我的二元分类问题中的所有数据都由X和表示y。现在，我对这些数据进行分层交叉验证，如下所示：

scoring = {'accuracy' : make_scorer(accuracy_score), 
           'precision' : make_scorer(precision_score),
           'recall' : make_scorer(recall_score), 
           'f1_score' : make_scorer(f1_score)}

model=RandomForestClassifier(n_estimators=50,random_state=10) 

results = cross_validate(estimator=model, X=X, y=y, cv=10, scoring=scoring)

如果运行代码，我将得到以下结果：

Accuracy : 0.5436815489342804
Precision : 0.020165565854870747
Recall : 0.11013513513513513
F1_score : 0.03315023853741518

X现在，我拆分y如下：

#Test, training data split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, stratify = y)

#Split the training data into validation set 
X_val_train, X_val_test, y_val_train, y_val_test = train_test_split(X_train, y_train, test_size = 0.1, random_state=0, stratify=y_train )

X_train现在，如果我像以前一样在and上执行相同的交叉验证过程X_train，我将得到以下结果：

Accuracy : 0.8424393681243558
Precision : 0.47658195862621017
Recall: 0.1964997354963851
F1_score : 0.2773991741912054

我不明白为什么结果如此不同以及为什么会发生这种情况。