Irrigation Method Yield Raincloud

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

np.random.seed(1515)

# Yield in tons per hectare
rainfed = np.random.normal(2.8, 0.8, 80)
flood = np.random.normal(4.2, 1.0, 85)
sprinkler = np.random.normal(5.5, 0.9, 90)
drip = np.random.normal(6.2, 0.7, 75)

rainfed = np.clip(rainfed, 1.0, 5.0)
flood = np.clip(flood, 2.0, 7.0)
sprinkler = np.clip(sprinkler, 3.0, 8.0)
drip = np.clip(drip, 4.5, 8.5)

F_stat, p_value = stats.f_oneway(rainfed, flood, sprinkler, drip)

BG_COLOR = "#ffffff"
COLOR_SCALE = ["#9ca3af", "#276CF5", "#27D3F5", "#6CF527"]

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

y_data = [rainfed, flood, sprinkler, drip]
positions = [0, 1, 2, 3]
labels = ["Rainfed", "Flood", "Sprinkler", "Drip"]

for h in [2, 4, 6, 8]:
    ax.axhline(h, color='#e5e7eb', ls=(0, (5, 5)), alpha=0.8, zorder=0)

# Break-even threshold
ax.axhline(y=3.5, color='#ef4444', ls='--', alpha=0.6, lw=2)
ax.text(3.55, 3.5, "Break-even", color='#ef4444', 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("#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]
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="#374151", zorder=3, lw=1.5)
    ax.text(i + 0.3, mean, f"μ={mean:.1f}t/ha", fontsize=10, va="center", color='#1f2937',
            bbox=dict(facecolor='white', edgecolor=color, boxstyle="round,pad=0.15", lw=2))

# Water efficiency
water_eff = ["100%", "45%", "75%", "90%"]
for i, (eff, color) in enumerate(zip(water_eff, COLOR_SCALE)):
    ax.text(i, 0.3, f"Efficiency: {eff}", 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("Yield (tons/hectare)", size=14, color='#1f2937', fontweight='bold')

ax.set_title("Crop Yield by Irrigation Method", fontsize=14, color="white", fontweight="bold", pad=20)


ax.set_ylim(0, 9.5)
plt.tight_layout()
plt.show()