R插入符号：将主题与数据子集进行交叉验证以进行培训？

Question

我想使用 R 插入符号执行遗漏主题交叉验证（参见 this example），但只使用训练中的数据子集来创建 CV 模型。尽管如此，遗漏的 CV 分区应该作为一个整体使用，因为我需要测试遗漏主题的所有数据（无论是否是由于计算限制而无法用于训练的数百万样本）。

我使用 caret::train 和 caret::trainControl 的 subset 和 index 参数创建了一个最小的 2 class class化示例为了达成这个。根据我的观察，这应该可以解决问题，但实际上我很难确保评估仍然以遗漏主题的方式进行。也许有此任务经验的人可以对此有所了解：

library(plyr)
library(caret)
library(pROC)
library(ggplot2)

# with diamonds we want to predict cut and look at results for different colors = subjects
d <- diamonds
d <- d[d$cut %in% c('Premium', 'Ideal'),] # make a 2 class problem
d$cut <- factor(d$cut)
indexes_data <- c(1,5,6,8:10)
indexes_labels <- 2 

# population independent CV indexes for trainControl
index <- llply(unique(d[,3]), function(cls) c(which(d[,3]!=cls)))
names(index) <- paste0('sub_', unique(d[,3]))
str(index) # indexes used for training models with CV = OK

m3 <- train(x = d[,indexes_data], 
            y = d[,indexes_labels], 
            method = 'glm', 
            metric = 'ROC',
            subset = sample(nrow(d), 5000), # does this subset the data used for training and obtaining models, but not the left out partition used for estimating CV performance?
            trControl = trainControl(returnResamp = 'final', 
                                    savePredictions = T,
                                    classProbs = T, 
                                    summaryFunction = twoClassSummary, 
                                    index = index))
str(m3$resample) # all samples used once = OK

# performance over all subjects
myRoc <- roc(predictor = m3$pred[,3], response = m3$pred$obs)

情节（myRoc，主要= 'all'）

个别科目的表现

l_ply(唯一(m3$pred$Resample), .fun = function(cls) { pred_sub <- m3$pred[m3$pred$Resample==cls,] myRoc <- roc（预测器 = pred_sub[3]，响应 = pred_sub$obs）情节（myRoc，主要= cls） })

感谢您的宝贵时间！

Answer 1

同时在 caret::trainControl 中使用 index 和 indexOut 参数似乎可以解决问题（感谢 Max 的提示 in this question）。这是更新后的代码：

library(plyr)
library(caret)
library(pROC)
library(ggplot2)
str(diamonds)

# with diamonds we want to predict cut and look at results for different colors = subjects
d <- diamonds
d <- d[d$cut %in% c('Premium', 'Ideal'),] # make a 2 class problem
d$cut <- factor(d$cut)
indexes_data <- c(1,5,6,8:10)
indexes_labels <- 2 

# population independent CV partitions for training and left out partitions for evaluation
indexes_populationIndependence_subjects <- 3
index <- llply(unique(d[,indexes_populationIndependence_subjects]), function(cls) c(which(d[,indexes_populationIndependence_subjects]!=cls)))
names(index) <- paste0('sub_', unique(d[,indexes_populationIndependence_subjects]))
indexOut <- llply(index, function(part) (1:nrow(d))[-part])
names(indexOut) <- paste0('sub_', unique(d[,indexes_populationIndependence_subjects]))
# subsample partitions for training
index <- llply(index, function(i) sample(i, 1000))

m3 <- train(x = d[,indexes_data], 
            y = d[,indexes_labels], 
            method = 'glm', 
            metric = 'ROC',
            trControl = trainControl(returnResamp = 'final',
                                    savePredictions = T,
                                    classProbs = T, 
                                    summaryFunction = twoClassSummary, 
                                    index = index, 
                                    indexOut = indexOut))
m3$resample # seems OK
str(m3$pred) # seems OK
myRoc <- roc(predictor = m3$pred[,3], response = m3$pred$obs)
plot(myRoc, main = 'all')
# analyze results per subject
l_ply(unique(m3$pred$Resample), .fun = function(cls) {
    pred_sub <- m3$pred[m3$pred$Resample==cls,]
    myRoc <- roc(predictor = pred_sub[,3], response = pred_sub$obs)
    plot(myRoc, main = cls)
} )

不过，我不确定这是否真的 以独立于人口的方式进行估计，所以如果有人了解详细信息，请分享您的想法！

R插入符号：将主题与数据子集进行交叉验证以进行培训？

R caret: leave subject out cross validation with data subset for training?

r

subset

cross-validation

r-caret

个别科目的表现