Question

使用的数据（样本）

EMpn Target Dailyrate DfrmHom

＆＃13;

Empnumber	Target	Dailyrate	DFrmHome	Education	Employeecount	Age	HourlyRate	Jobinvolvment	Joblevel
1	0	1	1	1	-1	1	1	1	1
2	1	1	1	1	1	1	1	1	1
3	0	1	-1	1	1	-1	1	1	1
4	1	1	1	1	1	1	1	1	1
5	0	1	-1	1	1	-1	1	1	1
6	1	1	-1	1	1	-1	1	-1	1
7	0	1	1	1	-1	1	1	1	1
8	1	1	1	1	1	1	1	1	1
9	1	1	-1	1	1	-1	1	1	1
10	1	1	1	1	1	1	1	1	1
11	0	1	-1	1	-1	-1	1	1	1
12	0	1	1	1	-1	1	1	1	1
13	0	1	1	1	1	1	1	1	1
14	1	1	1	1	1	-1	1	1	1
15	1	1	1	1	1	1	1	1	1
16	1	1	-1	1	1	-1	1	-1	1
17	0	1	1	1	1	-1	1	1	1
18	0	1	-1	1	1	-1	1	1	1
19	0	1	1	1	-1	1	1	1	1
20	0	1	-1	1	1	-1	1	1	1
21	0	1	1	1	-1	1	1	1	1
22	0	1	1	1	-1	1	1	1	1

＆＃13;

  Rcode :  
    library(NeuralNetTools)
    #Read the data for train and test data 
    CTDF = read.csv("Project-Attrition.csv",header=T,na.strings=c(""))
    # Let us set differnt seeds and extract 70 % of Poulation for arriving       
    at  Development, Test and Holdout samples
    CTDF.dev  = sample.split(CTDF$Target,SplitRatio=0.70)
    head(split,20)
    CTDF.train= subset(CTDF, split== TRUE)
    str(CTDF.train)
    View(CTDF.train)
    table(CTDF.train$Target)
    CTDF.test= subset(CTDF, split== FALSE)
    str(CTDF.test)
    table(CTDF.test$Target)
    CTDF.NND=CTDF.train
    CTDF.NNT=CTDF.test
    Model = =nnet(Target~Dailyrate+DFrmHome +
            +Education+Employeecount+Age+HourlyRate+Jobinvolvment+Joblevel, 
            data=CTDF.NND, size=30, rang= 0.1, decay = 5e-4 , maxit = 500)
    table(Actual=CTDF.NND$Target, Prediction=predict(Model, data=CTDF.NND))
    CTDF.NNT$predict.class = predict(Model, CTDF.NNT)   
    confusionMatrix(CTDF.NNT$predict.class, CTDF.NNT$Target)

Output : 
  str(CTDF.train)
      'data.frame': 3167 obs. of  10 variables:
  $ Empnumber    : int  1 2 4 5 6 7 11 12 14 15 ...
  $ Target       : int  0 1 1 0 1 0 0 0 1 1 ...
  $ Dailyrate    : int  1 1 1 1 1 1 1 1 1 1 ...
  $ DFrmHome     : int  1 1 1 -1 -1 1 -1 1 1 1 ...
  $ Education    : int  1 1 1 1 1 1 1 1 1 1 ...
  $ Employeecount: int  -1 1 1 1 1 -1 -1 -1 1 1 ...
  $ Age          : int  1 1 1 -1 -1 1 -1 1 -1 1 ...
  $ HourlyRate   : int  1 1 1 1 1 1 1 1 1 1 ...
  $ Jobinvolvment: int  1 1 1 1 -1 1 1 1 1 1 ...
  $ Joblevel     : int  1 1 1 1 1 1 1 1 1 1 ...

For＆＃34; table（Actual = CTDF.NND $ Target，Prediction = predict（Model，data = CTDF.NND））＆＃34;

I was expecting a confusion matrix like below.
    0    1 
 0 
 1

但我得到的是：

   Prediction

实际0.00892725347390036 0.0358546806229366 0.0376897872686173 0.10518235583921 0.124456456913317 0 3 242 1 34 197 1 0 9 0 4 28 预测实际0.1363541434416 0.236290782608584 0.286744920923175 0.331511427682813 0.613818492677834 0.726882504157994 0 19 42 5 474 51 6 1 3 13 2 235 81 16 预测

对于计算混淆矩阵的测试数据，我收到以下错误：

   confusionMatrix(CTDF.NNT$predict.class, CTDF.NNT$Target)

confusionMatrix.default（CTDF.NNT $ predict.class，CTDF.NNT $ Target）出错：数据的级别不能超过参考

请帮助克服这些问题。

计算混淆矩阵时出错 - Neuralnet包

0 个答案: