## ----setup, include=FALSE----------------------------------------------------- # The Chinese title in the YAML header is intentional; the index entry stays in # ASCII so that the vignette index is readable in any locale. options(rmarkdown.html_vignette.check_title = FALSE) knitr::opts_chunk$set( collapse = TRUE, comment = "#>", fig.width = 6, fig.height = 4, dpi = 110 ) ## ----quick-start-------------------------------------------------------------- library(uniml) development <- read.csv( system.file("extdata", "uniml-cvd-mortality.csv", package = "uniml") ) set.seed(123) development <- development[1:400, ] # 1. 声明任务 spec <- uniml_spec( task_type = "binary", outcome = "died", positive = "yes", id = "id" ) # 2. 预处理:中位数/众数填补 + z 分数标准化 + one-hot spec <- set_preprocess(spec, impute = "median_mode", scale = "zscore", encode = "onehot") # 3. 特征筛选:单因素 + LASSO 取交集 spec <- set_feature_selection(spec, methods = c("univariate", "lasso"), combine = "intersect") # 4. 模型:logistic(glmnet)和决策树 spec <- set_learners(spec, c("lr", "cart"), tune = FALSE) # 5. 评价设置:bootstrap 置信区间 + Platt 校准 + 用验证集选模型 spec <- set_evaluation( spec, ci = "bootstrap", calibration = "platt", select_on = "validation" ) # 6. SHAP:Kernel SHAP 是工作流里最贵的一步,解释行数与背景样本量由规格控制, # 这里取小值让 vignette 跑得快;要出论文级图时把两个数调大即可。 spec <- set_explain(spec, n_explain = 20, bg_n = 20) # 7. 切分并跑通 split <- make_split(as_uniml_data(development, spec), prop = c(0.8, 0.2), stratify = TRUE, seed = 123) result <- run_workflow( spec, train = split$train$data, validation = split$validation$data, ci_R = 25 ) ## ----results------------------------------------------------------------------ result$metrics[, c("model", "set", "probability", "auc", "brier", "accuracy")] result$ranking[, c("model", "score", "rank", "set")] result$selection$selected_features ## ----roc, fig.cap = "验证集 ROC 曲线"---------------------------------------------- plot_roc(result, set = "validation") ## ----calibration, fig.cap = "校准曲线(原始 vs 校准后)"--------------------------------- plot_calibration(result, set = "validation") ## ----dca, fig.cap = "决策曲线分析"-------------------------------------------------- plot_dca(result) ## ----shap, fig.cap = "最优模型的 SHAP 重要性"----------------------------------------- explained <- explain_shap(result, model = "best", n_explain = 25, bg_n = 15) plot_shap_importance(explained) ## ----predict------------------------------------------------------------------ scored <- predict_uniml(result, newdata = split$validation$data, model = "best") head(scored[, c("model", "prob", "calibrated_prob", "probability", "predicted")]) ## ----export------------------------------------------------------------------- out <- tempfile("uniml-zh-") exported <- export_results(result, dir = out, include_plots = FALSE) basename(exported$files) ## ----tripod------------------------------------------------------------------- checklist <- tripod_ai_check(result) table(checklist$status) subset(checklist, status != "reported", select = c("domain", "status"))