Urban vs Rural Income Distribution

import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import gaussian_kde

np.random.seed(555)
BG_COLOR = '#ffffff'
TEXT_COLOR = '#1f2937'

urban = np.random.lognormal(4.3, 0.55, 1000)
rural = np.random.lognormal(3.9, 0.65, 1000)
urban = urban[urban < 250]
rural = rural[rural < 250]

fig, ax = plt.subplots(figsize=(12, 7), facecolor=BG_COLOR)
ax.set_facecolor(BG_COLOR)

x = np.linspace(0, 250, 500)

kde_u = gaussian_kde(urban)
y_u = kde_u(x)
ax.fill_between(x, y_u, alpha=0.25, color='#4927F5')
ax.plot(x, y_u, color='#4927F5', linewidth=3, label='Urban (median=$%.0fK)' % np.median(urban))

kde_r = gaussian_kde(rural)
y_r = kde_r(x) * -1
ax.fill_between(x, y_r, alpha=0.25, color='#6CF527')
ax.plot(x, y_r, color='#6CF527', linewidth=3, label='Rural (median=$%.0fK)' % np.median(rural))

ax.axhline(0, color=TEXT_COLOR, linewidth=1.5)

poverty_line = 30
ax.axvline(poverty_line, color='#ef4444', linestyle='--', linewidth=2, alpha=0.7)
ax.fill_betweenx([min(y_r), max(y_u)], 0, poverty_line, alpha=0.08, color='#ef4444')
ax.text(poverty_line + 3, max(y_u)*0.85, 'Poverty Line', color='#ef4444', fontsize=10, fontweight='bold')

urban_poverty = (urban < poverty_line).mean() * 100
rural_poverty = (rural < poverty_line).mean() * 100

ax.scatter([np.median(urban)], [kde_u(np.median(urban))], color='#4927F5', s=120, zorder=5, edgecolors='white', linewidths=2)
ax.scatter([np.median(rural)], [-kde_r(np.median(rural))], color='#6CF527', s=120, zorder=5, edgecolors='white', linewidths=2)

gap = np.median(urban) - np.median(rural)
ax.annotate('', xy=(np.median(urban), max(y_u)*0.5), xytext=(np.median(rural), max(y_u)*0.5),
            arrowprops=dict(arrowstyle='<->', color='#F5276C', lw=2))
ax.text((np.median(urban)+np.median(rural))/2, max(y_u)*0.55, 'Gap: $%.0fK' % gap,
        ha='center', color='#F5276C', fontsize=11, fontweight='bold')

stats = 'Below Poverty: Urban %.1f%% | Rural %.1f%%' % (urban_poverty, rural_poverty)
ax.text(0.5, 0.98, stats, transform=ax.transAxes, ha='center', va='top',
        fontsize=10, color='#6b7280', fontfamily='monospace',
        bbox=dict(boxstyle='round,pad=0.4', facecolor=BG_COLOR, edgecolor='#e5e7eb', lw=1.5))

ax.set_xlabel('Annual Household Income ($K)', fontsize=12, color=TEXT_COLOR, fontweight='500')
ax.set_title('Income Inequality: Urban vs Rural', fontsize=16, color=TEXT_COLOR, fontweight='bold', pad=25)

ax.tick_params(colors=TEXT_COLOR, labelsize=10)
ax.set_yticks([])
for spine in ['top', 'right']:
    ax.spines[spine].set_visible(False)
for spine in ['bottom', 'left']:
    ax.spines[spine].set_color('#e5e7eb')
ax.legend(loc='upper right', facecolor=BG_COLOR, edgecolor='#e5e7eb', labelcolor=TEXT_COLOR, fontsize=10)

plt.tight_layout()
plt.show()