возможно мурлыканье по ступенчатой ​​регрессии на всех комбинациях XY

Question

Вот код, в котором я запускаю пошаговую регрессию для всех возможных комбинаций x и y.

library(tidyverse)

ys <- names(mtcars)

xs <- map(ys, ~setdiff(names(mtcars), .x)) %>% 
  map(~paste0(.x, collapse = "+")) %>%
  unlist()

models <- tibble(ys, xs) %>%
  mutate(startformula = paste0(ys, " ~ ", 1),
         endformula = paste0(ys, " ~ ", xs)) %>% 
  mutate(model = map2(startformula, endformula, ~possibly(glm(.x, data=mtcars, family=gaussian, maxit = 100) %>% step(direction = "forward", scope = .y, trace = FALSE), otherwise = NA))) %>% 
  mutate(pred = map(model, augment))

Когда я не использую, возможно, я получаю ошибку:

Evaluation error: No augment method for objects of class logical.

Чтобы избежать этого, когда я использую возможно, я получаю ошибку:

Evaluation error: Can't convert a `glm` object to function

Чего мне здесь не хватает?

Answer 1

Вот мой код, который, кажется, работает, используя library(broom)

library(tidyverse)
library(broom)

ys <- names(mtcars)

xs <- map(ys, ~setdiff(names(mtcars), .x)) %>% 
  map(~paste0(.x, collapse = "+")) %>%
  unlist()

models <- tibble(ys, xs) %>%
  mutate(startformula = paste0(ys, " ~ ", 1),
         endformula = paste0(ys, " ~ ", xs)) %>% 
  mutate(model = map2(startformula,
                      endformula,
                      ~glm(.x, data=mtcars, family=gaussian, maxit = 100) %>% 
                        step(direction = "forward", scope = .y, trace = FALSE), otherwise = NA)) %>% 
  mutate(pred = map(model, augment))

> models

 A tibble: 11 x 6
      ys                                        xs startformula                                     endformula     model                   pred
   <chr>                                     <chr>        <chr>                                          <chr>    <list>                 <list>
 1   mpg  cyl+disp+hp+drat+wt+qsec+vs+am+gear+carb      mpg ~ 1 mpg ~ cyl+disp+hp+drat+wt+qsec+vs+am+gear+carb <S3: glm> <data.frame [32 x 12]>
 2   cyl  mpg+disp+hp+drat+wt+qsec+vs+am+gear+carb      cyl ~ 1 cyl ~ mpg+disp+hp+drat+wt+qsec+vs+am+gear+carb <S3: glm> <data.frame [32 x 17]>
 3  disp   mpg+cyl+hp+drat+wt+qsec+vs+am+gear+carb     disp ~ 1 disp ~ mpg+cyl+hp+drat+wt+qsec+vs+am+gear+carb <S3: glm> <data.frame [32 x 14]>
 4    hp mpg+cyl+disp+drat+wt+qsec+vs+am+gear+carb       hp ~ 1 hp ~ mpg+cyl+disp+drat+wt+qsec+vs+am+gear+carb <S3: glm> <data.frame [32 x 13]>
...

информация о сеансе:

> sessionInfo()
R version 3.4.4 (2018-03-15)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 18.04.1 LTS

Matrix products: default
BLAS: /usr/lib/x86_64-linux-gnu/openblas/libblas.so.3
LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8     LC_MONETARY=en_US.UTF-8   
 [6] LC_MESSAGES=en_US.UTF-8    LC_PAPER=en_US.UTF-8       LC_NAME=C                  LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] broom_0.4.2     bindrcpp_0.2    forcats_0.2.0   stringr_1.2.0   dplyr_0.7.4     purrr_0.2.4     readr_1.1.1     tidyr_0.7.2    
 [9] tibble_1.3.4    ggplot2_2.2.1   tidyverse_1.2.1