Employee Tenure Distribution Raincloud

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

np.random.seed(1414)

# Tenure in years
engineering = np.random.lognormal(1.2, 0.6, 100)
sales = np.random.lognormal(0.8, 0.7, 90)
marketing = np.random.lognormal(1.0, 0.65, 75)
ops = np.random.lognormal(1.5, 0.5, 80)

engineering = np.clip(engineering, 0.5, 15)
sales = np.clip(sales, 0.3, 10)
marketing = np.clip(marketing, 0.4, 12)
ops = np.clip(ops, 0.6, 18)

F_stat, p_value = stats.f_oneway(engineering, sales, marketing, ops)

BG_COLOR = "#ffffff"
COLOR_SCALE = ["#4927F5", "#F5276C", "#F5B027", "#6CF527"]

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

y_data = [engineering, sales, marketing, ops]
positions = [0, 1, 2, 3]
labels = ["Engineering", "Sales", "Marketing", "Operations"]

for h in [2, 5, 10]:
    ax.axhline(h, color='#e5e7eb', ls=(0, (5, 5)), alpha=0.8, zorder=0)

# Industry average
ax.axhline(y=4.1, color='#6b7280', ls='--', alpha=0.6, lw=2)
ax.text(3.55, 4.1, "Industry\nAvg", color='#6b7280', 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]
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}y", fontsize=10, va="center", color='#1f2937',
            bbox=dict(facecolor='white', edgecolor=color, boxstyle="round,pad=0.15", lw=2))

# Turnover rates
turnover = ["12%", "28%", "22%", "8%"]
for i, (t, color) in enumerate(zip(turnover, COLOR_SCALE)):
    ax.text(i, -1.2, f"Turnover: {t}", 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("Tenure (Years)", size=14, color='#1f2937', fontweight='bold')

ax.set_title("Employee Tenure Distribution", fontsize=14, color="white", fontweight="bold", pad=20)


ax.set_ylim(-2, 20)
plt.tight_layout()
plt.show()