sklearn agglomerative clustering：动态更新集群数量

Question

sklearn.cluster.AgglomerativeClustering 的文档提到，

when varying the number of clusters and using caching, it may be advantageous to compute the full tree.

这似乎意味着可以先计算整棵树，然后根据需要快速更新所需簇的数量，而无需重新计算树（使用缓存）。

但是，似乎没有记录这种更改簇数的过程。我想这样做，但不确定如何进行。

更新：澄清一下，拟合方法不将簇数作为输入： http://scikit-learn.org/stable/modules/generated/sklearn.cluster.AgglomerativeClustering.html#sklearn.cluster.AgglomerativeClustering.fit

Answer 1

您使用参数 memory = 'mycachedir' 设置了一个缓存目录，然后如果您设置 compute_full_tree=True，当您使用不同的 n_clusters 值重新运行 fit 时，它将使用缓存的树而不是每次都重新计算。举例说明如何使用 sklearn 的网格搜索 API:

from sklearn.cluster import AgglomerativeClustering
from sklearn.grid_search import GridSearchCV

ac = AgglomerativeClustering(memory='mycachedir', 
                             compute_full_tree=True)
classifier = GridSearchCV(ac, 
                          {n_clusters: range(2,6)}, 
                          scoring = 'adjusted_rand_score', 
                          n_jobs=-1, verbose=2)
classifier.fit(X,y)

Answer 2

我知道这是一个老问题，但下面的解决方案可能会有所帮助

# scores = input matrix

from scipy.cluster.hierarchy import linkage
from scipy.cluster.hierarchy import cut_tree
from sklearn.metrics import silhouette_score
from sklearn.metrics.pairwise import euclidean_distances

linkage_mat = linkage(scores, method="ward")
euc_scores = euclidean_distances(scores)

n_l = 2
n_h = scores.shape[0]

silh_score = -2
# Selecting the best number of clusters based on the silhouette score
for i in range(n_l, n_h):
    local_labels = list(cut_tree(linkage_mat, n_clusters=i).flatten())
    sc = silhouette_score(
        euc_scores,
        metric="precomputed",
        labels=local_labels,
        random_state=42)
    if silh_score < sc:
        silh_score = sc
        labels = local_labels

n_clusters = len(set(labels))
print(f"Optimal number of clusters: {n_clusters}")
print(f"Best silhouette score: {silh_score}")
# ...

sklearn agglomerative clustering：动态更新集群数量

sklearn agglomerative clustering: dynamically updating the number of clusters

python

scikit-learn

hierarchical-clustering