White and Black Chess Ratings: A Distribution Analysis

How ratings vary between White and Black players across competitive chess matches

How chess ratings are distributed for White and Black players in competitive matches. Built in R.

Figure 1: The image displays two overlapping kernel density plots representing the distribution of chess player ratings for “White” and “Black” players. Both distributions peak around 1500 on the x-axis and range from 500 to 3000. The graph title is “White and Black Chess Ratings: A Distribution Analysis.”

Steps to Create this Graphic

1. Load Packages & Setup

```{r}
#| label: load

## 1. LOAD PACKAGES & SETUP ----
pacman::p_load(
  tidyverse,         # Easily Install and Load the 'Tidyverse'
  ggtext,            # Improved Text Rendering Support for 'ggplot2'
  showtext,          # Using Fonts More Easily in R Graphs
  janitor,           # Simple Tools for Examining and Cleaning Dirty Data
  skimr,             # Compact and Flexible Summaries of Data
  scales,            # Scale Functions for Visualization
  lubridate,         # Make Dealing with Dates a Little Easier
  glue,              # Interpreted String Literals
  ggfx               # Pixel Filters for 'ggplot2' and 'grid' # Pixel Filters for 'ggplot2' and 'grid' 
 )  

### |- figure size ---- 
camcorder::gg_record(
  dir    = here::here("temp_plots"),
  device = "png",
  width  =  7.5,
  height =  5,
  units  = "in",
  dpi    = 320
)

### |- resolution ----
showtext_opts(dpi = 320, regular.wt = 300, bold.wt = 800)
```

2. Read in the Data

```{r}
#| label: read

tt <-tidytuesdayR::tt_load(2024, week = 40) 

chess <- tt$chess |> clean_names() |> glimpse()

tidytuesdayR::readme(tt)
rm(tt)
```

3. Examing the Data

```{r}
#| label: examine

glimpse(chess)
skim(chess)
```

4. Tidy Data

```{r}
#| label: tidy

# Tidy
chess_data <- chess |>  
    select(white_rating, black_rating) |>
    pivot_longer(
        cols = c(white_rating, black_rating), 
        names_to = "player", 
        values_to = "rating") |>
    mutate(player = ifelse(player == "white_rating", "White", "Black"))

# Labels 
labels <- tibble(
    label = c("White", "Black"),
    player = c("White", "Black"),
    x = c(1600, 1600), 
    y = c(0.0001, 0.0001) 
)
```

5. Visualization Parameters

```{r}
#| label: params

### |- plot aesthetics ----
bkg_col      <- colorspace::lighten('#f7f5e9', 0.05)    
title_col    <- "gray20"           
subtitle_col <- "gray20"     
caption_col  <- "gray30"   
text_col     <- "gray20"    
col_palette  <- paletteer::paletteer_d("peRReo::don")[c(5,9)]

### |-  titles and caption ----
# icons
tt <- str_glue("#TidyTuesday: { 2024 } Week { 40 } &bull; Source: Chess Game Dataset (Lichess)<br>")
li <- str_glue("<span style='font-family:fa6-brands'>&#xf08c;</span>")
gh <- str_glue("<span style='font-family:fa6-brands'>&#xf09b;</span>")
mn <- str_glue("<span style='font-family:fa6-brands'>&#xf4f6;</span>")

# text
title_text    <- str_glue("White and Black Chess Ratings: A Distribution Analysis")
subtitle_text <- str_glue("How ratings vary between White and Black players across competitive chess matches")
caption_text  <- str_glue("{tt} {li} stevenponce &bull; {mn} @sponce1(graphic.social) {gh} poncest &bull; #rstats #ggplot2")

### |-  fonts ----
font_add("fa6-brands", "fonts/6.4.2/Font Awesome 6 Brands-Regular-400.otf")
font_add_google("Oswald", regular.wt = 400, family = "title")
font_add_google("Merriweather Sans", regular.wt = 400, family = "subtitle")
font_add_google("Merriweather Sans", regular.wt = 400, family = "text")
font_add_google("Noto Sans", regular.wt = 400, family = "caption")
showtext_auto(enable = TRUE)

### |-  plot theme ----
theme_set(theme_minimal(base_size = 14, base_family = "text"))                

theme_update(
    plot.title.position   = "plot",
    plot.caption.position = "plot",
    legend.position       = 'plot',
    plot.background       = element_rect(fill = bkg_col, color = bkg_col),
    panel.background      = element_rect(fill = bkg_col, color = bkg_col),
    plot.margin           = margin(t = 10, r = 20, b = 10, l = 20),

    axis.title.x          = element_text(margin = margin(10, 0, 0, 0), size = rel(1.1), 
                                         color = text_col, family = "text", face = "bold", hjust = 0.5),
    axis.title.y          = element_blank(),  
    axis.text.y           = element_blank(),
    axis.text.x           = element_text(color = text_col, family = "text", size = rel(0.9)),
    axis.ticks.x          = element_line(color = text_col),  # Show x-axis ticks
    panel.grid            = element_blank(),
    strip.text            = element_blank() # Remove strip text 
)
```

6. Plot

```{r}
#| label: plot

### |-  final plot ----
p <- ggplot(chess_data, aes(x = rating)) +

  # Geoms
  # Reference text layer
  as_reference(
    geom_text(
      data = labels, aes(x = x, y = y, label = label),
      family = "title", colour = "gray10", size = rel(35), hjust = 0.5, vjust = 0
    ),
    id = "text"
  ) +

  # Blending the text with the density plot
  with_inner_glow(
    with_blend(
      geom_density(aes(fill = player, color = player),
        alpha = 1, show.legend = FALSE,
        bw = 25,
        kernel = "epanechnikov"
      ),
      bg_layer = "text", blend_type = "xor"
    ),
    color = "gray10", sigma = 15
  ) +

  # Labs
  labs(
    x = "Player Rating",
    y = NULL,
    title = title_text,
    subtitle = subtitle_text,
    caption = caption_text
  ) +

  # Scales
  scale_x_continuous() +
  scale_y_continuous() +
  scale_fill_manual(values = col_palette) +
  scale_color_manual(values = col_palette) +
  coord_cartesian(clip = "off") +

  # Facet
  facet_wrap(~player, ncol = 1) +

  # Theme
  theme(
    plot.title = element_text(
      size = rel(1.55),
      family = "title",
      face = "bold",
      color = title_col,
      lineheight = 1.1,
      margin = margin(t = 5, b = 5)
    ),
    plot.subtitle = element_text(
      size = rel(0.85),
      family = "subtitle",
      color = subtitle_col,
      lineheight = 1.1,
      margin = margin(t = 5, b = 5)
    ),
    plot.caption = element_markdown(
      size = rel(0.50),
      family = "caption",
      color = caption_col,
      lineheight = 1.1,
      hjust = 0.5,
      halign = 1,
      margin = margin(t = 5, b = 5)
    )
  )
```

7. Save

```{r}
#| label: save

### |-  plot image ----  

# Save the plot again
ggsave(
    filename = here::here("data_visualizations/TidyTuesday/2024/tt_2024_40.png"),
    plot = p,
    width  = 7.5,
    height = 5,
    units  = "in",
    dpi    = 320
)

### |-  plot thumbnail----  
magick::image_read(here::here("data_visualizations/TidyTuesday/2024/tt_2024_40.png")) |> 
  magick::image_resize(geometry = "400") |> 
  magick::image_write(here::here("data_visualizations/TidyTuesday/2024/thumbnails/tt_2024_40.png"))
```

8. Session Info

```{r, eval=TRUE}
info <- capture.output(sessioninfo::session_info())
# Remove lines that contain "[1]" and "[2]" (the file paths)
filtered_info <- grep("\\[1\\]|\\[2\\]", info, value = TRUE, invert = TRUE)
cat(filtered_info, sep = "\n")
```

─ Session info ───────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.4.1 (2024-06-14 ucrt)
 os       Windows 11 x64 (build 22631)
 system   x86_64, mingw32
 ui       RTerm
 language (EN)
 collate  English_United States.utf8
 ctype    English_United States.utf8
 tz       America/New_York
 date     2025-05-22
 pandoc   3.4 @ C:/Program Files/RStudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────
 ! package     * version date (UTC) lib source
 P digest        0.6.37  2024-08-19 [?] RSPM (R 4.4.0)
 P evaluate      1.0.1   2024-10-10 [?] RSPM (R 4.4.0)
 P fastmap       1.2.0   2024-05-15 [?] RSPM (R 4.4.0)
 P htmltools     0.5.8.1 2024-04-04 [?] RSPM (R 4.4.0)
 P htmlwidgets   1.6.4   2023-12-06 [?] CRAN (R 4.4.0)
 P jsonlite      1.8.9   2024-09-20 [?] RSPM (R 4.4.0)
 P knitr         1.49    2024-11-08 [?] RSPM (R 4.4.0)
 P rmarkdown     2.29    2024-11-04 [?] RSPM (R 4.4.0)
 P rstudioapi    0.17.1  2024-10-22 [?] RSPM (R 4.4.0)
 P sessioninfo   1.2.2   2021-12-06 [?] RSPM (R 4.4.0)
 P xfun          0.49    2024-10-31 [?] RSPM (R 4.4.0)
 P yaml          2.3.10  2024-07-26 [?] RSPM (R 4.4.0)


 P ── Loaded and on-disk path mismatch.

──────────────────────────────────────────────────────────────────────────────