I am doing a random forest model on PC orders data, which is mostly in Chinese. I have done the model and accuracy checks. However, I can’t seem to generate the image due to a UnicodeEncodeError, which most likely is because of the Chinese characters contained in the dataset. I have tried StringIO and BytesIO, but nothing seems to work.

Here are my imports:

from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn import tree
from sklearn.tree import export_graphviz
import pydot
from IPython.display import Image
import six
import sys
sys.modules['sklearn.externals.six'] = six
from io import StringIO,BytesIO

Here is my random forest

from sklearn.ensemble import RandomForestClassifier

X = finaldata.drop(columns=['是否赢单'])  
y = finaldata['是否赢单']

categorical_cols = X.select_dtypes(include=['object']).columns
numerical_cols = X.select_dtypes(include=['number']).columns

preprocessor = ColumnTransformer(
    transformers=[
        ('num', 'passthrough', numerical_cols),
        ('cat', OneHotEncoder(handle_unknown='ignore'), categorical_cols)
    ])

clf = Pipeline(steps=[
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(random_state=42))
])

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

clf.fit(X_train, y_train)

y_pred = clf.predict(X_test)

and here is the plotting code

feature_names = clf.named_steps['preprocessor'].get_feature_names_out()

single_tree = clf.named_steps['classifier'].estimators_[0]

dot_data = StringIO()
export_graphviz(single_tree, out_file=dot_data, 
                filled=True, rounded=True,
                special_characters=True,
                feature_names=feature_names, 
                class_names=['Loss', 'Win'])

dot_data_str = dot_data.getvalue()

(graph,) = pydot.graph_from_dot_data(dot_data_str)
graph.write_png('decision_tree.png')

Image(filename='decision_tree.png')

Here is the error message

UnicodeEncodeError                        Traceback (most recent call last)
Cell In [18], line 13
     11 # Draw the graph using pydot
     12 (graph,) = pydot.graph_from_dot_data(dot_data.getvalue())
---> 13 graph.write_png('decision_tree.png')
     15 # Display the image
     16 Image(filename='decision_tree.png')

File c:UsersTheodoreAppDataLocalProgramsPythonPython310libsite-packagespydot.py:1743, in Dot.__init__.<locals>.new_method(path, f, prog, encoding)
   1739 def new_method(
   1740         path, f=frmt, prog=self.prog,
   1741         encoding=None):
   1742     """Refer to docstring of method `write.`"""
-> 1743     self.write(
   1744         path, format=f, prog=prog,
   1745         encoding=encoding)

File c:UsersTheodoreAppDataLocalProgramsPythonPython310libsite-packagespydot.py:1828, in Dot.write(self, path, prog, format, encoding)
   1826         f.write(s)
   1827 else:
-> 1828     s = self.create(prog, format, encoding=encoding)
   1829     with io.open(path, mode='wb') as f:
   1830         f.write(s)
...
File c:UsersTheodoreAppDataLocalProgramsPythonPython310libencodingscp1252.py:19, in IncrementalEncoder.encode(self, input, final)
     18 def encode(self, input, final=False):
---> 19     return codecs.charmap_encode(input,self.errors,encoding_table)[0]

UnicodeEncodeError: 'charmap' codec can't encode characters in position 163-166: character maps to <undefined>