数据分析进阶-Python绘制桑基图

前言

通过绘制桑基图来呈现不同时期用户的状态变更~

代码

import pandas as pd

data = pd.read_excel('data-2.xlsx', sheet_name = 'Sheet2')

# 取桑基图的节点
node = list()
each_node = list()
for i in data['col1']:
    each_node.append(i)
    
for i in data['col2']:
    each_node.append(i)

each_node = list(set(each_node))
for j in each_node:
    if j in ['2019回流期','2019睡眠期','2019衰退期','2019成长期-重启','2019成长期-起步',
             '2020回流期','2020睡眠期','2020衰退期','2020成长期-重启','2020成长期-起步',
           '2021回流期','2021睡眠期','2021衰退期','2021成长期-重启','2021成长期-起步']:
        continue
    dic = {}
    dic['name'] = j
    node.append(dic)


# 取桑基图的边
link = list()
for i in data.values.tolist():
    dic={}
    dic['source'] = i[0]
    dic['target'] = i[1]
    dic['value'] = i[2]
    link.append(dic)


from pyecharts import options as opts
from pyecharts.charts import Sankey

pic = (
    Sankey(init_opts=opts.InitOpts(width='1200px',height='600px')).add('',
         node,
         link,
         node_width=30, node_gap=10, node_align="left",
         linestyle_opt=opts.LineStyleOpts(opacity = 0.3, curve = 0.5, color = 'source'),
         label_opts=opts.LabelOpts(position = 'right'),
 
    )
)

pic.render_notebook()

结果示例