计算一条线上重叠的线段的总和

如果我理解正确，small_line则此处的变量无关紧要。其余的列可用于获取重叠段的总和：

步骤1。获取每个线段与相应线的重叠的起点和终点：

library(dplyr)

data1 <- data %>%
  rowwise() %>%
  mutate(overlap.start = max(left_line, left_small_line),
         overlap.end = min(right_line, right_small_line)) %>%
  ungroup() %>%
  select(line, overlap.start, overlap.end)

> data1
# A tibble: 8 x 3
  line  overlap.start overlap.end
  <fct>         <int>       <int>
1 A               100         111
2 A               119         120
3 B                70          73
4 B                70          80
5 B                70          85
6 C                20          21
7 C                24          40
8 C                35          40

第二步。在每行对应的行中，按顺序对重叠进行排序。如果它是第一个重叠，或者先前的重叠在开始之前结束，则将其视为新的重叠部分。标记每个新的重叠部分：

data2 <- data1 %>%
  arrange(line, overlap.start, overlap.end) %>%
  group_by(line) %>%
  mutate(new.section = is.na(lag(overlap.end)) | 
           lag(overlap.end) <= overlap.start) %>%
  mutate(section.number = cumsum(new.section)) %>%
  ungroup()

> data2
# A tibble: 8 x 5
  line  overlap.start overlap.end new.section section.number
  <fct>         <int>       <int> <lgl>                <int>
1 A               100         111 TRUE                     1
2 A               119         120 TRUE                     2
3 B                70          73 TRUE                     1
4 B                70          80 FALSE                    1
5 B                70          85 FALSE                    1
6 C                20          21 TRUE                     1
7 C                24          40 TRUE                     2
8 C                35          40 FALSE                    2

第三步。在每个重叠的部分中，以最早的起点和最新的终点。计算每个重叠的长度：

data3 <- data2 %>%
  group_by(line, section.number) %>%
  summarise(overlap.start = min(overlap.start),
            overlap.end = max(overlap.end)) %>%
  ungroup() %>%
  mutate(overlap = overlap.end - overlap.start)

> data3
# A tibble: 5 x 5
  line  section.number overlap.start overlap.end overlap
  <fct>          <int>         <dbl>       <dbl>   <dbl>
1 A                  1           100         111      11
2 A                  2           119         120       1
3 B                  1            70          85      15
4 C                  1            20          21       1
5 C                  2            24          40      16

第四步。对每行的重叠长度求和：

data4 <- data3 %>%
  group_by(line) %>%
  summarise(overlap = sum(overlap)) %>%
  ungroup()

> data4
# A tibble: 3 x 2
  line  overlap
  <fct>   <dbl>
1 A          12
2 B          15
3 C          17

现在，您的预期结果将显示每一行的预期重叠百分比，而不是总和。如果您要寻找的是，可以将每行的长度添加到data4，并据此进行计算：

data5 <- data4 %>%
  left_join(data %>% 
              select(line, left_line, right_line) %>%
              unique() %>% 
              mutate(length = right_line - left_line) %>%
              select(line, length),
            by = "line") %>%
  mutate(overlap.percentage = overlap / length)

> data5
# A tibble: 3 x 4
  line  overlap length overlap.percentage
  <fct>   <dbl>  <int>              <dbl>
1 A          12     20               0.6 
2 B          15     20               0.75
3 C          17     20               0.85