python第15周作业

代码

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


datasets = datasets.make_classification(n_samples=1000, n_features=10)
kf = cross_validation.KFold(len(datasets[0]), n_folds=10, shuffle=True)
clf = GaussianNB()
for train_index, test_index in kf:
    X_train, y_train = datasets[0][train_index], datasets[1][train_index]
    X_test, y_test = datasets[0][test_index], datasets[1][test_index]
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    acc = metrics.accuracy_score(y_test, pred)
    f1 = metrics.f1_score(y_test, pred)
    auc = metrics.roc_auc_score(y_test, pred)
    print("acc:", acc, "f1:", f1, "auc", auc)

    for C_data in [1e-02, 1e-01, 1e00, 1e01, 1e02]:
        clf = SVC(C=C_data, kernel='rbf', gamma=0.1)
        clf.fit(X_train, y_train)
        pred = clf.predict(X_test)
        acc = metrics.accuracy_score(y_test, pred)
        f1 = metrics.f1_score(y_test, pred)
        auc = metrics.roc_auc_score(y_test, pred)
        print("acc:", acc, "f1:", f1, "auc", auc)

    for n_data in [10,100,1000]:
        clf=RandomForestClassifier(n_estimators=n_data)
        clf.fit(X_train,y_train)
        pred=clf.predict(X_test)
        acc = metrics.accuracy_score(y_test, pred)
        f1 = metrics.f1_score(y_test, pred)
        auc = metrics.roc_auc_score(y_test, pred)
        print("acc:", acc, "f1:", f1, "auc", auc)