Skip to contents

Linelist Data Import

import_linelist.Rmd
# install or load packages
pacman::p_load(rio, 
               here,
               tidyverse)

Option 1. locally stored excel 

# import
linelist <- import(here("data","MSF_linelist.xlsx"))

# rename df and vars

Option 2. godata via godataR 

# Install godataR package
devtools::install_github("WorldHealthOrganization/godataR")
library(godataR)
library(getPass)
# Set Go.Data login credentials:

## Your Go.Data URL
## this should match whatever is the your Go.Data URL. the below a URL to a demo instance with fake data.
url <- "https://godata-r19.who.int/" 


## Your email address to log in to Go.Data

username <- getPass::getPass(msg = "Enter your Go.Data username (email address):") 
## you can use testuser7@who.int

# Your password to log in to Go.Data
## a pop-up box will appear for you to enter your pw
password <- getPass::getPass(msg = "Enter your Go.Data password:") 
## you can use godatatrombonestaple


# Get and clean case data from Go.Data API

# within outbreak API endpoint so this also requires getting active outbreak ID for disease of interest
# a few other cleaning steps that are a natural next step after data extraction


# Get ID for active outbreak:
outbreak_id <- godataR::get_active_outbreak(url = url, 
                                            username = username, 
                                            password = password)

cases <- get_cases(
  url = url,
  username = username,
  password = password,
  outbreak_id = outbreak_id)

language_tokens <- get_language_tokens(
  url = url,
  username = username,
  password = password,
  language = "english_us")

locations <- get_locations(
  url = url,
  username = username,
  password = password)

locations_clean <- clean_locations(
                        locations = locations,
                        language_tokens = language_tokens)

# other cleaned data required for `clean_cases()`
# these below are nested data and we are bringing in only one row per case.
cases_vacc_history_clean <- clean_case_vax_history(
                              cases = cases,
                              language_tokens = language_tokens)


cases_address_history_clean <- clean_case_address_history(
  cases = cases,
  locations_clean = locations_clean,
  language_tokens = language_tokens)

cases_dateranges_history_clean <- clean_case_med_history(
  cases = cases,
  language_tokens = language_tokens)

cases_clean <- clean_cases(
  cases = cases,
  cases_address_history_clean = cases_address_history_clean,
  cases_vacc_history_clean = cases_vacc_history_clean,
  cases_dateranges_history_clean = cases_dateranges_history_clean,
  language_tokens = language_tokens
)

Option 3. other??