export_table with gt? flextable? other?

[mattansb]

This is very easy to implement:

library(bayestestR)
#> Note: The default CI width (currently `ci=0.89`) might change in future versions (see https://github.com/easystats/bayestestR/issues/250). To prevent any issues, please set it explicitly when using bayestestR functions, via the 'ci' argument.
library(magrittr)
library(report)
#> report is in alpha - help us improve by reporting bugs on github.com/easystats/report/issues
library(insight)

lm1 <- lm(Sepal.Length ~ 1, data = iris)
lm2 <- lm(Sepal.Length ~ Species, data = iris)
lm3 <- lm(Sepal.Length ~ Species + Petal.Length, data = iris)
lm4 <- lm(Sepal.Length ~ Species * Petal.Length, data = iris)


t <- bayesfactor_models(lm1, lm2, lm3, lm4, denominator = 1) %>% 
  report_table() %>% 
  format()

attr(t, "table_caption") <- "Bayesian Model Comparison"
attr(t, "table_subtitle") <- "\nSome more words..."

cat(export_table(t))
#> Bayesian Model Comparison 
#> Some more words...
#> 
#> Model                      | BF against model 1 | BF against model 3 (best model)
#> ---------------------------------------------------------------------------------
#> [1] (Intercept only)       |               1.00 |                      1/5.84e+55
#> [2] Species                |           1.70e+29 |                      1/3.45e+26
#> [3] Species + Petal.Length |           5.84e+55 |                            1.00
#> [4] Species * Petal.Length |           2.20e+54 |                         1/26.52
#> 
#> Bayes Factor Type: BIC approximation
#> Against denominator: Model 1

export_table(t, format = "markdown")

Bayesian Model Comparison Some more words…

Model	BF against model 1	BF against model 3 (best model)
[1] (Intercept only)	1.00	1/5.84e+55
[2] Species	1.70e+29	1/3.45e+26
[3] Species + Petal.Length	5.84e+55	1.00
[4] Species * Petal.Length	2.20e+54	1/26.52

Bayesian Model Comparison
Some more words…

Bayes Factor Type: BIC approximation

library(gt)
gt(t) %>% 
  tab_header(
    title = attr(t, "table_caption"),
    subtitle = attr(t, "table_subtitle")
  ) %>% 
  tab_source_note(attr(t, "table_footer"))

[strengejacke]

I think we can discuss some pros and cons here, @mattansb @DominiqueMakowski @IndrajeetPatil and others? There are a lot of other packages, and I think I also mentioned flextable sometime, somewhere...

@mattansb Does your example render to markdown, or PDF/HTML?

[mattansb]

Isn't that what format argument does?

[strengejacke]

No, format() actually call insight::parameters_table(), to create these fancy CI-columns, add pretty names as parameter names, etc. - and maybe some other preparation like adding title/caption/footer attributes. format() just returns a "plain" data frame.

However, the style of table "syntax" is done in export_table() (like plain text, or these :--- for markdown table lines etc. export_table() create the character vector with markdown syntax, HTML syntax...

[mattansb]

I meant the format argument in export_table() (:

[strengejacke]

Ok, got it.

Isn't that what format argument does?

No, that is what I meant. format tells the function whether to use plain text, markdown, html, ... but not, which package to use to create the table string in markdown, html, ... So either, we decide now for a package, or we need to include the "engine", e.g. format = "html_gt" or format = "html_flextable".

[mattansb]

Okay, now I understand. I like the latter option more...

[strengejacke]

This is very easy to implement:

The question is, will it remain that easy for more complex models?

library(insight)
library(parameters)
m <- download_model("brms_zi_2")
mp <- model_parameters(m, effects = "all", component = "all")
print_md(mp)

# Fixed effects (conditional)

Parameter	Median	CI	pd	% in ROPE	Rhat	ESS
(Intercept)	-0.86	(-1.37, -0.34)	98.22%	1.30%	1.002	1003
persons	0.84	(0.68, 1.01)	100%	0%	1.002	878
child	-1.15	(-1.29, -1.00)	100%	0%	1.001	2166
camper	0.73	(0.58, 0.89)	100%	0%	1.000	3528

# Fixed effects (zero-inflated)

Parameter	Median	CI	pd	% in ROPE	Rhat	ESS
(Intercept)	-0.65	(-1.82, 0.47)	83.17%	7.80%	1.000	1174
child	1.86	(1.37, 2.42)	100%	0%	1.002	3022
camper	-0.84	(-1.40, -0.24)	98.95%	1.68%	1.000	3410

# Random effects (conditional) SD/Cor: persons

Parameter	Median	CI	pd	% in ROPE	Rhat	ESS
(Intercept)	0.12	(1.65e-04, 0.39)	100%	45.27%	1.005	819

# Random effects (zero-inflated) SD/Cor: persons

Parameter	Median	CI	pd	% in ROPE	Rhat	ESS
(Intercept)	1.32	(0.48, 2.49)	100%	0%	1.004	1331

^{Created on 2020-12-11 by the reprex package (v0.3.0)}

So, how to either a) insert "header rows", or b) append multiple table objects? I just mean how to do this in gt(), the implementation in export_table() should be easy.

[mattansb]

library(insight)
library(parameters)
m <- download_model("brms_zi_2")
mp <- model_parameters(m, effects = "all", component = "all")

library(gt)

mp %>% 
  dplyr::group_by(Component, Effects) %>% 
  gt()

(Couldn't copy the whole thing... But you get the idea)

[strengejacke]

Ok, there's a groupname_col-argument that does the trick:

library(insight)
library(parameters)
m <- download_model("brms_zi_2")
mp <- model_parameters(m, effects = "all", component = "all")

library(gt)
gt(mp, groupname_col = c("Effects", "Component"))

[strengejacke]

OMG, @strengejacke

Yes...

https://rpubs.com/sjPlot/export_table

[strengejacke]

`export_table(format = "html") needs some improvements, though:

• use table title for html
• currently, subtables are split by columns Response, Effects and Component - we may add an argument here for user-defined split-columns.

[mattansb]

Awesome!!

currently, subtables are split by columns Response, Effects and Component - we may add an argument here for user-defined split-columns.

Shouldn't group also be included?

df <- iris
df$Sepal.Big <- ifelse(df$Sepal.Width >= 3, "Yes", "No")

model <- aov(Sepal.Length ~ Sepal.Big + Error(Species), data = df)

parameters::model_parameters(model)
#> # Species
#> 
#> Parameter | Sum_Squares | df | Mean_Square |    F |     p
#> ---------------------------------------------------------
#> Sepal.Big |       28.27 |  1 |       28.27 | 0.81 | 0.534
#> Residuals |       34.94 |  1 |       34.94 |      |      
#> 
#> # Within
#> 
#> Parameter | Sum_Squares |  df | Mean_Square |     F |      p
#> ------------------------------------------------------------
#> Sepal.Big |        4.74 |   1 |        4.74 | 20.24 | < .001
#> Residuals |       34.21 | 146 |        0.23 |       |

^{Created on 2020-12-13 by the reprex package (v0.3.0)}