Make augment.factanal() more robust. Fixes #604.

[IndrajeetPatil]

I have also updated the examples to reflect how specifying different scoring methods won't break any of the methods.

Here is a reprex:

set.seed(123)

# data
v1 <- c(1,1,1,1,1,1,1,1,1,1,3,3,3,3,3,4,5,6)
v2 <- c(1,2,1,1,1,1,2,1,2,1,3,4,3,3,3,4,6,5)
v3 <- c(3,3,3,3,3,1,1,1,1,1,1,1,1,1,1,5,4,6)
v4 <- c(3,3,4,3,3,1,1,2,1,1,1,1,2,1,1,5,6,4)
v5 <- c(1,1,1,1,1,3,3,3,3,3,1,1,1,1,1,6,4,5)
v6 <- c(1,1,1,2,1,3,3,3,4,3,1,1,1,2,1,6,5,4)
m1 <- cbind.data.frame(v1,v2,v3,v4,v5,v6)

# new data
m2 <-
  cbind.data.frame(
    x1 = rev(v1),
    x2 = rev(v2),
    x3 = rev(v3),
    x4 = rev(v4),
    x5 = rev(v5),
    x6 = rev(v6)
  )

# objects
x1 <- stats::factanal(m1, factors = 3, scores = "Bartlett")
x2 <- stats::factanal(m1, factors = 3, scores = "regression")

# tidying the object
broom::tidy(x1)
#> # A tibble: 6 x 5
#>   variable uniqueness   fl1   fl2   fl3
#>   <chr>         <dbl> <dbl> <dbl> <dbl>
#> 1 v1           0.005  0.944 0.182 0.267
#> 2 v2           0.101  0.905 0.235 0.159
#> 3 v3           0.005  0.236 0.210 0.946
#> 4 v4           0.224  0.180 0.242 0.828
#> 5 v5           0.0843 0.242 0.881 0.286
#> 6 v6           0.005  0.193 0.959 0.196
broom::tidy(x2)
#> # A tibble: 6 x 5
#>   variable uniqueness   fl1   fl2   fl3
#>   <chr>         <dbl> <dbl> <dbl> <dbl>
#> 1 v1           0.005  0.944 0.182 0.267
#> 2 v2           0.101  0.905 0.235 0.159
#> 3 v3           0.005  0.236 0.210 0.946
#> 4 v4           0.224  0.180 0.242 0.828
#> 5 v5           0.0843 0.242 0.881 0.286
#> 6 v6           0.005  0.193 0.959 0.196

# augmented dataframe
broom::augment(x1)
#> # A tibble: 18 x 4
#>    .rownames   .fs1   .fs2   .fs3
#>    <chr>      <dbl>  <dbl>  <dbl>
#>  1 1         -0.904 -0.931  0.948
#>  2 2         -0.869 -0.933  0.935
#>  3 3         -0.908 -0.932  0.962
#>  4 4         -1.00  -0.253  0.818
#>  5 5         -0.904 -0.931  0.948
#>  6 6         -0.745  0.727 -0.788
#>  7 7         -0.710  0.725 -0.801
#>  8 8         -0.750  0.726 -0.774
#>  9 9         -0.808  1.40  -0.930
#> 10 10        -0.745  0.727 -0.788
#> 11 11         0.927 -0.931 -0.837
#> 12 12         0.963 -0.933 -0.849
#> 13 13         0.923 -0.932 -0.823
#> 14 14         0.829 -0.253 -0.967
#> 15 15         0.927 -0.931 -0.837
#> 16 16         0.422  2.05   1.29 
#> 17 17         1.47   1.29   0.545
#> 18 18         1.88   0.309  1.95
broom::augment(x2)
#> # A tibble: 18 x 4
#>    .rownames   .fs1   .fs2   .fs3
#>    <chr>      <dbl>  <dbl>  <dbl>
#>  1 1         -0.897 -0.925  0.936
#>  2 2         -0.861 -0.927  0.924
#>  3 3         -0.901 -0.926  0.950
#>  4 4         -0.993 -0.251  0.809
#>  5 5         -0.897 -0.925  0.936
#>  6 6         -0.741  0.720 -0.784
#>  7 7         -0.706  0.718 -0.796
#>  8 8         -0.745  0.719 -0.770
#>  9 9         -0.803  1.39  -0.923
#> 10 10        -0.741  0.720 -0.784
#> 11 11         0.917 -0.925 -0.830
#> 12 12         0.952 -0.927 -0.842
#> 13 13         0.913 -0.926 -0.816
#> 14 14         0.820 -0.252 -0.958
#> 15 15         0.917 -0.925 -0.830
#> 16 16         0.426  2.04   1.28 
#> 17 17         1.46   1.29   0.548
#> 18 18         1.88   0.314  1.95

# augmented dataframe (with new data)
broom::augment(x1, data = m2)
#> # A tibble: 18 x 10
#>    .rownames    x1    x2    x3    x4    x5    x6   .fs1   .fs2   .fs3
#>    <chr>     <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>  <dbl>  <dbl>
#>  1 1             6     5     6     4     5     4 -0.904 -0.931  0.948
#>  2 2             5     6     4     6     4     5 -0.869 -0.933  0.935
#>  3 3             4     4     5     5     6     6 -0.908 -0.932  0.962
#>  4 4             3     3     1     1     1     1 -1.00  -0.253  0.818
#>  5 5             3     3     1     1     1     2 -0.904 -0.931  0.948
#>  6 6             3     3     1     2     1     1 -0.745  0.727 -0.788
#>  7 7             3     4     1     1     1     1 -0.710  0.725 -0.801
#>  8 8             3     3     1     1     1     1 -0.750  0.726 -0.774
#>  9 9             1     1     1     1     3     3 -0.808  1.40  -0.930
#> 10 10            1     2     1     1     3     4 -0.745  0.727 -0.788
#> 11 11            1     1     1     2     3     3  0.927 -0.931 -0.837
#> 12 12            1     2     1     1     3     3  0.963 -0.933 -0.849
#> 13 13            1     1     1     1     3     3  0.923 -0.932 -0.823
#> 14 14            1     1     3     3     1     1  0.829 -0.253 -0.967
#> 15 15            1     1     3     3     1     2  0.927 -0.931 -0.837
#> 16 16            1     1     3     4     1     1  0.422  2.05   1.29 
#> 17 17            1     2     3     3     1     1  1.47   1.29   0.545
#> 18 18            1     1     3     3     1     1  1.88   0.309  1.95
broom::augment(x2, data = m2)
#> # A tibble: 18 x 10
#>    .rownames    x1    x2    x3    x4    x5    x6   .fs1   .fs2   .fs3
#>    <chr>     <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>  <dbl>  <dbl>  <dbl>
#>  1 1             6     5     6     4     5     4 -0.897 -0.925  0.936
#>  2 2             5     6     4     6     4     5 -0.861 -0.927  0.924
#>  3 3             4     4     5     5     6     6 -0.901 -0.926  0.950
#>  4 4             3     3     1     1     1     1 -0.993 -0.251  0.809
#>  5 5             3     3     1     1     1     2 -0.897 -0.925  0.936
#>  6 6             3     3     1     2     1     1 -0.741  0.720 -0.784
#>  7 7             3     4     1     1     1     1 -0.706  0.718 -0.796
#>  8 8             3     3     1     1     1     1 -0.745  0.719 -0.770
#>  9 9             1     1     1     1     3     3 -0.803  1.39  -0.923
#> 10 10            1     2     1     1     3     4 -0.741  0.720 -0.784
#> 11 11            1     1     1     2     3     3  0.917 -0.925 -0.830
#> 12 12            1     2     1     1     3     3  0.952 -0.927 -0.842
#> 13 13            1     1     1     1     3     3  0.913 -0.926 -0.816
#> 14 14            1     1     3     3     1     1  0.820 -0.252 -0.958
#> 15 15            1     1     3     3     1     2  0.917 -0.925 -0.830
#> 16 16            1     1     3     4     1     1  0.426  2.04   1.28 
#> 17 17            1     2     3     3     1     1  1.46   1.29   0.548
#> 18 18            1     1     3     3     1     1  1.88   0.314  1.95

^{Created on 2019-03-10 by the reprex package (v0.2.1.9000)}

[alexpghayes]

This looks good. I believe the new column names are a breaking change from the previous factor1, ..., factorn. Can you:

• Add a note in NEWS about the breaking change in column names
• Add quick regression tests

[IndrajeetPatil]

@alexpghayes Done!

[alexpghayes]

Added some more thoughts

[IndrajeetPatil]

@alexpghayes Done!

[alexpghayes]

Added some more comments. Thanks for cranking all these out!

[IndrajeetPatil]

@alexpghayes All comments addressed.

[github-actions]

This pull request has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue.