如何在具有各种移动窗口的连续区域中切碎字符串

Question

我有这样的数据

df<- structure(list(sname = structure(2:1, .Label = c("Carrot", "Melon"
), class = "factor"), sence = structure(1:2, .Label = c("RSNSNASSAVSTSCVSNRAMKGTTHYDTS", 
"TGMRHGGMVSVCMCVVDDNRRRHYNGAYDDHHRGGVCTS"), class = "factor")), class = "data.frame", row.names = c(NA, 
-2L))

让我们看一下第一行

Melon RSNSNASSAVSTSCVSNRAMKGTTHYDTS

我希望能够将字符串切入不同的窗口以及以不同的模式移动。 例如，假设在时间和 10 个窗口移动 1 个字母。 所以第一个输出将是这样的

RSNSNASSAV

所以这个是字母 1 ，2,3,4,5,6,7,8,9,10

第二个是向前移动 1 个字母，然后砍掉 10 个字母

SNSNASSAVS

所以这是字母 2,3,4,5,6,7,8,9,10,11它一直持续到最后。

请求的输出如下所示

output<- structure(list(position = structure(c(33L, 1L, 12L, 23L, 26L, 
27L, 28L, 29L, 30L, 31L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 
11L, 13L, 32L, 1L, 12L, 23L, 26L, 27L, 28L, 29L, 30L, 31L, 2L, 
3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 13L, 14L, 15L, 16L, 17L, 
18L, 19L, 20L, 21L, 22L, 24L, 25L), .Label = c("1,2,3,4,5,6,7,8,9,10", 
"10,11,12,13,14,15,16,17,18,19", "11,12,13,14,15,16,17,18,20", 
"12,13,14,15,16,17,18,19,20,21", "13,14,15,16,17,18,19,20,21,22", 
"14,15,16,17,18,19,20,21,22,23", "15,16,17,18,19,20,21,22,23,24", 
"16,17,18,19,20,21,22,23,24,25", "17,18,19,20,21,22,23,24,25,26", 
"18,19,20,21,22,23,24,25,26,27", "19,20,21,22,23,24,25,26,27,28", 
"2,3,4,5,6,7,8,9,10,11", "20,21,22,23,24,25,26,27,28,29", "21,22,23,24,25,26,27,28,29,30", 
"22,23,24,25,26,27,28,29,30,31", "23,24,25,26,27,28,29,30,31,32", 
"24,25,26,27,28,29,30,31,32,33", "25,26,27,28,29,30,31,32,33,34", 
"26,27,28,29,30,31,32,33,34,35", "27,28,29,30,31,32,33,34,35,36", 
"28,29,30,31,32,33,34,35,36,37", "29,30,31,32,33,34,35,36,37,38", 
"3,4,5,6,7,8,9,10,11,12", "30,31,32,33,34,35,36,37,38,39", "31,32,33,34,35,36,37,38,39,40", 
"4,5,6,7,8,9,10,11,12,13", "5,6,7,8,9,10,11,12,13,14", "6,7,8,9,10,11,12,14,15", 
"7,8,9,10,11,12,13,14,15,16", "8,9,10,11,12,13,14,15,16,17", 
"9,10,11,12,13,14,15,16,17,18", "Carrot", "Melon"), class = "factor"), 
    name = structure(c(20L, 32L, 37L, 26L, 35L, 35L, 2L, 38L, 
    33L, 3L, 46L, 39L, 42L, 34L, 7L, 45L, 36L, 24L, 27L, 1L, 
    21L, 5L, 41L, 15L, 22L, 28L, 17L, 14L, 16L, 23L, 47L, 40L, 
    43L, 6L, 19L, 8L, 19L, 8L, 48L, 44L, 10L, 12L, 25L, 31L, 
    30L, 29L, 18L, 50L, 13L, 4L, 49L, 9L, 11L), .Label = c("AMKGTTHYDT", 
    "ASSAVSTSCV", "AVSTSCVSNR", "AYDDHHRGGV", "Carrot", "CMCVVDDNRR", 
    "CVSNRAMKGT", "CVVDDNRRRH", "DDHHRGGVCT", "DDNRRRHYNG", "DHHRGGVCTS", 
    "DNRRRHYNGA", "GAYDDHHRGG", "GGMVSVCMCV", "GMRHGGMVSV", "GMVSVCMCVV", 
    "HGGMVSVCMC", "HYNGAYDDHH", "MCVVDDNRRR", "Melon", "MKGTTHYDTS", 
    "MRHGGMVSVC", "MVSVCMCVVD", "NRAMKGTTHY", "NRRRHYNGAY", "NSNASSAVST", 
    "RAMKGTTHYD", "RHGGMVSVCM", "RHYNGAYDDH", "RRHYNGAYDD", "RRRHYNGAYD", 
    "RSNSNASSAV", "SAVSTSCVSN", "SCVSNRAMKG", "SNASSAVSTS", "SNRAMKGTTH", 
    "SNSNASSAVS", "SSAVSTSCVS", "STSCVSNRAM", "SVCMCVVDDN", "TGMRHGGMVS", 
    "TSCVSNRAMK", "VCMCVVDDNR", "VDDNRRRHYN", "VSNRAMKGTT", "VSTSCVSNRA", 
    "VSVCMCVVDD", "VVDDNRRRHY", "YDDHHRGGVC", "YNGAYDDHHR"), class = "factor")), class = "data.frame", row.names = c(NA, 
-53L))

拆分为 2

RSNSNASSAV
NSNASSAVST
NASSAVSTSC
SSAVSTSCVS
AVSTSCVSNR
STSCVSNRAM
SCVSNRAMKG
VSNRAMKGTT
NRAMKGTTHY
AMKGTTHYDT
KGTTHYDTS

Answer 1

我们将factor列转换为character，然后transmute通过循环map行来创建"位置"，"名称"的tibble，根据分割宽度"n"和"sence"的字符数(nchar(创建substring s，将"sname"连接为first元素并unnest list输出以创建两列数据集

library(tidyverse)
f1 <- function(dat, n, mv = 1) {
 dat %>% 
    mutate_all(as.character) %>%
    transmute(out = map2(sence, sname, ~ {
        i1 <- seq_len(nchar(.x) - (n -1))
        i11 <- seq(i1[1], i1[length(i1)], by = mv)
        i2 <- n:nchar(.x) 
        i22 <- seq(i2[1], i2[length(i2)], by = mv) 
        tibble(position = c(.y, map2_chr(i11, i22,  ~ 
                        str_c(seq(.x, .y), collapse=","))),
                name = c(.y, substring(.x, i11, i22)))
               })) %>%
                unnest
   }

-测试- 移动窗口 - 1

f1(df, n = 10, mv = 1)
#                        position       name
#1                          Melon      Melon
#2           1,2,3,4,5,6,7,8,9,10 RSNSNASSAV
#3          2,3,4,5,6,7,8,9,10,11 SNSNASSAVS
#4         3,4,5,6,7,8,9,10,11,12 NSNASSAVST
#5        4,5,6,7,8,9,10,11,12,13 SNASSAVSTS
#6       5,6,7,8,9,10,11,12,13,14 NASSAVSTSC
#7      6,7,8,9,10,11,12,13,14,15 ASSAVSTSCV
#8     7,8,9,10,11,12,13,14,15,16 SSAVSTSCVS
#9    8,9,10,11,12,13,14,15,16,17 SAVSTSCVSN
#10  9,10,11,12,13,14,15,16,17,18 AVSTSCVSNR
#11 10,11,12,13,14,15,16,17,18,19 VSTSCVSNRA
#12 11,12,13,14,15,16,17,18,19,20 STSCVSNRAM
#13 12,13,14,15,16,17,18,19,20,21 TSCVSNRAMK
#14 13,14,15,16,17,18,19,20,21,22 SCVSNRAMKG
#15 14,15,16,17,18,19,20,21,22,23 CVSNRAMKGT
#16 15,16,17,18,19,20,21,22,23,24 VSNRAMKGTT
#17 16,17,18,19,20,21,22,23,24,25 SNRAMKGTTH
#18 17,18,19,20,21,22,23,24,25,26 NRAMKGTTHY
#19 18,19,20,21,22,23,24,25,26,27 RAMKGTTHYD
#20 19,20,21,22,23,24,25,26,27,28 AMKGTTHYDT
#21 20,21,22,23,24,25,26,27,28,29 MKGTTHYDTS
#22                        Carrot     Carrot
#23          1,2,3,4,5,6,7,8,9,10 TGMRHGGMVS
#24         2,3,4,5,6,7,8,9,10,11 GMRHGGMVSV
#25        3,4,5,6,7,8,9,10,11,12 MRHGGMVSVC
#26       4,5,6,7,8,9,10,11,12,13 RHGGMVSVCM
#27      5,6,7,8,9,10,11,12,13,14 HGGMVSVCMC
#28     6,7,8,9,10,11,12,13,14,15 GGMVSVCMCV
#29    7,8,9,10,11,12,13,14,15,16 GMVSVCMCVV
#30   8,9,10,11,12,13,14,15,16,17 MVSVCMCVVD
#31  9,10,11,12,13,14,15,16,17,18 VSVCMCVVDD
#32 10,11,12,13,14,15,16,17,18,19 SVCMCVVDDN
#33 11,12,13,14,15,16,17,18,19,20 VCMCVVDDNR
#34 12,13,14,15,16,17,18,19,20,21 CMCVVDDNRR
#35 13,14,15,16,17,18,19,20,21,22 MCVVDDNRRR
#36 14,15,16,17,18,19,20,21,22,23 CVVDDNRRRH
#37 15,16,17,18,19,20,21,22,23,24 VVDDNRRRHY
#38 16,17,18,19,20,21,22,23,24,25 VDDNRRRHYN
#39 17,18,19,20,21,22,23,24,25,26 DDNRRRHYNG
#40 18,19,20,21,22,23,24,25,26,27 DNRRRHYNGA
#41 19,20,21,22,23,24,25,26,27,28 NRRRHYNGAY
#42 20,21,22,23,24,25,26,27,28,29 RRRHYNGAYD
#43 21,22,23,24,25,26,27,28,29,30 RRHYNGAYDD
#44 22,23,24,25,26,27,28,29,30,31 RHYNGAYDDH
#45 23,24,25,26,27,28,29,30,31,32 HYNGAYDDHH
#46 24,25,26,27,28,29,30,31,32,33 YNGAYDDHHR
#47 25,26,27,28,29,30,31,32,33,34 NGAYDDHHRG
#48 26,27,28,29,30,31,32,33,34,35 GAYDDHHRGG
#49 27,28,29,30,31,32,33,34,35,36 AYDDHHRGGV
#50 28,29,30,31,32,33,34,35,36,37 YDDHHRGGVC
#51 29,30,31,32,33,34,35,36,37,38 DDHHRGGVCT
#52 30,31,32,33,34,35,36,37,38,39 DHHRGGVCTS

-移动窗口 - 2

f1(df, n = 10, mv = 2) %>%
            head
#                      position       name
#1                        Melon      Melon
#2         1,2,3,4,5,6,7,8,9,10 RSNSNASSAV
#3       3,4,5,6,7,8,9,10,11,12 NSNASSAVST
#4     5,6,7,8,9,10,11,12,13,14 NASSAVSTSC
#5   7,8,9,10,11,12,13,14,15,16 SSAVSTSCVS
#6 9,10,11,12,13,14,15,16,17,18 AVSTSCVSNR

-移动窗口 - 3

f1(df, n = 10, mv = 3) %>% 
         head
#                       position       name
#1                         Melon      Melon
#2          1,2,3,4,5,6,7,8,9,10 RSNSNASSAV
#3       4,5,6,7,8,9,10,11,12,13 SNASSAVSTS
#4    7,8,9,10,11,12,13,14,15,16 SSAVSTSCVS
#5 10,11,12,13,14,15,16,17,18,19 VSTSCVSNRA
#6 13,14,15,16,17,18,19,20,21,22 SCVSNRAMKG

-移动窗口 - 4

f1(df, n = 10, mv = 4) %>% 
          head
#                       position       name
#1                         Melon      Melon
#2          1,2,3,4,5,6,7,8,9,10 RSNSNASSAV
#3      5,6,7,8,9,10,11,12,13,14 NASSAVSTSC
#4  9,10,11,12,13,14,15,16,17,18 AVSTSCVSNR
#5 13,14,15,16,17,18,19,20,21,22 SCVSNRAMKG
#6 17,18,19,20,21,22,23,24,25,26 NRAMKGTTHY

Answer 2

library('tidyverse')
# use this function to make the blocks:
make_substrings = function(string, len, label){
  # set up the indices
  str_len = nchar(string)
  indices1 = 1:(str_len-len+1)
  indices2 = (len:str_len)
  # create the list of indices
  position = map2_chr(indices1, indices2, .f = function(x, y){paste(x:y, collapse = ', ')})
  # take substrings
  name = map2_chr(indices1, indices2, .f = substr, x = string)
  # add yoru food labels
  header = tibble(position = label,
                  name = label)
  header %>% 
    bind_rows(tibble(position,
                     name))
}
# your version had factors
df = df %>% 
  mutate_all(as.character)
# iterate over all the rows of df:
output = Map(f = make_substrings, string = df$sence, len = 10, label = df$sname) %>% 
  bind_rows