Classification metrics can't handle a mix of continuous and multiclass targets

Question

5. 训练模型

clfcv.fit(X_train, y_train.astype('int'))

6. 使用模型来对测试集进行预测

test_result = clfcv.predict(X_test.astype('int'))

7. 模型评估

import sklearn.metrics as metrics

print("决策树准确度:")
print(metrics.classification_report(y_test,test_result))

但是在运行代码的时候报错了

7. 模型评估

import sklearn.metrics as metrics
print("决策树准确度:")
print(metrics.classification_report(y_test,test_result))
报错:Classification metrics can't handle a mix of continuous and multiclass targets
请问该怎么解决呢

Answer 1

这里感觉是y_test, test_result的类型不一致，之前fit时y_train已转为'int'类型，因此test_result也为'int'类型，而y_test大概不是'int'类型。建议可将y_test转换后再传入classification_report

print(metrics.classification_report(y_test.astype('int'),test_result))