Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

co-cluster size zero #24

Open
Jayesh-Kumar-Sundaram opened this issue Aug 12, 2022 · 0 comments
Open

co-cluster size zero #24

Jayesh-Kumar-Sundaram opened this issue Aug 12, 2022 · 0 comments

Comments

@Jayesh-Kumar-Sundaram
Copy link

Jayesh-Kumar-Sundaram commented Aug 12, 2022

To find the optimal number of co-clusters, I used the coclust.evaluation.internal.best_modularity_partition() function and identified that there are five optimal clusters
code:
int_eval = coclust.evaluation.internal.best_modularity_partition(in_data=data['doc_term_matrix'],
nbr_clusters_range=range(2,50),
n_rand_init=1)

Then when I clustered the data using CoclustMod for 5 clusters I found one co-cluster to be of size (0,0). When I cluster the data to get 2-4 clusters I always clusters which has some size but If I try to get clusters of size >=5, I also end up with only 4 clusters whose size id not (0,0)
code:
model = CoclustMod(init=None, max_iter=20, n_clusters=5, n_init=1, random_state=0, tol=1e-09) #int_eval[0] #Best model
model.fit(X=data['doc_term_matrix'])
plot_cluster_sizes(model)

What is the issue? Why do I get co-clusters of size (0,0). I didn't find the co-cluster size to be (0,0) when I used "CoclustSpecMod" function.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant