数据框中的数字向量的字符值

Question

从数据框中，我获得了列的字符向量： 按日期，时间和group_by日期安排

fall_hc %>% arrange(a_dat,AZeit) %>% group_by(a_dat) %>%
        mutate(time_vec = str_c(snzeit,collapse= ",")) %>% 
        ungroup() %>% 
        filter(!is.na(time_vec))

此符号向量，例如：

x <- c("5, 31, 16, 64, 9, 10, 31") 

我需要在dataframe中的x中的数字向量： 5 31 16 64 9 10 31.
因为我想计算diff（x）：26 -15 48 -55 1 21.
并进一步处理这以计算否定差异的数量。

以下是一些数据：

tibble::tribble(
              ~a_dat,  ~AZeit, ~snzeit,
        "2019-01-02", "24180",      31,
        "2019-01-02", "24360",      27,
        "2019-01-02", "24480",      16,
        "2019-01-02", "24780",      64,
        "2019-01-02", "30420",       9,
        "2019-01-02", "30840",      10,
        "2019-01-02", "35280",      31,
        "2019-01-03", "24120",      40,
        "2019-01-03", "24120",      27,
        "2019-01-03", "24480",       6,
        "2019-01-03", "24480",       4,
        "2019-01-03", "24780",       9,
        "2019-01-03", "25380",      25,
        "2019-01-03", "26460",      33,
        "2019-01-04", "24000",       5,
        "2019-01-04", "24360",       2,
        "2019-01-04", "24900",       1,
        "2019-01-04", "27180",      29,
        "2019-01-04", "30600",       8,
        "2019-01-07", "24780",      25,
        "2019-01-07", "24840",       4,
        "2019-01-07", "28920",       3,
        "2019-01-07", "31620",      11,
        "2019-01-08", "24060",      46,
        "2019-01-08", "24480",       7,
        "2019-01-08", "25260",       4,
        "2019-01-08", "27900",       5,
        "2019-01-08", "29820",       5,
        "2019-01-08", "30060",      74,
        "2019-01-08", "33360",       5,
        "2019-01-08", "33600",      28,
        "2019-01-08", "34200",      15,
        "2019-01-08", "35520",      13,
        "2019-01-08", "36000",      19,
        "2019-01-08", "44100",      24
        )

它们已经对其进行分类，因此您可以删除％＆gt;％bepand（a_dat，azeit）。

为了澄清目的： 我需要知道如何对Snzeit进行分类，这是从切割到缝合线的时间。想确定从短到长时间分类的那些日子。

Answer 1

如果我正确理解了您的问题，您需要在第一名中创建该字符向量，您只需要列表柱子，然后在每个列表上应用diff并计算每个a_dat

library(dplyr)
library(tibble)


fall_hc <- tibble::tribble(
  ~a_dat,  ~AZeit, ~snzeit,
  "2019-01-02", "24180",      31,
  "2019-01-02", "24360",      27,
  "2019-01-02", "24480",      16,
  "2019-01-02", "24780",      64,
  "2019-01-02", "30420",       9,
  "2019-01-02", "30840",      10,
  "2019-01-02", "35280",      31,
  "2019-01-03", "24120",      40,
  "2019-01-03", "24120",      27,
  "2019-01-03", "24480",       6,
  "2019-01-03", "24480",       4,
  "2019-01-03", "24780",       9,
  "2019-01-03", "25380",      25,
  "2019-01-03", "26460",      33,
  "2019-01-04", "24000",       5,
  "2019-01-04", "24360",       2,
  "2019-01-04", "24900",       1,
  "2019-01-04", "27180",      29,
  "2019-01-04", "30600",       8,
  "2019-01-07", "24780",      25,
  "2019-01-07", "24840",       4,
  "2019-01-07", "28920",       3,
  "2019-01-07", "31620",      11,
  "2019-01-08", "24060",      46,
  "2019-01-08", "24480",       7,
  "2019-01-08", "25260",       4,
  "2019-01-08", "27900",       5,
  "2019-01-08", "29820",       5,
  "2019-01-08", "30060",      74,
  "2019-01-08", "33360",       5,
  "2019-01-08", "33600",      28,
  "2019-01-08", "34200",      15,
  "2019-01-08", "35520",      13,
  "2019-01-08", "36000",      19,
  "2019-01-08", "44100",      24
)


fall_hc %>%
    arrange(a_dat, AZeit) %>%
    group_by(a_dat) %>%
    summarise(
        time_vec = list(snzeit)
    ) %>%
    group_by(a_dat) %>%
    summarise(
        time_vec = diff(unlist(time_vec)) # caluculate diffs for each list
    ) %>%
    group_by(a_dat) %>%
    summarise(
        time_vec_neg = sum(time_vec < 0) # count number of negative values
    )

#> `summarise()` has grouped output by 'a_dat'. You can override using the
#> `.groups` argument.
#> # A tibble: 5 × 2
#>   a_dat      time_vec_neg
#>   <chr>             <int>
#> 1 2019-01-02            3
#> 2 2019-01-03            3
#> 3 2019-01-04            3
#> 4 2019-01-07            2
#> 5 2019-01-08            5

^{由 reprex软件包（v2.0.1）}

Answer 2

在 list 中将数字保留为 n数字：

mtcars %>% 
  group_by(cyl) %>% 
  summarise(x = list(mpg))
# # A tibble: 3 x 2
#         cyl x         
#      <dbl> <list>    
#    1     4 <dbl [11]>
#    2     6 <dbl [7]> 
#    3     8 <dbl [14]>

然后，我们可以在下面的数字列表中进行：

mtcars %>% 
  group_by(cyl) %>% 
  summarise(x = list(mpg)) %>% 
  group_by(cyl) %>% 
  summarise(xDiffSum = sum(diff(unlist(x))))
# # A tibble: 3 x 2
#      cyl xDiffSum
#   <dbl>    <dbl>
# 1     4    -1.40
# 2     6    -1.3 
# 3     8    -3.7