Why tbl_summary doesn't work?

juandmaz · September 9, 2024, 8:01pm

I have this df

>   head(df)
# A tibble: 6 × 18
  fecha_de_realizacion grupo a_usted_o_alguien_muy_cercano_han…¹ b_usted_participa_de…² c_usted_trabaja_o_es…³
  <dttm>               <chr> <chr>                               <chr>                  <chr>                 
1 2024-07-03 00:00:00  1     No                                  No                     No                    
2 2024-07-03 00:00:00  1     No                                  No                     No                    
3 2024-06-03 00:00:00  1     Si                                  No                     No                    
4 2024-07-03 00:00:00  1     No                                  No                     No                    
5 2024-07-03 00:00:00  2     No                                  No                     No                    
6 2024-03-03 00:00:00  2     Si                                  No                     No         

names(df)
[1] "fecha_de_realizacion"                                                                                                    
 [2] "grupo"                                                                                                                   
 [3] "a_usted_o_alguien_muy_cercano_han_tenido_en_los_ultimos_5_anos_algun_tipo_de_cancer_enfermedad_grave"                    
 [4] "b_usted_participa_de_alguna_institucion_asociacion_ong_o_fundacion_vinculadas_a_la_lucha_con_el_cancer"                  
 [5] "c_usted_trabaja_o_es_parte_de_alguna_empresa_farmaceutica"                                                               
 [6] "d_participa_o_trabaja_en_el_instituto_nacional_del_cancer_o_en_otra_institucion_del_sistema_de_salud"                    
 [7] "p2_usted_es"                                                                                                             
 [8] "p3_cual_es_su_ocupacion_actual_a_que_se_dedica"                                                                          
 [9] "p4_cual_es_el_maximo_nivel_educativo_alcanzado_por_ud"                                                                   
[10] "y_este_nivel_lo_completo"                                                                                                
[11] "p5_que_cobertura_de_salud_posee"                                                                                         
[12] "otra_opcion"                                                                                                             
[13] "p6_alguna_vez_le_realizaron_un_papanicolaou_pap"                                                                         
[14] "p7_alguna_vez_realizo_el_test_de_hpv_vph"                                                                                
[15] "p8_recuerda_cuando_realizo_el_ultimo_control_ginecologico"                                                               
[16] "p10_utiliza_internet_en_el_telefono_celular"                                                                             
[17] "p11_con_que_frecuencia_utiliza_usted_internet_en_su_celular"                                                             
[18] "p14_y_utiliza_apps_de_temas_de_salud_por_ejemplo_registrar_la_menstruacion_para_hacer_ejercicio_o_control_del_peso_otras"

And I try this code:

df %>%
  mutate_all(as.factor) %>% 
  tbl_summary(by= grupo,
              missing = "always",
              statistic = list(all_categorical() ~ "{n} {p}"),
              missing_text= "Casos perdidos",
              digits = list(all_categorical() ~ c(0,1)))

And it gaves me this error:

Error en names(df) <- repaired_names(c(names2(dimnames(x)), n), repair_hint = TRUE, : 
  'names' attribute [3] must be the same length as the vector [2]

I edit so I add a reprex:

> dput(df)
structure(list(fecha_de_realizacion = structure(c(1719964800, 
1719964800, 1717372800, 1719964800, 1719964800, 1709424000, 1719964800, 
1719964800, 1719964800, 1719964800, 1719964800, 1720051200, 1720051200, 
NA, 1720051200, 1720051200, 1720051200, NA, 1720051200, 1720051200, 
1720051200, 1720051200, NA, NA, NA, NA, 1720051200, NA), tzone = "UTC", class = c("POSIXct", 
"POSIXt")), grupo = c("1", "1", "1", "1", "2", "2", "2", "2", 
"2", "2", "2", "3", "3", "3", "3", "3", "3", "3", "3", "4", "4", 
"4", "4", "4", "4", "4", "4", "4"), a_usted_o_alguien_muy_cercano_han_tenido_en_los_ultimos_5_anos_algun_tipo_de_cancer_enfermedad_grave = c("No", 
"No", "Si", "No", "No", "Si", "No", "Si", "Si", "No", NA, "No", 
"No", "No lo sabe", "No", "Si", "No", "No", "No", "No", "No", 
"No", "No", "Si", "No", "No", "No", "No contesta"), b_usted_participa_de_alguna_institucion_asociacion_ong_o_fundacion_vinculadas_a_la_lucha_con_el_cancer = c("No", 
"No", "No", "No", "No", "No", "No", "No", "No", "No", "No", "No", 
"No", "No", "No", "No", "No", "No", "Si", "No", "No", "No", "No", 
"No", "No", "No", "Si", "No"), c_usted_trabaja_o_es_parte_de_alguna_empresa_farmaceutica = c("No", 
"No", "No", "No", "No", "No", "No", "No", "No", "No", "No", "No", 
"No", "No", "No", "No", "No", "No", "Si", "No", "No", "No", "No", 
"No", "No", "No", "No", "No"), d_participa_o_trabaja_en_el_instituto_nacional_del_cancer_o_en_otra_institucion_del_sistema_de_salud = c("No", 
"No", "No", "No", "No", "No", "No", "No", "No", "No", NA, NA, 
"No", "No", "No", "No", "No", "No", "Si", "No", "No", "No", "No", 
"No", "No", "No", "No", "No"), p2_usted_es = c("Mujer", "Mujer", 
"Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", 
"Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", 
"Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", "Mujer", 
"Mujer", "Mujer", "Mujer", "Mujer", "Mujer"), p3_cual_es_su_ocupacion_actual_a_que_se_dedica = c("Desempleada", 
"Limpieza", "Desocupada. Ama de casa", "Monotributista autonomo", 
"Masajista y Cocinera", NA, "Ama de casa", "Empleada de comercio", 
"Empleada", "Empleada domestica", "Niñera, vendedora Natura", 
"Ama de casa", "Cuidadora de adultos mayores", "Trabajo casa de familia", 
"Empleada domestica", "Trabajo por mi cuenta", "Empleada", "Vendedora de cosméticos", 
"Empleada domestica", "Vendedora por mi cuenta", "Comerciante. Ama de casa", 
"Chofer aplicación", "Desempleada", "Estetica/Manicura", "Repostera", 
"Independiente artesana", "Costurera", "Ama de casa"), p4_cual_es_el_maximo_nivel_educativo_alcanzado_por_ud = c("Primario/EGB", 
"Primario/EGB", "Secundario/Polimodal", "Primario/EGB", "Secundario/Polimodal", 
"Secundario/Polimodal", "Secundario/Polimodal", "Secundario/Polimodal", 
"Secundario/Polimodal", "Secundario/Polimodal", "Secundario/Polimodal", 
"Primario/EGB", "Primario/EGB", "Primario/EGB", "Primario/EGB", 
"Primario/EGB", "Secundario/Polimodal", "Primario/EGB", "Primario/EGB", 
"Secundario/Polimodal", "Secundario/Polimodal", "Secundario/Polimodal", 
"Secundario/Polimodal", "Secundario/Polimodal", "Secundario/Polimodal", 
"Secundario/Polimodal", "Secundario/Polimodal", "Secundario/Polimodal"
), y_este_nivel_lo_completo = c("Si", "Si", "No", "Si", "No", 
NA, "No", "Si", "No", "No", "Si", NA, NA, "Si", "No", NA, "Si", 
"Si", NA, "No", "Si", "No", "Si", "Si", "Si", "Si", "No", "No"
), p5_que_cobertura_de_salud_posee = c("Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Obra social Empresa de salud prepaga, plan hospitalario privado", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico", 
"Utiliza el hospital publico, salita, centro de salud publico"
), otra_opcion = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA), p6_alguna_vez_le_realizaron_un_papanicolaou_pap = c("Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "No lo sabe"
), p7_alguna_vez_realizo_el_test_de_hpv_vph = c("Sí", "Sí", 
"No lo sabe", "Sí", "Sí", "Sí", "No lo sabe", "No lo sabe", 
"No", "No", "No", "No", "No", "Sí", "Sí", "Sí", "No", "Sí", 
"No", "Sí", "No", "No", "No", "No", "Sí", "No", "Sí", "No lo sabe"
), p8_recuerda_cuando_realizo_el_ultimo_control_ginecologico = c("Ultimo año", 
"Nunca realizo", "Ultimo año", "Ultimo año", "Ultimo año", 
"Ultimo año", "Mas de un año", "Mas de un año", "Mas de un año", 
"Mas de un año", "Ultimo año", "Mas de un año", "Mas de un año", 
"Ultimo año", "Mas de un año", "Ultimo año", "Ultimo año", 
"Ultimo año", "Mas de un año", "Ultimo año", "Mas de un año", 
"Mas de un año", "Ultimo año", "Mas de un año", "Ultimo año", 
"Mas de un año", "Ultimo año", "Ultimo año"), p10_utiliza_internet_en_el_telefono_celular = c("Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", 
"Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí", "Sí"
), p11_con_que_frecuencia_utiliza_usted_internet_en_su_celular = c("Todos los días", 
"Todos los días", "Todos los días", "Todos los días", "Todos los días", 
"Todos los días", "Todos los días", "Todos los días", "Todos los días", 
"Todos los días", "Todos los días", "Todos los días", "Mas los días de la semana (L a V)", 
"Todos los días", "Todos los días", "Todos los días", "Todos los días", 
"Todos los días", "Todos los días", "Todos los días", "Todos los días", 
"Todos los días", "Todos los días", "Todos los días", "Todos los días", 
"Todos los días", "Todos los días", "Todos los días"), p14_y_utiliza_apps_de_temas_de_salud_por_ejemplo_registrar_la_menstruacion_para_hacer_ejercicio_o_control_del_peso_otras = c("No", 
"No lo sabe", "Sí", "No", "Sí", "Sí", "Sí", "No", "Sí", 
"Sí", "No", "No", "No", "No", "No", "No", "No", "No", "No", 
"Sí", "No", "Sí", "No", "No", "No", "Sí", "No", "No")), row.names = c(NA, 
-28L), class = c("tbl_df", "tbl", "data.frame"))

Anyone knows why?
if I take variables from the df it works, but it doesn't make sense because tbl_summary should work with any number of variables.

nirgrahamuk · September 10, 2024, 9:44am

This code works on a data.frame I made up.
I don't have ideas how to change my data.frame to break it ...

Could you provide a reprex ?

StatSteph · September 10, 2024, 11:31pm

To do this, share the output of the following code:

dput(head(df, 10))

juandmaz · September 12, 2024, 9:28pm

Hi, I just eddited the post to add a reprex

juandmaz · September 12, 2024, 9:28pm

Hi, just did it! So now there is a reprex

jrkrideau · September 13, 2024, 1:59pm

Have you loaded the {gtsummary}package?

StatSteph · September 13, 2024, 6:34pm

I think this is because the value for otra_opcion is always missing. I can't be certain but excluding that column yields code that works. Here's a much simpler example to show this. I recommend reporting this as a bug.

library(tidyverse)
library(gtsummary)

mydf <- tibble(
  Group=rep(1:4, each=20),
  CatValid=as.factor(sample(letters[1:4], 80, replace=TRUE)),
  CatNA=factor(NA)
)

mydf %>%
  select(-CatNA) %>%
  tbl_summary(by="Group")

Characteristic	1 N = 20¹	2 N = 20¹	3 N = 20¹	4 N = 20¹
CatValid
a	5 (25%)	1 (5.0%)	3 (15%)	7 (35%)
b	5 (25%)	4 (20%)	7 (35%)	5 (25%)
c	6 (30%)	5 (25%)	6 (30%)	4 (20%)
d	4 (20%)	10 (50%)	4 (20%)	4 (20%)
¹ n (%)


mydf %>%
  tbl_summary(by="Group")
#> Error in names(df) <- repaired_names(c(names2(dimnames(x)), n), repair_hint = TRUE, : 'names' attribute [3] must be the same length as the vector [2]

^{Created on 2024-09-13 with reprex v2.1.0}

statistishdan · September 14, 2024, 3:05pm

Thank you @StatSteph for the minimal reprex and posting an issue to the gtsummary GH repo.

@juandmaz You can read more details here (Bug Report: Variable with all NA levels causes error · Issue #1973 · ddsjoberg/gtsummary · GitHub) about the issue. Essentially, gtsummary will not summarize factor variables when either the levels are empty or any of the levels are NA.

You'll need to specify the factor levels to get a column of all NAs to tabulate (otherwise, there are no levels to count).

library(gtsummary)
set.seed(8675309)

mydf <- dplyr::tibble(
  Group=rep(1:4, each=20),
  CatValid=as.factor(sample(letters[1:4], 80, replace=TRUE)),
  CatNA=factor(NA, levels = c("Hello", "There"))
)

tbl_summary(mydf, by = Group) |> 
  bold_labels() |> 
  as_kable()

Characteristic	1 N = 20	2 N = 20	3 N = 20	4 N = 20
CatValid
a	5 (25%)	3 (15%)	4 (20%)	4 (20%)
b	4 (20%)	8 (40%)	6 (30%)	4 (20%)
c	8 (40%)	4 (20%)	6 (30%)	6 (30%)
d	3 (15%)	5 (25%)	4 (20%)	6 (30%)
CatNA
Hello	0 (NA%)	0 (NA%)	0 (NA%)	0 (NA%)
There	0 (NA%)	0 (NA%)	0 (NA%)	0 (NA%)
Unknown	20	20	20	20

^{Created on 2024-09-13 with reprex v2.1.0}