TidyTuesday_Tour_de_France.Rmd

---
title: "TidyTuesday: Tour de France"
output: html_document
---

# Load all packages
```{r}
# clear workspace
rm(list = ls())

# install necessary packages
library(install.load)
packages <-
  c("tidylog",
    "purrr",
    "tidyr",
    "magrittr",
    "ggplot2",
    "countrycode",
    "ggalluvial")

install_load(packages)

# Install via
devtools::install_github("thebioengineer/tidytuesdayR")
library(tidytuesdayR)
```

# Load the data and clean it
```{r}
tuesdata <- tidytuesdayR::tt_load(2020, week = 15)

stage_data <- tuesdata$stage_data
tdf_stages <- tuesdata$tdf_stages
tdf_winners <- tuesdata$tdf_winners

rm(tuesdata)
```

# Set color theme
The color theme is based on this [code](https://gist.github.com/jslefche/eff85ef06b4705e6efbc).
```{r}
theme_black = function(base_size = 12,
                       base_family = "") {
  theme_grey(base_size = base_size, base_family = base_family) %+replace%
    
    theme(
      # Specify axis options
      axis.line = element_blank(),
      axis.title.x = element_blank(),
      axis.title.y = element_blank(),
      axis.text.y = element_blank(),
      axis.ticks.y = element_blank(),
      axis.text.x = element_text(
        size = base_size * 0.8,
        color = "white",
        lineheight = 0.9
      ),
      # Specify legend options
      legend.background = element_rect(color = NA, fill = "black"),
      legend.key = element_rect(color = "white",  fill = "black"),
      legend.key.size = unit(1.2, "lines"),
      legend.key.height = NULL,
      legend.key.width = NULL,
      legend.text = element_text(size = base_size * 0.8, color = "white"),
      legend.title = element_text(
        size = base_size * 0.8,
        face = "bold",
        hjust = 0,
        color = "white"
      ),
      legend.position = "right",
      legend.text.align = NULL,
      legend.title.align = NULL,
      legend.direction = "vertical",
      legend.box = NULL,
      # Specify panel options
      panel.background = element_rect(fill = "black", color  =  NA),
      panel.border = element_rect(fill = NA, color = "black"),
      panel.grid.major = element_line(color = "black"),
      panel.grid.minor = element_line(color = "black"),
      #  plot.spacing = unit(0.5, "lines"),
      # Specify facetting options
      strip.background = element_rect(fill = "grey30", color = "grey10"),
      strip.text.x = element_text(size = base_size * 0.8, color = "white"),
      strip.text.y = element_text(
        size = base_size * 0.8,
        color = "white",
        angle = -90
      ),
      # Specify plot options
      plot.background = element_rect(color = "black", fill = "black"),
      plot.title = element_text(size = base_size * 2, color = "white"),
      plot.subtitle = element_text(size = base_size * 1.5, color = "white"),
      plot.caption = element_text(
        size = 9,
        color = "white",
        hjust = 1
      )
    )
}
```

# Prepare the data
```{r}
dat <- tdf_stages %>%
  # Rename some country names
  dplyr::mutate(Winner_Country = ifelse(
    Winner_Country == 'c("FRA", "FRA")',
    "FRA",
    ifelse(
      Winner_Country == 'c("BEL", "BEL")',
      "BEL",
      ifelse(Winner_Country == 'c("BEL", "GER")', "BEL", Winner_Country)
    )
  )) %>%
  # Filter to include only "plain stage" and "stages with mountains"
  dplyr::filter(Type == "Plain stage" |
                  Type == "Stage with mountain(s)" |
                  Type == "Stage with mountain") %>%
  # Rename the stages (to make it easier to visualize it later)
  dplyr::mutate(
    Type = ifelse(
      Type == "Stage with mountain" |
        Type == "Stage with mountain(s)",
      "Stage with \nmountain(s)",
      Type
    )
  ) %>%
  dplyr::filter(!is.na(Winner_Country)) %>%
  dplyr::ungroup() %>%
  # Generate a dichotomous dummy variable (200 is approximately both the median and the mean distance)
  dplyr::mutate(distance = ifelse(Distance < 200, "Less than \n200 km", "More than \n200 km")) %>%
  # Group by Winner_Country, Type, distance
  dplyr::group_by(Winner_Country, Type, distance) %>%
  count() %>%
  # Drop all observations that have fewer than 12 counts
  dplyr::filter(n > 12) %>%
  # Rename the country (to make it better readable later)
  dplyr::mutate(country = countrycode(Winner_Country, "iso3c", "country.name")) %>%
  dplyr::mutate(country = ifelse(
    Winner_Country == "NED",
    "The \nNetherlands",
    ifelse(Winner_Country == "SUI", "Switzerland", country)
  ))

```

# Plot it
```{r}
plot <- ggplot(dat,
               aes(
                 weight = n,
                 axis1 = Type,
                 axis2 = distance,
                 axis3 = country
               )) +
  geom_alluvium(
    aes(fill = Type, color = Type),
    width = 2 / 12,
    alpha = 0.7,
    knot.pos = 0.4
  ) +
  geom_stratum(
    width = 1 / 6,
    color = "grey",
    reverse = TRUE,
    alpha = .8
  ) +
  scale_fill_manual(values  = c("white", "#ffff00")) +
  scale_color_manual(values = c("white", "#ffff00")) +
  geom_text(stat = "stratum",
            label.strata = TRUE,
            size = 3) +
  theme_black() +
  labs(title = "Racing up that hill\n",
       subtitle = "Stage winners by stage type, distance, and nationality (1903-2017)",
       caption = "#TidyTuesday: Tour de France\n Based on data from the tdf package\n Visualization: @cosima_meyer") +
  theme(
    legend.position = "none",
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    axis.ticks.x = element_blank(),
    axis.text.x = element_blank()
  ) 

ggsave(
  filename = "figures/TidyTuesday_TdF.png",
  plot,
  width = 12,
  height = 9,
  dpi = 250,
  units = "in",
  device = 'png'
)
```

# Bonus plot
```{r}
tdf_winners %>%
  group_by(nationality, age) %>%
  count() %>%
  ggplot(aes(x = nationality, y = n, fill = age)) +
  geom_bar(stat = 'identity') + theme_light() +
  scale_fill_gradient(name="Age",
                      low = "#eaec00",
                      high = 'white',
                      limits = c(19, 36)) +
  theme(axis.title.y = element_text(angle = 0)) + coord_polar()  + theme_black() +
  labs(title = "Tour de France winners \nby age and nationality (1903-2017)") +
  theme(
    panel.grid.major = element_blank(),
    panel.grid.minor = element_blank(),
    text = element_text(size = 10),
    axis.text.x = element_text(size = 4.7, color = "white"),
    
  ) 
```