R：在循環中迭代隨機數

Question

我正在使用 R 編程語言。 在上一個問題（ R 語言：將循環的結果存儲到表中）中，我學習了如何為變量“i”的固定值迭代循環：

  #load libraries
    
        library(caret)
        library(rpart)
    
    #generate data
        
        a = rnorm(1000, 10, 10)
        
        b = rnorm(1000, 10, 5)
        
        c = rnorm(1000, 5, 10)
        
        group <- sample( LETTERS[1:2], 1000, replace=TRUE, prob=c(0.5,0.5) )
        group_1 <- 1:1000
        
        #put data into a frame
        d = data.frame(a,b,c, group, group_1)
        
        d$group = as.factor(d$group)

 #start the loop


e <- d

#here is the "i" variable

for (i in 400:405) {
  d <- e
  d$group_1 = as.integer(d$group_1 > i)
  d$group_1 = as.factor(d$group_1)
  
  trainIndex <- createDataPartition(d$group_1, p = .8,list = FALSE,times = 1)
  training = d[ trainIndex,]
  test  <- d[-trainIndex,]
  
  
  fitControl <- trainControl(## 10-fold CV
    method = "repeatedcv",
    number = 10,
    ## repeated ten times
    repeats = 10)
  
  TreeFit <- train(group_1 ~ ., data = training,
                   method = "rpart2",
                   trControl = fitControl)
  
  pred = predict(TreeFit, test, type = "prob")
  labels = as.factor(ifelse(pred[,2]>0.5, "1", "0"))
  con = confusionMatrix(labels, test$group_1)
  
  #update results into table
  row = i - 399
  final_table[row,1] = con$overall[1]
  final_table[row,2] = i
  
}

        #place results in table
        final_table = matrix(1, nrow = 6, ncol=2)

現在，我正在嘗試用隨機數列表替換“i”：（ (i in sample(100:400, 10))

但是，這會返回以下錯誤（注意：我將final_table = matrix(1, nrow = 6, ncol=2)更改為final_table = matrix(1, nrow = 100, ncol=2) ）：

Error in na.fail.default(list(group_1 = c(NA_integer_, NA_integer_, NA_integer_,  : 
  missing values in object

有人可以告訴我我做錯了什么嗎？ 有沒有更簡單的方法可以將循環中的所有結果存儲到矩陣（或表）中，而無需明確定義所需的行數？ 計算機可以自動為“i”的每個新值添加一個新行嗎？

謝謝

Answer 1

要使用隨機數，您可以將代碼更新為：

a = rnorm(1000, 10, 10)
b = rnorm(1000, 10, 5)
c = rnorm(1000, 5, 10)
group <- sample( LETTERS[1:2], 1000, replace=TRUE, prob=c(0.5,0.5) )
group_1 <- 1:1000
#put data into a frame
d = data.frame(a,b,c, group, group_1)
d$group = as.factor(d$group)

#start the loop
#place results in table
final_table = matrix(1, nrow = 10, ncol=2)

e <- d
#here is the "i" variable
vec <- sample(100:400, 10)

for (i in seq_along(vec)) {
  d <- e
  d$group_1 = as.integer(d$group_1 > vec[i])
  d$group_1 = as.factor(d$group_1)
  
  trainIndex <- createDataPartition(d$group_1, p = .8,list = FALSE,times = 1)
  training = d[ trainIndex,]
  test  <- d[-trainIndex,]
  
  
  fitControl <- trainControl(## 10-fold CV
    method = "repeatedcv",
    number = 10,
    ## repeated ten times
    repeats = 10)
  
  TreeFit <- train(group_1 ~ ., data = training,
                   method = "rpart2",
                   trControl = fitControl)
  
  pred = predict(TreeFit, test, type = "prob")
  labels = as.factor(ifelse(pred[,2]>0.5, "1", "0"))
  con = confusionMatrix(labels, test$group_1)
  
  #update results into table
  final_table[i,1] = con$overall[1]
  final_table[i,2] = vec[i]
  
}