利用面积图探索各国财富变化

import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from scipy.interpolate import make_interp_spline
from PIL import Image
import matplotlib.cm as cm

# 导入数据
url = "https://raw.githubusercontent.com/holtzy/R-graph-gallery/master/DATA/wealth_data.xlsx"
df = pd.read_excel(url)

df.head()

pivot_df = df.pivot(index='year', columns='country', values='total_wealth')

# 数据透视
pivot_df = df.pivot(index='year', columns='country', values='total_wealth')

# 初始化布局
plt.figure(figsize=(6, 6))

# 绘制堆叠面积图
plt.stackplot(pivot_df.index,
              pivot_df.values.T,
              labels=pivot_df.columns)

plt.xlabel('Year') 
plt.ylabel('Total Wealth') 
plt.title('A Simple Stacked Area Chart') 
plt.legend(loc='upper left') 

plt.show()

# 数据透视
pivot_df = df.pivot(index='year', columns='country', values='total_wealth')

# 自定义颜色列表
custom_colors = ["#003f5c","#2f4b7c","#665191","#a05195","#d45087","#f95d6a","#ff7c43","#ffa600"]

# 使用样条插值平滑线条
x_smooth = np.linspace(pivot_df.index.min(), pivot_df.index.max(), 300)
pivot_smooth = pd.DataFrame({country: make_interp_spline(pivot_df.index, pivot_df[country])(x_smooth)
                             for country in pivot_df.columns})

# 布局
plt.figure(figsize=(6, 6))

# 绘制堆叠面积图
plt.stackplot(x_smooth,
              pivot_smooth.values.T,
              labels=pivot_smooth.columns,
              colors=custom_colors)
plt.xlabel('Year')
plt.ylabel('Total Wealth')
plt.title('Stacked Area Chart with Smoothing and Customized Colors')
plt.legend(loc='upper left')


plt.show()

# 数据透视
pivot_df = df.pivot(index='year', columns='country', values='total_wealth')

# 自定义颜色列表
custom_colors = ["#003f5c","#2f4b7c","#665191","#a05195","#d45087","#f95d6a","#ff7c43","#ffa600"]

# 自定义顺序
desired_order = ["United States", "China", "Japan", "Germany", "United Kingdom", "France", "India", "Other"]
pivot_df = pivot_df[desired_order]


# 使用样本插值平滑线条
x_smooth = np.linspace(pivot_df.index.min(), pivot_df.index.max(), 300)
pivot_smooth = pd.DataFrame({country: make_interp_spline(pivot_df.index, pivot_df[country])(x_smooth)
                             for country in pivot_df.columns})

# 布局
plt.figure(figsize=(6, 6))

# 绘制堆叠面积图
plt.stackplot(x_smooth,
              pivot_smooth.values.T,
              labels=pivot_smooth.columns,
              colors=custom_colors)
plt.xlabel('Year')
plt.ylabel('Total Wealth')
plt.title('Stacked Area Chart with Smoothing and Customized Colors')
plt.legend(loc='upper left')


plt.show()

# 数据透视
pivot_df = df.pivot(index='year', columns='country', values='total_wealth')

# 自定义颜色列表
custom_colors = ["#003f5c","#2f4b7c","#665191","#a05195","#d45087","#f95d6a","#ff7c43","#ffa600"]

# 自定义排序
desired_order = ["United States", "China", "Japan", "Germany", "United Kingdom", "France", "India", "Other"]
pivot_df = pivot_df[desired_order]

# 使用样本插值平滑线条
x_smooth = np.linspace(pivot_df.index.min(), pivot_df.index.max(), 300)
pivot_smooth = pd.DataFrame({country: make_interp_spline(pivot_df.index, pivot_df[country])(x_smooth)
                             for country in pivot_df.columns})

# 布局
plt.figure(figsize=(8, 8))  
# 绘制堆叠面积图
plt.stackplot(x_smooth, pivot_smooth.values.T, labels=pivot_smooth.columns, colors=custom_colors)

# 获取当前轴
ax = plt.gca()

# 自定义函数注释每年数据
def add_annotations_year(year):
    """
    year： 年份
    结果：每年绘制一条直线，顶部记录当年的财富总额
    """
    
    # 计算财富总额
    y_end = df[df["year"]==year]["total_wealth"].sum()
    
    # 自定义位置
    if year==2021:
        modif_xaxis = -3.3
        modif_yaxis = 20000
    else:
        modif_xaxis = -1.5
        modif_yaxis = 26000
    
    # 添加文本
    plt.text(year+modif_xaxis,
             y_end+modif_yaxis,
             f'${y_end}M',
             fontsize=10,
             color='black',
             fontweight = 'bold')
    
    # 添加线（两个点的直线）
    ax.plot([year, year], 
            [0, y_end*1.05], 
            color='black', 
            linewidth=1)
    
    # 添加点（位于线顶端）
    ax.plot(year, 
            y_end*1.05, 
            marker='o', 
            markersize=5, 
            color='black') 

# 指定年份调用add_annotations_year函数
for year in [2000,2005,2010,2015,2021]:
    add_annotations_year(year)
    
# 自定义函数注释每个国家/地区数据
def add_annotations_country(country, value_placement, amount, color):
    """
    在指定位置注释每个国家的名称、颜色、财富总额
    """
    plt.text(2021.5, value_placement, f'{country} ${amount}M', fontsize=10, color=color, fontweight='bold')

# 自定义参数值country、value_placement、amount、color
countries = ['Rest of the world', 'India', 'France', 'UK', 'Germany', 'Japan', 'China', 'USA']
values_placement = [400000, 310000, 295000, 275000, 260000, 240000, 180000, 70000]
amounts = [142841, 14225, 16159, 16261, 17489, 25692, 85107, 145793]
custom_colors.reverse() # 保证颜色与国家面积图颜色一致

# 遍历国家增加注释
for country, value, amount, color in zip(countries, values_placement, amounts, custom_colors):
    add_annotations_country(country, value, amount, color)

# 标题
plt.text(2000, 320000,
         'Aggregated \nHousehold \nWealth', 
         fontsize=40, 
         color='black',
         fontweight = 'bold')

# 著作信息
plt.text(2000, -50000, 'Data:', fontsize=8, color='black', fontweight = 'bold')
plt.text(2001.4, -50000, 'James Davies, Rodrigo Lluberas and Anthony Shorrocks, Credit Suisse Global Wealth Databook 2022', fontsize=8, color='black')
plt.text(2000, -63000, 'Design:', fontsize=8, color='black', fontweight = 'bold')
plt.text(2001.9, -63000, 'Gilbert Fontana', fontsize=8, color='black')


# 移除部分边框
ax.spines['left'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)

# 删除刻度和标签
ax.tick_params(left=False, labelleft=False)

plt.show()