main.py 文件源码

def calculate(X, y):
    kf = KFold(len(data), n_folds=5, shuffle=True, random_state=42)
    best_k, best_score = 0, 0
    for k in xrange(1, 51):
        knn = KNeighborsClassifier(n_neighbors=k)
        score = cross_val_score(knn, X, y, cv=kf, scoring='accuracy').mean()
        if score > best_score:
            best_score = score
            best_k = k
    return best_k, best_score