高级编程技术第十七次作业 sklearn

from sklearn import metrics
from sklearn import datasets
from sklearn.model_selection import KFold
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier

data = datasets.make_classification(n_samples = 1000, n_features = 10)
kf = KFold(n_splits = 10)

for tr_ind, te_ind in kf.split(data[0]):
    X_tr, X_te = data[0][tr_ind], data[0][te_ind]
    Y_tr, Y_te = data[1][tr_ind], data[1][te_ind]
    clfs = [GaussianNB(), SVC(C = 0.1, kernel = 'rbf', gamma = 0.1), RandomForestClassifier(n_estimators = 100)]
    for clf in clfs:
        clf.fit(X_tr, Y_tr)
        pred = clf.predict(X_te)
        print(str(clf))
        print('Accuracy: ', metrics.accuracy_score(Y_te, pred))
        print('F1_score: ', metrics.f1_score(Y_te, pred))
        print('AUC ROC: ', metrics.roc_auc_score(Y_te, pred), '\n')