tp2_solutions.py 文件源码

def ex3_kmeans(X, y):
    """ Tries to find the best value for K when applying the KMeans algorithm
    on X, y. There are multiple ways to score a model but here we count what is
    the ratio of clusters with a negative Silhouette score and try to minimize
    it, for K from 2 to 20.

    Returns:
        best_k: the value of K that gives the best score.
        best_score: the score associated with best_k.
    """
    best_k = 1
    best_score = -1

    for k in range(2, 20+1):
        model = KMeans(k).fit(X, y)

        scores = metrics.silhouette_samples(X, model.labels_)
        negative_scores_count = len([x for x in scores if x < 0])
        model_score = negative_scores_count / float(len(scores))

        print "K=%d, score=%f" % (k, model_score)

        if model_score > best_score:
            best_score = model_score
            best_k = k

    # Unsurprisingly the best K is usually 2 because we have two classes of
    # messages: spams and hams.
    return best_k, best_score


# Ex 4