配对前后变化图

# 配对前后变化图：同一受试者两次测量
# 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-paired-change-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：每行一位受试者在一个时间点的测量；每人两行。 使用唯一 id 配对，保持 Before / After 的时间顺序，检查每人每时间点只有一行。
# 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。
baseline <- rnorm(36, 15, 3)
data <- data.frame(id = rep(1:36, 2), visit = rep(c("Before", "After"), each = 36),
                   value = c(baseline, baseline - 2 + rnorm(36, 0, 1.8)))
data$visit <- factor(data$visit, levels = c("Before", "After"))
stopifnot(all(table(data$id, data$visit) == 1))
stopifnot(!anyNA(data))

# 4. 统计计算与绘图。连线连接同一人的两次测量，点为原始值。演示含 36 个完整配对，不作独立样本检验。真实数据需明确不完整配对的处理方法。
p <- ggplot(data, aes(visit, value, group = id)) + geom_line(color = "#8DA5B6", alpha = .5) +
  geom_point(aes(color = visit, shape = visit), size = 2.3) + scale_color_manual(values = colors) + guides(color = "none", shape = "none") +
  labs(x = NULL, y = "Measurement (demo units)", title = "Within-participant change")
metrics <- list(pairs = length(unique(data$id)), change = mean(data$value[data$visit == "After"] - data$value[data$visit == "Before"]))
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)