## ----setup, include = FALSE--------------------------------------------------- knitr::opts_chunk$set( collapse = TRUE, comment = "#>", fig.align = "center", warning = FALSE, message = FALSE, fig.width = 8, fig.height = 5, out.width = "100%" ) ## ----load-pkg----------------------------------------------------------------- library(xaiHydro) ## ----sim-streamflow----------------------------------------------------------- df_flow <- sim_streamflow_data(n = 365, seed = 2026) head(df_flow, 6) ## ----sim-str------------------------------------------------------------------ str(df_flow) ## ----sim-drought-show--------------------------------------------------------- df_drought <- sim_drought_data(n = 240, seed = 2026) head(df_drought, 6) ## ----train-rf, eval=FALSE----------------------------------------------------- # library(randomForest) # # # Separate predictors and response # y_flow <- df_flow$streamflow # X_flow <- df_flow[, setdiff(names(df_flow), "streamflow")] # # set.seed(42) # rf_model <- randomForest( # x = X_flow, # y = y_flow, # ntree = 300, # mtry = 3, # importance = TRUE # ) # # print(rf_model) # # Mean of squared residuals: ~X.XX # # % Var explained: ~XX.X ## ----train-xgb, eval=FALSE---------------------------------------------------- # library(xgboost) # # y_spei <- df_drought$spei # X_drought <- df_drought[, setdiff(names(df_drought), "spei")] # # xgb_mat <- xgboost::xgb.DMatrix(as.matrix(X_drought), label = y_spei) # xgb_model <- xgboost::xgboost( # data = xgb_mat, # nrounds = 150, # max_depth = 4, # eta = 0.1, # objective = "reg:squarederror", # verbose = 0 # ) ## ----explainer, eval=FALSE---------------------------------------------------- # exp_flow <- hydro_explainer( # model = rf_model, # data = X_flow, # y = y_flow, # variable = "streamflow", # units = "m3/s", # label = "RandomForest" # ) # # print(exp_flow) # # == xaiHydro Explainer == # # Target variable : streamflow [m3/s] # # Model label : RandomForest # # Observations : 365 # # Predictors : 8 # # Model class : randomForest ## ----explainer-xgb, eval=FALSE------------------------------------------------ # pfun_xgb <- function(model, newdata) { # predict(model, xgboost::xgb.DMatrix(as.matrix(newdata))) # } # # exp_drought <- hydro_explainer( # model = xgb_model, # data = X_drought, # y = y_spei, # variable = "drought_index", # units = "SPEI", # label = "XGBoost", # predict_function = pfun_xgb # ) ## ----shap-compute, eval=FALSE------------------------------------------------- # shap_vals <- hydro_shap( # explainer = exp_flow, # nsim = 50, # Monte Carlo replicates — increase for stability # seed = 42 # ) # # # Returns a tidy data frame: # # id | feature | shap_value | feature_value | mean_abs_shap # head(shap_vals, 8) ## ----shap-summary, eval=FALSE------------------------------------------------- # plot_shap_summary(shap_vals, top_n = 8) ## ----shap-waterfall, eval=FALSE----------------------------------------------- # # Explain a high-flow day (e.g., observation 180 after a storm event) # plot_shap_waterfall(shap_vals, obs_id = 180, top_n = 7) ## ----lime, eval=FALSE--------------------------------------------------------- # lime_result <- hydro_lime( # explainer = exp_flow, # new_obs = X_flow[180, , drop = FALSE], # n_features = 6, # top-6 features in the local model # kernel_width = 0.75 # ) # # # Local R² indicates surrogate model quality (closer to 1 = better) # plot_lime_hydro(lime_result) ## ----pdp, eval=FALSE---------------------------------------------------------- # pdp_result <- hydro_pdp( # explainer = exp_flow, # variable = c("precipitation", "soil_moisture", # "lag1_precip", "temperature"), # type = "partial", # grid_points = 60 # ) # # plot_pdp_hydro(pdp_result, ncol = 2) ## ----ale, eval=FALSE---------------------------------------------------------- # ale_result <- hydro_pdp( # explainer = exp_flow, # variable = c("precipitation", "soil_moisture"), # type = "accumulated" # ) # # plot_pdp_hydro(ale_result, ncol = 2) ## ----importance, eval=FALSE--------------------------------------------------- # imp <- hydro_importance( # explainer = exp_flow, # loss_function = "rmse", # B = 20 # repetitions — reduces variance of estimate # ) # # plot_importance_hydro(imp, top_n = 8) ## ----breakdown, eval=FALSE---------------------------------------------------- # bd <- hydro_breakdown( # explainer = exp_flow, # new_obs = X_flow[180, , drop = FALSE], # type = "shap", # or "break_down" # B = 25 # ) # # plot_breakdown_hydro(bd, max_features = 8) ## ----residuals, eval=FALSE---------------------------------------------------- # hydro_residuals(exp_flow) ## ----report, eval=FALSE------------------------------------------------------- # hydro_xai_report( # explainer = exp_flow, # nsim = 50, # top_n = 6, # new_obs = X_flow[180, , drop = FALSE], # seed = 42, # save_path = "xaiHydro_streamflow_report.png", # width = 16, # height = 11, # dpi = 300 # ) ## ----drought-full, eval=FALSE------------------------------------------------- # library(xgboost) # # # Data # df_d <- sim_drought_data(n = 240, seed = 2026) # y_d <- df_d$spei # X_d <- df_d[, setdiff(names(df_d), "spei")] # # # Model # xgb_m <- xgboost::xgboost( # data = xgboost::xgb.DMatrix(as.matrix(X_d), label = y_d), # nrounds = 150, max_depth = 4, eta = 0.1, # objective = "reg:squarederror", verbose = 0 # ) # # # Explainer # pfun <- function(m, nd) predict(m, xgboost::xgb.DMatrix(as.matrix(nd))) # exp_d <- hydro_explainer(xgb_m, X_d, y_d, # variable = "drought_index", # units = "SPEI", # label = "XGBoost", # predict_function = pfun) # # # XAI suite # shap_d <- hydro_shap(exp_d, nsim = 50) # imp_d <- hydro_importance(exp_d, B = 20) # pdp_d <- hydro_pdp(exp_d, variable = c("spi_3", "spi_12", "et_deficit")) # # plot_shap_summary(shap_d, top_n = 6, # title = "SHAP Summary — SPEI drought model (XGBoost)") # plot_importance_hydro(imp_d) # plot_pdp_hydro(pdp_d, ncol = 3) # hydro_residuals(exp_d) ## ----session------------------------------------------------------------------ sessionInfo()