Question

我当前正在使用混合类型数据的数据集。我正在使用R软件中的caret软件包来训练SVM，LogitBoost，RF .....

我的数据集的尺寸为124x28，正如我所指出的那样，预测变量是数值变量或因子（在某些情况下为有序因子）。

我试图根据从重要性最低的变量的数据集中消除预测变量的方法：每次迭代预测变量的数量减少一。我使用插入符号包中的varImp函数来评估变量的重要性。要分类的变量是第一个称为State的变量，它是2级的因子。

我遇到的问题是varImp不适用于特定的一组预测变量，但可以用于该特定组的一个或多个预测变量集。特别是，对于运行varImp之后的那组特定的预测变量，控制台将显示以下错误：

auc3_（实际，预测，等级）中的错误：与不兼容要求的类型：[type = character; target = double]。

代码如下：

超出设置

rm(list = ls())
library(readxl)
library(caret)
library(ROCR)
library(kernlab)
library(e1071)
library(openxlsx)

tutti <- read_excel("C:/Users/Matteo/Tesi/data set.xlsx")
tutti<-data.frame(tutti)
tutti$State = as.character(tutti$State)
tutti$State = factor(tutti$State)
tutti$T_Anxiety_40fl2 = factor(tutti$T_Anxiety_40fl2)
tutti$SmkAroundLMP2 = factor(tutti$SmkAroundLMP2)
tutti$SmkTrimester1_overall = factor(tutti$SmkTrimester1_overall)
tutti$SmkTrimester2_overall = factor(tutti$SmkTrimester2_overall)
tutti$AnyDrugs2 = factor(tutti$AnyDrugs2)
tutti$ACC_G = factor(tutti$ACC_G,ordered=TRUE)
tutti$ACC_P = factor(tutti$ACC_P,ordered=TRUE)
tutti$DEC = factor(tutti$DEC,ordered=TRUE)

tutti<-tutti[-c(2,11,4,16,8,19,6,5,20,26,23,7,10,18,27,9)]


train.index <- sample.int(nrow(tutti),ceiling(nrow(tutti)*0.7));
trainset <- tutti[train.index,] 
testset <- tutti[-train.index,]
testX<-testset[-1]

ctrl<-trainControl(method="cv",number=10,     summaryFunction=twoClassSummary,classProbs=TRUE)
grid <- expand.grid(C=(2))
svm.tune <- train(State ~ .,data=trainset,method = "svmLinear",tuneGrid =  grid,trControl=ctrl)
all <- varImp(svm.tune)

######################

特定集

rm(list = ls())
library(readxl)
library(caret)
library(ROCR)
library(kernlab)
library(e1071)
library(openxlsx)

tutti <- read_excel("C:/Users/Matteo/Tesi/data set.xlsx")
tutti<-data.frame(tutti)
tutti$State = as.character(tutti$State)
tutti$State = factor(tutti$State)
tutti$T_Anxiety_40fl2 = factor(tutti$T_Anxiety_40fl2)
tutti$SmkAroundLMP2 = factor(tutti$SmkAroundLMP2)
tutti$SmkTrimester1_overall = factor(tutti$SmkTrimester1_overall)
tutti$SmkTrimester2_overall = factor(tutti$SmkTrimester2_overall)
tutti$AnyDrugs2 = factor(tutti$AnyDrugs2)
tutti$ACC_G = factor(tutti$ACC_G,ordered=TRUE)
tutti$ACC_P = factor(tutti$ACC_P,ordered=TRUE)
tutti$DEC = factor(tutti$DEC,ordered=TRUE)

tutti<-tutti[-c(2,11,4,16,8,19,6,5,20,26,23,7,10,18,27,9,25)]

train.index <- sample.int(nrow(tutti),ceiling(nrow(tutti)*0.7));
trainset <- tutti[train.index,] 
testset <- tutti[-train.index,]
testX<-testset[-1]

ctrl<-trainControl(method="cv",number=10,     summaryFunction=twoClassSummary,classProbs=TRUE)
grid <- expand.grid(C=(2))
svm.tune <- train(State ~ .,data=trainset,method = "svmLinear",tuneGrid =  grid,trControl=ctrl)
all <- varImp(svm.tune)

#############################

子集

rm(list = ls())
library(readxl)
library(caret)
library(ROCR)
library(kernlab)
library(e1071)
library(openxlsx)

tutti <- read_excel("C:/Users/Matteo/Tesi/data set.xlsx")
tutti<-data.frame(tutti)
tutti$State = as.character(tutti$State)
tutti$State = factor(tutti$State)
tutti$T_Anxiety_40fl2 = factor(tutti$T_Anxiety_40fl2)
tutti$SmkAroundLMP2 = factor(tutti$SmkAroundLMP2)
tutti$SmkTrimester1_overall = factor(tutti$SmkTrimester1_overall)
tutti$SmkTrimester2_overall = factor(tutti$SmkTrimester2_overall)
tutti$AnyDrugs2 = factor(tutti$AnyDrugs2)
tutti$ACC_G = factor(tutti$ACC_G,ordered=TRUE)
tutti$ACC_P = factor(tutti$ACC_P,ordered=TRUE)
tutti$DEC = factor(tutti$DEC,ordered=TRUE)

tutti<-tutti[-c(2,11,4,16,8,19,6,5,20,26,23,7,10,18,27,9,25,24)]

train.index <- sample.int(nrow(tutti),ceiling(nrow(tutti)*0.7));
trainset <- tutti[train.index,] 
testset <- tutti[-train.index,]
testX<-testset[-1]

ctrl<-trainControl(method="cv",number=10,     summaryFunction=twoClassSummary,classProbs=TRUE)
grid <- expand.grid(C=(2))
svm.tune <- train(State ~ .,data=trainset,method = "svmLinear",tuneGrid =  grid,trControl=ctrl)
all <- varImp(svm.tune)

实际上，如果一组预测变量仅包含一个因子变量，则varImp返回该错误。（除了要预测的变量）

您能帮我解决这个问题吗？

我已经更新了R的每个软件包。

快速查看源代码后，我认为这是源代码（C ++）问题。我说的对吗？

如何解决此错误：“ auc3 _（（实际，预测，排名）错误：与请求的类型不兼容：[type = character; target = double]。”

超出设置

特定集

子集

0 个答案: