剪切R功能產生的水平的操縱

Question

我想對cut R函數產生的水平進行一些操作。 我想在我的MWE中擁有exp(Labs) 。

set.seed(12345)
Y <- rnorm(n = 50, mean = 500, sd = 1)
Y1 <-  cut(log(Y), 5)
Labs <- levels(Y1)
Labs
[1] "(6.21,6.212]"  "(6.212,6.213]" "(6.213,6.215]" "(6.215,6.217]" "(6.217,6.219]"

exp(cbind(lower = as.numeric( sub("\\((.+),.*", "\\1", Labs) ),
      upper = as.numeric( sub("[^,]*,([^]]*)\\]", "\\1", Labs) )))
        lower    upper

[1,] 497.7013 498.6976
[2,] 498.6976 499.1966
[3,] 499.1966 500.1960
[4,] 500.1960 501.1974
[5,] 501.1974 502.2008

題

我如何在這里獲得exp(Labs) ？

期望的輸出

"(497.7013, 498.6976]"  "(498.6976, 499.1966]" "(499.1966, 500.1960]" "(500.1960, 501.1974]"  "(501.1974, 502.2008]" 

編輯

基於@akrun的答案：

    Labs1 <- c("(-2.32,0.99]", "(0.99,4.28]", "(4.28,7.58]", "(7.58,10.9]", "(10.9,14.2]")

Labs1
    [1] "(-2.32,0.99]" "(0.99,4.28]"  "(4.28,7.58]"  "(7.58,10.9]"  "(10.9,14.2]"

    exp(cbind(lower = as.numeric( sub("\\((.+),.*", "\\1", Labs1) ),
              upper = as.numeric( sub("[^,]*,([^]]*)\\]", "\\1", Labs1) )))

            lower        upper
[1,] 9.827359e-02 2.691234e+00
[2,] 2.691234e+00 7.224044e+01
[3,] 7.224044e+01 1.958629e+03
[4,] 1.958629e+03 5.417636e+04
[5,] 5.417636e+04 1.468864e+06


    gsubfn('([0-9.]+)', ~round(exp(as.numeric(x)),4), Labs1)

[1] "(-10.1757,2.6912]"         "(2.6912,72.2404]"          "(72.2404,1958.629]"       
[4] "(1958.629,54176.3638]"     "(54176.3638,1468864.1897]"

    res1 <-  exp(as.data.frame(t(sapply(strsplit(Labs1, '[^0-9.]+'), 
                                       function(x) as.numeric(x[-1])))))
    sprintf('(%s]', do.call(paste, c(round(res1,4), sep=", ")))


[1] "(10.1757, 2.6912]"          "(2.6912, 72.2404]"          "(72.2404, 1958.629]"       
[4] "(1958.629, 54176.3638]"     "(54176.3638, 1468864.1897]"

Answer 1

一個緊湊的選擇是使用gsubfn 。 我們在pattern參數中將數字元素與點（ ([0-9.]+) ）匹配，並通過首先將匹配的對象轉換為'numeric'來替換匹配的對象，取exp和round 。

library(gsubfn)
gsubfn('([-0-9.]+)', ~round(exp(as.numeric(x)),4), Labs)
#[1] "(497.7013,498.6976]" "(498.6976,499.1966]" "(499.1966,500.196]" 
#[4] "(500.196,501.1974]"  "(501.1974,502.2008]"

注意：這取決於我們使用的模式。

---

否則將避免strsplit避免兩次調用sub另一種選擇。 我們split非數字元素。 輸出將是一個list因此我們可以使用lapply/sapply遍歷列表元素，轉換為numeric類，並創建具有兩列的“ data.frame”。

res <-  exp(as.data.frame(t(sapply(strsplit(Labs, '[^-0-9.]+'), 
              function(x) as.numeric(x[-1])))))

---

關於根據OP的代碼獲得預期的輸出。 我改變cbind到data.frame原代碼，以便do.call可以使用。

 res <-  exp(data.frame(lower = as.numeric( sub("\\((.+),.*", "\\1", Labs) ),
         upper = as.numeric( sub("[^,]*,([^]]*)\\]", "\\1", Labs) )))

我們paste 'res'（ do.call(paste0 ）的行元素，然后用sprintf或其他paste添加其他括號。

  sprintf('(%s]', do.call(paste, c(round(res,4), sep=", ")))
  #[1] "(497.7013, 498.6976]" "(498.6976, 499.1966]" "(499.1966, 500.196]" 
  #[4] "(500.196, 501.1974]"  "(501.1974, 502.2008]"

更新

使用“ Labs1”檢查輸出

 gsubfn('([-0-9.]+)', ~round(exp(as.numeric(x)),4), Labs1)
 #[1] "(0.0983,2.6912]"           "(2.6912,72.2404]"         
 #[3] "(72.2404,1958.629]"        "(1958.629,54176.3638]"    
 #[5] "(54176.3638,1468864.1897]"


 exp(as.data.frame(t(sapply(strsplit(Labs1, '[^-0-9.]+'), 
             function(x) as.numeric(x[-1])))))
 #           V1           V2
 #1 9.827359e-02 2.691234e+00
 #2 2.691234e+00 7.224044e+01
 #3 7.224044e+01 1.958629e+03
 #4 1.958629e+03 5.417636e+04
 #5 5.417636e+04 1.468864e+06