python-2.7 - 从字符串而不是文件中读取networkx中的点图

Question

根据 documentation here read_dot()方法将文件句柄作为输入。

即使它工作正常，如果我这样做，

g = nx.drawing.nx_agraph.read_dot(dotFile)

哪里 dotFile是文件句柄。但是，如果我有 dot变量中的格式化图形，如何以 nx 图形格式导入？

编辑 -
我的变量看起来像这样，

dotFormat = """
digraph G{
edge [dir=forward]
node [shape=plaintext]
0 [label="0 (None)"]
0 -> 7 [label="root"]
1 [label="1 (The)"]
4 [label="4 (great Indian Circus)"]
4 -> 4 [label="compound"]
4 -> 1 [label="det"]
4 -> 4 [label="amod"]
5 [label="5 (is)"]
6 [label="6 (in)"]
7 [label="7 (Mumbai)"]
7 -> 6 [label="case"]
7 -> 5 [label="cop"]
7 -> 4 [label="nsubj"]
}
"""

编辑 2 - 我也尝试阅读 py_dot然后像这样转换为networkx图。

pg = pydot.graph_from_dot_data(dotFormat)
g = nx.nx_pydot.from_pydot(pg)

然后我收到以下错误

if P.get_strict(None): # pydot bug: get_strict() shouldn't take argument
AttributeError: 'list' object has no attribute 'get_strict'

我该怎么办？

Answer 1

您可以通过显式使用 pygraphviz 加载图形，然后将其转换为 networkx 图(在本例中为 MultiDiGraph)来实现。

In [1]: import pygraphviz

In [2]: from networkx.drawing import nx_agraph

In [3]: dotFormat = """
digraph G{
edge [dir=forward]
node [shape=plaintext]
0 [label="0 (None)"]
0 -> 7 [label="root"]
1 [label="1 (The)"]
4 [label="4 (great Indian Circus)"]
4 -> 4 [label="compound"]
4 -> 1 [label="det"]
4 -> 4 [label="amod"]
5 [label="5 (is)"]
6 [label="6 (in)"]
7 [label="7 (Mumbai)"]
7 -> 6 [label="case"]
7 -> 5 [label="cop"]
7 -> 4 [label="nsubj"]
}
"""

In [4]: G = nx_agraph.from_agraph(pygraphviz.AGraph(dotFormat))