full_join() don't recognizes values

Lekmonm · June 15, 2021, 9:41pm

Hello, I need to full join two df: DS90 and LCM_QAR, and for each row of LCM_QAR assign the corresponding value from the DS90 df (columns Tabla. 1 to Tabla.5). I used full_join() but instead of the values from the DS90 df, NA appears per each Tabla.1 to Tabla.5.

Thank you for your help.

library(tidyverse)
#> Warning: package 'readr' was built under R version 4.0.5
library(dplyr)

datapasta::dpasta(head(DS90))
#> Error in head(DS90): objeto 'DS90' no encontrado

tibble::tribble(
             ~Parametro, ~Tabla.1, ~Tabla.2, ~Tabla.3, ~Tabla.4, ~Tabla.5,
  "Aluminio total (Al)",        5,       10,        1,        1,       10,
  "Arsenico total (As)",      0.5,        1,      0.1,      0.2,      0.5,
    "Cadmio total (Cd)",     0.01,      0.3,     0.02,     0.02,      0.5,
      "Cinc total (Zn)",        3,       20,        5,        5,        5,
     "Cobre total (Cu)",        1,        3,      0.1,        1,        3,
     "Cromo total (Cr)",       NA,       NA,      2.5,      2.5,       10
  )
#> # A tibble: 6 x 6
#>   Parametro           Tabla.1 Tabla.2 Tabla.3 Tabla.4 Tabla.5
#>   <chr>                 <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
#> 1 Aluminio total (Al)    5       10      1       1       10  
#> 2 Arsenico total (As)    0.5      1      0.1     0.2      0.5
#> 3 Cadmio total (Cd)      0.01     0.3    0.02    0.02     0.5
#> 4 Cinc total (Zn)        3       20      5       5        5  
#> 5 Cobre total (Cu)       1        3      0.1     1        3  
#> 6 Cromo total (Cr)      NA       NA      2.5     2.5     10

datapasta::dpasta(head(LCM_QAR))
#> Error in head(LCM_QAR): objeto 'LCM_QAR' no encontrado

tibble::tribble(
    ~Año,        ~Cod_EA, ~Cod_ETFA,            ~Metodo,            ~Parametro,  ~LCM,
  "2020", "EA-SMA-02-20",  "010-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.09,
  "2020", "EA-SMA-02-20",  "016-01",                 NA, "Aluminio total (Al)",    NA,
  "2020", "EA-SMA-02-20",  "010-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.164,
  "2020", "EA-SMA-02-20",  "011-01", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.034,
  "2020", "EA-SMA-02-20",  "021-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.05,
  "2020", "EA-SMA-02-20",  "021-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.005
  )
#> # A tibble: 6 x 6
#>   Año   Cod_EA       Cod_ETFA Metodo           Parametro              LCM
#>   <chr> <chr>        <chr>    <chr>            <chr>                <dbl>
#> 1 2020  EA-SMA-02-20 010-01   NCh2313/25.Of97. Aluminio total (Al)  0.09 
#> 2 2020  EA-SMA-02-20 016-01   <NA>             Aluminio total (Al) NA    
#> 3 2020  EA-SMA-02-20 010-03   NCh2313/25.Of97. Aluminio total (Al)  0.164
#> 4 2020  EA-SMA-02-20 011-01   NCh2313/25.Of97. Aluminio total (Al)  0.034
#> 5 2020  EA-SMA-02-20 021-01   NCh2313/25.Of97. Aluminio total (Al)  0.05 
#> 6 2020  EA-SMA-02-20 021-03   NCh2313/25.Of97. Aluminio total (Al)  0.005

fulljoin<-full_join(LCM_QAR,DS90,by="Parametro")
#> Error in full_join(LCM_QAR, DS90, by = "Parametro"): objeto 'LCM_QAR' no encontrado

datapasta::dpasta(head(fulljoin))
#> Error in head(fulljoin): objeto 'fulljoin' no encontrado
tibble::tribble(
    ~Año,        ~Cod_EA, ~Cod_ETFA,            ~Metodo,            ~Parametro,  ~LCM, ~Tabla.1, ~Tabla.2, ~Tabla.3, ~Tabla.4, ~Tabla.5,
  "2020", "EA-SMA-02-20",  "010-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.09,       NA,       NA,       NA,       NA,       NA,
  "2020", "EA-SMA-02-20",  "016-01",                 NA, "Aluminio total (Al)",    NA,       NA,       NA,       NA,       NA,       NA,
  "2020", "EA-SMA-02-20",  "010-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.164,       NA,       NA,       NA,       NA,       NA,
  "2020", "EA-SMA-02-20",  "011-01", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.034,       NA,       NA,       NA,       NA,       NA,
  "2020", "EA-SMA-02-20",  "021-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.05,       NA,       NA,       NA,       NA,       NA,
  "2020", "EA-SMA-02-20",  "021-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.005,       NA,       NA,       NA,       NA,       NA
  )
#> # A tibble: 6 x 11
#>   Año   Cod_EA Cod_ETFA Metodo Parametro    LCM Tabla.1 Tabla.2 Tabla.3 Tabla.4
#>   <chr> <chr>  <chr>    <chr>  <chr>      <dbl> <lgl>   <lgl>   <lgl>   <lgl>  
#> 1 2020  EA-SM~ 010-01   NCh23~ Aluminio~  0.09  NA      NA      NA      NA     
#> 2 2020  EA-SM~ 016-01   <NA>   Aluminio~ NA     NA      NA      NA      NA     
#> 3 2020  EA-SM~ 010-03   NCh23~ Aluminio~  0.164 NA      NA      NA      NA     
#> 4 2020  EA-SM~ 011-01   NCh23~ Aluminio~  0.034 NA      NA      NA      NA     
#> 5 2020  EA-SM~ 021-01   NCh23~ Aluminio~  0.05  NA      NA      NA      NA     
#> 6 2020  EA-SM~ 021-03   NCh23~ Aluminio~  0.005 NA      NA      NA      NA     
#> # ... with 1 more variable: Tabla.5 <lgl>

^{Created on 2021-06-15 by the reprex package (v1.0.0)}

williaml · June 15, 2021, 11:28pm

Works for me. I get an 11 x 11 with your example data:

> full_join(LCM_QAR,DS90,by="Parametro")
# A tibble: 11 x 11
   Año   Cod_EA       Cod_ETFA Metodo           Parametro              LCM Tabla.1 Tabla.2 Tabla.3 Tabla.4 Tabla.5
   <chr> <chr>        <chr>    <chr>            <chr>                <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
 1 2020  EA-SMA-02-20 010-01   NCh2313/25.Of97. Aluminio total (Al)  0.09     5       10      1       1       10  
 2 2020  EA-SMA-02-20 016-01   NA               Aluminio total (Al) NA        5       10      1       1       10  
 3 2020  EA-SMA-02-20 010-03   NCh2313/25.Of97. Aluminio total (Al)  0.164    5       10      1       1       10  
 4 2020  EA-SMA-02-20 011-01   NCh2313/25.Of97. Aluminio total (Al)  0.034    5       10      1       1       10  
 5 2020  EA-SMA-02-20 021-01   NCh2313/25.Of97. Aluminio total (Al)  0.05     5       10      1       1       10  
 6 2020  EA-SMA-02-20 021-03   NCh2313/25.Of97. Aluminio total (Al)  0.005    5       10      1       1       10  
 7 NA    NA           NA       NA               Arsenico total (As) NA        0.5      1      0.1     0.2      0.5
 8 NA    NA           NA       NA               Cadmio total (Cd)   NA        0.01     0.3    0.02    0.02     0.5
 9 NA    NA           NA       NA               Cinc total (Zn)     NA        3       20      5       5        5  
10 NA    NA           NA       NA               Cobre total (Cu)    NA        1        3      0.1     1        3  
11 NA    NA           NA       NA               Cromo total (Cr)    NA       NA       NA      2.5     2.5     10

Lekmonm · June 16, 2021, 3:28pm

Excellent, but not for me:

jrkrideau · June 16, 2021, 8:11pm

Hi @ Lekmonm

I tried your data a code and got the same results that @ williaml did.

It may be samething specific to your machine. This sounds stupid but try closing Rstudio and restarting. Or even better completely shut down the computer. Three or four times in the last 5 years I have gotten anomalous results and a shutdown and reboot has cured the problem.

Lekmonm · June 16, 2021, 9:10pm

I did all that (I closed RStudio; I restarted my computer and shut down the computer) and it's still all the same. Thanks anyway.

jrkrideau · June 16, 2021, 11:13pm

Sorry, it was a long shot but has worked for me and at least one other user I know.

nirgrahamuk · June 17, 2021, 12:08pm

It may be that the examples you provided do not reflect your data 'well enough'.

I recommend that you verify what happens when you run the reprex/example code that you provided to us... and see if that does or does not work as you intended.
I'll strip out the uneeded comments and references to datapasta, and make it actually shareable/runnable...

library(tidyverse)

DS90 <- tibble::tribble(
  ~Parametro, ~Tabla.1, ~Tabla.2, ~Tabla.3, ~Tabla.4, ~Tabla.5,
  "Aluminio total (Al)",        5,       10,        1,        1,       10,
  "Arsenico total (As)",      0.5,        1,      0.1,      0.2,      0.5,
  "Cadmio total (Cd)",     0.01,      0.3,     0.02,     0.02,      0.5,
  "Cinc total (Zn)",        3,       20,        5,        5,        5,
  "Cobre total (Cu)",        1,        3,      0.1,        1,        3,
  "Cromo total (Cr)",       NA,       NA,      2.5,      2.5,       10
)

LCM_QAR <- tibble::tribble(
  ~Año,        ~Cod_EA, ~Cod_ETFA,            ~Metodo,            ~Parametro,  ~LCM,
  "2020", "EA-SMA-02-20",  "010-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.09,
  "2020", "EA-SMA-02-20",  "016-01",                 NA, "Aluminio total (Al)",    NA,
  "2020", "EA-SMA-02-20",  "010-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.164,
  "2020", "EA-SMA-02-20",  "011-01", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.034,
  "2020", "EA-SMA-02-20",  "021-01", "NCh2313/25.Of97.", "Aluminio total (Al)",  0.05,
  "2020", "EA-SMA-02-20",  "021-03", "NCh2313/25.Of97.", "Aluminio total (Al)", 0.005
)

fulljoin<-full_join(LCM_QAR,DS90,by="Parametro")

system · July 8, 2021, 12:09pm

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.