如何在 R 中的某个标记之后在列表中剪切 dataframe？

Question

I would like to cut my dataframe after a certain marker. Means after the first time 3 or more times TRUE shows up (=marker) in V1, I would like to cut the dataframes within a list and take the following next 4 rows as my new dataframe within a list.

library(dplyr)
set.seed(94756)
mat1 <- matrix(sample(seq(-1,100, 0.11),70, replace = TRUE),ncol = 5) 
mat1 <- as.tibble(mat1)

mat2 <- matrix(sample(seq(-1,100, 0.11),70, replace = TRUE),ncol = 5)  
mat2 <- as.tibble(mat2)
mat2[3,1] <- NA
mat2[6,1] <- NA

mat3 <- matrix(sample(seq(-1,100, 0.11), 70,replace = TRUE),ncol = 5)  
mat3 <- as.tibble(mat3)
mat3[4,1] <- NA


data <- list(mat1, mat2, mat3)
data1 <- map(data, ~add_column(., V1_logical = between(.$V1, 20, 80), .after = 'V1'))

r_pre <- lapply(data1, "[", 2)

Maybe it is helpful to add an ID column for each dataframe within the list

r_pre1 <- rbindlist(r_pre, idcol = "ID")
r_pre1 <- split(r_pre1, r_pre1$ID)

So the result should be like:

mat1re <- data.frame(V1 = c(93.16, 47.18, 12.86, 38.71), 
                     V2 = c(56.75, 57.85, 18.69, 3.18), 
                     V3 = c(-0.01, 14.95, 46.08, 96.46), 
                     V4 = c(20.89, 32.55, 91.73, 58.73),
                     V5 = c(66.54, 56.75, 92.94, 77.54)) 
                   
mat2re <- data.frame(V1 = c(87.99, 53.23, 40.36, 0.65),
                     V2 = c(89.42, 81.28, 36.84, 73.58), 
                     V3 = c(89.86, 78.75, 76.77, 61.81), 
                     V4 = c(47.18, 22.98, 34.64, 25.18), 
                     V5 = c(18.69, 77.21, 58.29, 94.04))

mat3re <- data.frame(V1 = c(81.50, 43.55, 54.55, 9.45), 
                     V2 = c(33.21, 70.83, 21.66, 88.10), 
                     V3 = c(72.15, -0.45, 11.65, 15.06), 
                     V4 = c(47.07, 47.95, 88.10, 81.50), 
                     V5 = c(80.07, 67.75, 14.84, 10.33))

result <- list(mat1re, mat2re, mat3re)

What I've tried already:

data2 <- lapply(data1, function(x) {x$V1_logical[x$V1_logical== TRUE] <- 1; x})
data3 <- lapply(data2, function(x) {x$V1_logical[x$V1_logical== FALSE] <- 0; x})
data4 <- map(data3, ~add_column(., ind = rleid(.$V1_logical), .after = "V1_logical"))

So in data 4 it's about to find the marker: $V1_logical = 1 & $ind = number that shows up >= 3 times consecutively (eg 5, 5, 5) and cut the data before away incl. marker or in other word start new dataframes after the marker.

The following code is also close, but doesn't cut the beginning incl. marker out when NA's are included in the data...Have a look at the second list here, doesn't cut the beginning and marker out.

matrix_final <- map(data, ~ .x %>% 
                      mutate(V1_logical = between(V1, 20, 80), ind = rleid(V1_logical), .after = "V1") %>% 
                      group_by(ind) %>% 
                      mutate(rn = if(n() >=3 && first(V1_logical)) row_number() else NA_integer_) %>% 
                      ungroup  %>% 
                      slice(seq(max(which.max(rn) + 1, 1, replace_na = TRUE), length.out = 4)) %>% 
                      select(-ind, -rn) %>%
                      mutate(across(everything(), round, digits = 2)))

print(matrix_final[[2]])

Thanks in advance!

Answer 1

We may loop over the list with map , create the logical column on 'V1' with between , create a grouping column with rleid (returns a sequence column that increments when there is a change in value in adjacent elements) and slice the rows based on the condition

library(dplyr)
library(purrr)
library(data.table)
library(tidyr)
map(data, ~ .x %>% 
    mutate(V1_logical = replace_na(between(V1, 20, 80), FALSE), 
       ind = rleid(V1_logical), .after = "V1") %>% 
   group_by(ind) %>%
   mutate(rn = if(n() >=3 && first(V1_logical)) row_number() else
          NA_integer_) %>% 
   ungroup  %>% 
   slice(seq(max(which.max(rn) + 1, 1, na.rm = TRUE), length.out = 4)) %>%
   select(-ind, -rn, -V1_logical) %>%
   mutate(across(everything(), round, digits = 2)))

-output

[[1]]
# A tibble: 4 × 5
     V1    V2      V3    V4    V5
  <dbl> <dbl>   <dbl> <dbl> <dbl>
1  93.2 56.8  -0.0100  20.9  66.5
2  47.2 57.8  15.0     32.6  56.8
3  12.9 18.7  46.1     91.7  92.9
4  38.7  3.18 96.5     58.7  77.5

[[2]]
# A tibble: 4 × 5
     V1    V2    V3    V4    V5
  <dbl> <dbl> <dbl> <dbl> <dbl>
1 88.0   89.4  89.9  47.2  18.7
2 53.2   81.3  78.8  23.0  77.2
3 40.4   36.8  76.8  34.6  58.3
4  0.65  73.6  61.8  25.2  94.0

[[3]]
# A tibble: 4 × 5
     V1    V2    V3    V4    V5
  <dbl> <dbl> <dbl> <dbl> <dbl>
1 81.5   33.2 72.2   47.1  80.1
2 43.6   70.8 -0.45  48.0  67.8
3 54.6   21.7 11.6   88.1  14.8
4  9.45  88.1 15.1   81.5  10.3