Renewable Energy Capacity Factor Raincloud

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

np.random.seed(999)

# Capacity factor percentage
solar = np.random.normal(25, 6, 100)
onshore_wind = np.random.normal(35, 8, 95)
offshore_wind = np.random.normal(45, 7, 70)
hydro = np.random.normal(42, 10, 80)

solar = np.clip(solar, 10, 45)
onshore_wind = np.clip(onshore_wind, 15, 55)
offshore_wind = np.clip(offshore_wind, 28, 65)
hydro = np.clip(hydro, 20, 70)

F_stat, p_value = stats.f_oneway(solar, onshore_wind, offshore_wind, hydro)

BG_COLOR = "#0d1117"
COLOR_SCALE = ["#F5D327", "#6CF527", "#27D3F5", "#276CF5"]

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

y_data = [solar, onshore_wind, offshore_wind, hydro]
positions = [0, 1, 2, 3]
labels = ["Solar PV", "Onshore Wind", "Offshore Wind", "Hydropower"]

for h in [20, 40, 60]:
    ax.axhline(h, color='#333333', ls=(0, (5, 5)), alpha=0.5, zorder=0)

# Grid parity threshold
ax.axhline(y=30, color='#22c55e', ls='--', alpha=0.7, lw=2)
ax.text(3.55, 30, "Grid Parity", color='#22c55e', fontsize=9, 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("#F5B027")
    pc.set_linewidth(2)

bp = ax.boxplot(y_data, positions=positions, showfliers=False, showcaps=False,
                medianprops=dict(linewidth=3, color='white'),
                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=55, color=color, alpha=0.55, 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}%", fontsize=10, va="center", color='white',
            bbox=dict(facecolor=BG_COLOR, edgecolor=color, boxstyle="round,pad=0.15", lw=2))

# LCOE annotations
lcoe = ["$30/MWh", "$35/MWh", "$55/MWh", "$40/MWh"]
for i, (cost, color) in enumerate(zip(lcoe, COLOR_SCALE)):
    ax.text(i, 5, f"LCOE: {cost}", ha='center', fontsize=9, color=color)

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=11, color='white')
ax.set_ylabel("Capacity Factor (%)", size=14, color='white', fontweight='bold')

ax.set_title("Renewable Energy Capacity Factors", fontsize=14, color="white", fontweight="bold", pad=20)


ax.set_ylim(0, 75)
plt.tight_layout()
plt.show()