# set a table relabelling function
rename_cols = function(col) {
  dplyr::case_when(
    col == "hos.cat" ~ "Location",
    col == "steroids" ~ "Steroid treatment",
    TRUE ~ stringr::str_to_sentence(col)
  )
}

# set it using an option
# we are not going to reset this as we will use in all the subsequent examples:
options("tableone.labeller"=rename_cols)

gcd %>% compare_population(formula) 

old = options(
  # set a mid point as decimal point
  "tableone.dp"="\u00B7",
  "tableone.font"="Arial Narrow",
  "tableone.font_size"=12,
  "tableone.pvalue_column_name"="p-value",
  # the p-value formatter must be a function that takes a vector of numbers and returns
  # a vector of characters. The example here is a function that returns a function.
  "tableone.pvalue_formatter" = 
          scales::label_pvalue(accuracy = 0.01,decimal.mark = "\u00B7"),
  "tableone.show_pvalue_method"=FALSE
)


gcd %>% compare_population(formula) 

# reset
options(old)

# override_type - names list of column names and summary type out of options

# with this looser definition of normality (i.e. less likely to reject the null
# that the data is normally distributed), height and weight are found to be
# and hence the t-test is used.
old = options(
  "tableone.normality_test"="lillie",
  "tableone.normality_significance"=0.00001
)

gcd %>% compare_population(
    formula,
    # age is still not normally distributed but we can override it to be 
    # presented as a mean and SD.
    override_type = list(age="mean_sd")
  )

options(old)

# the following option also controls which parametric test is chosen (between)
# wilcoxon and ks tests:
# options("tableone.tolerance_to_ties"=0.25)

gcd %>% compare_population(
    formula,
    # can supply either the "5f" (for 5 digits floating point) or "6g"
    # for 6 significant figures syntax:
    override_real_dp = list(age="0f",height="0f",weight="2f"),
    # or a plain set of numbers. If the option is unnamed it is applied to 
    # all the variables:
    override_percent_dp = 0
  )

gcd %>% compare_population(
    formula,
    layout = "relaxed"
  )

list(
    subtype_count = list(
        characteristic = "{level} % [95% CI]",
        Value = "{.sprintf_na('%1.1f%% [%1.1f%%—%1.1f%%]',prob.0.5*100,prob.0.025*100,prob.0.975*100)}",
        `Count (N={N})` = "{.sprintf_na('%d/%d',x,n)}"
    ),
    median_iqr = list(
        characteristic = "Median [IQR]",
        Value = "{.sprintf_na('%1.3g %s [%1.3g—%1.3g]',q.0.5,unit,q.0.25,q.0.75)}",
        `Count (N={N})` = "{.sprintf_na('%d',n)}"
    ),
    mean_sd = list(
        characteristic = "Mean ± SD", Value = "{.sprintf_na('%1.3g %s ± %1.3g',mean,unit,sd)}",
        `Count (N={N})` = "{.sprintf_na('%d',n)}"
    ),
    skipped = list(
        characteristic = "—", Value = "—",
        `Count (N={N})` = "{.sprintf_na('%d',n)}"
    )
)

custom = list(
    subtype_count = list(
        characteristic = "{level}",
        "Value (N={N}/{N_total})" = "{.sprintf_na('%1.1f%% (%d/%d)',prob.0.5*100,x,n)}"
    ),
    median_iqr = list(
        characteristic = "Median (N)",
        "Value (N={N}/{N_total})" = "{.sprintf_na('%1.3g (%d)',q.0.5,n)}"
    ),
    mean_sd = list(
        characteristic = "Mean (N)", 
        "Value (N={N}/{N_total})" = "{.sprintf_na('%1.3g (%d)',mean,n)}"
    ),
    skipped = list(
        characteristic = "(N)", 
        "Value (N={N}/{N_total})" = "{.sprintf_na('— (%d)',n)}"
    )
)

# printing control the following options control missing values
# produced by the .sprintf_na function:
# getOption("tableone.missing","<?>")
# getOption("tableone.na","\u2014")


gcd %>% compare_population(
    formula,
    layout = custom
  )

 gcd %>% compare_population(
   formula,
   footer_text = c(
      "IQR: Interquartile range; CI: Confidence interval",
      "Additional information could be supplied")
   )

old = options("tableone.hide_footer"=TRUE)

# or we can choose to hide the footer altogether
gcd %>% compare_population(formula)

options(old)