data_utils.py 文件源码

def perc_var_explained(X,k):
    """
    Compute the percentage of variance explained defined as between sum of squares
    divided but the total sum of squares.
    WARNING: It will take a while.
    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:
    --------
    pve: percentage of variance explained
    """

    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)
    tot_withinss = sum(dist**2)
    totss = sum(pdist(X)**2)/X.shape[0]
    betweenss = totss - tot_withinss
    pve = (betweenss/totss  *100)

    return pve