Beautiful Tables

We are going to reproduce some of the tables of this paper Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs https://doi.org/10.1371/journal.pone.0140464

# install.packages("gt")
library(gt)
library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.0     ✔ readr     2.1.6
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.2     ✔ tibble    3.3.1
✔ lubridate 1.9.4     ✔ tidyr     1.3.2
✔ purrr     1.2.1     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Load the data

data <- read.csv("data/Adamczyk_PLOSdata.csv")

Have a look at the data

data |> glimpse()

Rows: 150
Columns: 24
$ year                                <int> 2013, 2013, 2013, 2013, 2013, 2013…
$ month                               <int> 6, 6, 6, 7, 7, 7, 7, 7, 7, 7, 7, 7…
$ day                                 <int> 26, 26, 26, 3, 3, 3, 10, 10, 10, 1…
$ julian_date                         <int> 13177, 13177, 13177, 13184, 13184,…
$ sampling_date                       <int> 1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4…
$ lake                                <chr> "Murray", "Miramar", "Poway", "Mur…
$ h2o_temp_c                          <dbl> 26.11111, 24.44444, 25.55556, 25.8…
$ air_temp_c                          <dbl> 27.22222, 30.50000, 32.38889, 24.1…
$ wind_speed_kph                      <dbl> 6.437376, 9.656064, 6.437376, 10.4…
$ ph                                  <dbl> 8.85, 8.35, 8.99, 8.78, 8.45, 9.10…
$ total_alkalinity_ppm                <int> 196, 203, 172, 261, 271, 240, 91, …
$ chlorophyll_a_ugL                   <dbl> 4.30, 2.54, 1.03, 5.10, 2.29, 2.01…
$ salinity_ppt                        <dbl> 0.3796530, 0.3787916, 0.3497159, 0…
$ pco2_water_ppm                      <dbl> 173.438, 582.045, 106.694, 273.342…
$ bacteria_number_per_L               <int> NA, 14204, 18078, 10330, 18078, 14…
$ total_nitrogen_mgL                  <dbl> 3.170, 2.530, 1.630, 3.620, 3.120,…
$ total_phosphorus._mgL               <dbl> 0.01720, 0.00837, 0.00868, 0.02150…
$ dissolved_organic_carbon_mgL        <dbl> 4.450445, 2.726669, 3.482022, 5.21…
$ particulate_organic_nitrogen_mgL    <dbl> 0.06960000, NA, 0.02266667, 0.0696…
$ particulate_organic_carbon_mgL      <dbl> 0.30894545, NA, 0.07393939, 0.3427…
$ co2_flux_mmol_m_day                 <dbl> -2.039, 3.738, -2.646, -2.987, 6.5…
$ pco2_atmosphere_ppm                 <dbl> 399.06, 399.06, 399.06, NA, NA, NA…
$ zooplankton_community_avg_legnth_mm <dbl> 0.2245817, 0.7466187, 0.8807347, 0…
$ zooplankton_community_biomass_mgL   <dbl> 0.9987292, 4.9275362, 9.3057214, 3…

Let’s have a look at the first rows of our dataset

data |> head() |> gt()

year	month	day	julian_date	sampling_date	lake	h2o_temp_c	air_temp_c	wind_speed_kph	ph	total_alkalinity_ppm	chlorophyll_a_ugL	salinity_ppt	pco2_water_ppm	bacteria_number_per_L	total_nitrogen_mgL	total_phosphorus._mgL	dissolved_organic_carbon_mgL	particulate_organic_nitrogen_mgL	particulate_organic_carbon_mgL	co2_flux_mmol_m_day	pco2_atmosphere_ppm	zooplankton_community_avg_legnth_mm	zooplankton_community_biomass_mgL
2013	6	26	13177	1	Murray	26.11111	27.22222	6.437376	8.85	196	4.30	0.3796530	173.438	NA	3.17	0.01720	4.450445	0.06960000	0.30894545	-2.039	399.06	0.2245817	0.9987292
2013	6	26	13177	1	Miramar	24.44444	30.50000	9.656064	8.35	203	2.54	0.3787916	582.045	14204	2.53	0.00837	2.726669	NA	NA	3.738	399.06	0.7466187	4.9275362
2013	6	26	13177	1	Poway	25.55556	32.38889	6.437376	8.99	172	1.03	0.3497159	106.694	18078	1.63	0.00868	3.482022	0.02266667	0.07393939	-2.646	399.06	0.8807347	9.3057214
2013	7	3	13184	2	Murray	25.83333	24.16667	10.460736	8.78	261	5.10	0.2849283	273.342	10330	3.62	0.02150	5.212524	0.06964706	0.34271658	-2.987	NA	0.3035989	3.4809318
2013	7	3	13184	2	Miramar	26.94444	25.22222	11.265408	8.45	271	2.29	0.1741368	635.311	18078	3.12	0.02190	3.404073	0.03226667	0.25940606	6.549	NA	0.5070355	4.7456874
2013	7	3	13184	2	Poway	22.11111	27.16667	0.804672	9.10	240	2.01	0.3805866	108.509	14204	2.53	0.02830	5.087733	0.01880000	0.16833939	-0.042	NA	0.5773348	3.2551055

Now let’s create a summary table of the average air temperature for each basin

data_air <- temp_basin <- data |>
  select(year, lake, air_temp_c) |>
  group_by(year, lake) |>
    summarise(average_air_temp = mean(air_temp_c))

`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by year and lake.
ℹ Output is grouped by year.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(year, lake))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.

data_air

# A tibble: 6 × 3
# Groups:   year [2]
   year lake    average_air_temp
  <int> <chr>              <dbl>
1  2013 Miramar             24.9
2  2013 Murray              24.4
3  2013 Poway               27.4
4  2014 Miramar             20.6
5  2014 Murray              21.1
6  2014 Poway               20.9

Now let’s make this a nice table

gt_air <-
  data_air |>
  gt() |>
  tab_header(
    title = "Average air temperature (C) per lake and year",
    subtitle = "major reservoirs in San Diego County"
  )

# Show the gt Table
gt_air

lake	average_air_temp
Average air temperature (C) per lake and year
major reservoirs in San Diego County
2013
Miramar	24.92844
Murray	24.35022
Poway	27.36000
2014
Miramar	20.55600
Murray	21.10280
Poway	20.87200

Add reference

gt_air <-
  data_air |>
  gt() |>
  tab_header(
    title = "Average air temperature (C) per lake and year",
    subtitle = "major reservoirs in San Diego County"
  ) |>
 tab_source_note(
    source_note = md("Source: _Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464_")
  )

# Show the gt Table
gt_air

lake	average_air_temp
Average air temperature (C) per lake and year
major reservoirs in San Diego County
2013
Miramar	24.92844
Murray	24.35022
Poway	27.36000
2014
Miramar	20.55600
Murray	21.10280
Poway	20.87200
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

With more measurements

data_measurements <- temp_basin <- data |>
  select(year, lake, air_temp_c, pco2_atmosphere_ppm, h2o_temp_c, ph, pco2_water_ppm) |>
  group_by(year, lake) |>
    summarise(avg_air_temp = mean(air_temp_c),
              avg_pco2_atmosphere_ppm = mean(pco2_atmosphere_ppm, na.rm=TRUE),
              avg_h2o_temp_c = mean(h2o_temp_c, na.rm=TRUE),
              avg_ph = mean(ph, na.rm=TRUE),
              avg_pco2_water_ppm = mean(pco2_water_ppm, na.rm=TRUE)
    )

`summarise()` has regrouped the output.
ℹ Summaries were computed grouped by year and lake.
ℹ Output is grouped by year.
ℹ Use `summarise(.groups = "drop_last")` to silence this message.
ℹ Use `summarise(.by = c(year, lake))` for per-operation grouping
  (`?dplyr::dplyr_by`) instead.

Add title and Footnote

gt_measurements <-
  data_measurements |>
  gt() |>
  tab_header(
    title = "Average measurements per lake and year",
    subtitle = "major reservoirs in San Diego County"
  ) |>
 tab_source_note(
    source_note = md("Source: _Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464_")
  )

# Show the gt Table
gt_measurements

lake	avg_air_temp	avg_pco2_atmosphere_ppm	avg_h2o_temp_c	avg_ph	avg_pco2_water_ppm
Average measurements per lake and year
major reservoirs in San Diego County
2013
Miramar	24.92844	395.0941	23.94800	8.4264	353.8672
Murray	24.35022	395.0905	23.47222	8.6096	218.0030
Poway	27.36000	395.1236	23.34178	8.7964	126.2890
2014
Miramar	20.55600	399.6909	19.46750	8.2524	335.5639
Murray	21.10280	399.6973	20.25739	8.4504	245.7339
Poway	20.87200	399.7452	19.07800	8.5016	172.2162
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

Adding headers for multiple columns

gt_measurements <-
  data_measurements |>
  gt() |>
  tab_header(
    title = "Average measurements per lake and year",
    subtitle = "major reservoirs in San Diego County"
  ) |>
 tab_source_note(
    source_note = md("Source: _Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464_")
  ) |>
  tab_spanner(
    label = "Air",
    columns = c(avg_air_temp, avg_pco2_atmosphere_ppm)
  ) |>
  tab_spanner(
    label = "Water",
    columns = c(avg_h2o_temp_c, avg_ph, avg_pco2_water_ppm)
  )


# Show the gt Table
gt_measurements

lake	Air		Water
Average measurements per lake and year
major reservoirs in San Diego County
lake	avg_air_temp	avg_pco2_atmosphere_ppm	avg_h2o_temp_c	avg_ph	avg_pco2_water_ppm
2013
Miramar	24.92844	395.0941	23.94800	8.4264	353.8672
Murray	24.35022	395.0905	23.47222	8.6096	218.0030
Poway	27.36000	395.1236	23.34178	8.7964	126.2890
2014
Miramar	20.55600	399.6909	19.46750	8.2524	335.5639
Murray	21.10280	399.6973	20.25739	8.4504	245.7339
Poway	20.87200	399.7452	19.07800	8.5016	172.2162
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

More styling on sub headers

gt_measurements <-
  data_measurements |>
  gt() |>
  tab_header(
    title = "Average measurements per lake and year",
    subtitle = "major reservoirs in San Diego County"
  ) |>
 tab_source_note(
    source_note = md("Source: _Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464_")
  ) |>
  tab_spanner(
    label = md("**Air**"),
    columns = c(avg_air_temp, avg_pco2_atmosphere_ppm)
  ) |>
  tab_spanner(
    label = md("**Water**"),
    columns = c(avg_h2o_temp_c, avg_ph, avg_pco2_water_ppm)
  )


# Show the gt Table
gt_measurements

lake	Air		Water
Average measurements per lake and year
major reservoirs in San Diego County
lake	avg_air_temp	avg_pco2_atmosphere_ppm	avg_h2o_temp_c	avg_ph	avg_pco2_water_ppm
2013
Miramar	24.92844	395.0941	23.94800	8.4264	353.8672
Murray	24.35022	395.0905	23.47222	8.6096	218.0030
Poway	27.36000	395.1236	23.34178	8.7964	126.2890
2014
Miramar	20.55600	399.6909	19.46750	8.2524	335.5639
Murray	21.10280	399.6973	20.25739	8.4504	245.7339
Poway	20.87200	399.7452	19.07800	8.5016	172.2162
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

Simplify the column names

gt_measurements  <- gt_measurements |> cols_label(
    avg_air_temp = "Temp (C)",
    avg_pco2_atmosphere_ppm = "pC02 (ppm)",
    avg_h2o_temp_c = "Temp (C)",
    avg_ph = 'pH',
    avg_pco2_water_ppm = "pC02 (ppm)"
  )

gt_measurements

lake	Air		Water
Average measurements per lake and year
major reservoirs in San Diego County
lake	Temp (C)	pC02 (ppm)	Temp (C)	pH	pC02 (ppm)
2013
Miramar	24.92844	395.0941	23.94800	8.4264	353.8672
Murray	24.35022	395.0905	23.47222	8.6096	218.0030
Poway	27.36000	395.1236	23.34178	8.7964	126.2890
2014
Miramar	20.55600	399.6909	19.46750	8.2524	335.5639
Murray	21.10280	399.6973	20.25739	8.4504	245.7339
Poway	20.87200	399.7452	19.07800	8.5016	172.2162
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

Limiting to 2 decimals

gt_measurements |>  fmt_number(
    columns = everything(),
    decimals = 2,
    use_seps = FALSE
  )

lake	Air		Water
Average measurements per lake and year
major reservoirs in San Diego County
lake	Temp (C)	pC02 (ppm)	Temp (C)	pH	pC02 (ppm)
2013
Miramar	24.93	395.09	23.95	8.43	353.87
Murray	24.35	395.09	23.47	8.61	218.00
Poway	27.36	395.12	23.34	8.80	126.29
2014
Miramar	20.56	399.69	19.47	8.25	335.56
Murray	21.10	399.70	20.26	8.45	245.73
Poway	20.87	399.75	19.08	8.50	172.22
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464

Styling

gt_measurements |> opt_stylize(style = 6, color = 'gray')

lake	Air		Water
Average measurements per lake and year
major reservoirs in San Diego County
lake	Temp (C)	pC02 (ppm)	Temp (C)	pH	pC02 (ppm)
2013
Miramar	24.92844	395.0941	23.94800	8.4264	353.8672
Murray	24.35022	395.0905	23.47222	8.6096	218.0030
Poway	27.36000	395.1236	23.34178	8.7964	126.2890
2014
Miramar	20.55600	399.6909	19.46750	8.2524	335.5639
Murray	21.10280	399.6973	20.25739	8.4504	245.7339
Poway	20.87200	399.7452	19.07800	8.5016	172.2162
Source: Adamczyk EM, Shurin JB (2015) Seasonal Changes in Plankton Food Web Structure and Carbon Dioxide Flux from Southern California Reservoirs. PLoS ONE 10(10): e0140464. https://doi.org/10.1371/journal.pone.0140464