Clustering model

gistfile1.txt

minibatch = False
true_k = 4

if minibatch:
    km = MiniBatchKMeans(n_clusters = true_k, init='k-means++', n_init=1,
                         init_size=1000, batch_size=1000, verbose = False)
else:
    km = KMeans(n_clusters=true_k, init='k-means++', max_iter=100, n_init=1,
                verbose = False)

print("Clustering sparse data with %s" % km)
t0 = time()
km.fit(X)
print("done in %0.3fs" % (time() - t0))
print()