R：带有自定义变量重要性 permimp 的 Caret rfe

Question

我想用插入符号rfe() 和替代变量重要性算法permimp 运行递归特征消除。 permimp 排列重要性使用 cforest 和 cforest_unbiased()。为了运行rfe 和permimp() 和cforest，我还需要自定义哪些其他插入符号函数？

这是我目前的代码：

library(caret)

permimpRFE <- list(summary = defaultSummary,
                   fit = function(x, y, first, last, ...){
                     library(party)
                     tmp <- as.data.frame(x, stringsAsFactors = TRUE)
                     tmp$y <- y
                     party::cforest(y ~ ., data = tmp,
                                    control = party::cforest_unbiased(ntree = 50))
                   },
                   pred = function(object, x)  predict(object, x),
                   rank = function(object, x, y) {
                     library(permimp)
                     vimp <- permimp::permimp(object, conditional = TRUE, threshold = .95, do_check = FALSE)
                     vimp <- as.data.frame(vimp$values)
                     colnames(vimp) <- "Overall"
                     vimp <- vimp[order(vimp$Overall, decreasing = TRUE),, drop = FALSE]
                     if (ncol(x) == 1) {
                       vimp$var <- colnames(x)
                     } else vimp$var <- rownames(vimp)
                     vimp
                   },
                   selectSize = pickSizeBest,
                   selectVar = pickVars)


# specify rfeControl
contr <- caret::rfeControl(functions=permimpRFE, method="repeatedcv", number=3, repeats=2, 
                           saveDetails = TRUE)

dat <- as.data.frame(ChickWeight)[1:50,]

preds <- dat[,2:4]
response <- dat[,1]

# recursive feature elimination caret (Algorithm 2)
set.seed(43, kind = "Mersenne-Twister", normal.kind = "Inversion")
results <- caret::rfe(x = preds, 
                      y = response,
                      sizes=c(1:3),
                      metric= "RMSE", 
                      rfeControl=contr)

我收到错误Error in { : task 1 failed - "invalid 'x' type in 'x && y'"

如何让rfe 与permimp 和cforest 一起运行？

Answer 1

在尝试为rfe() 自定义变量重要性函数时，实现所需函数及其依赖函数的准确语法非常重要。

就我而言，我必须将 predict(object, x) 更改为 predict(object, newdata = x)。

现在代码 sn-p 正在运行：

library(caret)

permimpRFE <- list(summary = defaultSummary,
                   fit = function(x, y, first, last, ...){
                     library(party)
                     tmp <- as.data.frame(x, stringsAsFactors = TRUE)
                     tmp$y <- y
                     party::cforest(y ~ ., data = tmp,
                                    control = party::cforest_unbiased(ntree = 50))
                   },
                   pred = function(object, x) {
                     x <- as.data.frame(x, stringsAsFactors = TRUE)
                     predict(object, newdata = x)
                   },
                   rank = function(object, x, y) {
                     library(permimp)
                     vimp <- permimp::permimp(object, conditional = TRUE, threshold = .95, do_check = FALSE)
                     vimp <- as.data.frame(vimp$values)
                     colnames(vimp) <- "Overall"
                     vimp <- vimp[order(vimp$Overall, decreasing = TRUE),, drop = FALSE]
                     if (ncol(x) == 1) {
                       vimp$var <- colnames(x)
                     } else vimp$var <- rownames(vimp)
                     vimp
                   },
                   selectSize = pickSizeBest,
                   selectVar = pickVars)


# specify rfeControl
contr <- caret::rfeControl(functions=permimpRFE, method="repeatedcv", number=3, repeats=2, 
                           saveDetails = TRUE)

dat <- as.data.frame(ChickWeight)[1:50,]

preds <- dat[,2:4]
response <- dat[,1]

# recursive feature elimination caret (Algorithm 2)
set.seed(43, kind = "Mersenne-Twister", normal.kind = "Inversion")
results <- caret::rfe(x = preds, 
                      y = response,
                      sizes=c(1:3),
                      metric= "RMSE", 
                      rfeControl=contr)