回归系数图

# 回归系数图：多变量线性回归系数及 95% CI
# 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-regression-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。 替换结局和模型变量，明确分类参考组、连续变量单位与调整变量。
# 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 = 1:160, age = runif(160, 30, 75),
 sex = factor(rep(c("Female", "Male"), 80), levels = c("Female", "Male")),
 group = factor(sample(rep(c("Control", "Treatment"), each = 80)), levels = c("Control", "Treatment")))
data$value <- 8 + .08 * data$age + (data$sex == "Male") - 1.5 * (data$group == "Treatment") + rnorm(160, 0, 2.5)
stopifnot(!anyNA(data))

# 4. 统计计算与绘图。普通最小二乘模型 value ~ group + age + sex；显示非截距系数与基于 t 分布的 95% CI。年龄系数按每增加 1 岁解释，其他系数按参考组解释。无效线为 0，不能比较不同单位系数大小判断变量重要性；需检查模型假设。
model <- lm(value ~ group + age + sex, data = data)
ci <- confint(model, level = .95)[-1, , drop = FALSE]
effects <- data.frame(term = c("Treatment vs Control", "Age (per year)", "Male vs Female"), estimate = unname(coef(model)[-1]), lower = ci[,1], upper = ci[,2])
p <- ggplot(effects, aes(estimate, term)) + geom_vline(xintercept = 0, linetype = "dashed", color = "#8DA5B6") +
 geom_segment(aes(x = lower, xend = upper, yend = term), color = colors[1], linewidth = .8) + geom_point(color = colors[1], size = 3) +
 labs(x = "Adjusted coefficient (95% CI)", y = NULL, title = "Multivariable linear regression")
metrics <- list(estimate = effects$estimate, lower = effects$lower, upper = effects$upper)
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)