import matplotlib.pyplot as plt
import numpy as np

np.random.seed(42)
data = np.random.normal(170, 10, 1000)  # 키 데이터

fig, axes = plt.subplots(1, 3, figsize=(15, 4))

# bin 수에 따른 차이
for ax, bins in zip(axes, [10, 30, 100]):
    ax.hist(data, bins=bins, color='#4a9eca', edgecolor='white', alpha=0.8)
    ax.set_title(f'bins={bins}')
    ax.set_xlabel('키 (cm)')
    ax.set_ylabel('빈도')

plt.suptitle('히스토그램 — bin 크기의 영향', fontsize=14)
plt.tight_layout()
plt.show()

# 밀도 히스토그램 + KDE 곡선
fig, ax = plt.subplots(figsize=(8, 5))
ax.hist(data, bins=30, density=True, color='#4a9eca', edgecolor='white', alpha=0.7, label='히스토그램')

# KDE 곡선 추가
from scipy import stats
x_range = np.linspace(data.min(), data.max(), 100)
kde = stats.gaussian_kde(data)
ax.plot(x_range, kde(x_range), color='#e6a23c', linewidth=2, label='KDE')

ax.set_title('키 분포 (밀도)')
ax.legend()
plt.tight_layout()
plt.show()

np.random.seed(42)
groups = {
    '개발': np.random.normal(5000, 800, 50),
    '영업': np.random.normal(4500, 600, 50),
    '마케팅': np.random.normal(4200, 500, 50),
}

fig, ax = plt.subplots(figsize=(8, 5))
bp = ax.boxplot(groups.values(), labels=groups.keys(),
                patch_artist=True, showmeans=True,
                meanprops={'marker': 'D', 'markerfacecolor': '#e6a23c'})

# 색상 설정
colors = ['#4a9eca', '#4a9e4a', '#e6a23c']
for patch, color in zip(bp['boxes'], colors):
    patch.set_facecolor(color)
    patch.set_alpha(0.6)

ax.set_title('부서별 연봉 분포')
ax.set_ylabel('연봉 (만원)')
ax.grid(axis='y', alpha=0.3)
plt.tight_layout()
plt.show()

fig, ax = plt.subplots(figsize=(8, 5))

data_list = [groups['개발'], groups['영업'], groups['마케팅']]
vp = ax.violinplot(data_list, showmeans=True, showmedians=True)

# 색상 설정
for i, body in enumerate(vp['bodies']):
    body.set_facecolor(colors[i])
    body.set_alpha(0.6)

ax.set_xticks([1, 2, 3])
ax.set_xticklabels(['개발', '영업', '마케팅'])
ax.set_title('부서별 연봉 분포 (바이올린)')
ax.set_ylabel('연봉 (만원)')
plt.tight_layout()
plt.show()