knn_classify_sklearn.py 文件源码

def cross_validation():
    x_train, x_test, y_train, y_test = load_data()
    k_lst = list(range(1, 30))
    lst_scores = []

    for k in k_lst:
        knn = KNeighborsClassifier(n_neighbors=k)
        scores = cross_val_score(knn, x_train, y_train, cv=10, scoring='accuracy')
        lst_scores.append(scores.mean())

    # changing to misclassification error
    MSE = [1 - x for x in lst_scores]
    optimal_k = k_lst[MSE.index(min(MSE))]
    print "The optimal number of neighbors is %d" % optimal_k
    # plot misclassification error vs k
    # plt.plot(k_lst, MSE)
    # plt.ylabel('Misclassification Error')
    plt.plot(k_lst, lst_scores)
    plt.xlabel('Number of Neighbors K')
    plt.ylabel('correct classification rate')
    plt.show()