What is this?

GT package is one of the most amazing package to create tables, and we want to show a gallery of examples with full R code to encourage you to use it in your projects.

• How to start with GT Tables
• How to customize a basic table
• Examples about how to use

How to create a good table?

An informal definition could be: “A good table is used to read a set of numerical data in the quickest and easiest way”

1. Vertical table

library(gt)
library(tidyverse)

Warning: package 'tibble' was built under R version 3.5.2

Warning: package 'tidyr' was built under R version 3.5.2

Warning: package 'purrr' was built under R version 3.5.2

Warning: package 'dplyr' was built under R version 3.5.2

Warning: package 'stringr' was built under R version 3.5.2

Warning: package 'forcats' was built under R version 3.5.2

library(glue)

# Define the start and end dates for the data range
start_date <- "2010-06-07"
end_date <- "2010-06-14"

# Create a gt table based on preprocessed
# `sp500` table data
sp500 %>%
  dplyr::filter(date >= start_date & date <= end_date) %>%
  dplyr::select(-adj_close) %>%
  dplyr::mutate(date = as.character(date)) %>%
  gt() %>%
  tab_header(
    title = "S&P 500",
    subtitle = glue::glue("{start_date} to {end_date}")
  ) %>%
  fmt_date(
    columns = vars(date),
    date_style = 3
  ) %>%
  fmt_currency(
    columns = vars(open, high, low, close),
    currency = "USD"
  ) %>%
  fmt_number(
    columns = vars(volume),
    scale_by = 1 / 1E9,
    pattern = "{x}B"
  )

2. Horizontal Table

3. Table with references

This example is from Table 1 From proceedings of the Workshop on Language in Social Media (LSM 2011), pages 30–38, Portland, Oregon, 23 June 2011. (c) 2011 Association for Computational Linguistics

# the table's data
exa <- data.frame( acronym = c("gr8, gr8t", "lol", "rotf", "bff"),
                  english = c("great","laughing out loud", "rolling on the floor", "best friend forever"))

# create the gt table
gt(exa) %>%
  cols_align("left") %>%
  cols_label(acronym="Acronym",
             english="English expansion") %>%
  tab_source_note(
    source_note = "Table 1: Example acrynom and their expansion in the acronym dictionary."
  )

3. Table with spanning columns

This example is Table S2 in Broman et al. (2015) Genetics 192:267-279 doi:10.1534/genetics.112.142448

# the table's data
tab <- data.frame(n=c(300, 450, 600),
                  all_part_all_crosses = c(4.56, 4.51, 4.49),
                  all_part_min_crosses = c(4.48, 4.47, 4.44),
                  tree_part_all_crosses = c(4.43, 4.36, 4.32),
                  tree_part_min_crosses = c(4.33, 4.33, 4.29))

# create the gt table
gt(tab) %>%
    cols_align("center") %>%
    cols_label(n="total sample size",
               all_part_all_crosses="all crosses",
               all_part_min_crosses="min crosses",
               tree_part_all_crosses="all crosses",
               tree_part_min_crosses="min crosses") %>%
    tab_spanner(label="Tree partitions",
                starts_with("tree")) %>%
    tab_spanner(label="All partitions",
                starts_with("all"))

4. Counts and percentages

This example is Table S2 of Lobo et al. bioRxiv doi:10.1101/529040, with columns containing both counts and percentages, with the percentages in parentheses.

tab <- data.frame(A_count = c(8863572, 2870063, 671722),
                  A_proportion=c(0.853601028762177, 0.727484285290261, 0.556184650236973),
                  B_count = c(1520169, 1075126, 536010),
                  B_proportion=c(0.146398971237823, 0.272515714709739, 0.443815349763027),
                  row.names=c("AA", "AB", "BB"))
tab$genotype <- rownames(tab)

gt(tab, rowname_col="genotype") %>%
    fmt_percent(ends_with("proportion"),
                decimals=1,
                pattern="({x})") %>%
    cols_align("center") %>%
    cols_align("right", columns=ends_with("count")) %>%
    cols_label(A_count = "A count",
               A_proportion = "(%)",
               B_count = "B count",
               B_proportion = "(%)") %>%
    tab_spanner(label="allele in DO-360 microbiome",
                columns=TRUE) %>%
    tab_stubhead_label("DO-360 genotype")

5. Counts and percentages, with an extra column.

This example is Table S4 of Lobo et al. bioRxiv doi:10.1101/529040. It is much like example 5, but has an additional column at the beginning.

tab <- data.frame(DO358_genotype = c("AA", "AA", "AA", "AB", "AB", "AB", "BB", "BB", "BB"),
                  DO344_genotype = c("AA", "AB", "BB", "AA", "AB", "BB", "AA", "AB", "BB"),
                  A_count = c(2394215, 869613, 103036, 686970, 297500, 55982, 73727, 47000, 542),
                  A_proportion = c(0.99747944497795, 0.794823306181542, 0.590911176362635,
                                   0.718274560155246, 0.51429835873996, 0.299220173924198,
                                   0.428685226532701, 0.219100940269354, 0.00457986885689177),
                   B_count = c(6050, 224483, 71332, 269447, 280958, 131111, 98257, 167513, 117802),
                   B_proportion = c(0.00252055502204965, 0.205176693818458, 0.409088823637365,
                                    0.281725439844754, 0.48570164126004, 0.700779826075802,
                                    0.571314773467299, 0.780899059730646, 0.995420131143108),
                   stringsAsFactors=FALSE)

gt(tab) %>%
    fmt_percent(ends_with("proportion"),
                decimals=1,
                pattern="({x})") %>%
    cols_align("right") %>%
    cols_align("center", columns=ends_with("genotype")) %>%
    cols_label(DO358_genotype="DO 358 genotype",
               DO344_genotype="DO 344 genotype",
               A_count = "A count",
               A_proportion = "(%)",
               B_count = "B count",
               B_proportion = "(%)") %>%
    tab_spanner(label="allele in DO-358 microbiome",
                columns=matches("^[AB]_"))

6. Adding colors from Viridis palette

This example is using the dataset gtcars included into gt package and Viridis palette.

library(tidyverse) 
library(viridis)
library(scales)
library(gt) 

#selecting the data
exa2 <- gtcars %>% 
  select(mfr, hp) %>% 
  group_by(mfr) %>% 
  summarise(mean(hp))

#choosing colors
q_colors =  19 
v_colors =  viridis(q_colors, option ="D")

#creating table
gt(exa2) %>% 
  data_color(columns=vars("mean(hp)"), 
             color=scales::col_bin( bins=c(100, 200, 300, 400, 500, 600,700), 
             palette = v_colors, 
             domain=c(0, 700)) ) 

7. Table of coefficients

For a table of estimated regression coefficients from the fit of a linear model, you might first want to use the broom package to tidy the output.

lm_out <- lm(Volume ~ Height * Girth, data=trees)
broom::tidy(lm_out) %>%
    gt(rowname_col="term") %>%
    tab_stubhead_label("term") %>%
    fmt_number(column=matches("^[^p]"), decimals=2) %>%
    fmt_number(column=matches("^p"), decimals=6) %>%
    cols_label(std.error="SE",
               statistic="t stat")

8. Compare of fit of multiple model

To compare the fit of multiple models, you may be interested in the gt summary package. For example, here is a comparison of the fit of a linear model with and without an interaction term.

lm_add <- lm(Volume ~ Height + Girth, data=trees)
lm_int <- lm(Volume ~ Height * Girth, data=trees)
list(add=lm_add, int=lm_int) %>%
    gtsummary::gtsummary(statistic="conf.int") %>%
    cols_label(add="Additive",
               int="Interactive")

Session information

sessionInfo()

R version 3.5.1 (2018-07-02)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: OS X El Capitan 10.11.6

Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRlapack.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

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

other attached packages:
 [1] scales_1.0.0      viridis_0.5.1     viridisLite_0.3.0
 [4] glue_1.3.0        forcats_0.4.0     stringr_1.4.0    
 [7] dplyr_0.8.0.1     purrr_0.3.1       readr_1.3.1      
[10] tidyr_0.8.3       tibble_2.0.1      ggplot2_3.1.0    
[13] tidyverse_1.2.1   gt_0.1.0         

loaded via a namespace (and not attached):
 [1] tidyselect_0.2.5     xfun_0.5             gtsummary_0.0.0.9000
 [4] haven_2.1.0          lattice_0.20-38      colorspace_1.4-0    
 [7] generics_0.0.2       htmltools_0.3.6      yaml_2.2.0          
[10] rlang_0.3.1          pillar_1.3.1         withr_2.1.2         
[13] modelr_0.1.4         readxl_1.3.0         plyr_1.8.4          
[16] munsell_0.5.0        commonmark_1.7       gtable_0.2.0        
[19] workflowr_1.2.0      cellranger_1.1.0     rvest_0.3.2         
[22] evaluate_0.13        knitr_1.22           broom_0.5.1         
[25] Rcpp_1.0.0           backports_1.1.3      checkmate_1.9.1     
[28] jsonlite_1.6         fs_1.2.6             gridExtra_2.3       
[31] hms_0.4.2            digest_0.6.18        stringi_1.3.1       
[34] grid_3.5.1           rprojroot_1.3-2      cli_1.0.1           
[37] tools_3.5.1          magrittr_1.5         sass_0.1.0.9000     
[40] lazyeval_0.2.1       crayon_1.3.4         whisker_0.3-2       
[43] pkgconfig_2.0.2      xml2_1.2.0           lubridate_1.7.4     
[46] assertthat_0.2.0     rmarkdown_1.11       httr_1.4.0          
[49] rstudioapi_0.9.0     R6_2.4.0             nlme_3.1-137        
[52] git2r_0.24.0         compiler_3.5.1