How to handle null values /NAs in network analysis-CodePudding

This question is basically extension of my previous question posted here.
How to handle null values/NAs in these types of situations. Example scenario and data

df1 <- data.frame(
  stringsAsFactors = FALSE,
                    id_1 = c("ABC","ABC","BCD",
                             "CDE","DEF","EFG","GHI","HIJ","IJK","JKL",
                             "GHI","KLM","LMN","MNO","NOP"),
                    id_2 = c("1A","2A","3A",
                             "1A","4A","5A","6A",NA,"9A","10A","7A",
                             "12A","13A",NA,"15A"),
                    id_3 = c("Z3","Z2","Z1",
                             "Z4","Z1","Z5","Z5","Z6","Z7","Z8","Z6","Z8",
                             "Z9","Z9","Z1"),
                    Name = c("StackOverflow1",
                             "StackOverflow2","StackOverflow3","StackOverflow4",
                             "StackOverflow5","StackOverflow6",
                             "StackOverflow7","StackOverflow8","StackOverflow9",
                             "StackOverflow10","StackOverflow11","StackOverflow12",
                             "StackOverflow13","StackOverflow14","StackOverflow15"),
          desired_output = c(1L,1L,2L,1L,2L,
                             3L,3L,3L,4L,5L,3L,5L,6L,6L,2L)
      )

df1
   id_1 id_2 id_3            Name desired_output
1   ABC   1A   Z3  StackOverflow1              1
2   ABC   2A   Z2  StackOverflow2              1
3   BCD   3A   Z1  StackOverflow3              2
4   CDE   1A   Z4  StackOverflow4              1
5   DEF   4A   Z1  StackOverflow5              2
6   EFG   5A   Z5  StackOverflow6              3
7   GHI   6A   Z5  StackOverflow7              3
8   HIJ <NA>   Z6  StackOverflow8              3
9   IJK   9A   Z7  StackOverflow9              4
10  JKL  10A   Z8 StackOverflow10              5
11  GHI   7A   Z6 StackOverflow11              3
12  KLM  12A   Z8 StackOverflow12              5
13  LMN  13A   Z9 StackOverflow13              6
14  MNO <NA>   Z9 StackOverflow14              6
15  NOP  15A   Z1 StackOverflow15              2

But the three approaches suggested in the linked post are not working and giving me errors.

Please suggest.

CodePudding user response：

Maybe you can replace NA in column id_2 by the values in id_1, and the follow the answers in previous questions.

You can try this

transform(
  df,
  GRP = membership(
    components(
      graph_from_data_frame(
        reshape(
          transform(
            df,
            id_2 = ifelse(is.na(id_2), id_1, id_2)
          ),
          direction = "long",
          idvar = c("id_1", "Name"),
          varying = 2:3,
          v.names = "to"
        )[c("id_1", "to")]
      )
    )
  )[id_1]
)

which gives

   id_1 id_2 id_3            Name GRP
1   ABC   1A   Z3  StackOverflow1   1
2   ABC   2A   Z2  StackOverflow2   1
3   BCD   3A   Z1  StackOverflow3   2
4   CDE   1A   Z4  StackOverflow4   1
5   DEF   4A   Z1  StackOverflow5   2
6   EFG   5A   Z5  StackOverflow6   3
7   GHI   6A   Z5  StackOverflow7   3
8   HIJ <NA>   Z6  StackOverflow8   3
9   IJK   9A   Z7  StackOverflow9   4
10  JKL  10A   Z8 StackOverflow10   5
11  GHI   7A   Z6 StackOverflow11   3
12  KLM  12A   Z8 StackOverflow12   5
13  LMN  13A   Z9 StackOverflow13   6
14  MNO <NA>   Z9 StackOverflow14   6
15  NOP  15A   Z1 StackOverflow15   2

CodePudding user response：

Just remove NA:

df$desired_output <- df %>%
  select(matches("^id_[0-9] $")) %>%
  mutate(row = row_number()) %>%
  pmap(~c(...) %>% .[!is.na(.)]) %>%
  map(f) %>%
  flatten() %>%
  reduce(rbind) %>%
  igraph::graph_from_edgelist() %>% 
  components() %>%
  membership() %>%
  .[as.character(seq_len(nrow(df)))]