桑基图绘制

桑基图还是很简单的，直接调用pyecharts就行，套用我的代码即可实现。

注意：1.节点名称唯一。

2.关系用的节点必须是已经创建的。

首先上效果图：

代码如下：

#coding='utf-8'
from pyecharts import options as opts
from pyecharts.charts import Sankey
#问题是节点名称不能一样
#所有关键词和主题词是节点，然后在同一年份的目标指向是主题词；主题词间又根据时间进行指向
#更新：四个关键词为一行，一个主题词为一行，间隔一行为年
nodes=[   # 所有节点名称
    #关键词，使用后缀无空格代表15-16，后缀一个空格代表17-18，后缀两个空格代表19-20
    {"name": "图书馆"},{"name": "数字"},{"name": "资源"},{"name": "互联网"},
    {"name": "大数据"},{"name": "突发事件"},{"name": "政府"},{"name": "媒体"},
    {"name": "文献整理"},{"name": "数字化"},{"name": "口述资料"},{"name": "古籍"},
    {"name": "数字资源"},{"name": "版权"},{"name": "作品"},{"name": "语义"}, 
    {"name": "知识"},{"name": "信息熵"},{"name": "产业链"},{"name": "关联数据"},
    {"name": "阅读推广"},{"name": "农民工"},{"name": "公民"},{"name": "满意度"},
    #15-16
    {"name": "图书馆 "},{"name": "阅读 "},{"name": "信息服务 "},{"name": "公共 "},
    {"name": "知识 "},{"name": "科学 "},{"name": "大数据 "},{"name": "专利 "},
    {"name": "文献 "},{"name": "文化遗产 "},{"name": "医药 "},{"name": "数字化 "},
    {"name": "文献整理 "},{"name": "出土 "},{"name": "藏文 "},{"name": "佛教 "},
    {"name": "科技馆 "},{"name": "科学素养 "},{"name": "档案 "},{"name": "保障体系 "},  
    {"name": "数字人文 "},{"name": "扶贫 "},{"name": "西北 "},{"name": "贫困 "},    
    #17-18
    {"name": "档案  "},{"name": "公共卫生  "},{"name": "在线健康社区  "},{"name": "大数据  "},
    {"name": "文献整理  "},{"name": "出土  "},{"name": "史料  "},{"name": "民间  "},
    {"name": "图书馆  "},{"name": "公共图书馆  "},{"name": "阅读推广  "},{"name": "知识服务  "},
    {"name": "数据库  "},{"name": "知识流动  "},{"name": "科技成果  "},{"name": "转化  "},
    {"name": "情报  "},{"name": "知识图谱  "},{"name": "突发事件  "},{"name": "危机  "},
    {"name": "学术论文  "},{"name": "科研人员  "},{"name": "学术交流  "},{"name": "知识  "},
    #19-20 over
    #主题词 start 
    {"name": "图书馆建设"},
    {"name": "大数据舆情"},
    {"name": "文献数字化"},
    {"name": "知识产权"},
    {"name": "数据科学"},
    {"name": "信息服务"},
    #15-16over
    {"name": "图书馆建设 "},
    {"name": "大数据科研 "},
    {"name": "文献数字化 "},
    {"name": "古籍文献整理 "},
    {"name": "信息素养教育 "},
    {"name": "信息扶贫 "},
    #17-18over
    {"name": "大数据健康  "},
    {"name": "古籍文献整理  "},
    {"name": "信息服务  "},
    {"name": "信息产业  "},
    {"name": "大数据舆情  "},
    {"name": "数据科学  "},
    #19-20 over
]

links = [  # 每一条链路的数据，包含：父节点source + 子节点target + 数据值value（根据权重*100不四舍五入）
    #一年的——两年链接——新一年的
    #第一年的关键词需要链接后两年的
    #先将1年的关键词连接到对应的主题词，然后匹配下一年对应的关键词，接着关键词继续链接到对应的主题词
    {"source": "图书馆", "target": "图书馆建设", "value": 3},   
    {"source": "数字", "target": "图书馆建设", "value": 1},
    {"source": "资源", "target": "图书馆建设", "value": 2},
    {"source": "互联网", "target": "图书馆建设", "value": 1},
    {"source": "大数据", "target": "大数据舆情", "value": 2},   
    {"source": "突发事件", "target": "大数据舆情", "value": 2},
    {"source": "政府", "target": "大数据舆情", "value": 1},
    {"source": "媒体", "target": "大数据舆情", "value": 1},
    {"source": "文献整理", "target": "文献数字化", "value": 3},   
    {"source": "数字化", "target": "文献数字化", "value": 2},
    {"source": "口述资料", "target": "文献数字化", "value": 1},
    {"source": "古籍", "target": "文献数字化", "value": 2},
    {"source": "数字资源", "target": "知识产权", "value": 1},   
    {"source": "版权", "target": "知识产权", "value": 2},
    {"source": "作品", "target": "知识产权", "value": 1},
    {"source": "语义", "target": "知识产权", "value": 1},
    {"source": "知识", "target": "数据科学", "value": 2},   
    {"source": "信息熵", "target": "数据科学", "value": 1},
    {"source": "产业链", "target": "数据科学", "value": 1},
    {"source": "关联数据", "target": "数据科学", "value": 1},
    {"source": "阅读推广", "target": "信息服务", "value": 2},   
    {"source": "农民工", "target": "信息服务", "value": 1},
    {"source": "公民", "target": "信息服务", "value": 2},
    {"source": "满意度", "target": "信息服务", "value": 1},#15-16关键词链接到主题词
    #15-16主题词连接到17-18关键词，同时需要15-16主题词链接到19-20关键词
    {"source": "图书馆建设", "target": "图书馆 ", "value": 3},   
    {"source": "图书馆建设", "target": "图书馆  ", "value": 6},
    {"source": "大数据舆情", "target": "大数据 ", "value": 4},
    {"source": "大数据舆情", "target": "大数据  ", "value": 3},
    {"source": "大数据舆情", "target": "突发事件  ", "value": 2},
    {"source": "文献数字化", "target": "文献整理 ", "value": 4},
    {"source": "文献数字化", "target": "数字化 ", "value": 1},   
    {"source": "文献数字化", "target": "文献整理  ", "value": 1},    
    {"source": "数据科学", "target": "知识 ", "value": 3},
    {"source": "数据科学", "target": "知识  ", "value": 3},
    {"source": "信息服务", "target": "阅读推广  ", "value": 2},
    #开始将17-18年关键词链接到当年主题词
    {"source": "图书馆 ", "target": "图书馆建设 ", "value": 6},
    {"source": "阅读 ", "target": "图书馆建设 ", "value": 2},   
    {"source": "信息服务 ", "target": "图书馆建设 ", "value": 1},
    {"source": "公共 ", "target": "图书馆建设 ", "value": 1},
    {"source": "知识 ", "target": "大数据科研 ", "value": 3},
    {"source": "科学 ", "target": "大数据科研 ", "value": 2},   
    {"source": "大数据 ", "target": "大数据科研 ", "value": 4},
    {"source": "专利 ", "target": "大数据科研 ", "value": 1},
    {"source": "文献 ", "target": "文献数字化 ", "value": 4},
    {"source": "文化遗产 ", "target": "文献数字化 ", "value": 1},   
    {"source": "医药 ", "target": "文献数字化 ", "value": 1},
    {"source": "数字化 ", "target": "文献数字化 ", "value": 2},
    {"source": "文献整理 ", "target": "古籍文献整理 ", "value": 4},
    {"source": "出土 ", "target": "古籍文献整理 ", "value": 1},   
    {"source": "藏文 ", "target": "古籍文献整理 ", "value": 1},
    {"source": "佛教 ", "target": "古籍文献整理 ", "value": 1},
    {"source": "科技馆 ", "target": "信息素养教育 ", "value": 2},
    {"source": "科学素养 ", "target": "信息素养教育 ", "value": 3},   
    {"source": "档案 ", "target": "信息素养教育 ", "value": 1},
    {"source": "保障体系 ", "target": "信息素养教育 ", "value": 1},
    {"source": "数字人文 ", "target": "信息扶贫 ", "value": 1},
    {"source": "扶贫 ", "target": "信息扶贫 ", "value": 2},   
    {"source": "西北 ", "target": "信息扶贫 ", "value": 1},
    {"source": "贫困 ", "target": "信息扶贫 ", "value": 1},
    #17-18主题词连接到19-20关键词
    {"source": "图书馆建设 ", "target": "图书馆  ", "value": 3},
    {"source": "大数据科研 ", "target": "大数据  ", "value": 3},   
    {"source": "大数据科研 ", "target": "知识  ", "value": 1},  
    {"source": "古籍文献整理 ", "target": "文献整理  ", "value": 4},
    {"source": "古籍文献整理 ", "target": "出土  ", "value": 1},
    {"source": "信息素养教育 ", "target": "档案  ", "value": 1},
    #开始将19-20年关键词链接到当年主题词
    {"source": "档案  ", "target": "大数据健康  ", "value": 3},   
    {"source": "公共卫生  ", "target": "大数据健康  ", "value": 2},
    {"source": "在线健康社区  ", "target": "大数据健康  ", "value": 1},
    {"source": "大数据  ", "target": "大数据健康  ", "value": 3},
    {"source": "文献整理  ", "target": "古籍文献整理  ", "value": 4},
    {"source": "出土  ", "target": "古籍文献整理  ", "value": 1},   
    {"source": "史料  ", "target": "古籍文献整理  ", "value": 1},
    {"source": "民间  ", "target": "古籍文献整理  ", "value": 2},
    {"source": "图书馆  ", "target": "信息服务  ", "value": 3},
    {"source": "公共图书馆  ", "target": "信息服务  ", "value": 2},   
    {"source": "阅读推广  ", "target": "信息服务  ", "value": 2},
    {"source": "知识服务  ", "target": "信息服务  ", "value": 1},
    {"source": "数据库  ", "target": "信息产业  ", "value": 4},
    {"source": "知识流动  ", "target": "信息产业  ", "value": 2},   
    {"source": "科技成果  ", "target": "信息产业  ", "value": 2},
    {"source": "转化  ", "target": "信息产业  ", "value": 1},
    {"source": "情报  ", "target": "大数据舆情  ", "value": 5},
    {"source": "知识图谱  ", "target": "大数据舆情  ", "value": 3},
    {"source": "突发事件  ", "target": "大数据舆情  ", "value": 3},   
    {"source": "危机  ", "target": "大数据舆情  ", "value": 1},
    {"source": "学术论文  ", "target": "数据科学  ", "value": 3},
    {"source": "科研人员  ", "target": "数据科学  ", "value": 3},
    {"source": "学术交流  ", "target": "数据科学  ", "value": 1},   
    {"source": "知识  ", "target": "数据科学  ", "value": 1},
]

c = (
    Sankey()
    .add(
        "",
        nodes,
        links,
        linestyle_opt=opts.LineStyleOpts(opacity=0.2, curve=0.5, color="source"),
        label_opts=opts.LabelOpts(position="right"),
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="主题演化"))
    
)
c.render("主题演化.html")    #生成HTML文件