Silhouettes：聚类结果衡量指标

import numpy as np
from sklearn import datasets
from sklearn.metrics import pairwise_distances
from sklearn.preprocessing import LabelEncoder


def silhouette_samples(X, labels, metric='euclidean', **kwds):
    le = LabelEncoder()
    labels = le.fit_transform(labels)
    unique_labels = le.classes_
    distances = pairwise_distances(X, metric=metric, **kwds)
    intra_clust_dists = np.ones(distances.shape[0], dtype=distances.dtype)
    inter_clust_dists = np.inf * intra_clust_dists
    for curr_label in unique_labels:
        mask = curr_label == labels
        current_distances = distances[mask]
        n_samples_curr_lab = np.sum(mask) - 1
        if n_samples_curr_lab != 0:
            intra_clust_dists[mask] = np.sum(current_distances[:, mask], axis=1) / n_samples_curr_lab
        for other_label in unique_labels:
            if other_label != curr_label: