RandomForestClassifier抛出错误:一个字段包含逗号分隔值

import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder

# 示例数据集
data = {
    'feature1': ['1,2,3', '4,5,6', '7,8,9'],
    'feature2': ['A', 'B', 'C'],
    'target': [0, 1, 0]
}

df = pd.DataFrame(data)

# 处理逗号分隔值
df['feature1'] = df['feature1'].apply(lambda x: [int(i) for i in x.split(',')])

# 将列表转换为适合模型的格式（例如，使用平均值）
df['feature1'] = df['feature1'].apply(lambda x: sum(x) / len(x))

# 处理类别特征
label_encoder = LabelEncoder()
df['feature2'] = label_encoder.fit_transform(df['feature2'])

# 分割数据集
X = df[['feature1', 'feature2']]
y = df['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练模型
clf = RandomForestClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)
print(y_pred)