流程图（三）利用python绘制桑基图

HsuHeinrich

发布于 2025-01-01 12:44:54

9550

文章被收录于专栏：HsuHeinrichHsuHeinrich

流程图（三）利用python绘制桑基图

桑基图（Sankey diagram）简介

1、桑基图经常用于能源、金融行业，对材料、成本的流动进行可视化分析。现在很多互联网行业还使用桑基图做用户流动性分析，能很好地观察数据成分的变动大小及变动方向。

快速绘制

基于plotly

import plotly.graph_objects as go
import urllib, json

# 导入数据
url = 'https://raw.githubusercontent.com/plotly/plotly.js/master/test/image/mocks/sankey_energy.json'
response = urllib.request.urlopen(url)
data = json.loads(response.read())

# 将所有的"magenta"颜色更改为rgba(255,0,255, 0.8)，并将所有连接颜色更改为其对应的'source'节点颜色且透明度是0.4
opacity = 0.4
data['data'][0]['node']['color'] = ['rgba(255,0,255, 0.8)' if color == "magenta" else color for color in data['data'][0]['node']['color']]
data['data'][0]['link']['color'] = [data['data'][0]['node']['color'][src].replace("0.8", str(opacity))
                                    for src in data['data'][0]['link']['source']]

fig = go.Figure(data=[go.Sankey(
    valueformat = ".0f",
    valuesuffix = "TWh",
    # 定义节点
    node = dict(
      pad = 15,
      thickness = 15,
      line = dict(color = "black", width = 0.5),
      label =  data['data'][0]['node']['label'],
      color =  data['data'][0]['node']['color']
    ),
    # 添加连接
    link = dict(
      source =  data['data'][0]['link']['source'],
      target =  data['data'][0]['link']['target'],
      value =  data['data'][0]['link']['value'],
      label =  data['data'][0]['link']['label'],
      color =  data['data'][0]['link']['color']
))])

fig.update_layout(title_text="Energy forecast for 2050<br>Source: Department of Energy & Climate Change, Tom Counsell via <a href='https://bost.ocks.org/mike/sankey/'>Mike Bostock</a>",
                  font_size=10)

2、基于pyecharts

import pyecharts.options as opts
from pyecharts.charts import Sankey
import urllib, json

# 导入数据
url = 'https://echarts.apache.org/examples/data/asset/data/energy.json'
response = urllib.request.urlopen(url)
data = json.loads(response.read())

c = (
    Sankey()
    .add(
        series_name="",
        nodes=data["nodes"],
        links=data["links"],
        itemstyle_opts=opts.ItemStyleOpts(border_width=1, border_color="#aaa"),
        linestyle_opt=opts.LineStyleOpts(color="source", curve=0.5, opacity=0.5),
        tooltip_opts=opts.TooltipOpts(trigger_on="mousemove"),
    )
    .set_global_opts(title_opts=opts.TitleOpts(title=""))
)

c.render_notebook()

3、基于pysankey

import pandas as pd
from pySankey.sankey import sankey

# 基于source和target，数据可重复出现，出现次数越多，权重越大（即线越粗）
url = "https://raw.githubusercontent.com/anazalea/pySankey/master/pysankey/fruits.txt"
df = pd.read_csv(url, sep=" ", names=["true", "predicted"])

colors = {
    "apple": "#f71b1b",
    "blueberry": "#1b7ef7",
    "banana": "#f3f71b",
    "lime": "#12e23f",
    "orange": "#f78c1b"
}

sankey(df["true"], df["predicted"], aspect=20, colorDict=colors, fontsize=12)

import pandas as pd
from pySankey.sankey import sankey

# 基于source和、target和value，数据可仅出现一次，value即权重
url = "https://raw.githubusercontent.com/anazalea/pySankey/master/pysankey/customers-goods.csv"
df = pd.read_csv(url, sep=",")

sankey(
    left=df["customer"], right=df["good"], 
    leftWeight= df["revenue"], rightWeight=df["revenue"], 
    aspect=20, fontsize=20
)