data_utils.py 文件源码

def avg_within_ss(X, k):
    """
    Compute the average within-cluster sum of squares. The code here can be
    found "almost" anywhere online

    Params:
    --------
    X: numpy array with observations and features to be clustered
    k: number of clusters

    Returns:
    --------
    avgwithinss: average within-cluster sum of squares
    """

    model = MiniBatchKMeans(init='k-means++', n_clusters=k, batch_size=50,
                          n_init=3, max_no_improvement=10, verbose=0)
    model.fit(X)

    centroids = model.cluster_centers_
    dist_c = cdist(X, centroids, 'euclidean')
    dist   = np.min(dist_c, axis=1)
    avgwithinss = sum(dist**2)/X.shape[0]

    return avgwithinss