如何在Pandas&Graphviz家谱生成程序中实现配偶节点相邻

数据结构（CSV） #

原代码 #

from graphviz import Digraph
import pandas as pd
import numpy as np

rawdf = pd.read_csv('/content/drive/MyDrive/ftdata.csv', keep_default_na=False)  ## Change file path
el1 = rawdf[['ID','MotherID','SpouseID']]
el2 = rawdf[['ID','FatherID','SpouseID']]
el1.columns = ['Child', 'ParentID','SpouseID']
el2.columns = el1.columns
el = pd.concat([el1, el2])
el.replace('', np.nan, regex=True, inplace = True)
t = pd.DataFrame({'tmp':['no_entry'+str(i) for i in range(el.shape[0])]})
el['ParentID'].fillna(t['tmp'], inplace=True)
el['SpouseID'].fillna(t['tmp'], inplace=True)
df = el.merge(rawdf, left_index=True, right_index=True, how='left')
df['name'] = df[df.columns[4:6]].apply(lambda x: ' '.join(x.dropna().astype(str)),axis=1)
df = df.drop(['Child','FatherID', 'ID', 'First name', 'Last name'], axis=1)
df = df[['ID', 'name', 'S', 'DoB', 'DoD', 'Place of birth', 'Job', 'ParentID']]

f = Digraph('neato', format='jpg', encoding='utf8', filename='testfile', node_attr={'style': 'filled'},  graph_attr={"concentrate": "true", "splines":"ortho"})
f.attr('node', shape='box')
for index, row in df.iterrows():
    f.node(row['ID'],
           label=
             str(row['name'])
              + '\n' +
             str(row['Job'])
             + '\n'+ 
             str(row['DoB'])
             + '\n' +
             str(row['Place of birth'])
             + '\n†' +
             str(row['DoD']),
           _attributes={'color':'lightpink' if row['S']=='F' else 'lightblue'if row['S']=='M' else 'lightgray'})
for index, row in df.iterrows():
    f.edge(str(row["ParentID"]), str(row["ID"]), label='')
f.view()

问题描述 #

当前生成的家谱中，配偶节点未被分组相邻，导致家谱结构可读性差，需要调整布局让配偶节点显示在同一水平位置且相邻。

解决方案 #

核心修改点 #

1. 去重节点：原代码因合并父母系数据导致节点重复，需去重避免重复渲染
2. 识别唯一配偶对：避免重复处理双向配偶关系（如A→B和B→A只处理一次）
3. 子图强制同层级：通过subgraph给配偶节点添加rank=same属性，强制处于同一水平行
4. 区分配偶与亲子边：用无方向虚线连接配偶，和亲子实线做区分
5. 切换布局引擎：改用dot层级布局，比neato力导向布局更适配家谱结构

修改后的完整代码 #

from graphviz import Digraph
import pandas as pd
import numpy as np

rawdf = pd.read_csv('/content/drive/MyDrive/ftdata.csv', keep_default_na=False)  ## Change file path

# 处理亲子关系数据
el1 = rawdf[['ID','MotherID','SpouseID']]
el2 = rawdf[['ID','FatherID','SpouseID']]
el1.columns = ['Child', 'ParentID','SpouseID']
el2.columns = el1.columns
el = pd.concat([el1, el2])
el.replace('', np.nan, regex=True, inplace = True)
t = pd.DataFrame({'tmp':['no_entry'+str(i) for i in range(el.shape[0])]})
el['ParentID'].fillna(t['tmp'], inplace=True)
el['SpouseID'].fillna(t['tmp'], inplace=True)
df = el.merge(rawdf, left_index=True, right_index=True, how='left')
df['name'] = df[['First name', 'Last name']].apply(lambda x: ' '.join(x.dropna().astype(str)),axis=1)
df = df.drop(['Child','FatherID', 'ID_y', 'First name', 'Last name'], axis=1)
df = df.rename(columns={'ID_x': 'ID'})
df = df[['ID', 'name', 'S', 'DoB', 'DoD', 'Place of birth', 'Job', 'ParentID', 'SpouseID']]
# 去重，避免同一节点重复处理
df = df.drop_duplicates(subset=['ID']).reset_index(drop=True)

# 初始化Graphviz，改用dot层级布局
f = Digraph('dot', format='jpg', encoding='utf8', filename='family_tree', 
            node_attr={'style': 'filled'},  
            graph_attr={"concentrate": "true", "splines":"ortho", "rankdir": "TB"})
f.attr('node', shape='box')

# 添加所有节点，优化标签显示
for index, row in df.iterrows():
    dod_text = f'\n†{row["DoD"]}' if row["DoD"] else ''
    label = (f'{row["name"]}\n{row["Job"]}\n{row["DoB"]}\n{row["Place of birth"]}'
             f'{dod_text}')
    f.node(row['ID'],
           label=label,
           color='lightpink' if row['S']=='F' else 'lightblue' if row['S']=='M' else 'lightgray')

# 添加亲子边，跳过空父/母ID
for index, row in df.iterrows():
    if row['ParentID'] not in t['tmp'].values:
        f.edge(str(row["ParentID"]), str(row["ID"]), label='')

# 处理配偶关系，创建唯一配偶对
processed_couples = set()
for index, row in df.iterrows():
    spouse_id = row['SpouseID']
    if spouse_id not in t['tmp'].values and (spouse_id, row['ID']) not in processed_couples:
        # 子图设置配偶同层级
        with f.subgraph() as s:
            s.attr(rank='same')
            s.node(row['ID'])
            s.node(spouse_id)
        # 添加无方向虚线连接配偶
        f.edge(row['ID'], spouse_id, style='dashed', dir='none')
        processed_couples.add((row['ID'], spouse_id))

f.view()

修改效果说明 #

• 配偶节点会被强制放在同一水平行，相邻显示
• 用虚线区分配偶关系，实线区分亲子关系，结构更清晰
• 优化了空死亡日期的标签显示，避免出现无效字符
• dot布局让家谱保持垂直层级结构，符合传统家谱阅读习惯

内容的提问来源于stack exchange，提问作者Kshitij Khandelwal