{"id":5471,"library":"scikit-network","title":"Scikit-network","description":"Scikit-network is a Python library for the analysis of large graphs, providing state-of-the-art algorithms for clustering, classification, ranking, embedding, and more. It is currently at version 0.33.5 and actively maintained with frequent minor releases that include new features, bug fixes, and Python version support.","status":"active","version":"0.33.5","language":"en","source_language":"en","source_url":"https://github.com/sknetwork-team/scikit-network","tags":["graph algorithms","network analysis","clustering","classification","ranking","embedding","graph neural networks"],"install":[{"cmd":"pip install scikit-network","lang":"bash","label":"Install stable version"}],"dependencies":[{"reason":"Core dependency for numerical operations, graph representation.","package":"numpy","optional":false},{"reason":"Core dependency for sparse matrix operations and scientific computing.","package":"scipy","optional":false}],"imports":[{"note":"Common clustering algorithm.","symbol":"Louvain","correct":"from sknetwork.clustering import Louvain"},{"note":"Example graph dataset for quick experimentation.","symbol":"KarateClub","correct":"from sknetwork.data import karate_club"},{"note":"Example of a classification algorithm.","symbol":"DiffusionClassifier","correct":"from sknetwork.classification import DiffusionClassifier"},{"note":"Example of a ranking algorithm.","symbol":"PageRank","correct":"from sknetwork.ranking import PageRank"}],"quickstart":{"code":"from sknetwork.data import karate_club\nfrom sknetwork.clustering import Louvain\n\n# Load an example graph (Karate Club dataset)\ngraph = karate_club()\nadjacency = graph.adjacency\n\n# Apply Louvain clustering algorithm\nlouvain = Louvain()\nlabels = louvain.fit_predict(adjacency)\n\nprint(f\"Number of nodes: {adjacency.shape[0]}\")\nprint(f\"Detected cluster labels (first 10): {labels[:10]}\")\nprint(f\"Unique clusters found: {len(set(labels))}\")","lang":"python","description":"This quickstart demonstrates how to load a sample graph and apply the Louvain clustering algorithm to detect communities. It prints the number of nodes, a snippet of the assigned labels, and the total number of unique clusters found."},"warnings":[{"fix":"Review the documentation for `sknetwork.clustering`, `sknetwork.classification`, `sknetwork.ranking`, and `sknetwork.gnn` modules. Update method calls and parameter names to match the new API (e.g., use `fit_predict` or `fit_transform`).","message":"Major API changes for clustering, classification, ranking, and GNN algorithms. Methods like `fit_transform` were introduced, and parameter names were changed (e.g., `seeds` to `labels` for classification, `seeds` to `weights` for ranking).","severity":"breaking","affected_versions":"0.29.0 and later"},{"fix":"If you were using the `membership` parameter in soft classification or clustering algorithms, update your code to use `probs` instead.","message":"The parameter `membership` was renamed to `probs` in soft classification and clustering algorithms.","severity":"breaking","affected_versions":"0.31.0 and later"},{"fix":"Ensure your Python environment is running version 3.10 or newer. Upgrade your Python interpreter if necessary to use the latest scikit-network versions.","message":"Support for older Python versions has been dropped. Python 3.9 was dropped in 0.33.5, and Python 3.8 was dropped in 0.33.0.","severity":"breaking","affected_versions":"0.33.0 and later"},{"fix":"If your application relied on hierarchical Louvain embedding, you will need to find an alternative approach or algorithm for hierarchical graph analysis, as this specific feature is no longer available.","message":"The 'hierarchical Louvain embedding' feature was removed.","severity":"deprecated","affected_versions":"0.32.1 and later"},{"fix":"Migrate to newer link prediction methods provided by the library, such as nearest neighbor methods, which were introduced alongside this change. Consult the `sknetwork.link_prediction` module documentation.","message":"First-order methods for link prediction were removed.","severity":"deprecated","affected_versions":"0.29.0 and later"}],"env_vars":null,"last_verified":"2026-04-13T00:00:00.000Z","next_check":"2026-07-12T00:00:00.000Z"}