+
+# Read reported cases -----------------------------------------------------
+disease_dat <- readr::read_rds(
+  #<COMPLETE>
+)
+
+disease_dat
+
+
+# Create incidence object ------------------------------------------------
+disease_incidence <- disease_dat %>%
+  incidence2::incidence(
+    #<COMPLETE>
+  )
+
+plot(disease_incidence)
+
+
+# Confirm {cfr} data input format ----------------------------------------
+
+# does input data already adapted to {cfr} input? 
+disease_adapted <- disease_dat
+# OR
+# does input data require to be adapted to {cfr}? 
+disease_adapted <- disease_incidence %>%
+  cfr::prepare_data(
+    #<COMPLETE>
+  )
+
+disease_adapted
+
+# Access delay distribution -----------------------------------------------
+disease_delay <- epiparameter::#<COMPLETE>
+
+
+# Estimate naive and adjusted CFR ----------------------------------------
+
+# Estimate Static CFR
+disease_adapted %>%
+  filter(
+    #<COMPLETE>
+  ) %>%
+  cfr::cfr_static()
+
+# Estimate Static Delay-Adjusted CFR
+disease_adapted %>%
+  filter(
+    #<COMPLETE>
+  ) %>%
+  cfr::cfr_static(
+    delay_density = function(x) density(disease_delay, x)
+  )
+
+# nolint end

03-practical-activity-1.R

@@ -0,0 +1,67 @@
+# nolint start
+
+# Practical 3
+# Activity 1
+
+# Load packages -----------------------------------------------------------
+library(epicontacts)
+library(fitdistrplus)
+library(tidyverse)
+
+
+# Read linelist and contacts ----------------------------------------------
+dat_contacts <- readr::read_rds("link/to/contact/data/url")
+
+dat_linelist <- readr::read_rds("link/to/linelist/data/url")
+
+
+# Create an epicontacts object -------------------------------------------
+epi_contacts <- epicontacts::#<COMPLETE>
+
+# print output
+epi_contacts
+
+# visualize the contact network
+contact_network <- epicontacts::#<COMPLETE>
+
+# print output
+contact_network
+
+
+# Count secondary cases per subject in contacts and linelist --------
+secondary_cases <- epicontacts::#<COMPLETE>
+
+# plot the histogram of secondary cases
+individual_reproduction_num <- secondary_cases %>%
+  enframe() %>% 
+  ggplot(aes(value)) +
+  geom_histogram(binwidth = 1) +
+  labs(
+    x = "Number of secondary cases",
+    y = "Frequency"
+  )
+
+# print output
+individual_reproduction_num
+
+
+# Fit a negative binomial distribution -----------------------------------
+offspring_fit <- #<COMPLETE>
+
+# print output
+offspring_fit
+
+
+# Estimate proportion of new cases from a cluster of secondary cases -----
+
+# Set seed for random number generator
+set.seed(33)
+
+# Estimate the proportion of new cases originating from 
+# a transmission cluster of at least 5, 10, or 25 cases
+proportion_cases_by_cluster_size <- #<COMPLETE>
+
+# print output
+proportion_cases_by_cluster_size
+
+# nolint end