TidyTuesday dataset of 2025-12-09

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import matplotlib.ticker as ticker
import matplotlib.patches as patches
import matplotlib as mpl

qatarcars = pd.read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-12-09/qatarcars.csv')
qatarcars

def millions_formatter(x, pos):
    """The two args are the value and tick position"""
    return f'{x / 1000000:.1f}M'

df_melted = pd.melt(qatarcars, id_vars=['type', 'enginetype'], value_vars=['price'])
df_melted['type_engine'] = df_melted['type'] + '_' + df_melted['enginetype']
df_melted.sort_values(by=['type', 'enginetype'], ascending=False, inplace=True)
df_melted

df_max = qatarcars.loc[qatarcars.groupby(['type', 'enginetype'])['price'].idxmax()]
df_max.sort_values(by=['type', 'enginetype'], ascending=False, inplace=True)
df_max

bg_color = '#F5F5F5'
plot_colors = mpl.rcParams["axes.prop_cycle"].by_key()["color"]
fig, ax = plt.subplots(figsize=(8, 4))
sns.swarmplot(data=df_melted, x='type_engine', y='value', log_scale=True, hue='enginetype', legend=False)
ax.yaxis.set_major_formatter(ticker.FuncFormatter(millions_formatter))
plt.ylabel('Qatari Riyal (1M QAR ≈ 275K USD)')
plt.xlabel('')

ax.axvspan(2.5, 5.5, color='#FAFAFA', zorder=0)
ax.axvspan(6.5, 9.25, color='#FAFAFA', zorder=0)

ax.text(1, 25000, "Sedan", ha='center')
ax.text(4, 25000, "SUV", ha='center')
ax.text(6, 25000, "Hatchback", ha='center')
ax.text(8, 25000, "Coupe", ha='center')

# label the max values
for ind, (i, row) in enumerate(df_max.iterrows()):
    price_M = f"{row['price']/1000000:.2f}M"
    if (row['enginetype'] == 'Petrol'):
      ax.text(ind, row['price']*1.2, f"{row['make']}, {row['model']} \n {price_M}", ha='center', color=plot_colors[0])
    elif (row['enginetype'] == 'Hybrid'):
      if(row['model'] == 'Flying Spur'):
        ax.text(ind, row['price']*0.45, f"{row['make']}, {row['model']} \n {price_M}", ha='center', color=plot_colors[1])
      else:
        ax.text(ind, row['price']*1.2, f"{row['make']}, {row['model']} \n {price_M}", ha='center', color=plot_colors[1])
    else:
      ax.text(ind, row['price']*1.2, f"{row['make']}, {row['model']} \n {price_M}", ha='center', color=plot_colors[2])


sns.despine(bottom=True, left=True)
ax.tick_params(bottom=False, labelbottom=False)
ax.tick_params(axis='y', which='both', left=False, pad=-5)
ax.grid(True, axis='y', linestyle=':', alpha=0.5)
ax.figure.set_facecolor(bg_color)
ax.set_facecolor(bg_color)

plt.title("Price distribution of qatarcars by type and engine type.\nMax in each category is labelled.", \
          ha='left', x=-0.05, fontfamily='Serif', fontsize=14)
ax.annotate(
    'Petrol', 
    xy=(-0.09, 1), xycoords='axes fraction',
    xytext=(0.015, 0.10), textcoords='axes fraction', color=plot_colors[0],
    rotation=90, fontfamily='monospace'
)

ax.annotate(
    'Electric', 
    xy=(-0.09, 1), xycoords='axes fraction',
    xytext=(0.54, 0.03), textcoords='axes fraction', color=plot_colors[2],
    rotation=90, fontfamily='monospace'
)

ax.annotate(
    'Hybrid', 
    xy=(-0.09, 1), xycoords='axes fraction',
    xytext=(0.83, 0.3), textcoords='axes fraction', color=plot_colors[1],
    rotation=90, fontfamily='monospace'
)
plt.tight_layout()
plt.savefig('Qatarcars.png', dpi=300, bbox_inches='tight')
plt.show()