我正在使用插入包开发一个简单的rpart模型。
library(caret)
data <- fread(sprintf("%s/%s", dataDir, dataFile), header=T, stringsAsFactors = TRUE)
split <- createDataPartition(y = data$Audit, p = 0.7, list = FALSE)
trainSet <- data[split,]
test <- data[-split,]
fitControl <- trainControl( method = "repeatedcv", number = 10,repeats = 10)
fitControl <- trainControl( method = "repeatedcv", number = 10,repeats = 10)
fit <- train(Audit ~ Activity1 + Activity2 + Activity3 + Activity4 + Activity5 + Activity6 + Activity7 + Activity8, data = trainSet, method="rpart", trControl = fitControl)
现在我试图创建一个混淆矩阵:
preds<-predict(fit2, newdata = test)
cm<-confusionMatrix(preds,test$Audit)
print(cm)
当我看到输出时,我看到了:
[,1] [,2]
[1,] 0 0
[2,] 4 0
这对我来说真的很困惑,而且没有意义。我期待这样的事情成为我的困惑矩阵
preds A B U
A 0 0 0
B 0 4 0
U 2 0 9
这是我的数据的快照:
这是我的数据输入:
dput(as.data.frame(data))
structure(list(Activity1 = structure(c(2L, 1L, 2L, 1L, 1L, 1L,
1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 2L,
2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 2L), .Label = c("a", "b"), class = "factor"), Activity2 =
structure(c(2L,
1L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 2L,
1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L,
2L, 1L, 2L, 2L, 1L, 2L, 2L), .Label = c("a", "b"), class = "factor"),
Activity3 = structure(c(2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = c("a", "b"), class = "factor"), Activity4 = structure(c(2L,
1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("b",
"e"), class = "factor"), Activity5 = structure(c(2L, 1L,
2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L,
2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("b", "d"), class = "factor"),
Activity6 = structure(c(2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L), .Label = c("d", "e"), class = "factor"), Activity7 = structure(c(1L,
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L,
2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L,
1L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L), .Label = c("a",
"c"), class = "factor"), Activity8 = structure(c(2L, 2L,
4L, 2L, 2L, 2L, 2L, 4L, 2L, 1L, 3L, 1L, 2L, 4L, 1L, 2L, 2L,
2L, 2L, 2L, 4L, 2L, 3L, 2L, 4L, 2L, 1L, 2L, 3L, 4L, 2L, 2L,
1L, 2L, 2L, 2L, 3L, 4L, 1L, 2L, 2L, 2L, 3L, 1L, 1L, 2L, 2L,
3L, 2L, 2L, 2L, 3L, 2L, 2L, 4L, 3L), .Label = c("a", "c",
"d", "e"), class = "factor"), Audit = structure(c(3L, 1L,
3L, 2L, 1L, 1L, 1L, 3L, 3L, 2L, 3L, 2L, 2L, 3L, 2L, 1L, 3L,
3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 2L, 3L, 3L, 3L, 1L, 2L,
2L, 1L, 3L, 2L, 3L, 3L, 2L, 1L, 3L, 3L, 3L, 2L, 2L, 3L, 3L,
3L, 3L, 3L, 2L, 3L, 3L, 2L, 3L, 3L), .Label = c("A", "B",
"U"), class = "factor")), .Names = c("Activity1", "Activity2",
"Activity3", "Activity4", "Activity5", "Activity6", "Activity7",
"Activity8", "Audit"), row.names = c(NA, -56L), class = "data.frame")
以下是我的测试数据的输入:
> dput(as.data.frame(test))
structure(list(Activity1 = structure(c(1L, 1L, 1L, 2L, 2L, 1L,
1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 2L), .Label = c("a", "b"), class =
"factor"),
Activity2 = structure(c(1L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 2L), .Label = c("a", "b"), class = "factor"),
Activity3 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = c("a", "b"), class = "factor"),
Activity4 = structure(c(2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 2L, 2L, 2L, 2L, 2L), .Label = c("b", "e"), class = "factor"),
Activity5 = structure(c(2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L,
2L, 2L, 2L, 2L, 2L, 2L), .Label = c("b", "d"), class = "factor"),
Activity6 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L), .Label = c("d", "e"), class = "factor"),
Activity7 = structure(c(2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L), .Label = c("a", "c"), class = "factor"),
Activity8 = structure(c(2L, 2L, 2L, 4L, 2L, 2L, 2L, 3L, 2L,
2L, 3L, 2L, 2L, 4L, 3L), .Label = c("a", "c", "d", "e"), class = "factor"),
Audit = structure(c(2L, 3L, 2L, 3L, 3L, 1L, 2L, 3L, 1L, 3L,
3L, 3L, 2L, 3L, 3L), .Label = c("A", "B", "U"), class = "factor")), .Names = c("Activity1",
"Activity2", "Activity3", "Activity4", "Activity5", "Activity6",
"Activity7", "Activity8", "Audit"), class = "data.frame", row.names = c(NA,
-15L))
有人可以帮我吗?感谢
答案 0 :(得分:0)
我刚刚发现了为什么我的confusionMatrix是nbot正常工作的原因。这是因为我在代码的开头加载了库(插入符号)以及库(ModelMetrics)。一旦我评论了库(ModelMetrics)并重新启动了我的R,我就能让混淆矩阵完美地工作。