详解R语言caret包trainControl函数

caret::trainControl <- 
function (method = "boot", number = ifelse(grepl("cv", method), 10, 25), repeats = ifelse(grepl("[d_]cv$", method), 1, NA), p = 0.75, search = "grid", initialWindow = NULL,  horizon = 1, fixedWindow = TRUE, skip = 0, verboseIter = FALSE， returnData = TRUE, returnResamp = "final", savePredictions = FALSE, 
    classProbs = FALSE, summaryFunction = defaultSummary, selectionFunction = "best", 
    preProcOptions = list(thresh = 0.95, ICAcomp = 3, k = 5, 
        freqCut = 95/5, uniqueCut = 10, cutoff = 0.9), sampling = NULL, 
    index = NULL, indexOut = NULL, indexFinal = NULL, timingSamps = 0, 
    predictionBounds = rep(FALSE, 2), seeds = NA, adaptive = list(min = 5, 
        alpha = 0.05, method = "gls", complete = TRUE), 
    trim = FALSE, allowParallel = TRUE) 
{
    if (is.null(selectionFunction)) 
        stop("null selectionFunction values not allowed")
    if (!(returnResamp %in% c("all", "final", "none"))) 
        stop("incorrect value of returnResamp")
    if (length(predictionBounds) > 0 && length(predictionBounds) != 
        2) 
        stop("'predictionBounds' should be a logical or numeric vector of length 2")
    if (any(names(preProcOptions) == "method")) 
        stop("'method' cannot be specified here")
    if (any(names(preProcOptions) == "x")) 
        stop("'x' cannot be specified here")
    if (!is.na(repeats) & !(method %in% c("repeatedcv", 
        "adaptive_cv"))) 
        warning("`repeats` has no meaning for this resampling method.", 
            call. = FALSE)
    if (!(adaptive$method %in% c("gls", "BT"))) 
        stop("incorrect value of adaptive$method")
    if (adaptive$alpha < 1e-07 | adaptive$alpha > 1) 
        stop("incorrect value of adaptive$alpha")
    if (grepl("adapt", method)) {
        num <- if (method == "adaptive_cv") 
            number * repeats
        else number
        if (adaptive$min >= num) 
            stop(paste("adaptive$min should be less than", 
                num))
        if (adaptive$min <= 1) 
            stop("adaptive$min should be greater than 1")
    }
    if (!(search %in% c("grid", "random"))) 
        stop("`search` should be either 'grid' or 'random'")
    if (method == "oob" & any(names(match.call()) == "summaryFunction")) {
        warning("Custom summary measures cannot be computed for out-of-bag resampling. ", 
            "This value of `summaryFunction` will be ignored.", 
            call. = FALSE)
    }
    list(method = method, number = number, repeats = repeats, 
        search = search, p = p, initialWindow = initialWindow, 
        horizon = horizon, fixedWindow = fixedWindow, skip = skip, 
        verboseIter = verboseIter, returnData = returnData, returnResamp = returnResamp, 
        savePredictions = savePredictions, classProbs = classProbs, 
        summaryFunction = summaryFunction, selectionFunction = selectionFunction, 
        preProcOptions = preProcOptions, sampling = sampling, 
        index = index, indexOut = indexOut, indexFinal = indexFinal, 
        timingSamps = timingSamps, predictionBounds = predictionBounds, 
        seeds = seeds, adaptive = adaptive, trim = trim, allowParallel = allowParallel)
}

library(mlbench) #使用包中的数据
Warning message:
程辑包‘mlbench'是用R版本4.1.3 来建造的 
> data(Sonar)
> str(Sonar[, 1:10])
'data.frame':   208 obs. of  10 variables:
 $ V1 : num  0.02 0.0453 0.0262 0.01 0.0762 0.0286 0.0317 0.0519 0.0223 0.0164 ...
 $ V2 : num  0.0371 0.0523 0.0582 0.0171 0.0666 0.0453 0.0956 0.0548 0.0375 0.0173 ...
 $ V3 : num  0.0428 0.0843 0.1099 0.0623 0.0481 ...
 $ V4 : num  0.0207 0.0689 0.1083 0.0205 0.0394 ...
 $ V5 : num  0.0954 0.1183 0.0974 0.0205 0.059 ...
 $ V6 : num  0.0986 0.2583 0.228 0.0368 0.0649 ...
 $ V7 : num  0.154 0.216 0.243 0.11 0.121 ...
 $ V8 : num  0.16 0.348 0.377 0.128 0.247 ...
 $ V9 : num  0.3109 0.3337 0.5598 0.0598 0.3564 ...
 $ V10: num  0.211 0.287 0.619 0.126 0.446 ...

library(caret)
set.seed(998)
inTraining <- createDataPartition(Sonar$Class, p = .75, list = FALSE)
training <- Sonar[ inTraining,] #训练集
testing  <- Sonar[-inTraining,] #测试集

fitControl <- trainControl(## 10折交叉验证
                           method = "repeatedcv",
                           number = 10,
                           ## 重复10次
                           repeats = 1)
                           
set.seed(825)
gbmFit1 <- train(Class ~ ., data = training, 
                 method = "gbm", # 助推树
                 trControl = fitControl,
                 verbose = FALSE)
gbmFit1   
Stochastic Gradient Boosting 

157 samples
 60 predictor
  2 classes: 'M', 'R' 

No pre-processing
Resampling: Cross-Validated (10 fold, repeated 10 times) 
Summary of sample sizes: 141, 142, 141, 142, 141, 142, ... 
Resampling results across tuning parameters:

  interaction.depth  n.trees  Accuracy   Kappa    
  1                   50      0.7935784  0.5797839
  1                  100      0.8171078  0.6290208
  1                  150      0.8219608  0.6383173
  2                   50      0.8041912  0.6027771
  2                  100      0.8296176  0.6544713
  2                  150      0.8283627  0.6520181
  3                   50      0.8110343  0.6170317
  3                  100      0.8301275  0.6551379
  3                  150      0.8310343  0.6577252

Tuning parameter 'shrinkage' was held constant at a value of 0.1

Tuning parameter 'n.minobsinnode' was held constant at a value of 10
Accuracy was used to select the optimal model using the largest value.
The final values used for the model were n.trees = 150, interaction.depth
 = 3, shrinkage = 0.1 and n.minobsinnode = 10.