Home Price by Neighborhood Raincloud

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

np.random.seed(1313)

# Price in thousands USD
downtown = np.random.lognormal(6.4, 0.35, 80)
midtown = np.random.lognormal(6.1, 0.4, 95)
suburbs = np.random.lognormal(5.7, 0.45, 120)
rural = np.random.lognormal(5.3, 0.5, 70)

downtown = np.clip(downtown, 400, 1500)
midtown = np.clip(midtown, 300, 1000)
suburbs = np.clip(suburbs, 200, 700)
rural = np.clip(rural, 100, 500)

F_stat, p_value = stats.f_oneway(downtown, midtown, suburbs, rural)

BG_COLOR = "#ffffff"
COLOR_SCALE = ["#F5276C", "#F5B027", "#27D3F5", "#6CF527"]

fig, ax = plt.subplots(figsize=(10, 6), facecolor=BG_COLOR)
ax.set_facecolor(BG_COLOR)

y_data = [downtown, midtown, suburbs, rural]
positions = [0, 1, 2, 3]
labels = ["Downtown", "Midtown", "Suburbs", "Rural"]

for h in [250, 500, 750, 1000]:
    ax.axhline(h, color='#e5e7eb', ls=(0, (5, 5)), alpha=0.8, zorder=0)

# Median income affordability line
ax.axhline(y=400, color='#22c55e', ls='--', alpha=0.6, lw=2)
ax.text(3.55, 400, "Median\nAffordable", color='#22c55e', fontsize=8, va='center')

violins = ax.violinplot(y_data, positions=positions, widths=0.5, 
                         bw_method="silverman", showmeans=False, 
                         showmedians=False, showextrema=False)
for pc in violins["bodies"]:
    pc.set_facecolor("none")
    pc.set_edgecolor("#374151")
    pc.set_linewidth(1.8)

bp = ax.boxplot(y_data, positions=positions, showfliers=False, showcaps=False,
                medianprops=dict(linewidth=3, color='#1f2937'),
                whiskerprops=dict(linewidth=2, color='#9ca3af'),
                boxprops=dict(linewidth=2, color='#9ca3af'))

for i, (y, color) in enumerate(zip(y_data, COLOR_SCALE)):
    x_jitter = np.array([i] * len(y)) + stats.t(df=6, scale=0.04).rvs(len(y))
    ax.scatter(x_jitter, y, s=50, color=color, alpha=0.5, zorder=2)

means = [y.mean() for y in y_data]
medians = [np.median(y) for y in y_data]
for i, (mean, median, color) in enumerate(zip(means, medians, COLOR_SCALE)):
    ax.scatter(i, mean, s=180, color='#C82909', zorder=5, edgecolors='white', linewidths=2)
    ax.plot([i, i + 0.28], [mean, mean], ls="dashdot", color="#374151", zorder=3, lw=1.5)
    ax.text(i + 0.3, mean, f"μ=${mean:.0f}K", fontsize=10, va="center", color='#1f2937',
            bbox=dict(facecolor='white', edgecolor=color, boxstyle="round,pad=0.15", lw=2))

# Price per sqft
ppsf = ["$650", "$485", "$320", "$195"]
for i, (p, color) in enumerate(zip(ppsf, COLOR_SCALE)):
    ax.text(i, 50, f"$/sqft: {p}", ha='center', fontsize=9, color=color)

ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
ax.spines["left"].set_color('#d1d5db')
ax.spines["bottom"].set_color('#d1d5db')
ax.tick_params(colors='#374151', length=0)

xlabels_full = [f"{l}\n(n={len(y_data[i])})" for i, l in enumerate(labels)]
ax.set_xticks(positions)
ax.set_xticklabels(xlabels_full, size=11, color='#1f2937')
ax.set_ylabel("Home Price ($K)", size=14, color='#1f2937', fontweight='bold')

ax.set_title("Home Sale Prices by Neighborhood", fontsize=14, color="white", fontweight="bold", pad=20)


ax.set_ylim(0, 1600)
plt.tight_layout()
plt.show()