Generic Function to Prepare TB Burden Data for Plotting

This function is used internally by plot_tb_burden and plot_tb_burden_overview to prepare data for plotting.

prepare_df_plot(
  df = NULL,
  dict = NULL,
  metric = "e_inc_100k",
  conf = NULL,
  metric_label = NULL,
  countries = NULL,
  years = NULL,
  compare_to_region = FALSE,
  facet = NULL,
  annual_change = FALSE,
  trans = "identity",
  download_data = TRUE,
  save = TRUE,
  verbose = FALSE,
  ...
)

Arguments

df	Dataframe of TB burden data, as sourced by get_tb_burden. If not specified then will source the WHO TB burden data, either locally if available or directly from the WHO (if download_data = TRUE).
dict	A tibble of the data dictionary. See get_data_dict for details. If not supplied the function will attempt to load a saved version of the dictionary. If this fails and download_data = TRUE then the dictionary will be downloaded.
metric	Character string specifying the metric to plot
conf	Character vector specifying the name variations to use to specify the upper and lower confidence intervals. Defaults to NULL for which no confidence intervals are used. Used by annual_change.
metric_label	Character string specifying the metric label to use.
countries	A character string specifying the countries to target.
years	Numeric vector of years. Defaults to NULL which includes all years in the data.
compare_to_region	Logical, defaults to FALSE. If TRUE all countries that share a region with those listed in countries will be plotted. Note that this will override settings for facet, unless it is set to "country".
facet	Character string, the name of the variable to facet by.
annual_change	Logical, defaults to FALSE. If TRUE then the percentage annual change is computed for the specified metric.
trans	A character string specifying the transform to use on the specified metric. Defaults to no transform ("identity"). Other options include log scaling ("log") and log base 10 scaling ("log10"). For a complete list of options see ggplot2::continous_scale.
download_data	Logical, defaults to TRUE. If not found locally should the data be downloaded from the specified URL?
save	Logical, should the data be saved for reuse during the current R session. Defaults to TRUE. If TRUE then the data is saved to the temporary directory specified by tempdir.
verbose	Logical, defaults to FALSE. Should additional status and progress messages be displayed.
...	Additional arguments to pass to get_tb_burden.

Value

A list containing 3 elements, the dataframe to plot, the facet to use and the label to assign to the metric axis.

See also

plot_tb_burden plot_tb_burden_overview

Examples

prepare_df_plot(countries = "Guinea")
#> $df
#> # A tibble: 19 x 73
#>    country iso2  iso3  iso_numeric g_whoregion  year e_pop_num e_inc_100k
#>    <fct>   <chr> <chr>       <int> <chr>       <int>     <int>      <dbl>
#>  1 Guinea  GN    GIN           324 Africa       2000   8240730        228
#>  2 Guinea  GN    GIN           324 Africa       2001   8417081        224
#>  3 Guinea  GN    GIN           324 Africa       2002   8586074        221
#>  4 Guinea  GN    GIN           324 Africa       2003   8753093        218
#>  5 Guinea  GN    GIN           324 Africa       2004   8925743        214
#>  6 Guinea  GN    GIN           324 Africa       2005   9109581        210
#>  7 Guinea  GN    GIN           324 Africa       2006   9307425        206
#>  8 Guinea  GN    GIN           324 Africa       2007   9518162        200
#>  9 Guinea  GN    GIN           324 Africa       2008   9738792        195
#> 10 Guinea  GN    GIN           324 Africa       2009   9964469        190
#> 11 Guinea  GN    GIN           324 Africa       2010  10192176        186
#> 12 Guinea  GN    GIN           324 Africa       2011  10420472        183
#> 13 Guinea  GN    GIN           324 Africa       2012  10652031        180
#> 14 Guinea  GN    GIN           324 Africa       2013  10892817        177
#> 15 Guinea  GN    GIN           324 Africa       2014  11150982        177
#> 16 Guinea  GN    GIN           324 Africa       2015  11432088        177
#> 17 Guinea  GN    GIN           324 Africa       2016  11738429        176
#> 18 Guinea  GN    GIN           324 Africa       2017  12067519        176
#> 19 Guinea  GN    GIN           324 Africa       2018  12414293        176
#> # … with 65 more variables: e_inc_100k_lo <dbl>, e_inc_100k_hi <dbl>,
#> #   e_inc_num <int>, e_inc_num_lo <int>, e_inc_num_hi <int>,
#> #   e_tbhiv_prct <dbl>, e_tbhiv_prct_lo <dbl>, e_tbhiv_prct_hi <dbl>,
#> #   e_inc_tbhiv_100k <dbl>, e_inc_tbhiv_100k_lo <dbl>,
#> #   e_inc_tbhiv_100k_hi <dbl>, e_inc_tbhiv_num <int>, e_inc_tbhiv_num_lo <int>,
#> #   e_inc_tbhiv_num_hi <int>, e_mort_exc_tbhiv_100k <dbl>,
#> #   e_mort_exc_tbhiv_100k_lo <dbl>, e_mort_exc_tbhiv_100k_hi <dbl>,
#> #   e_mort_exc_tbhiv_num <int>, e_mort_exc_tbhiv_num_lo <int>,
#> #   e_mort_exc_tbhiv_num_hi <int>, e_mort_tbhiv_100k <dbl>,
#> #   e_mort_tbhiv_100k_lo <dbl>, e_mort_tbhiv_100k_hi <dbl>,
#> #   e_mort_tbhiv_num <int>, e_mort_tbhiv_num_lo <int>,
#> #   e_mort_tbhiv_num_hi <int>, e_mort_100k <dbl>, e_mort_100k_lo <dbl>,
#> #   e_mort_100k_hi <dbl>, e_mort_num <int>, e_mort_num_lo <int>,
#> #   e_mort_num_hi <int>, cfr <dbl>, cfr_lo <dbl>, cfr_hi <dbl>, cfr_pct <int>,
#> #   cfr_pct_lo <int>, cfr_pct_hi <int>, c_newinc_100k <dbl>, c_cdr <dbl>,
#> #   c_cdr_lo <dbl>, c_cdr_hi <dbl>, source_rr_new <chr>,
#> #   source_drs_coverage_new <chr>, source_drs_year_new <int>,
#> #   e_rr_pct_new <dbl>, e_rr_pct_new_lo <dbl>, e_rr_pct_new_hi <dbl>,
#> #   e_mdr_pct_rr_new <int>, source_rr_ret <chr>, source_drs_coverage_ret <chr>,
#> #   source_drs_year_ret <int>, e_rr_pct_ret <dbl>, e_rr_pct_ret_lo <dbl>,
#> #   e_rr_pct_ret_hi <dbl>, e_mdr_pct_rr_ret <int>, e_inc_rr_num <int>,
#> #   e_inc_rr_num_lo <int>, e_inc_rr_num_hi <int>, e_mdr_pct_rr <dbl>,
#> #   e_rr_in_notified_labconf_pulm <int>,
#> #   e_rr_in_notified_labconf_pulm_lo <int>,
#> #   e_rr_in_notified_labconf_pulm_hi <int>, `Estimated incidence (all forms)
#> #   per 100 000 population` <dbl>, Year <int>
#> 
#> $facet
#> NULL
#> 
#> $metric_label
#> [1] "Estimated incidence (all forms) per 100 000 population"
#>