chapter_4.py 文件源码

def use_sbs_with_knn(columns, X_train, X_test, y_train, y_test):
    knn = KNeighborsClassifier(n_neighbors=2)
    sbs = SBS(knn, k_features=1)
    sbs.fit(X_train, y_train)

    k_feat = [len(k) for k in sbs.subsets_]
    plt.plot(k_feat, sbs.scores_, marker='o')
    plt.ylim([0.7, 1.1])
    plt.ylabel('Accuracy')
    plt.xlabel('Number of features')
    plt.grid()
    plt.show()

    k5 = list(sbs.subsets_[8])
    print(columns[1:][k5])

    knn.fit(X_train, y_train)
    print("Training accuracy: %s" % knn.score(X_train, y_train))
    print("Test accuracy: %s" % knn.score(X_test, y_test))

    knn.fit(X_train[:, k5], y_train)
    print("Training accuracy: %s" % knn.score(X_train[:, k5], y_train))
    print("Test accuracy: %s" % knn.score(X_test[:, k5], y_test))