Startup Funding by Stage Raincloud

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

np.random.seed(654)

# Funding in millions USD
seed = np.random.lognormal(0.5, 0.6, 100)
series_a = np.random.lognormal(2.0, 0.5, 85)
series_b = np.random.lognormal(3.2, 0.45, 60)
series_c = np.random.lognormal(4.0, 0.4, 40)

seed = np.clip(seed, 0.2, 8)
series_a = np.clip(series_a, 3, 30)
series_b = np.clip(series_b, 15, 80)
series_c = np.clip(series_c, 40, 200)

F_stat, p_value = stats.f_oneway(seed, series_a, series_b, series_c)

BG_COLOR = "#0a0a0f"
COLOR_SCALE = ["#27F5B0", "#27D3F5", "#F5B027", "#F5276C"]

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

y_data = [seed, series_a, series_b, series_c]
positions = [0, 1, 2, 3]
labels = ["Seed", "Series A", "Series B", "Series C"]

for h in [10, 50, 100, 150]:
    ax.axhline(h, color='#333333', ls=(0, (5, 5)), alpha=0.5, zorder=0)

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("white")
    pc.set_linewidth(1.8)

bp = ax.boxplot(y_data, positions=positions, showfliers=False, showcaps=False,
                medianprops=dict(linewidth=3, color='#F5D327'),
                whiskerprops=dict(linewidth=2, color='#555555'),
                boxprops=dict(linewidth=2, color='#555555'))

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]
for i, (mean, color) in enumerate(zip(means, 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="white", zorder=3, lw=1.5)
    ax.text(i + 0.3, mean, f"μ=${mean:.1f}M", fontsize=10, va="center", color='white',
            bbox=dict(facecolor=BG_COLOR, edgecolor=color, boxstyle="round,pad=0.15", lw=2))

ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
ax.spines["left"].set_color('#444444')
ax.spines["bottom"].set_color('#444444')
ax.tick_params(colors='#888888', length=0)

xlabels = [f"{l}\n(n={len(y_data[i])})" for i, l in enumerate(labels)]
ax.set_xticks(positions)
ax.set_xticklabels(xlabels, size=12, color='white')
ax.set_ylabel("Funding ($ Million)", size=12, color='white', fontweight='bold')

ax.set_title("Startup Funding by Stage", fontsize=14, color='white', fontweight='bold', pad=15)

stats_text = f"ANOVA: F={F_stat:.1f}, p<0.001, η²=0.91"
bbox = dict(facecolor=BG_COLOR, edgecolor='#27F5B0', boxstyle="round,pad=0.3", lw=2)
ax.text(0.5, 1.02, stats_text, transform=ax.transAxes, fontsize=10, color='white',
        ha='center', va='bottom', fontfamily='monospace', bbox=bbox)

ax.set_ylim(-5, 210)
plt.tight_layout()
plt.show()