library(boot)
library(tidyverse)

melanoma2 <- melanoma
melanoma2$status <- 
  factor(melanoma2$status,
         levels = c(2,1,3),
         labels = c("Alive",#reference 注意顺序
                    "Melanoma death",
                    "Non-melanoma death"))

library(table1)

table1(~factor(sex)+age+factor(ulcer)+thickness|status,data = melanoma2)

melanoma2$sex <- 
  factor(melanoma2$sex, levels=c(1,0),
         labels=c("Male", 
                  "Female"))
 
melanoma2$ulcer <- 
  factor(melanoma2$ulcer, levels=c(0,1),
         labels=c("Absent", 
                  "Present"))

label(melanoma2$sex)       <- "Sex"
label(melanoma2$age)       <- "Age"
label(melanoma2$ulcer)     <- "Ulceration"
label(melanoma2$thickness) <- "Thicknessᵃ"

units(melanoma2$age)       <- "years"
units(melanoma2$thickness) <- "mm"

caption  <- "Basic stats"
footnote <- "ᵃ Also known as Breslow thickness"

table1(~ sex + age + ulcer + thickness | status, data=melanoma2,
    overall=c(left="Total"), caption=caption, footnote=footnote)

labels <- list(
    variables=list(sex="Sex",
                   age="Age (years)",
                   ulcer="Ulceration",
                   thickness="Thicknessᵃ (mm)"),
    groups=list("", "", "Death"))

# 将"death"这个词从标签中移除, 因为上面groups定义了
levels(melanoma2$status) <- c("Alive", "Melanoma", "Non-melanoma")

strata <- c(list(Total=melanoma2), split(melanoma2, melanoma2$status))

#连续变量
my.render.cont <- function(x) {
    with(stats.apply.rounding(stats.default(x), digits=2), c("",
        "Mean (SD)"=sprintf("%s (&plusmn; %s)", MEAN, SD)))
}

#分类变量
my.render.cat <- function(x) {
    c("", sapply(stats.default(x), function(y) with(y,
        sprintf("%d (%0.0f %%)", FREQ, PCT))))
}

table1(strata, labels, groupspan=c(1, 1, 2), caption=caption, footnote=footnote,
       render.continuous=my.render.cont, render.categorical=my.render.cat)

pvalue <- function(x, ...) {
  # 构建数据y的向量，和分组变量g 
  y <- unlist(x)
  g <- factor(rep(1:length(x), times=sapply(x, length)))
  if (is.numeric(y)) {
    # 数值型变量，采用标准的t检验（两组比较）
    p <- t.test(y ~ g)$p.value
  } else {
    # 分类变量，此案用卡方检验
    p <- chisq.test(table(y, g))$p.value
  }
  # 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)))
}

#统计量
stats <- function(x, ...) {
  y <- unlist(x)
  g <- factor(rep(1:length(x), times=sapply(x, length)))
  if (is.numeric(y)) {
    s <- t.test(y ~ g)$statistic
  } else {
    s <- chisq.test(table(y, g))$statistic
  }
  c("", sprintf("%.4f", s))
}

library(MatchIt)

data(lalonde)

lalonde$treat    <- factor(lalonde$treat, levels=c(0, 1), labels=c("Control", "Treatment"))
lalonde$married  <- as.logical(lalonde$married == 1)
lalonde$nodegree <- as.logical(lalonde$nodegree == 1)
lalonde$race     <- factor(lalonde$race, levels=c("white", "black", "hispan"),
                           labels=c("White", "Black", "Hispanic"))

label(lalonde$race)     <- "Race"
label(lalonde$married)  <- "Married"
label(lalonde$nodegree) <- "No high school diploma"
label(lalonde$age)      <- "Age"
label(lalonde$re74)     <- "1974 Income"
label(lalonde$re75)     <- "1975 Income"
label(lalonde$re78)     <- "1978 Income"
units(lalonde$age)      <- "years"

table1(~ age + race + married + nodegree + re74 + re75 + re78 | treat,
       data=lalonde, overall=F, extra.col=list(`P-value`=pvalue, `statistic`=stats))

x <- table1(~ age + race + married + nodegree + re74 + re75 + re78 | treat,
       data=lalonde, overall=F, extra.col=list(`P-value`=pvalue, `statistic`=stats))
as.data.frame(x)

knitr::kable(as.data.frame(x),booktabs=TRUE)

t1kable(x)