Ecosyste.ms: Repos
An open API service providing repository metadata for many open source software ecosystems.
Package Usage: pypi: clusim
Clustering simliarity
7 versions
Latest release: about 4 years ago
204 downloads last month
View more package details: https://packages.ecosyste.ms/registries/pypi.org/packages/clusim
View more repository details: https://repos.ecosyste.ms/hosts/GitHub/repositories/Hoosier-Clusters%2Fclusim
Dependent Repos 2
lodovicoazzini/unboxer
Heatmap Clustering to Understand the Misbehaviours Exposed by Automatically Generated Test Inputs- * requirements.txt
Size: 63.5 MB - Last synced: 10 months ago - Pushed: almost 2 years ago
sunfanyunn/vGraph
Official code for "vGraph: A Generative Model for Joint CommunityDetection and Node Representation Learning" (Neurips 2019)- * requirements.txt
Size: 869 KB - Last synced: 7 months ago - Pushed: 7 months ago
dpacassi/dynamic-event-detection-in-data-streams
- * app/data_processing/requirements.txt
Size: 60.7 MB - Last synced: about 1 year ago - Pushed: about 4 years ago
wrongu/modularity
- ==0.4 requirements.txt
Size: 1.71 MB - Last synced: about 1 month ago - Pushed: almost 2 years ago
junipertcy/bipartiteSBM
A Bayesian model+algorithm for community detection in bipartite networks- >=0.3.1 requirements.txt
Size: 4.1 MB - Last synced: over 1 year ago - Pushed: over 3 years ago
University-of-Windsor/NICASN
Discovering clusters in social networks is of fundamental and practical interest. This paper presents a novel clustering strategy for large-scale highly-connected social net- works. We propose a new hybrid clustering technique based on non-negative matrix fac- torization and independent component analysis for finding complex relationships among users of a large-scale network. We extract the important features of the network and then perform clustering on independent and important components of the network. Above this, we introduce a new k-means centroid initialization method by which we achieve higher performance. We apply our approach on four well-known social networks: Face- book, Twitter, Academia and Youtube. The experimental results show that our approach generally achieves better results in terms of the Silhouette coefficient compared to well- known clustering methods such as Hierarchical Louvain, Multiple Local Community detection, and k-means++. In general, our approach outperforms the state-of-the-art techniques when dealing with complex and highly-connected networks- ==0.4 requirements.txt
Size: 20 MB - Last synced: about 1 year ago - Pushed: about 1 year ago
letiziaia/multilayer-alignment
- * Pipfile
- ==0.4 Pipfile.lock
Size: 250 KB - Last synced: 3 months ago - Pushed: 3 months ago
zohdit/DeepAtash
- ==0.4 IMDB/requirements.txt
- ==0.4 MNIST/requirements.txt
Size: 610 MB - Last synced: 2 months ago - Pushed: 9 months ago