目标

Question

数据位于页面的最底部，称为LDA.scores＆＃39;。这是一个分类任务，我在数据集上执行了三种有监督的机器学习分类技术。提供所有编码以显示如何产生这些ROC曲线。我为问一个加载的问题而道歉，但我一直试图使用不同的代码组合解决这些问题将近两周，所以如果有人可以帮助我，那么谢谢你。主要问题是朴素贝叶斯曲线显示1的完美分数，这显然是错误的，我无法解决如何将线性判别分析曲线合并到单个ROC图中以与所提供的编码进行比较。

线性判别分析（LDA）在＆＃34; MASS＆＃34;封装
朴素贝叶斯（NB）在＆＃34; kLAR＆＃34;封装
＆＃34; rpart＆＃34;中的分类树（CT）封装

目标

单个ROC图显示ROC曲线，用于每种分类技术之间的比较，与图例相结合。
计算每种分类技术的曲线下面积

问题

每种分类技术都在不同的R包中进行，我很难将这些ROC曲线合并到一个图上。所有错误消息都显示在页面底部
LDA和NB的ROC曲线看起来很虚假
我无法应用图例和体验错误消息

我提供了所有三种技术的编码，因此任何人都可以逐步评估我的逻辑

线性判别分析

   library(MASS)
   predictors<-as.matrix(LDA.scores[,2:13])
   response<-as.factor(LDA.scores[,1])

   #Perform LDA 

   Family.lda<-lda(response~predictors, CV=TRUE)
   predict.Family <-predict(Family.lda)
   tab <- table(response, Family.lda$class)

构造混淆矩阵以预测类

   conCV1 <- rbind(tab[1, ]/sum(tab[1, ]), tab[2, ]/sum(tab[2, ]))
   dimnames(conCV1) <- list(Actual = c("No", "Yes"), "Predicted (cv)"= c("No", "Yes"))

   print(round(conCV1, 3))

情节判别分数

    library(lattice)
    windows(width=10, height=7)
    densityplot(~predict.Family$x, groups=LDA.scores$Family)

计算混淆矩阵的函数

 confusion <- function(actual, predicted, names = NULL, printit = TRUE, prior = NULL) {                    
  if (is.null(names))
  names <- levels(actual)
  tab <- table(actual, predicted)
  acctab <- t(apply(tab, 1, function(x) x/sum(x)))
  dimnames(acctab) <- list(Actual = names, "Predicted (cv)" = names)
  if (is.null(prior)) {
  relnum <- table(actual)
  prior <- relnum/sum(relnum)
  acc <- sum(tab[row(tab) == col(tab)])/sum(tab)
  }
 else {
  acc <- sum(prior * diag(acctab))
  names(prior) <- names
  }
  if (printit)
  print(round(c("Overall accuracy" = acc, "Prior frequency" = prior),
                + 4))
  if (printit) {
  cat("\nConfusion matrix", "\n")
  print(round(acctab, 4))
  }
  invisible(acctab)
  }

更改比例以创建训练和测试集（70:30）

  prior <- c(0.7, 0.3)
  lda.70.30 <- lda(response~predictors, CV=TRUE, prior=prior)
  confusion(response, lda.70.30$class, prior = c(0.7, 0.3))

创建ROC曲线的函数

 truepos <- numeric(19)
 falsepos <- numeric(19)
 p1 <- (1:19)/20
 for (i in 1:19) {
 p <- p1[i]
 Family.ROC <- lda(response~predictors, CV = TRUE, prior = c(p,  1 - p))

 confmat <- confusion(LDA.scores$Family, Family.ROC$class, printit = FALSE)
 falsepos[i] <- confmat[1, 2]
 truepos[i] <- confmat[2, 2]
 }

绘制ROC曲线

 windows(width=10, height=7)
 LDA.ROC<-plot(truepos~falsepos, type = "l", lwd=2, 
               xlab = "False     positive    rate (Specificity)", 
               ylab = "True positive rate (Sensitivity)" col ="green")
               abline(a=0,b=1, col="red")

图1

分类树

生成测试和训练集70:30

  index<-1:nrow(LDA.scores) 
  trainindex.LDA=sample(index, trunc(length(index)*0.70), replace=FALSE) 
  LDA.70.trainset<-LDA.scores[trainindex,]
  LDA.30.testset<-LDA.scores[-trainindex,]

以70％的训练集种植树木

#Grow Tree the tree with the 70 % training set

  library(rpart)
  tree.split3<-rpart(Family~., data=LDA.70.trainset3, method="class")
  summary(tree.split3)
  print(tree.split3)
  plot(tree.split3)
  text(tree.split3,use.n=T,digits=0)
  printcp(tree.split3)

使用测试和训练集（70:30）

 res3=predict(tree.split3,newdata=LDA.30.testset3)
 res4=as.data.frame(res3)

为分类分组因子的二项分布创建二进制系统（0或1）

 res4$actual2 = NA
 res4$actual2[res4$actual=="G8"]= 1
 res4$actual2[res4$actual=="V4"]= 0

绘制ROC曲线

 roc_pred <- prediction(re4$Predicted.prob, res4$actual2)
 perf <- performance(roc_pred, "tpr", "fpr")
 plot(perf, col="blue", lwd=2)
 abline(0,1,col="grey")

图2

朴素贝叶斯

 library(klaR)
 library(caret)

生成测试和训练集70:30

 trainIndex <- createDataPartition(LDA.scores$Family, p=0.70, list=FALSE)
 sig.train=LDA.scores[trainIndex,]
 sig.test=LDA.scores[-trainIndex,]

构建NB模型并对测试集进行预测

 sig.train$Family<-as.factor(sig.train$Family)
 sig.test$Family<-as.factor(sig.test$Family)
 nbmodel<-NaiveBayes(Family~., data=sig.train)
 prediction<-predict(nbmodel, sig.test[2:13])
 NB<-as.data.frame(prediction)
 colnames(NB)<-c("Family", "Actual", "Predicted")

为分类因子

 NB$actual2 = NA
 NB$actual2[NB$Family=="V4"]=1
 NB$actual2[NB$Family=="G8"]=0
 NB2<-as.data.frame(NB)

PLOT ROC CURVE - 这条曲线看起来很可疑

 library(ROCR)
 windows(width=10, height=7)
 roc_pred.NB<- prediction(NB2$Predicted, NB2$actual2)
 perf.NB <- performance(roc_pred.NB, "tpr", "fpr")
 plot(perf.NB, col="orange", lwd=2)
 abline(0,1,col="grey")

图3：此ROC曲线显然错误

将所有ROC曲线绘制到单个图上

 windows(width=10, height=7)
 plot(fit.perf, col="blue", lwd=2); #CT
 plot(LDA.ROC, col="green", lwd=2, add=T); #LDA
 plot(perf.NB,lwd=2,col="orange", lwd=2, add=T);NB
 abline(0,1,col="red", lwd=2)

错误消息

 Warning in min(x) : no non-missing arguments to min; returning Inf
 Warning in max(x) : no non-missing arguments to max; returning -Inf
 Warning in min(x) : no non-missing arguments to min; returning Inf
 Warning in max(x) : no non-missing arguments to max; returning -Inf
 Warning in plot.window(...) : "add" is not a graphical parameter
 Error in plot.window(...) : need finite 'xlim' values
 plot(fit.NB,lwd=2,col="orange", lwd=2, add=T); #NB
 Error in plot(fit.NB, lwd = 2, col = "orange", lwd = 2, add = T) : 
 error in evaluating the argument 'x' in selecting a method for function          
 Warning in plot.window(...) : "add" is not a graphical parameter
 Error in plot.window(...) : need finite 'xlim' values

曲线下面积

  auc1<-performance(fit.pred,"auc")#CT
  auc2<-performance(fit.NB, "auc")#NB

我不确定如何根据提供的LDA代码计算区域

制作传奇

此代码生成错误消息

legend(c('fit.pred',fit.NB','LDA.ROC'), col=c('blue',orange','green'),lwd=3)

名为LDA.scores的数据

       Family    Swimming Not.Swimming      Running  Not.Running
    1      v4 -0.48055680 -0.086292700 -0.157157188 -0.438809944
    2      v4  0.12600625 -0.074481895  0.057316151 -0.539013927
    3      v4  0.06823834 -0.056765686  0.064711783 -0.539013927
    4      v4  0.67480139 -0.050860283  0.153459372 -0.539013927
    5      v4  0.64591744 -0.050860283  0.072107416 -0.472211271
    6      v4  0.21265812 -0.068576492  0.057316151 -0.071395338
    7      v4 -0.01841352 -0.068576492 -0.053618335 -0.071395338
    8      v4  0.12600625  0.055436970  0.012942357  0.296019267
    9      v4 -0.22060120  0.114491000 -0.038827070  0.563229889
    10     v4  0.27042603 -0.021333268  0.049920519 -0.037994010
    11     v4  0.03935439 -0.044954880  0.012942357  0.195815284
    12     v4 -0.45167284  0.008193747 -0.075805232 -0.171599321
    13     v4 -0.04729748 -0.056765686  0.035129254 -0.305204632
    14     v4 -0.10506539  0.008193747 -0.046222702  0.062209973
    15     v4  0.09712230  0.037720761  0.109085578 -0.104796666
    16     v4 -0.07618143  0.014099150 -0.038827070  0.095611301
    17     v4  0.29930998  0.108585597  0.057316151  0.028808645
    18     v4  0.01047043 -0.074481895  0.020337989 -0.071395338
    19     v4 -0.24948516  0.002288344  0.035129254  0.329420595
    20     v4 -0.04729748  0.049531567  0.057316151  0.296019267
    21     v4 -0.01841352  0.043626164  0.005546724 -0.171599321
    22     v4 -0.19171725  0.049531567 -0.016640173 -0.071395338
    23     v4 -0.48055680  0.020004552 -0.142365923  0.596631217
    24     v4  0.01047043  0.008193747  0.220020063  0.062209973
    25     v4 -0.42278889  0.025909955 -0.149761556  0.028808645
    26     v4 -0.45167284  0.031815358 -0.134970291 -0.138197994
    27     v4 -0.30725307  0.049531567  0.042524886  0.095611301
    28     v4  0.24154207 -0.039049477  0.072107416 -0.104796666
    29     v4  1.45466817 -0.003617059  0.064711783  0.296019267
    30     v4 -0.01841352  0.002288344  0.020337989  0.028808645
    31     G8  0.38596185  0.084963985  0.049920519 -0.037994010
    32     G8  0.15489021 -0.080387298  0.020337989 -0.338605960
    33     G8 -0.04729748  0.067247776  0.138668107  0.129012629
    34     G8  0.27042603  0.031815358  0.049920519  0.195815284
    35     G8 -0.07618143  0.037720761  0.020337989 -0.037994010
    36     G8 -0.10506539  0.025909955 -0.083200864  0.396223251
    37     G8 -0.01841352  0.126301805 -0.024035805  0.362821923
    38     G8  0.01047043  0.031815358 -0.016640173 -0.138197994
    39     G8  0.06823834  0.037720761 -0.038827070  0.262617940
    40     G8 -0.16283329 -0.050860283 -0.038827070 -0.405408616
    41     G8 -0.01841352 -0.039049477  0.005546724 -0.205000649
    42     G8 -0.39390493 -0.003617059 -0.090596497  0.129012629
    43     G8 -0.04729748  0.008193747 -0.009244540  0.195815284
    44     G8  0.01047043 -0.039049477 -0.016640173 -0.205000649
    45     G8  0.01047043 -0.003617059 -0.075805232 -0.004592683
    46     G8  0.06823834  0.008193747 -0.090596497 -0.205000649
    47     G8 -0.04729748  0.014099150  0.012942357 -0.071395338
    48     G8 -0.22060120 -0.015427865 -0.075805232 -0.171599321
    49     G8 -0.16283329  0.020004552 -0.061013967 -0.104796666
    50     G8 -0.07618143  0.031815358 -0.038827070 -0.138197994
    51     G8 -0.22060120  0.020004552 -0.112783394 -0.104796666
    52     G8 -0.19171725 -0.033144074 -0.068409599 -0.071395338
    53     G8 -0.16283329 -0.039049477 -0.090596497 -0.104796666
    54     G8 -0.22060120 -0.009522462 -0.053618335 -0.037994010
    55     G8 -0.13394934 -0.003617059 -0.075805232 -0.004592683
    56     G8 -0.27836911 -0.044954880 -0.090596497 -0.238401977
    57     G8 -0.04729748 -0.050860283  0.064711783  0.028808645
    58     G8  0.01047043 -0.044954880  0.012942357 -0.305204632
    59     G8  0.12600625 -0.068576492  0.042524886 -0.305204632
    60     G8  0.06823834 -0.033144074 -0.061013967 -0.271803305
    61     G8  0.06823834 -0.027238671 -0.061013967 -0.037994010
    62     G8  0.32819394 -0.068576492  0.064711783 -0.372007288
    63     G8  0.32819394  0.014099150  0.175646269  0.095611301
    64     G8 -0.27836911  0.002288344 -0.068409599  0.195815284
    65     G8  0.18377416  0.025909955  0.027733621  0.162413956
    66     G8  0.55926557 -0.009522462  0.042524886  0.229216612
    67     G8 -0.19171725 -0.009522462 -0.038827070  0.229216612
    68     G8 -0.19171725  0.025909955 -0.009244540  0.396223251
    69     G8  0.01047043  0.155828820  0.027733621  0.630032545
    70     G8 -0.19171725  0.002288344 -0.031431438  0.463025906
    71     G8 -0.01841352 -0.044954880 -0.046222702  0.496427234
    72     G8 -0.07618143 -0.015427865 -0.031431438  0.062209973
    73     G8 -0.13394934  0.008193747 -0.068409599 -0.071395338
    74     G8 -0.39390493  0.037720761 -0.120179026  0.229216612
    75     G8 -0.04729748  0.008193747  0.035129254 -0.071395338
    76     G8 -0.27836911 -0.015427865 -0.061013967 -0.071395338
    77     G8  0.70368535 -0.056765686  0.397515240 -0.205000649
    78     G8  0.29930998  0.079058582  0.138668107  0.229216612
    79     G8 -0.13394934 -0.056765686  0.020337989 -0.305204632
    80     G8  0.21265812  0.025909955  0.035129254  0.396223251
       Family    Fighting Not.Fighting        Resting  Not.Resting
    1      v4 -0.67708172 -0.097624192  0.01081204879 -0.770462870
    2      v4 -0.58224128 -0.160103675 -0.03398160805  0.773856776
    3      v4 -0.11436177 -0.092996082  0.05710879700 -2.593072768
    4      v4 -0.34830152 -0.234153433 -0.04063432116 -2.837675606
    5      v4 -0.84568695 -0.136963126 -0.13084281035 -1.680828329
    6      v4 -0.32933343 -0.157789620 -0.02997847693 -0.947623773
    7      v4  0.35984044 -0.157789620  0.12732080268 -0.947623773
    8      v4 -0.32511830 -0.023574435 -0.10281705810 -2.607366431
    9      v4  1.51478626  0.001880170  0.08155320398 -0.637055341
    10     v4  0.11114773 -0.224897213 -0.17932134171 -1.818396455
    11     v4  0.27975296 -0.109194467 -0.14338902206  2.170944974
    12     v4 -0.89626852 -0.069855533 -0.02058415581 -0.658126752
    13     v4  0.12379312 -0.123078796 -0.11528274705 -0.808243774
    14     v4  0.66965255 -0.111508522 -0.11764091337  2.377766908
    15     v4  1.56536783 -0.143905291  0.04389156236  2.111220276
    16     v4  0.56427428 -0.099938247  0.01399844913 -0.322326312
    17     v4 -0.71291033 -0.118450687 -0.05755560242  2.218858946
    18     v4 -0.75927677  1.519900201  0.04711630687  3.920878638
    19     v4 -0.75295407  0.177748344  0.01584280360 -0.304945754
    20     v4 -1.00164679  0.108326696  0.09348590900  1.038591535
    21     v4 -1.03958296  0.652129604  0.09677967302  1.752268128
    22     v4  0.82139726  0.638245274  0.02053612974  0.907465624
    23     v4 -1.07541157 -0.072169588 -0.03608286844  1.137774798
    24     v4 -1.03115270  0.087500202  0.07805238146 -3.663486997
    25     v4 -0.98900139 -0.180930170 -0.00009686695  2.350924346
    26     v4 -1.06908888 -0.146219346 -0.02285413055  0.067293462
    27     v4 -1.20186549 -0.049029039 -0.00424187149 -1.898454393
    28     v4  0.58324237 -0.125392851  0.01446241356 -2.497647463
    29     v4 -0.97003330 -0.134649071  0.03187450017 -4.471716512
    30     v4  0.22917139 -0.060599313  0.11323315542 -1.465081244
    31     G8  0.41042201 -0.086053918 -0.01171898422 -0.232806371
    32     G8 -1.11545531 -0.197128554 -0.06499053655 -3.043893581
    33     G8 -0.19023412 -0.083739863 -0.07758659568 -2.323908986
    34     G8  0.25446217 -0.092996082 -0.07399758157  1.437404886
    35     G8 -0.05324237  0.844196163 -0.11503350996  1.079056696
    36     G8  0.09007207  0.055103433  0.02167111711  1.110865131
    37     G8  1.21129685  1.971140911  0.01904454162  1.404724068
    38     G8  0.62539368 -0.111508522  0.05768779393 -1.706664294
    39     G8  1.32932051 -0.224897213  0.05555202379  0.736746935
    40     G8  0.40199175 -0.187872334 -0.01031175326 -0.005516985
    41     G8  0.44625062 -0.160103675 -0.00458313459  1.727170333
    42     G8  0.60221046 -0.194814499  0.17430774591  1.685228831
    43     G8  0.33665722 -0.053657149  0.00481502094  1.836016918
    44     G8 -0.63493041 -0.206384774 -0.00928412956  0.466173920
    45     G8 -0.28296700  0.108326696  0.09047589183  1.697173771
    46     G8 -0.32722587 -0.164731785  0.08917985896  1.057314221
    47     G8 -0.11646933  0.187004564 -0.05671203072  0.933704227
    48     G8 -0.10171637  0.025020719 -0.05333390954  0.482480775
    49     G8  0.13643851  0.057417488  0.08541446168  0.680713089
    50     G8 -0.57802615  0.434608441  0.10140397965  0.090780703
    51     G8  0.05002833  0.057417488 -0.02509342995  0.680713089
    52     G8 -0.16072820  0.073615872 -0.03698779080 -0.982921741
    53     G8 -0.29139726 -0.035144709  0.04609635201 -2.281900378
    54     G8  0.13222338 -0.051343094  0.06524159499  0.972089090
    55     G8 -0.41152848 -0.134649071  0.08459773090  0.027767791
    56     G8  0.68229794 -0.185558279 -0.03239032508 -0.162881500
    57     G8 -0.24292325  0.013450444 -0.03208740616 -0.530221948
    58     G8 -0.11646933 -0.134649071  0.06264952925 -0.385741863
    59     G8 -0.21341734 -0.215640993  0.05241547086 -0.972251823
    60     G8 -0.24292325 -0.185558279 -0.03437271856  0.002267358
    61     G8 -0.24292325 -0.005061995 -0.03437271856 -1.134447998
    62     G8  0.09007207 -0.238781543 -0.06747523863  0.626424009
    63     G8 -0.34197883 -0.099938247 -0.01270059491 -0.722750217
    64     G8 -0.30825778 -0.167045840  0.10014629095 -0.382722075
    65     G8 -0.08696342 -0.208698829 -0.02872845706 -0.356550578
    66     G8 -0.81196590  0.048161268 -0.00950652573 -1.851614124
    67     G8  0.49683219  0.048161268  0.04867308008 -1.851614124
    68     G8 -0.13754498 -0.037458764  0.02486518629  1.731465143
    69     G8 -0.48318570  0.161549960 -0.05951115497  0.254319006
    70     G8  0.39988418  0.031962884 -0.02353665674  2.043778341
    71     G8  0.90148474 -0.102252302 -0.01967923345 -0.289913920
    72     G8  0.28396809 -0.123078796 -0.10148651548  1.386940871
    73     G8  1.05322945 -0.139277181 -0.00480936518  0.054207713
    74     G8  1.24923303 -0.208698829 -0.00098261723  0.594212936
    75     G8  0.47154141 -0.118450687 -0.13970798195  1.551821303
    76     G8  1.27873894 -0.072169588 -0.00286148145  3.100704184
    77     G8  0.05002833 -0.044400929 -0.05492902692  0.327263666
    78     G8  1.54218461 -0.030516599  0.10732815358 -1.055195336
    79     G8  0.74763247 -0.132335016  0.11660744219 -1.134447998
    80     G8  0.11747042 -0.037458764 -0.02016620439  1.730726972
       Family    Fighting      Hunting Not.Hunting     Grooming
    1      v4 -0.67708172  0.114961983   0.2644238  0.105443109
    2      v4 -0.58224128  0.556326739  -1.9467488 -0.249016133
    3      v4 -0.11436177  0.326951992   2.1597867 -0.563247851
    4      v4 -0.34830152  0.795734469   2.1698228 -0.611969290
    5      v4 -0.84568695  0.770046573   0.2554708 -0.230476117
    6      v4 -0.32933343  0.736574466   0.1225477 -0.270401826
    7      v4  0.35984044  0.215724268   0.1225477  1.057451389
    8      v4 -0.32511830 -0.200731013   0.2593696 -0.260830004
    9      v4  1.51478626 -2.160535836   0.8687508  1.030589923
    10     v4  0.11114773  0.660462182   1.7955299 -0.809959417
    11     v4  0.27975296 -0.293709087  -0.8377330 -0.292132450
    12     v4 -0.89626852  0.565754284   1.3339454 -0.573854465
    13     v4  0.12379312 -0.499644710  -0.5100101 -0.372285683
    14     v4  0.66965255  0.080624964  -2.6852985 -0.470590886
    15     v4  1.56536783 -4.076143639  -0.8432925  1.657328707
    16     v4  0.56427428 -0.127040484  -0.8662526 -0.161145079
    17     v4 -0.71291033  0.661240603  -2.1990933 -0.381900622
    18     v4 -0.75927677  0.294950237  -3.5062302 -0.121909231
    19     v4 -0.75295407  0.548369546  -1.3326746 -0.338568723
    20     v4 -1.00164679  0.137622686  -1.7580862 -0.312742050
    21     v4 -1.03958296  0.019302681  -2.2730277  0.708985315
    22     v4  0.82139726 -0.043057497  -3.1829838 -0.378408200
    23     v4 -1.07541157  0.351515502  -0.3762928 -0.304161903
    24     v4 -1.03115270 -0.007163636   1.3605877 -0.431053223
    25     v4 -0.98900139  0.253780410  -1.1388134 -0.554883286
    26     v4 -1.06908888  0.700680605   0.6629041  0.113074697
    27     v4 -1.20186549  0.340704098   0.9979915 -0.693545361
    28     v4  0.58324237 -1.727041782   1.5589254  0.180163686
    29     v4 -0.97003330  0.209410408   1.7613786 -0.258156792
    30     v4  0.22917139 -2.441026901   1.3929340  0.276959818
    31     G8  0.41042201  0.383257784  -0.5374467  0.165978418
    32     G8 -1.11545531 -1.098682982   2.9654839  0.148947473
    33     G8 -0.19023412  0.873144122   2.5120581 -0.846910101
    34     G8  0.25446217  0.968889915  -0.4130434 -0.938661624
    35     G8 -0.05324237  0.936455703  -2.5993065 -0.949914982
    36     G8  0.09007207 -0.467815937  -1.0766479  1.474170593
    37     G8  1.21129685 -1.239490708  -4.1335895  1.357023559
    38     G8  0.62539368  0.177235670   2.4989896  1.393241265
    39     G8  1.32932051 -4.736158229  -0.5718146  2.467225606
    40     G8  0.40199175  0.342693397   0.5675981  0.648320657
    41     G8  0.44625062  0.488950070  -1.6998195  0.709588943
    42     G8  0.60221046 -0.415575233  -1.4313741  0.728473890
    43     G8  0.33665722  0.353937257  -2.2985148  0.379706002
    44     G8 -0.63493041  0.262083568   0.2245685 -0.367629121
    45     G8 -0.28296700  0.574316915  -1.0020637  0.280710938
    46     G8 -0.32722587  0.323665326  -1.1559252  0.119455912
    47     G8 -0.11646933  0.786566398   0.1746772 -0.858206576
    48     G8 -0.10171637  0.718065343  -0.2673407 -0.552555005
    49     G8  0.13643851  0.584868846  -0.1203383 -0.335378116
    50     G8 -0.57802615 -0.053955393   0.6359729  0.057885811
    51     G8  0.05002833  0.738563765  -0.1203383 -0.188308359
    52     G8 -0.16072820  0.778263240   2.1906890 -0.545138998
    53     G8 -0.29139726  0.751018502   1.6039070  0.198100074
    54     G8  0.13222338  0.297804447  -0.5217068 -0.514310832
    55     G8 -0.41152848  0.102161281   0.3866610 -0.036323341
    56     G8  0.68229794  0.371667959   1.6179863 -0.176365139
    57     G8 -0.24292325  0.631574111   1.4206594 -0.269668849
    58     G8 -0.11646933 -0.004568899   1.6827511  0.003731717
    59     G8 -0.21341734  0.214080935   1.0590019  0.036586351
    60     G8 -0.24292325  0.796339908   1.2727184 -0.615289246
    61     G8 -0.24292325  0.796339908   2.6745838 -0.615289246
    62     G8  0.09007207 -0.396720145   0.2644238  0.290800156
    63     G8 -0.34197883  0.441985331   1.4545220 -0.520648930
    64     G8 -0.30825778 -2.489721464   1.3587105  1.711267220
    65     G8 -0.08696342  0.407907785   0.8136610 -0.273333736
    66     G8 -0.81196590  0.554423932   1.3666527 -0.594420949
    67     G8  0.49683219  0.697912886   1.3666527 -0.446661330
    68     G8 -0.13754498  0.491198842  -1.3307974 -0.333825929
    69     G8 -0.48318570  0.604848320  -0.1305910 -0.601492025
    70     G8  0.39988418  0.773938679  -0.5078441 -0.712559657
    71     G8  0.90148474  0.734412186  -0.1166561 -0.548803885
    72     G8  0.28396809  1.145505011  -1.3062489 -0.921846260
    73     G8  1.05322945  0.616784110   0.9039851 -0.165629176
    74     G8  1.24923303  0.329287256   0.3647117  0.111867440
    75     G8  0.47154141 -0.016764163  -1.1586689 -0.476713403
    76     G8  1.27873894  0.007799347  -3.0386529  0.215087903
    77     G8  0.05002833  0.209496900  -1.5080522  0.324560232
    78     G8  1.54218461 -5.031179821   1.6811626  2.366893936
    79     G8  0.74763247 -0.325105405   1.6851337  1.351590903
    80     G8  0.11747042 -0.756350687  -1.3315194  0.375911766

       Family Not.Grooming
    1      v4  0.019502286
    2      v4 -0.290451956
    3      v4  0.359948884
    4      v4  0.557840914
    5      v4  0.117453376
    6      v4  0.126645924
    7      v4  0.126645924
    8      v4  0.196486873
    9      v4  0.152780228
    10     v4  0.354469789
    11     v4 -0.261430968
    12     v4  0.176448238
    13     v4 -0.007374708
    14     v4 -0.557848621
    15     v4 -0.213674557
    16     v4 -0.005819262
    17     v4 -0.470070992
    18     v4 -0.786078864
    19     v4  0.006063789
    20     v4 -0.271842650
    21     v4 -0.349418792
    22     v4 -0.338096262
    23     v4 -0.165119403
    24     v4  0.346566439
    25     v4 -0.344191931
    26     v4  0.074321265
    27     v4  0.179825379
    28     v4  0.278407054
    29     v4  0.593125727
    30     v4  0.199177375
    31     G8 -0.058900625
    32     G8  0.633875622
    33     G8  0.428150308
    34     G8 -0.206023441
    35     G8 -0.436958199
    36     G8 -0.291839246
    37     G8 -0.907641911
    38     G8  0.448567295
    39     G8 -0.127186127
    40     G8  0.024715134
    41     G8 -0.416345030
    42     G8 -0.330697382
    43     G8 -0.469720666
    44     G8 -0.047494017
    45     G8 -0.301732446
    46     G8 -0.138901021
    47     G8  0.098101379
    48     G8 -0.002063769
    49     G8 -0.028324190
    50     G8  0.071630763
    51     G8 -0.028324190
    52     G8  0.295110588
    53     G8  0.347112947
    54     G8 -0.083577573
    55     G8 -0.036886152
    56     G8  0.189045953
    57     G8  0.467596992
    58     G8  0.303378276
    59     G8  0.218879697
    60     G8  0.092005711
    61     G8  0.270111340
    62     G8 -0.012909856
    63     G8  0.262292068
    64     G8  0.107125772
    65     G8  0.123422927
    66     G8  0.299426602
    67     G8  0.299426602
    68     G8 -0.326871824
    69     G8 -0.022088391
    70     G8 -0.428508341
    71     G8 -0.014675497
    72     G8 -0.114462294
    73     G8  0.087227267
    74     G8 -0.031519161
    75     G8 -0.159318008
    76     G8 -0.397875854
    77     G8  0.101520559
    78     G8  0.244481505
    79     G8  0.529968994
    80     G8 -0.326619590

Answer 1

首先，关于将数据子集化为训练和测试子集的最重要问题之一是在子集化之前，数据必须随机化，否则您将在训练和测试数据子集中对类别进行不等分。

以下代码的一些注释。为了简化模型拟合方法，我使用了caret包。

library(pROC)
library(MASS)
library(caret)

set.seed(1234)

mydat <- read.table("~/Desktop/family.txt", header = TRUE, stringsAsFactors= FALSE)
mydat$Family <- factor(mydat$Family, levels = c("v4", "G8"))

# Randomly permute the data before subsetting
mydat_idx <- sample(1:nrow(mydat), replace = FALSE)
mydat <- mydat[mydat_idx, ]

mydat_resampled_idx <- createDataPartition(mydat_idx, times = 1, p = 0.7, list = FALSE)
mydat_resampled <- mydat[mydat_resampled_idx, ] # Training portion of the data

线性判别分析

lda_mod <-train(x = mydat_resampled[, 2:9], y = as.factor(mydat_resampled[, 1]),
  method = "lda", trControl = trainControl(method = "cv", classProbs = TRUE))

# Generate model predictions 
lda_pred <- predict(lda_mod, newdata = mydat[ , 2:9], type = "prob")

# Store the predictions with the data set
mydat['lda_pred'] <- lda_pred["G8"] # Here we only want the probability associated
                                    # with the class (Y = 1), or in this case, G8

朴素贝叶斯

nb_tune <- data.frame(usekernel =TRUE, fL = 0)
nb_mod <- train(x = mydat_resampled[, 2:9], y = as.factor(mydat_resampled[, 1]), 
    method = "nb", trControl = trainControl(method = "cv", classProbs = TRUE), tuneGrid = nb_tune)

# Model predictions
nb_pred <- predict(nb_mod, newdata = mydat[ , 2:9], type = "prob")
mydat['nb_pred'] <- nb_pred["G8"]

分类树

ct_mod <- train(x = mydat_resampled[, 2:9], y = as.factor(mydat_resampled[, 1]), 
method = "rpart", trControl = trainControl(method = "cv", classProbs = TRUE))
ct_pred <- predict(ct_mod, newdata = mydat[ , 2:9], type = "prob")
mydat['ct_pred'] <- ct_pred["G8"]

数据训练和测试部分的ROC曲线

编辑：更改了AUC曲线的计算和图表以使用pROC包

mydat$binary_response <- as.numeric(mydat$Family) - 1 # convert factor to 0, 1 with G8  = 1

lda_train_roc <- roc(binary_response ~ lda_pred, data = mydat[mydat_resampled_idx, ], ci = TRUE)
nb_train_roc <- roc(binary_response ~ nb_pred, data =  mydat[mydat_resampled_idx, ], ci = TRUE)
ct_train_roc <- roc(binary_response ~ ct_pred, data =  mydat[mydat_resampled_idx, ], ci = TRUE)

lda_test_roc <- roc(binary_response ~ lda_pred, data =  mydat[-mydat_resampled_idx, ], ci = TRUE)
nb_test_roc <- roc(binary_response ~ nb_pred, data =  mydat[-mydat_resampled_idx, ], ci = TRUE)
ct_test_roc <- roc(binary_response ~ ct_pred, data =  mydat[-mydat_resampled_idx, ], ci = TRUE)


par(mfrow = c(2, 1))
plot(lda_train_roc, las = 1, main = "Training data")
plot(nb_train_roc, add = TRUE, col = "red")
plot(ct_train_roc, add = TRUE, col = "blue")
legend(0.4, 0.4, legend = c("lda", "nb", "ct"), lty = c(1,1,1), col = c("black", "red", "blue"))

plot(lda_test_roc, las = 1, main = "Testing data")
plot(nb_test_roc, add = TRUE, col = "red")
plot(ct_test_roc, add = TRUE, col = "blue")
legend(0.4, 0.4, legend = c("lda", "nb", "ct"), lty = c(1,1,1), col =     c("black", "red", "blue"))
par(mfrow = c(1, 1))

# AUC with 95% CL
lda_train_roc$ci[c(2, 1, 3)] #  0.8353741 0.7235472 0.9472011

nb_train_roc$ci[c(2, 1, 3)] # 0.9714286 [0.9303684, 1.0000000]

ct_train_roc$ci[c(2, 1, 3)] # 0.7619048 [0.6524637, 0.8713458]
lda_test_roc$ci[c(2, 1, 3)] # 0.6148148 [0.3555396, 0.8740900]

nb_test_roc$ci[c(2, 1, 3)] # 0.7407407 [0.5345984, 0.9468831]
ct_test_roc$ci[c(2, 1, 3)] # 0.6000000 [0.4139795, 0.7860205]

在单个ROC图上绘制线性判别分析，分类树和朴素贝叶斯曲线

目标

问题

我提供了所有三种技术的编码，因此任何人都可以逐步评估我的逻辑

线性判别分析

构造混淆矩阵以预测类

情节判别分数

计算混淆矩阵的函数

更改比例以创建训练和测试集（70:30）

创建ROC曲线的函数

绘制ROC曲线

图1

分类树

生成测试和训练集70:30

以70％的训练集种植树木

使用测试和训练集（70:30）

为分类分组因子的二项分布创建二进制系统（0或1）

绘制ROC曲线

朴素贝叶斯

生成测试和训练集70:30

构建NB模型并对测试集进行预测

为分类因子

PLOT ROC CURVE - 这条曲线看起来很可疑

将所有ROC曲线绘制到单个图上

错误消息

曲线下面积

我不确定如何根据提供的LDA代码计算区域

制作传奇

此代码生成错误消息

名为LDA.scores的数据

1 个答案: