olympicdash-py-3.qmd

---
title: "Olympic Games"
format: 
  dashboard:
    orientation: columns
    nav-buttons: [github]
    github: https://github.com/posit-conf-2024/olympicdash
logo: images/olympics-logo.svg
logo-alt: "Olympics logo with multicolored circles."
---

```{python}
#| label: load-packages
from plotnine import *
import great_tables as gt
import pandas as pd
```

```{python}
#| label: load-data
olympics_full = pd.read_csv("data/olympics.csv", low_memory = False)
```

```{python}
#| label: prep-data
# Filter for non-NA medals
olympics = olympics_full[(olympics_full["medal"].notna())]

# Split the team column at "-" into two columns
split_data = olympics["team"].str.split("-", n = 1, expand = True)
olympics.loc[:, "team"] = split_data[0]

# Reorder the medal column categories
olympics["medal"] = pd.Categorical(olympics["medal"], categories = ["Bronze", "Silver", "Gold"])
```

# 🌞 Summer Olympics

```{python}
#| label: summmer-prep-data
summer_olympics = olympics[(olympics["season"] == "Summer")]
summer_olympics.reset_index(drop=True, inplace=True)
```

## Column - Medals by sport and year {width=65%}

### Row - Medals by sport {height=60%}

```{python}
#| label: summer-medals-by-sport
#| title: Medals by sport

# Lump the sport column to top 15 categories, grouping others as Other
top_15_sports = summer_olympics["sport"].value_counts().nlargest(15).index
summer_olympics["sport"] = summer_olympics["sport"].apply(lambda x: x if x in top_15_sports else "Other")

# Convert the sport column to a categorical type with order based on frequency, and reverse the order
summer_olympics["sport"] = pd.Categorical(summer_olympics["sport"], categories = summer_olympics["sport"].value_counts().index[::-1])

# Move the Other category of the sport column to the beginning
new_order = ["Other"] + [cat for cat in summer_olympics["sport"].cat.categories if cat != "Other"]
summer_olympics["sport"] = summer_olympics["sport"].cat.reorder_categories(new_order)

# Plot
(
    ggplot(summer_olympics, aes(x = "sport", fill = "medal")) +
    geom_bar() +
    coord_flip() +
    guides(fill = guide_legend(reverse = True)) +
    labs(
        x = "",
        y = "",
        fill = "Medal"
    ) +
    theme_minimal() +
    theme(
        legend_position = "inside",
        legend_position_inside = (0.9, 0.2),
        legend_direction = "horizontal",
        legend_background = element_rect(fill = "white", color = "gray"),
        figure_size = (10, 6.18)
    )
)
```

### Row - Medals by year {height=40%}

::: {.card title="Medals by year"}
Due to World War II, no olympic games were held in 1940 and 1944.

```{python}
#| label: summer-medals-by-year
#| title: Medals by year

# Count the occurrences of each medal per year
summer_olympics_count = summer_olympics.groupby(["year", "medal"], observed=True).size().reset_index(name = "n")

# Plot
(
    ggplot(summer_olympics_count, aes(x = "year", y = "n", color = "medal")) +
    geom_point(size = 0.5) +
    geom_line() +
    guides(color = guide_legend(reverse = True)) + 
    scale_x_continuous(breaks = range(1896, 2020, 8)) +
    labs(x = "Year", y = "", color = "Medal") +
    theme_minimal() +
    theme(
        legend_position = "inside",
        legend_position_inside = (0.9, 0.2),
        legend_direction = "horizontal",
        legend_background = element_rect(fill = "white", color = "gray"),
        figure_size = (10, 3)
    )
)
```
:::

## Column - Medals by country {width=35%}

### Row - Value boxes {height=30%}

```{python}
#| label: summer-calculate-most-medals

# Filter for gold medals
gold_medals = summer_olympics[summer_olympics['medal'] == 'Gold']
# Group by team and count gold medals
gold_medal_counts = gold_medals.groupby('team').size()
# Find the team with the most gold medals
most_gold_medals = gold_medal_counts.idxmax()
count_most_gold_medals = gold_medal_counts.max()

# Filter for silver medals
silver_medals = summer_olympics[summer_olympics['medal'] == 'Silver']
# Group by team and count silver medals
silver_medal_counts = silver_medals.groupby('team').size()
# Find the team with the most silver medals
most_silver_medals = silver_medal_counts.idxmax()
count_most_silver_medals = silver_medal_counts.max()

# Filter for bronze medals
bronze_medals = summer_olympics[summer_olympics['medal'] == 'Bronze']
# Group by team and count bronze medals
bronze_medal_counts = bronze_medals.groupby('team').size()
# Find the team with the most bronze medals
most_bronze_medals = bronze_medal_counts.idxmax()
count_most_bronze_medals = bronze_medal_counts.max()
```

::: {.valuebox icon="award-fill" color="#d4af37"}
Most golds: 

`{python} str(count_most_gold_medals)`

`{python} most_gold_medals`
:::

::: {.valuebox icon="award-fill" color="#c0c0c0"}
Most silvers: 

`{python} str(count_most_silver_medals)`

`{python} most_silver_medals`
:::

::: {.valuebox icon="award-fill" color="#cd7f32"}
Most bronzes: 

`{python} str(count_most_bronze_medals)`

`{python} most_bronze_medals`
:::

### Row - Tabsets of tables {height=70% .tabset}

```{python}
#| label: summer-medals-by-country
#| title: Medals by country

# Count the occurrences of each medal per team
summer_olympics_count = summer_olympics.groupby(["team", "medal"]).size().reset_index(name="n")

# Pivot olympics_count to get medals as columns
summer_olympics_pivot = summer_olympics_count.pivot_table(index = "team", columns = "medal", values = "n", fill_value = 0)

# Calculate the total number of medals
summer_olympics_pivot["Total"] = summer_olympics_pivot[["Bronze", "Gold", "Silver"]].sum(axis=1)

# Reset the index and rearrange columns
summer_olympics_pivot = summer_olympics_pivot.reset_index()
summer_olympics_pivot = summer_olympics_pivot[["team", "Gold", "Silver", "Bronze", "Total"]]

# Sort by Total medals, then team
summer_olympics_sorted_descending = summer_olympics_pivot.sort_values(by=["Total", "team"], ascending=[False, True])
summer_olympics_sorted_ascending = summer_olympics_pivot.sort_values(by=["Total", "team"], ascending=[True, True])

# Remove Total
summer_olympics_sorted_descending = summer_olympics_sorted_descending[["team", "Gold", "Silver", "Bronze"]]
summer_olympics_sorted_ascending = summer_olympics_sorted_ascending[["team", "Gold", "Silver", "Bronze"]]

# Rename the team column to Team
summer_olympics_sorted_descending.rename(columns={"team": "Team"}, inplace=True)
summer_olympics_sorted_ascending.rename(columns={"team": "Team"}, inplace=True)

# Find top and bottom 30
summer_olympics_sorted_descending_top30 = summer_olympics_sorted_descending.head(30)
summer_olympics_sorted_descending_top30.reset_index(drop=True, inplace=True)
summer_olympics_sorted_ascending_bottom30 = summer_olympics_sorted_ascending.head(30)
summer_olympics_sorted_ascending_bottom30.reset_index(drop=True, inplace=True)
```

::: {.card title="Top 30 total medals"}
Teams sorted in descending order of total medals.

```{python}
#| label: summer-top-30-medals
(
    gt.GT(summer_olympics_sorted_descending_top30).data_color(
        columns=["Gold", "Silver", "Bronze"],
        palette="Oranges"
    )
)
```
:::

::: {.card title="Bottom 30 total medals"}
Teams sorted in ascending order of total medals.

```{python}
#| label: summer-bottom-30-medals
(
    gt.GT(summer_olympics_sorted_ascending_bottom30).data_color(
        columns=["Gold", "Silver", "Bronze"],
        palette="Blues"
    )
)
```
:::

# ❄️ Winter Olympics

```{python}
#| label: winter-prep-data
winter_olympics = olympics[(olympics["season"] == "Winter")]
winter_olympics.reset_index(drop=True, inplace=True)
```

## Column - Medals by sport and year {width=65%}

### Row - Medals by sport {height=60%}

```{python}
#| label: winter-medals-by-sport
#| title: Medals by sport

# Lump the sport column to top 15 categories, grouping others as Other
top_15_sports = winter_olympics["sport"].value_counts().nlargest(15).index
winter_olympics["sport"] = winter_olympics["sport"].apply(lambda x: x if x in top_15_sports else "Other")

# Convert the sport column to a categorical type with order based on frequency, and reverse the order
winter_olympics["sport"] = pd.Categorical(winter_olympics["sport"], categories = winter_olympics["sport"].value_counts().index[::-1])

# Move the Other category of the sport column to the beginning
new_order = ["Other"] + [cat for cat in winter_olympics["sport"].cat.categories if cat != "Other"]
winter_olympics["sport"] = winter_olympics["sport"].cat.reorder_categories(new_order)

# Plot
(
    ggplot(winter_olympics, aes(x = "sport", fill = "medal")) +
    geom_bar() +
    coord_flip() +
    guides(fill = guide_legend(reverse = True)) +
    labs(
        x = "",
        y = "",
        fill = "Medal"
    ) +
    theme_minimal() +
    theme(
        legend_position = "inside",
        legend_position_inside = (0.9, 0.2),
        legend_direction = "horizontal",
        legend_background = element_rect(fill = "white", color = "gray"),
        figure_size = (10, 6.18)
    )
)
```

### Row - Medals by year {height=40%}

::: {.card title="Medals by year"}
Due to World War II, no olympic games were held in 1940 and 1944.

```{python}
#| label: winter-medals-by-year

# Count the occurrences of each medal per year
winter_olympics_count = winter_olympics.groupby(["year", "medal"], observed=True).size().reset_index(name = "n")

# Plot
(
    ggplot(winter_olympics_count, aes(x = "year", y = "n", color = "medal")) +
    geom_point(size = 0.5) +
    geom_line() +
    guides(color = guide_legend(reverse = True)) + 
    scale_x_continuous(breaks = range(1896, 2020, 8)) +
    labs(x = "Year", y = "", color = "Medal") +
    theme_minimal() +
    theme(
        legend_position = "inside",
        legend_position_inside = (0.9, 0.2),
        legend_direction = "horizontal",
        legend_background = element_rect(fill = "white", color = "gray"),
        figure_size = (10, 3)
    )
)
```
:::

## Column - Medals by country {width=35%}

### Row - Value boxes {height=30%}

```{python}
#| label: winter-calculate-most-medals

# Filter for gold medals
gold_medals = winter_olympics[winter_olympics['medal'] == 'Gold']
# Group by team and count gold medals
gold_medal_counts = gold_medals.groupby('team').size()
# Find the team with the most gold medals
most_gold_medals = gold_medal_counts.idxmax()
count_most_gold_medals = gold_medal_counts.max()

# Filter for silver medals
silver_medals = winter_olympics[winter_olympics['medal'] == 'Silver']
# Group by team and count silver medals
silver_medal_counts = silver_medals.groupby('team').size()
# Find the team with the most silver medals
most_silver_medals = silver_medal_counts.idxmax()
count_most_silver_medals = silver_medal_counts.max()

# Filter for bronze medals
bronze_medals = winter_olympics[winter_olympics['medal'] == 'Bronze']
# Group by team and count bronze medals
bronze_medal_counts = bronze_medals.groupby('team').size()
# Find the team with the most bronze medals
most_bronze_medals = bronze_medal_counts.idxmax()
count_most_bronze_medals = bronze_medal_counts.max()
```

::: {.valuebox icon="award-fill" color="#d4af37"}
Most golds: 

`{python} str(count_most_gold_medals)`

`{python} most_gold_medals`
:::

::: {.valuebox icon="award-fill" color="#c0c0c0"}
Most silvers: 

`{python} str(count_most_silver_medals)`

`{python} most_silver_medals`
:::

::: {.valuebox icon="award-fill" color="#cd7f32"}
Most bronzes: 

`{python} str(count_most_bronze_medals)`

`{python} most_bronze_medals`
:::

### Row - Tabsets of tables {height=70% .tabset}

```{python}
#| label: winter-medals-by-country
#| title: Medals by country

# Count the occurrences of each medal per team
winter_olympics_count = winter_olympics.groupby(["team", "medal"]).size().reset_index(name="n")

# Pivot olympics_count to get medals as columns
winter_olympics_pivot = winter_olympics_count.pivot_table(index = "team", columns = "medal", values = "n", fill_value = 0)

# Calculate the total number of medals
winter_olympics_pivot["Total"] = winter_olympics_pivot[["Bronze", "Gold", "Silver"]].sum(axis=1)

# Reset the index and rearrange columns
winter_olympics_pivot = winter_olympics_pivot.reset_index()
winter_olympics_pivot = winter_olympics_pivot[["team", "Gold", "Silver", "Bronze", "Total"]]

# Sort by Total medals, then team
winter_olympics_sorted_descending = winter_olympics_pivot.sort_values(by=["Total", "team"], ascending=[False, True])
winter_olympics_sorted_ascending = winter_olympics_pivot.sort_values(by=["Total", "team"], ascending=[True, True])

# Remove Total
winter_olympics_sorted_descending = winter_olympics_sorted_descending[["team", "Gold", "Silver", "Bronze"]]
winter_olympics_sorted_ascending = winter_olympics_sorted_ascending[["team", "Gold", "Silver", "Bronze"]]

# Rename the team column to Team
winter_olympics_sorted_descending.rename(columns={"team": "Team"}, inplace=True)
winter_olympics_sorted_ascending.rename(columns={"team": "Team"}, inplace=True)

# Find top and bottom 30
winter_olympics_sorted_descending_top30 = winter_olympics_sorted_descending.head(30)
winter_olympics_sorted_descending_top30.reset_index(drop=True, inplace=True)
winter_olympics_sorted_ascending_bottom30 = winter_olympics_sorted_ascending.head(30)
winter_olympics_sorted_ascending_bottom30.reset_index(drop=True, inplace=True)
```

::: {.card title="Top 30 total medals"}
Teams sorted in descending order of total medals.

```{python}
#| label: winter-top-30-medals
(
    gt.GT(winter_olympics_sorted_descending_top30).data_color(
        columns=["Gold", "Silver", "Bronze"],
        palette="Oranges"
    )
)
```
:::

::: {.card title="Bottom 30 total medals"}
Teams sorted in ascending order of total medals.

```{python}
#| label: winter-bottom-30-medals
(
    gt.GT(winter_olympics_sorted_ascending_bottom30).data_color(
        columns=["Gold", "Silver", "Bronze"],
        palette="Blues"
    )
)
```
:::