箱线图叠加散点

# 箱线图叠加散点：两组连续指标分布
# 项目原创脚本，MIT 许可；模拟数据 CC0-1.0；图形 CC BY 4.0。
# 在全新 R 会话运行。每次运行会更新下方 output_dir 中的本示例文件。
# 图形标签使用英文以避免不同电脑缺少中文字体；可在参数和 labs() 中修改。

# 1. 依赖：首次使用时手动运行以下安装命令，脚本不会自动安装。
# install.packages(c("ggplot2", "jsonlite"))
required_packages <- c("ggplot2", "jsonlite")
missing_packages <- required_packages[!vapply(required_packages, requireNamespace, logical(1), quietly = TRUE)]
if (length(missing_packages)) stop("Please install: ", paste(missing_packages, collapse = ", "))
library(ggplot2)

# 2. 可修改参数：颜色、字体、导出尺寸和路径。输出路径相对于当前工作目录。
set.seed(20261014)
colors <- c("#007F96", "#B66A46")
font_family <- "sans"
figure_width <- 8
figure_height <- 5.5
output_dir <- file.path(getwd(), "rfig-boxplot-output")
dir.create(output_dir, recursive = TRUE, showWarnings = FALSE)
theme_set(theme_minimal(base_size = 12, base_family = font_family) +
 theme(plot.background = element_rect(fill = "white", color = NA), panel.grid.minor = element_blank(),
       plot.title = element_text(face = "bold", size = 15), legend.position = "bottom",
       plot.margin = margin(14, 18, 14, 14)))

# 3. 示例数据：每行一位独立受试者。 替换 group 与 value；检查组别顺序和测量单位。
# 使用自己的 CSV 时，将以下数据生成段替换为：
# data <- read.csv("your-data.csv", stringsAsFactors = FALSE)
# 再按本例要求设置分类顺序、检查字段、单位及缺失值。
data <- data.frame(id = 1:120, group = rep(c("Control", "Treatment"), each = 60),
                   value = c(rnorm(60, 12, 3), rnorm(60, 10, 3)))
data$group <- factor(data$group, levels = c("Control", "Treatment"))
stopifnot(!anyNA(data))

# 4. 统计计算与绘图。箱体为第 25 至第 75 百分位数，中线为中位数；须延伸至 1.5 倍 IQR 范围内最远观测。所有原始值由散点展示，关闭额外离群点符号以避免重复。未添加显著性检验。
p <- ggplot(data, aes(group, value, fill = group)) + geom_boxplot(width = .45, outlier.shape = NA, alpha = .25) +
  geom_point(aes(shape = group, color = group), position = position_jitter(width = .13, height = 0, seed = 24), alpha = .65, size = 2) +
  scale_fill_manual(values = colors) + scale_color_manual(values = colors) + guides(fill = "none", color = "none", shape = "none") +
  labs(x = NULL, y = "Measurement (demo units)", title = "Distribution and individual observations")
metrics <- list(medians = unname(tapply(data$value, data$group, median)))
print(p)

# 5. 导出：CSV 与绘图所用 data 完全一致，preview 与科研图片均来自同一个 p。
write.csv(data, file.path(output_dir, "data.csv"), row.names = FALSE, fileEncoding = "UTF-8")
ggsave(file.path(output_dir, "preview.png"), p, width = figure_width, height = figure_height, dpi = 160, bg = "white")
ggsave(file.path(output_dir, "figure.png"), p, width = figure_width, height = figure_height, dpi = 300, bg = "white")
ggsave(file.path(output_dir, "figure.pdf"), p, width = figure_width, height = figure_height, device = grDevices::pdf, bg = "white")
ggsave(file.path(output_dir, "figure.tiff"), p, width = figure_width, height = figure_height, dpi = 300, compression = "lzw", bg = "white")
jsonlite::write_json(metrics, file.path(output_dir, "metrics.json"), auto_unbox = TRUE, digits = 16, pretty = TRUE)