sklearn中K-Fold交叉验证中每个折叠的预测值

Question

我已经使用 python sklearn，

对我拥有的数据集执行了 10 折交叉验证

result = cross_val_score(best_svr, X, y, cv=10, scoring='r2')
print(result.mean())

我已经能够得到r2分数的平均值作为最终结果。我想知道是否有办法打印出每次折叠的预测值（在本例中为 10 组值）。

Answer 1

我相信您正在寻找 cross_val_predict 函数。

Answer 2

要打印每个折叠的预测，

for k in range(2,10):
    result = cross_val_score(best_svr, X, y, cv=k, scoring='r2')
    print(k, result.mean())
    y_pred = cross_val_predict(best_svr, X, y, cv=k)
    print(y_pred)

Answer 3

一个迟到的答案，只是添加到@jh314，cross_val_predict做了return所有的预测，但我们不知道每个预测属于哪个折叠。为此，我们需要提供折叠数，而不是整数：

import seaborn as sns
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_val_predict, StratifiedKFold 

iris = sns.load_dataset('iris')
X=iris.iloc[:,:4]
y=(iris['species'] == "versicolor").astype('int')

rfc = RandomForestClassifier()
skf = StratifiedKFold(n_splits=10,random_state=111,shuffle=True)

pred = cross_val_predict(rfc, X, y, cv=skf)

现在我们遍历 Kfold 对象并提取与每个折叠对应的预测：

fold_pred = [pred[j] for i, j in skf.split(X,y)]
fold_pred

[array([0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0]),
 array([0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0]),
 array([0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1]),
 array([0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0]),
 array([0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0]),
 array([0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0]),
 array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0]),
 array([0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0]),
 array([0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0]),
 array([0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0])]

sklearn中K-Fold交叉验证中每个折叠的预测值

Predicted values of each fold in K-Fold Cross Validation in sklearn

python

scikit-learn

regression

cross-validation