skmultilearn.cluster.networkx module

class skmultilearn.cluster.NetworkXLabelGraphClusterer(graph_builder, method)[source]

Bases: skmultilearn.cluster.base.LabelGraphClustererBase

Cluster label space with NetworkX community detection

This clusterer constructs a NetworkX representation of the Label Graph generated by graph builder and detects communities in it using methods from the NetworkX library. Detected communities are converted to a label space clustering.

  • graph_builder (a GraphBuilderBase inherited transformer) – the graph builder to provide the adjacency matrix and weight map for the underlying graph
  • method (string) –

    the community detection method to use, this clusterer supports the following community detection methods:

    Method name string Description
    louvain Detecting communities with largest modularity using incremental greedy search
    label_propagation Detecting communities from multiple async label propagation on the graph

networkx.Graph – the networkx Graph object containing the graph representation of graph builder’s adjacency matrix and weights


{ ‘weight’ : list of values in edge order of graph edges } – edge weights stored in a format recognizable by the networkx module


If you use this clusterer please cite the igraph paper and the clustering paper:

    author = {Hagberg, Aric and Swart, Pieter and S Chult, Daniel},
    year = {2008},
    month = {01},
    title = {Exploring Network Structure, Dynamics, and Function Using NetworkX},
    booktitle = {Proceedings of the 7th Python in Science Conference}

  title={Fast unfolding of communities in large networks},
  author={Blondel, Vincent D and Guillaume, Jean-Loup and Lambiotte, Renaud and Lefebvre, Etienne},
  journal={Journal of statistical mechanics: theory and experiment},
  publisher={IOP Publishing}


An example code for using this clusterer with a classifier looks like this:

from sklearn.ensemble import RandomForestClassifier
from skmultilearn.problem_transform import LabelPowerset
from skmultilearn.cluster import NetworkXLabelGraphClusterer, LabelCooccurrenceGraphBuilder
from skmultilearn.ensemble import LabelSpacePartitioningClassifier

# construct base forest classifier
base_classifier = RandomForestClassifier(n_estimators=1000)

# construct a graph builder that will include
# label relations weighted by how many times they
# co-occurred in the data, without self-edges
graph_builder = LabelCooccurrenceGraphBuilder(
    weighted = True,
    include_self_edges = False

# setup problem transformation approach with sparse matrices for random forest
problem_transform_classifier = LabelPowerset(classifier=base_classifier,
    require_dense=[False, False])

# setup the clusterer to use, we selected the modularity-based approach
clusterer = NetworkXLabelGraphClusterer(graph_builder=graph_builder, method='louvain')

# setup the ensemble metaclassifier
classifier = LabelSpacePartitioningClassifier(problem_transform_classifier, clusterer)

# train, y_train)

# predict
predictions = classifier.predict(X_test)

For more use cases see the label relations exploration guide.

fit_predict(X, y)[source]

Performs clustering on y and returns list of label lists

Builds a label graph using the provided graph builder’s transform method on y and then detects communities using the selected method.

Sets self.weights_ and self.graph_.

  • X (None) – currently unused, left for scikit compatibility
  • y (scipy.sparse) – label space of shape (n_samples, n_labels)

label space division, each sublist represents labels that are in that community

Return type:

arrray of arrays of label indexes (numpy.ndarray)