R(插入符)- 在循环中训练 "mlpML"模型时出错

Question

我正在使用 R 中的 Caret 包来训练多层感知器 (mlpML) 模型。

我想做的是前向特征消除技术，并了解 mlpML 模型如何针对不同数量的特征执行。

这就是为什么我在循环中训练 mlpML 模型，其中每次迭代都会添加一个新功能并将其输入到模型中。

这是我得到的错误 -

Error: Please use column names for `x`

这是我的代码 -

ig_features <- c("F1", "F2", "F3", "F4", "F5")

library(caret)

x_features <- c()

for (i in ig_features) {

  x_features <- c(x_features, i)
  y_features <- c("Status")

  #------------------------------------------ Building Model ---------------------------------------------------
  set.seed(1234)

  mlp_grid = expand.grid(layer1 = 10,
                         layer2 = 10,
                         layer3 = 10)

  mlp_fit = caret::train(x = TRAIN[,x_features], 
                         y = TRAIN[,y_features],
                         method = "mlpML",
                         preProc =  c('center', 'scale', 'knnImpute', 'pca'),
                         trControl = trainControl(method = "cv", verboseIter = TRUE, returnData = FALSE),
                         tuneGrid = mlp_grid)

  #------------------------------------------ Prediction & Evaluation -----------------------------------------
  predictions <- predict(mlp_fit, newdata=TEST[,x_features])

  cat("Accuracy:",confusionMatrix(predictions, 
                                  PARKINSON_TRAIN$Status, 
                                  dnn = c("Prediction", "Actual"), 
                                  positive="1")$overall[[1]],"\n")
}

Answer 1

您缺少 x 的列名称，在本例中为 TRAIN[,x_features]。请参阅 ?caret::train 文档，其中指出:

x: For the default method, x is an object where samples are in rows and features are in columns. This could be a simple matrix, data frame or other type (e.g. sparse matrix) but must have column names (see Details below).