Getting different results on the same data set

[alooferyj]

Hi,

Am I supposed to get different clustering result from each run on the same data set? I was running the following code:

univariate_ts_datasets = np.expand_dims(np.random.rand(200, 60), axis=2)
num_clusters = 3

CPU Model

for j in range(5):
ksc = KShapeClusteringCPU(num_clusters, centroid_init='zero', max_iter=100, n_jobs=-1)
ksc.fit(univariate_ts_datasets)

labels = ksc.labels_ # or ksc.predict(univariate_ts_datasets)
cluster_centroids = ksc.centroids_
print(labels)

My understanding is that there's nothing random in the algo since I set the centroid init to be zero. But I get different results, e.g. sometimes the first ts and second ts belong to the same cluster and sometimes they don't

Thanks,
James

[HaojunLi]

Hi James,
K-Shape indeed has randomness. In your code, you set centroid init to zero, but k-Shape will randomly assign time series into clusters as an initialization. Please check here:

Also, when a cluster becomes empty during iterations, k-Shape will randomly assign a time series to that empty cluster. If you want to have a deterministic result, you need to set a random seed. I hope my answer can help.
Best,
Haojun