---

一、现象

......
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
recall = recall_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
......

执行语句到**“recall = recall_score(y_test, y_pred)”**这里发现报错

pos_label=1 is not a valid label. It should be one of [‘0’, ‘1’]

二、解决方案

查看y_test的数据类型，也就是标签y

df['label'].describle()

发现dtype：object，怪不得报错！

转成数值类型，即可解决

df['label'] = pd.numeric(df['label'], errors='coerce')

重新跑，跑到**“recall = recall_score(y_test, y_pred)”**，不会再报错误

---

解决方案：带疑问，多交流，勤动手，频思考