问没有交叉验证的Scikit学习GridSearchCV (无监督学习)

EN

from sklearn.metrics import silhouette_score as sc

def cv_silhouette_scorer(estimator, X):
    estimator.fit(X)
    cluster_labels = estimator.labels_
    num_labels = len(set(cluster_labels))
    num_samples = len(X.index)
    if num_labels == 1 or num_labels == num_samples:
        return -1
    else:
        return sc(X, cluster_labels)

cv = [(slice(None), slice(None))]
gs = GridSearchCV(estimator=sklearn.cluster.MeanShift(), param_grid=param_dict, 
                  scoring=cv_silhouette_scorer, cv=cv, n_jobs=-1)
gs.fit(df[cols_of_interest])

from multiprocessing.dummy import Pool
from sklearn.cluster import KMeans
import functools

kmeans = KMeans()

# define your custom function for passing into each thread
def find_cluster(n_clusters, kmeans, X):
    from sklearn.metrics import silhouette_score  # you want to import in the scorer in your function

    kmeans.set_params(n_clusters=n_clusters)  # set n_cluster
    labels = kmeans.fit_predict(X)  # fit & predict
    score = silhouette_score(X, labels)  # get the score

    return score

# Now's the parallel implementation
clusters = [3, 4, 5]
pool = Pool()
results = pool.map(functools.partial(find_cluster, kmeans=kmeans, X=X), clusters)
pool.close()
pool.join()

# print the results
print(results)  # will print a list of scores that corresponds to the clusters list