Summarize

summarize.py

from sklearn.metrics import pairwise_distances_argmin_min

avg = []
for j in range(n_clusters):
    idx = np.where(kmeans.labels_ == j)[0]
    avg.append(np.mean(idx))
closest, _ = pairwise_distances_argmin_min(kmeans.cluster_centers_, encoded)
ordering = sorted(range(n_clusters), key=lambda k: avg[k])
summary = ' '.join([email[closest[idx]] for idx in ordering])