#绘制箱线图和小提琴图描述数据分布

import numpy as np
import pandas as pd

# 使用Gamma分布模拟企业中员工年龄的分布
np.random.seed(1994)
age = np.random.gamma(shape=5, scale=2, size=1000) + 20 # 使年龄最小在20以上

# 年龄取整
age_rounded = np.round(age).astype(int)

# 构建数据集
employee_dataset = pd.DataFrame({
    "Employee ID": [f"E{str(i).zfill(4)}" for i in range(1, 1001)],
    "Age": age_rounded
})

import plotly.graph_objects as go

# 创建箱线图
box = go.Box(y=employee_dataset['Age'], name='箱线图', boxpoints='outliers')

# 创建小提琴图
violin = go.Violin(y=employee_dataset['Age'], name='小提琴图', box_visible=True, meanline_visible=True, points='outliers')

# 将图表数据组合在一起
data = [box, violin]

# 定义图表布局
layout = go.Layout(title='年龄分布箱线图与小提琴图', yaxis_title='年龄', width=600, height=600)

# 创建图表
fig = go.Figure(data=data, layout=layout)

fig.update_layout(width=800, height=600)

# 显示图表
fig.show()

import plotly.express as px

fig = px.violin(employee_dataset, y='Age', width=600, height=600, box=True, points="outliers",
                title='年龄分布小提琴图')


# 计算中位值和四分位数
median = int(employee_dataset['Age'].median())
q1 = int(employee_dataset['Age'].quantile(0.25))
q3 = int(employee_dataset['Age'].quantile(0.75))
max_value = int(employee_dataset['Age'].max())
min_value = int(employee_dataset['Age'].min())

# 添加注解
annotations = [
    dict(x=0.07, y=median, xanchor='left', yanchor='middle', text=f"中位数: {median}", showarrow=False,
         bgcolor='rgba(211,211,211,0.5)', font=dict(size=12)),
    dict(x=0.07, y=q1, xanchor='left', yanchor='middle', text=f"下四分位: {q1}", showarrow=False,
         bgcolor='rgba(211,211,211,0.5)', font=dict(size=12)),
    dict(x=0.07, y=q3, xanchor='left', yanchor='middle', text=f"上四分位: {q3}", showarrow=False,
         bgcolor='rgba(211,211,211,0.5)', font=dict(size=12)),
    dict(x=0.07, y=max_value, xanchor='left', yanchor='middle', text=f"最大值: {max_value}", showarrow=False,
         bgcolor='rgba(211,211,211,0.5)', font=dict(size=12)),
    dict(x=0.07, y=min_value, xanchor='left', yanchor='middle', text=f"最小值: {min_value}", showarrow=False,
         bgcolor='rgba(211,211,211,0.5)', font=dict(size=12))
]

for ann in annotations:
    fig.add_annotation(ann)

# 显示图表
fig.show()