Class Size Impact on Scores Raincloud

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

np.random.seed(1111)

# Test scores (0-100)
small = np.random.normal(82, 8, 80)  # <15 students
medium = np.random.normal(76, 10, 120)  # 15-25 students
large = np.random.normal(71, 12, 100)  # 25-35 students
xlarge = np.random.normal(65, 14, 70)  # >35 students

small = np.clip(small, 55, 100)
medium = np.clip(medium, 45, 98)
large = np.clip(large, 35, 95)
xlarge = np.clip(xlarge, 25, 92)

F_stat, p_value = stats.f_oneway(small, medium, large, xlarge)

BG_COLOR = "#ffffff"
GREY_LIGHT = "#d1d5db"
COLOR_SCALE = ["#6CF527", "#27D3F5", "#F5B027", "#F5276C"]

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

y_data = [small, medium, large, xlarge]
positions = [0, 1, 2, 3]
labels = ["Small\n(<15)", "Medium\n(15-25)", "Large\n(25-35)", "X-Large\n(>35)"]

for h in [50, 70, 90]:
    ax.axhline(h, color=GREY_LIGHT, ls=(0, (5, 5)), alpha=0.8, zorder=0)

# Passing grade
ax.axhline(y=60, color='#ef4444', ls='--', alpha=0.6, lw=2)
ax.text(3.55, 60, "Pass", 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}", fontsize=10, va="center", color='#1f2937',
            bbox=dict(facecolor='white', edgecolor=color, boxstyle="round,pad=0.15", lw=2))

# Comparison bracket
tick = 3
ax.plot([0, 0, 3, 3], [98-tick, 98, 98, 98-tick], c="#374151", lw=1.5)
ax.text(1.5, 100, "p<0.001, Games-Howell", fontsize=10, va="bottom", ha="center", color='#C82909')

ax.spines["right"].set_visible(False)
ax.spines["top"].set_visible(False)
ax.spines["left"].set_color(GREY_LIGHT)
ax.spines["bottom"].set_color(GREY_LIGHT)
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=10, color='#1f2937')
ax.set_ylabel("Test Score", size=14, color='#1f2937', fontweight='bold')
ax.set_xlabel("Class Size", size=14, color='#1f2937', fontweight='bold')

ax.set_title("Class Size Effect on Student Achievement", fontsize=14, color="white", fontweight="bold", pad=20)


ax.set_ylim(20, 105)
plt.tight_layout()
plt.show()