插入符号中基于重采样的性能度量

Resampling based performance measure in caret

我执行惩罚逻辑回归,并使用 caret (glmnet) 训练模型。

model_fit <- train(Data[,-1], Data[,1],
               method = "glmnet",
               family="binomial",
               metric = "ROC",
               maximize="TRUE",
               trControl = ctrl,
               preProc = c("center", "scale"),
               tuneGrid=expand.grid(.alpha=0.5,.lambda=lambdaSeq)
               )

根据 caret 文档,函数 train“[...] 计算基于重采样的性能度量”和 "Across each data set, the performance of held-out samples is calculated and the mean and standard deviation is summarized for each combination."

results是"A data frame"(含)"the training error rate and values of the tuning parameters."

model_fit$results$ROC 是跨重采样的性能度量平均值的向量(大小等于我的调整参数 lambda 的大小)吗? (而不是在针对 lambda 的每个值对整个样本重新估计模型之后对整个样本计算的性能度量?)

Is model_fit$results$ROC a vector (with size equal to the size of my tuning parameter lambda) of the mean of the performance measure across resampling?

是的;准确地说,长度将等于 tuneGrid 的行数,这里正好与 lambdaSeq 的长度一致(因为唯一的其他参数 alpha , 保持不变)。

这是一个简单的例子,改编自 caret docs(它使用 gbmAccuracy 指标,但思想是相同的):

library(caret)
library(mlbench)
data(Sonar)

set.seed(998)
inTraining <- createDataPartition(Sonar$Class, p = .75, list = FALSE)
training <- Sonar[ inTraining,]
testing  <- Sonar[-inTraining,]

fitControl <- trainControl(method = "cv",
                           number = 5)

set.seed(825)

gbmGrid <-  expand.grid(interaction.depth = 3, 
                        n.trees = (1:3)*50, 
                        shrinkage = 0.1,
                        n.minobsinnode = 20)

gbmFit1 <- train(Class ~ ., data = training, 
                 method = "gbm", 
                 trControl = fitControl,
                 tuneGrid = gbmGrid,
                 ## This last option is actually one
                 ## for gbm() that passes through
                 verbose = FALSE)

此处,gbmGrid 有 3 行,即它仅由三 (3) 个不同的 n.trees 值组成,其他参数保持不变;因此,相应的 gbmFit1$results$Accuracy 将是一个长度为 3 的向量:

gbmGrid
#   interaction.depth n.trees shrinkage n.minobsinnode
# 1                 3      50       0.1             20
# 2                 3     100       0.1             20
# 3                 3     150       0.1             20

gbmFit1$results
#   shrinkage interaction.depth n.minobsinnode n.trees  Accuracy     Kappa AccuracySD   KappaSD
# 1       0.1                 3             20      50 0.7450672 0.4862194 0.05960941 0.1160537
# 2       0.1                 3             20     100 0.7829704 0.5623801 0.05364031 0.1085451
# 3       0.1                 3             20     150 0.7765188 0.5498957 0.05263735 0.1061387

gbmFit1$results$Accuracy
# [1] 0.7450672 0.7829704 0.7765188

返回的 3 个 Accuracy 值中的每一个都是我们用作重采样技术的 5 重交叉验证的 验证 折叠中的度量结果;更准确地说,它是在这 5 次折叠中计算的验证准确度的 mean(你可以看到有一个 AccuracySD 列,也包含它的标准偏差)。

And NOT the performance measure computed over the whole sample after re-estimating the model over the whole sample for each value of lambda?

对,不是那样的。