FileNotFoundError 使用 CHAID 渲染决策树

Question

我用下面的代码得到了CHAID的决策树

independent_variable_columns = ['gender', 'grade', 'no_renewals', 'complaint_count']
dep_variable = 'switch'
tree = Tree.from_pandas_df(
    df,
    dict(zip(independent_variable_columns, ['nominal'] * 38)),
    dep_variable,
    max_depth=2
)
tree.to_tree()
tree.render()

但我收到以下错误

  File "C:\Users\data\AppData\Local\Continuum\anaconda3\lib\site-packages\CHAID\graph.py", line 93, in <listcomp>
    [os.remove(file) for file in self.files]
FileNotFoundError: [WinError 3] The system cannot find the path specified: '/tmp/157840175993116164207458496094.png'

Answer 1

在生成文件名和处理临时文件时，该特定库没有实施最佳实践。这使得他们的代码在 Windows 上以多种方式中断。

我已在 similar issue with the same root cause 上发表评论，提出修改以解决这些问题。

您可以通过运行以下代码在本地解决此问题：

import os
from datetime import datetime
from tempfile import TemporaryDirectory

import plotly.io as pio
import colorlover as cl
from graphviz import Digraph

from CHAID import graph

def Graph_render(self, path, view):
    if path is None:
        path = os.path.join("trees", f"{datetime.now():%Y-%m-%d %H:%M:%S}.gv")
    with TemporaryDirectory() as self.tempdir:
        g = Digraph(
            format="png",
            graph_attr={"splines": "ortho"},
            node_attr={"shape": "plaintext", "labelloc": "b"},
        )
        for node in self.tree:
            image = self.bar_chart(node)
            g.node(str(node.node_id), image=image)
            if node.parent is not None:
                edge_label = f"     ({', '.join(map(str, node.choices))})     \n ")
                g.edge(str(node.parent), str(node.node_id), xlabel=edge_label)

        g.render(path, view=view)

def Graph_bar_chart(self, node):
    fig = {
        "data": [
            {
                "values": list(node.members.values()),
                "labels": list(node.members),
                "showlegend": node.node_id == 0,
                "domain": {"x": [0, 1], "y": [0.4, 1.0]},
                "hole": 0.4,
                "type": "pie",
                "marker_colors": cl.scales["5"]["qual"]["Set1"],
            },
        ],
        "layout": {
            "margin_t": 50,
            "annotations": [{"font_size": 18, "x": 0.5, "y": 0.5}, {"y": [0, 0.2]}],
        },
    }

    if not node.is_terminal:
        p = None if node.p is None else format(node.p, ".5f")
        score = None if node.score is None else format(node.score, ".2f")
        self.append_table(fig, [p, score, node.split.column])

    filename = os.path.join(self.tempdir, f"node-{node.node_id}.png")
    pio.write_image(fig, file=filename, format="png")
    return filename

graph.Graph.render = Graph_render
graph.Graph.bar_chart = Graph_bar_chart

以上是该库中Graph 类的两个方法的重构，切换到使用tempdir.TemporaryDirectory() 处理临时文件，并清理文件名的生成方式。我还冒昧地清理了代码中的一些小问题。

我已经把它变成了pull request to update the project itself。