时间戳

首页 > 解决方案 > R：在循环中迭代随机数

r - R：在循环中迭代随机数

问题描述

我正在使用 R 编程语言。在上一个问题（R 语言：将循环的结果存储到表中）中，我学习了如何为变量“i”的固定值迭代循环：

  #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)

现在，我正在尝试用随机数列表替换“i”： (i in sample(100:400, 10))

但是，这会返回以下错误（注意：我改为final_table = matrix(1, nrow = 6, ncol=2)）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

有人可以告诉我我做错了什么吗？有没有更简单的方法可以将循环中的所有结果存储到矩阵（或表）中，而无需明确定义所需的行数？计算机可以自动为“i”的每个新值添加一个新行吗？

谢谢

标签： rloopsrandomiteration

解决方案

要使用随机数，您可以将代码更新为：

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]
  
}

推荐阅读