Question

我有一个像这样的数据框：

df<- data.frame(region= c("1","1","1","1","2","2","2","3","3", "4", 
"4"), 
 loc=c("1A","1A","1B","1C","2A","2B","2C","3A","3B","4A","4B"), sp1= 
c("a","a","b","a","c","c","c","a","a","d","d"), sp2= 
c("b","b","c","b","d","d","d","b","b", "e","e"), inter= 
c("a_b","a_b","b_c","a_b","c_d","c_d","c_d","a_b","a_b", 
"d_e","d_e"))

我想首先按区域对df进行分组，然后在每个inter中找到重复的region WITHIN。然后我想在所有地区找到重复的inter。第一个子集看起来像：

subset1<- data.frame(region=c("1","2","3","4"), sp1= c("a", "c", "a", 
"d"),sp2= c("b", "d", "b", "e"), inter= c("a_b", "c_d", "a_b", 
"d_e"))

最终输出如下：

df<- data.frame(sp1= c("a"), sp2= c("b"), inter=c("a_b"))

Answer 1

对于每个区域内的重复项：使用dplyr，filter在区域内重复，然后找到distinct region-inter组合：

library(dplyr)

within_region <- df %>%
  group_by(region) %>%
  filter(duplicated(inter)) %>%
  distinct(region, inter, .keep_all = TRUE)

#   region    loc    sp1    sp2  inter
# 1      1     1A      a      b    a_b
# 2      2     2B      c      d    c_d
# 3      3     3B      a      b    a_b
# 4      4     4B      d      e    d_e

对于所有地区中inter个重复项的计数：

all_region <- df %>%
  count(inter)

#    inter     n
# 1    a_b     5
# 2    b_c     1
# 3    c_d     3
# 4    d_e     2

Answer 2

Try this ( just need to drop some columns to meet your goal): 

#1
df=df%>%group_by(region,inter)%>%dplyr::mutate(n=n())%>%filter(row_number()==n()&n>1)

> df
Source: local data frame [4 x 6]
Groups: region, inter [4]

  region    loc    sp1    sp2  inter     n
  <fctr> <fctr> <fctr> <fctr> <fctr> <int>
1      1     1C      a      b    a_b     3
2      2     2C      c      d    c_d     3
3      3     3B      a      b    a_b     2
4      4     4B      d      e    d_e     2
#2
df%>%group_by(inter)%>%dplyr::mutate(n=n())%>%filter(row_number()==n()&n>1)

Source: local data frame [1 x 6]
Groups: inter [1]

  region    loc    sp1    sp2  inter     n
  <fctr> <fctr> <fctr> <fctr> <fctr> <int>
1      3     3B      a      b    a_b     2

在嵌套df

2 个答案: