# 假设我们有一个名为df的数据框，它包含了一些数值型变量
# 如果没有，我们可以创建一个示例数据框
set.seed(123) # 为了结果的可重复性
df <- data.frame(
Var1 = rnorm(100, mean = 50, sd = 10),
Var2 = rnorm(100, mean = 100, sd = 20),
Var3 = rnorm(100, mean = 150, sd = 30),
CatVar = sample(c("A", "B", "C"), 100, replace = TRUE) # 这是一个分类变量，不参与计算
)
# 筛选出数值型变量
numeric_vars <- sapply(df, is.numeric)
numeric_df <- df[, numeric_vars]
# 计算描述性统计量
desc_stats <- lapply(numeric_df, function(x) {
c(
Mean = mean(x, na.rm = TRUE),
Median = median(x, na.rm = TRUE),
SD = sd(x, na.rm = TRUE),
Min = min(x, na.rm = TRUE),
Max = max(x, na.rm = TRUE),
Q1 = quantile(x, probs = 0.25, na.rm = TRUE),
Q3 = quantile(x, probs = 0.75, na.rm = TRUE)
)
})
# 将列表转换为数据框，以便更好地展示
desc_stats_df <- do.call(rbind, lapply(names(desc_stats), function(nm) {
data.frame(Variable = nm, Value = unlist(desc_stats[[nm]]), row.names = NULL)
}))
# 重塑数据框以便于按变量分组
library(tidyr)
desc_stats_tidy <- pivot_wider(desc_stats_df, names_from = "Variable", values_from = "Value")
# 打印结果
print(desc_stats_tidy)
