Tips of table1 R Package and Summary Tables

## Data from package
library(boot) 

melanoma2 <- melanoma
 
# Factor the basic variables that
# we're interested in
melanoma2$status <- 
  factor(melanoma2$status, 
         levels=c(2,1,3),
         labels=c("Alive", # Reference
                  "Melanoma death", 
                  "Non-melanoma death"))


## Simulated data
f <- function(x, n, ...) factor(sample(x, n, replace=T, ...), levels=x)
set.seed(427)

n <- 146
dat <- data.frame(id=1:n)
dat$treat <- f(c("Placebo", "Treated"), n, prob=c(1, 2)) # 2:1 randomization
dat$age   <- sample(18:65, n, replace=TRUE)
dat$sex   <- f(c("Female", "Male"), n, prob=c(.6, .4))  # 60% female
dat$wt    <- round(exp(rnorm(n, log(70), 0.23)), 1)

# Add some missing data
dat$wt[sample.int(n, 5)] <- NA

dat = dat %>% 
  mutate(treat = as.factor(treat),
         sex = factor(sex, levels = c("Female", "Male")))


table1_dat = expss::apply_labels(dat,
                                 age="Age",
                                 sex="Sex",
                                 wt="Weight",
                                 treat="Treatment Group")


units(table1_dat$age)   <- "years"
units(table1_dat$wt)    <- "kg"

render.cont <- function(x, name, table1_data, ...) {
    MIN <- min(x, na.rm = T)
    MAX <- max(x, na.rm = T)
    median <- median(x, na.rm = T)
    Q1 <- quantile(x, 0.25, na.rm = T)
    Q3 <- quantile(x, 0.75, na.rm = T)
    N = length(x) - sum(is.na(x))
    MEAN = mean(x, na.rm = T)
    SD = sd(x, na.rm = T)
    nmiss <- sum(is.na(x))
    miss = (nmiss/length(x))*100

    out <- c(#"N"=paste0("(N=",N,")"),
             "N"=paste0(" "),
             "Mean (SD)" = paste0(sprintf("%.1f",MEAN), " (", sprintf("%.1f",SD),")"),
             "Min - Max" = paste0(sprintf("%.1f",MIN), " - ", sprintf("%.1f",MAX)),
             "Median [Q1, Q3]" = paste0(sprintf("%.1f", median), " [", sprintf("%.1f", Q1), ", ", sprintf("%.1f", Q3), "]"))
         #    "Missing" = paste0(sprintf("%.0f",nmiss), " (", sprintf("%.1f",miss),"%)"))

    out
}

render.cat = function(x) { 
  N = length(x) - sum(is.na(x))
  FREQ_PCT = sub('.', '.', c(sapply(stats.default(x), 
  function(y) with(y, sprintf("%d (%0.1f %%)", FREQ, PCT)))), fixed = TRUE)
  
  out = c(#"N"=paste0("(N=",N,")"),
          "N"=paste0(" "),
          FREQ_PCT)
  out
}

pvalue_para <- function(x, ...) {
    # Construct vectors of data y, and groups (strata) g
    y <- unlist(x)
    g <- factor(rep(1:length(x), times=sapply(x, length)))
    if (is.numeric(y)) {
        # For numeric variables, perform a standard 2-sample t-test
        p <- t.test(y ~ g)$p.value
    } else {
      if (nrow(table(y,g)) !=1) {
        # For categorical variables, perform a chi-squared test of independence
        p <- chisq.test(table(y, g))$p.value
      }
      else {p <- ""}
    }
    # Format the p-value, using an HTML entity for the less-than sign.
    # The initial empty string places the output on the line below the variable label.
    if (!p %in% "") {
    c("", sub("<", "<", format.pval(p, digits=3, eps=0.001)))
    }
}

pvalue_nonpara <- function(x, ...) {
    # Construct vectors of data y, and groups (strata) g
    y <- unlist(x)
    g <- factor(rep(1:length(x), times=sapply(x, length)))
    if (is.numeric(y)) {
        # For numeric variables, perform a standard 2-sample t-test
        p <- wilcox.test(y ~ g)$p.value # non-parameric: wilcoxon rank sum test
    } else {
      if (nrow(table(y,g)) !=1) {
        # For categorical variables, perform a chi-squared test of independence
        p <- fisher.test(table(y, g))$p.value # non-parameric: fisher's exact test
      }
      else {p <- ""} # If only one level has non-missing counts, skip the testing.
    }
    # Format the p-value, using an HTML entity for the less-than sign.
    # The initial empty string places the output on the line below the variable label.
    if (!p %in% "") {
    c("", sub("<", "<", format.pval(p, digits=3, eps=0.001)))
    }
}

pvalueANOVA <- function(x, ...) {
  # Construct vectors of data y, and groups (strata) g
  y <- unlist(x)
  g <- factor(rep(1:length(x), times=sapply(x, length)))
  
  if (is.numeric(y)) {
    # For numeric variables, perform an ANOVA test
    ano <- aov(y ~ g)
    p <- summary(ano)[[1]][[5]][1]
    
  } else {
    if (nrow(table(y,g)) >=2) {
    # For categorical variables, perform a chi-squared test of independence
    p <- chisq.test(table(y, g))$p.value
    }
    else {p <- ""}
  }
  # Format the p-value, using an HTML entity for the less-than sign.
  # The initial empty string places the output on the line below the variable label.
  c("", sub("<", "&lt;", format.pval(p, digits=3, eps=0.001)))
}

pvalueKW <- function(x, ...) {
  # Construct vectors of data y, and groups (strata) g
  y <- unlist(x)
  g <- factor(rep(1:length(x), times=sapply(x, length)))
  
  if (is.numeric(y)) {
    # For numeric variables, perform a Kruskal-Wallis test
    km <- kruskal.test(y ~ g)
    p <- km$p.value
    
  } else {
    if (nrow(table(y,g)) >=2) {
    # For categorical variables, perform a fisher's exact test of independence
    p <- fisher.test(table(y, g))$p.value
    }
    else {p <- ""}
  }
  # Format the p-value, using an HTML entity for the less-than sign.
  # The initial empty string places the output on the line below the variable label.
  c("", sub("<", "&lt;", format.pval(p, digits=3, eps=0.001)))
}

table1_ex1 = table1(~ age + sex + wt | treat, data=table1_dat,
                   render.continuous=render.cont, # optional, your continuous variable render
                   render.categorical=render.cat, # optional, your categorical variable render
                   # render.missing=NULL, 
                   overall = "Modify Overall Column Name Here"
                   )

table1_ex1

table1_ex2 = table1(~ age + sex + wt | treat, data=table1_dat,
                   render.continuous=render.cont, # optional, your continuous variable render
                   render.categorical=render.cat, # optional, your categorical variable render
                   overall = F,
                   extra.col=list(`Parametric P-value`=pvalue_para,
                                  `Non-Parametric P-value`=pvalue_nonpara)
                   )

table1_ex2

table1_ex3 = table1(~ factor(sex) + age + factor(ulcer) + thickness | status, data=melanoma2,
                   render.continuous=render.cont, # optional, your continuous variable render
                   render.categorical=render.cat, # optional, your categorical variable render
                   overall = F,
                   extra.col=list(`Parametric P-value`=pvalueANOVA,
                                  `Non-Parametric P-value`=pvalueKW)
                   )

table1_ex3

t1kable(your_table1_object)

t1flex(your_table1_object)

table1_ex1 %>% 
  t1flex() %>%
  line_spacing(space = 0, part = "body") %>% 
  bg(bg = "white", part = "all") # Change the background color to 'white' to display the table properly in 'Dark' mode. This step is unnecessary if you're generating your own report.