Question

我是R编程的新手，在满足过滤条件后尝试删除每组行中的某些行。

方案：对于每个GROUP，如果连续有2个类型“ B”，请删除该GROUP的所有以下行。 “包含在数据集中”列显示了输出内容。

这是我的示例输入：

GROUP   TYPE    Include in DataSet?
--------------------------------------------
1       A       yes
1       A       yes
1       B       yes
1       B       yes
1       B       no
2       A       yes
2       B       yes
2       B       yes
2       A       no
2       B       no
2       B       no

DF = structure(list(GROUP = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 
2L, 2L), TYPE = c("A", "A", "B", "B", "B", "A", "B", "B", "A", 
"B", "B"), inc = c("yes", "yes", "yes", "yes", "no", "yes", "yes", 
"yes", "no", "no", "no")), .Names = c("GROUP", "TYPE", "inc"), row.names = c(NA, 
-11L), class = "data.frame")

预期输出：

GROUP   TYPE    Include in DataSet?
--------------------------------------------
1       A       yes
1       A       yes
1       B       yes
1       B       yes
2       A       yes
2       B       yes
2       B       yes

我尝试编写一些代码，但由于分组问题而没有运气。

i=1
j=2
x <- allrows
for (i in x){
  for(j in x){
    if(i==j){
      a$REMOVE=1
    }
    else{
      a$REMOVE=2
    }
  }
}

Answer 1

您可以通过创建一个新变量来标识“双B”行，然后过滤出组中第一“双B”行之后的行来实现此目的：

library(dplyr)
df %>%
    group_by(GROUP) %>%
    # Create new variable that tests if each row and the one below it TYPE==B
    mutate(double_B = (TYPE == 'B' & lag(TYPE) == 'B')) %>%
    # Find the first row with `double_B` in each group, filter out rows after it
    filter(row_number() <= min(which(double_B == TRUE))) %>%
    # Optionally, remove `double_B` column when done with it
    select(-double_B)

# A tibble: 7 x 3
# Groups:   GROUP [2]
  GROUP TYPE  IncludeinDataSet
  <int> <chr> <chr>           
1     1 A     yes             
2     1 A     yes             
3     1 B     yes             
4     1 B     yes             
5     2 A     yes             
6     2 B     yes             
7     2 B     yes

正如@Frank在评论中指出的那样，您无需创建double_B变量：您只需在内部的which语句中测试“双B”条件即可filter：

df %>%
    group_by(GROUP) %>%
    # Find the first row with `double_B` in each group, filter out rows after it
    filter(row_number() <= min(which(TYPE == 'B' & lag(TYPE) == 'B')))

此外，如果在组中未找到“双B”条件，它将返回警告，但仍会正确过滤

Answer 2

这可以通过将“ TYPE”的当前值与下一个“ TYPE”的值进行检查以找到数字索引来完成，使用seq_len来获取从1到该数字的序列以对行进行子集设置（ slice内

library(dplyr)
df1 %>% 
  group_by(GROUP) %>% 
  slice(seq_len(which((TYPE == "B") & lead(TYPE) == "B")[1] + 1))
# A tibble: 7 x 3
# Groups:   GROUP [2]
#  GROUP TYPE  IncludeInDataSet
#  <int> <chr> <chr>           
#1     1 A     yes             
#2     1 A     yes             
#3     1 B     yes             
#4     1 B     yes             
#5     2 A     yes             
#6     2 B     yes             
#7     2 B     yes

数据

df1 <- structure(list(GROUP = c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 
 2L, 2L), TYPE = c("A", "A", "B", "B", "B", "A", "B", "B", "A", 
 "B", "B"), IncludeInDataSet = c("yes", "yes", "yes", "yes", "no", 
  "yes", "yes", "yes", "no", "no", "no")), class = "data.frame", 
 row.names = c(NA, -11L))

Answer 3

另一种方法可能是：

library(dplyr)
library(data.table)

df %>%
  group_by(GROUP, rleid(TYPE)) %>%
  mutate(temp = seq_along(TYPE)) %>%
  ungroup() %>%
  group_by(GROUP) %>%
  filter(row_number() <= min(which(TYPE == "B" & temp == 2))) %>%
  select(GROUP, TYPE, IncludeInDataSet)

Answer 4

这是基本的R解决方案：

subset(DF, as.logical(ave(DF$TYPE,DF$GROUP, FUN= function(x) 
  seq_along(x) <= which((sequence(rle(x=="B")$length) * (x=="B")) %in% 2)[1])))
#   GROUP TYPE inc
# 1     1    A yes
# 2     1    A yes
# 3     1    B yes
# 4     1    B yes
# 6     2    A yes
# 7     2    B yes
# 8     2    B yes

发生条件后如何过滤出每组的行

4 个答案:

数据