这有点不同,因为对于非二进制分类,交叉值分数不能计算精度/召回率,所以需要使用recision-score、recall-score和手工进行交叉验证。参数average='micro'计算全局精度/召回。在import numpy as np
from sklearn import cross_validation
from sklearn import datasets
from sklearn import svm
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import precision_score, recall_score
iris = datasets.load_iris()
skf = StratifiedKFold(n_splits=10)
clf = svm.SVC(kernel='linear', C=1)
X = iris.data
y = iris.target
precision_scores = []
recall_scores = []
for train_index, test_index in skf.split(X, y):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
y_pred = clf.fit(X_train, y_train).predict(X_test)
precision_scores.append(precision_score(y_test, y_pred, average='micro'))
recall_scores.append(recall_score(y_test, y_pred, average='micro'))
print(precision_scores)
print("Recall: %0.2f (+/- %0.2f)" % (np.mean(precision_scores), np.std(precision_scores) * 2))
print(recall_scores)
print("Recall: %0.2f (+/- %0.2f)" % (np.mean(recall_scores), np.std(recall_scores) * 2))