Error in NextMethod() : only 0's may be mixed with negative subscripts

user_7630763 0
Viewed 33

I prepared a fake dataframe to ask a question about segmentation here. But oddly enough, I faced another error, while trying to filter the dataframe in dplyr using `filter, which keeps throwing this error:

Error in NextMethod() : only 0's may be mixed with negative subscripts

The most bizarre thing!

Here is the code that throws the error:

datv %>%
  dplyr::filter(str_detect(campaign, "campaign_z|campaign_x"))

Here is the dataframe:

structure(list(campaign = c("campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_y", "campaign_y", "campaign_y", 
"campaign_y", "campaign_y", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z", "campaign_z", "campaign_z", "campaign_z", 
"campaign_z", "campaign_z"), com_elm = c("campaign_x_C3", "campaign_x_B1", 
"campaign_x_B2", "campaign_x_C3", "campaign_x_C3", "campaign_x_B1", 
"campaign_x_B2", "campaign_x_C3", "campaign_x_C3", "campaign_x_B1", 
"campaign_x_B2", "campaign_x_C3", "campaign_x_B1", "campaign_x_C3", 
"campaign_x_B1", "campaign_x_A1", "campaign_x_C3", "campaign_x_B1", 
"campaign_x_B1", "campaign_x_C3", "campaign_x_B1", "campaign_x_A1", 
"campaign_x_C3", "campaign_x_C3", "campaign_x_B1", "campaign_x_B2", 
"campaign_x_C3", "campaign_x_B1", "campaign_x_C3", "campaign_x_C3", 
"campaign_y_C3", "campaign_y_B1", "campaign_y_B2", "campaign_y_C3", 
"campaign_y_C3", "campaign_y_B1", "campaign_y_B2", "campaign_y_C3", 
"campaign_y_C3", "campaign_y_B1", "campaign_y_B2", "campaign_y_C3", 
"campaign_y_B1", "campaign_y_C3", "campaign_y_B1", "campaign_y_A1", 
"campaign_y_C3", "campaign_y_B1", "campaign_y_B1", "campaign_y_C3", 
"campaign_y_B1", "campaign_y_A1", "campaign_y_C3", "campaign_y_C3", 
"campaign_y_B1", "campaign_y_B2", "campaign_y_C3", "campaign_y_B1", 
"campaign_y_C3", "campaign_y_C3", "campaign_z_C3", "campaign_z_B1", 
"campaign_z_B2", "campaign_z_C3", "campaign_z_C3", "campaign_z_B1", 
"campaign_z_B2", "campaign_z_C3", "campaign_z_C3", "campaign_z_B1", 
"campaign_z_B2", "campaign_z_C3", "campaign_z_B1", "campaign_z_C3", 
"campaign_z_B1", "campaign_z_A1", "campaign_z_C3", "campaign_z_B1", 
"campaign_z_B1", "campaign_z_C3", "campaign_z_B1", "campaign_z_A1", 
"campaign_z_C3", "campaign_z_C3", "campaign_z_B1", "campaign_z_B2", 
"campaign_z_C3", "campaign_z_B1", "campaign_z_C3", "campaign_z_C3"
), com_elm_id = c(808001L, 811001L, 814001L, 509005L, 729060L, 
817002L, 820002L, 792002L, 793003L, 820003L, 824003L, 792002L, 
811001L, 787001L, 811001L, 468023L, 792002L, 812001L, 812001L, 
808001L, 811001L, 468023L, 468006L, 491014L, 825002L, 828002L, 
741001L, 825002L, 512001L, 733001L, 808001L, 811001L, 814001L, 
509005L, 729060L, 817002L, 820002L, 792002L, 793003L, 820003L, 
824003L, 792002L, 811001L, 787001L, 811001L, 468023L, 792002L, 
812001L, 812001L, 808001L, 811001L, 468023L, 468006L, 491014L, 
825002L, 828002L, 741001L, 825002L, 512001L, 733001L, 808001L, 
811001L, 814001L, 509005L, 729060L, 817002L, 820002L, 792002L, 
793003L, 820003L, 824003L, 792002L, 811001L, 787001L, 811001L, 
468023L, 792002L, 812001L, 812001L, 808001L, 811001L, 468023L, 
468006L, 491014L, 825002L, 828002L, 741001L, 825002L, 512001L, 
733001L), recipient_id = c(5432L, 5432L, 5432L, 197L, 197L, 8388L, 
8388L, 8426L, 8426L, 10903L, 10903L, 14469L, 14469L, 17466L, 
17466L, 17807L, 21666L, 23935L, 24287L, 25412L, 25412L, 31361L, 
31361L, 31361L, 31365L, 31365L, 40849L, 40860L, 41737L, 41737L, 
5432L, 5432L, 5432L, 197L, 197L, 8388L, 8388L, 8426L, 8426L, 
10903L, 10903L, 1446945L, 1446945L, 1746645L, 1746645L, 1780745L, 
2166645L, 2393545L, 24287L, 25412L, 25412L, 3136145L, 3136145L, 
3136145L, 3136545L, 3136545L, 40849L, 40860L, 4173745L, 4173745L, 
5432L, 5432L, 5432L, 19732L, 19732L, 838832L, 838832L, 842632L, 
842632L, 10903L, 10903L, 14469L, 14469L, 1746632L, 1746632L, 
1780732L, 2166645L, 2393545L, 2428745L, 25412L, 25412L, 3136145L, 
3136145L, 3136145L, 3136545L, 3136545L, 40849L, 40860L, 41737L, 
41737L), step = c(3, 1, 2, 3, 3, 1, 2, 3, 3, 1, 2, 3, 1, 3, 1, 
1, 3, 1, 1, 3, 1, 1, 3, 3, 1, 2, 3, 1, 3, 3, 3, 1, 2, 3, 3, 1, 
2, 3, 3, 1, 2, 3, 1, 3, 1, 1, 3, 1, 1, 3, 1, 1, 3, 3, 1, 2, 3, 
1, 3, 3, 3, 1, 2, 3, 3, 1, 2, 3, 3, 1, 2, 3, 1, 3, 1, 1, 3, 1, 
1, 3, 1, 1, 3, 3, 1, 2, 3, 1, 3, 3), date = structure(c(19029, 
19032, 19035, 18778, 18960, 19037, 19040, 19016, 19019, 19040, 
19043, 19015, 19032, 19011, 19032, 18746, 19015, 19033, 19033, 
19029, 19032, 18746, 18746, 18764, 19044, 19047, 18969, 19044, 
18781, 18962, 19029, 19032, 19035, 18778, 18960, 19037, 19040, 
19016, 19019, 19040, 19043, 19015, 19032, 19011, 19032, 18746, 
19015, 19033, 19033, 19029, 19032, 18746, 18746, 18764, 19044, 
19047, 18969, 19044, 18781, 18962, 19029, 19032, 19035, 18778, 
18960, 19037, 19040, 19016, 19019, 19040, 19043, 19015, 19032, 
19011, 19032, 18746, 19015, 19033, 19033, 19029, 19032, 18746, 
18746, 18764, 19044, 19047, 18969, 19044, 18781, 18962), class = "Date")), row.names = c(NA, 
-90L), groups = structure(list(campaign = c("campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x", 
"campaign_x", "campaign_x", "campaign_x", "campaign_x", "campaign_x"
), recipient_id = c(54L, 197L, 8388L, 8426L, 10903L, 14469L, 
17466L, 17807L, 21666L, 23935L, 24287L, 25412L, 31361L, 31365L, 
40849L, 40860L, 41737L), .rows = structure(list(1:3, 4:5, 6:7, 
    8:9, 10:11, 12:13, 14:15, 16L, 17L, 18L, 19L, 20:21, 22:24, 
    25:26, 27L, 28L, 29:30), ptype = integer(0), class = c("vctrs_list_of", 
"vctrs_vctr", "list"))), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -17L), .drop = TRUE), class = c("grouped_df", 
"tbl_df", "tbl", "data.frame"))

Any idea what could be causing that?

When combining the above code with the rest of my code like this:

datv %>%   filter(str_detect(campaign, "campaign_z|campaign_x")) %>%
            group_by(recipient_id) %>%
            summarise(rank = dense_rank(campaign)) %>%
            ungroup() %>%
            group_by(recipient_id,rank) %>%
            summarise(count = n()) %>% #used to remove duplicates with count() to sense check work. Can use distinct()
            ungroup() %>%
            group_by(recipient_id) %>%
            summarise(max_rank=max(rank)) %>%
            ungroup() %>%
            group_by(max_rank) %>%
            summarise(count=n())

I get this another warning and error:

Warning in NextMethod() :
  number of items to replace is not a multiple of replacement length
Error:
! Assigned data `rows` must be compatible with existing data.
x Existing data has 17 rows.
x Assigned data has 925904432 rows.
ℹ Only vectors of size 1 are recycled.
Backtrace:
  1. ... %>% summarise(count = n())
 28. tibble `<fn>`(`<vctrs___>`)

either I have gone insane, or my R installation is gone corrupt, or some unusual thing is in play here!

dplyr r
1 Answers

It is a grouped dataset and the filter is applied on one of the grouping columns.

library(dplyr)
group_vars(datv)
[1] "campaign"     "recipient_id"

Instead, ungroup and then apply

library(stringr)
datv %>% 
  ungroup %>%
  dplyr::filter(str_detect(campaign, "campaign_z|campaign_x"))

-output

# A tibble: 60 × 6
   campaign   com_elm       com_elm_id recipient_id  step date      
   <chr>      <chr>              <int>        <int> <dbl> <date>    
 1 campaign_x campaign_x_C3     808001         5432     3 2022-02-06
 2 campaign_x campaign_x_B1     811001         5432     1 2022-02-09
 3 campaign_x campaign_x_B2     814001         5432     2 2022-02-12
 4 campaign_x campaign_x_C3     509005          197     3 2021-05-31
 5 campaign_x campaign_x_C3     729060          197     3 2021-11-29
 6 campaign_x campaign_x_B1     817002         8388     1 2022-02-14
 7 campaign_x campaign_x_B2     820002         8388     2 2022-02-17
 8 campaign_x campaign_x_C3     792002         8426     3 2022-01-24
 9 campaign_x campaign_x_C3     793003         8426     3 2022-01-27
10 campaign_x campaign_x_B1     820003        10903     1 2022-02-17
# … with 50 more rows

Also, the ungroup after summarise can be removed if we make use of the .groups argument in summarise

 datv %>%
     ungroup %>% 
     filter(str_detect(campaign, "campaign_z|campaign_x")) %>%
     group_by(recipient_id) %>%
     summarise(rank = dense_rank(campaign), .groups = 'drop') %>%
     group_by(recipient_id,rank) %>%
     summarise(count = n(), .groups = 'drop') %>%    
     group_by(recipient_id) %>%
     summarise(max_rank=max(rank), .groups = 'drop') %>%
     group_by(max_rank) %>%
     summarise(count=n(), .groups = 'drop')

-output

# A tibble: 2 × 2
  max_rank count
     <int> <int>
1        1    20
2        2     7
user_37322710
Related