Scikit-Learn Clustering

The following Scikit-Learn module types are clustering methods.

Modules

  1. AffinityPropagation
  2. AgglomerativeClustering
  3. Birch
  4. BisectingKMeans
  5. DBSCAN
  6. FeatureAgglomeration
  7. HDBSCAN
  8. KMeans
  9. MeanShift
  10. MiniBatchKMeans
  11. SpectralBiclustering
  12. SpectralClustering
  13. SpectralCoclustering

AffinityPropagation

Scikit-Learn module documentation: AffinityPropagation

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Damping factor for message-passing --skl_damping Float in [0.5, 1.0) None damping
Maximum number of iterations --skl_max_iter Integer ≥ 1 None max_iter

AgglomerativeClustering

Scikit-Learn module documentation: AgglomerativeClustering

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Distance metric for linkage --skl_metric String; see sklearn docs None metric
Linkage criterion --skl_linkage ward | complete | average | single None linkage

Birch

Scikit-Learn module documentation: Birch

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters for the final step --skl_n_clusters Integer ≥ 1 None n_clusters
Radius threshold for subclusters --skl_threshold Float > 0 None threshold
Maximum number of subclusters per node --skl_branching_factor Integer ≥ 1 None branching_factor

BisectingKMeans

Scikit-Learn module documentation: BisectingKMeans

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Maximum number of iterations per bisection --skl_max_iter Integer ≥ 1 None max_iter
Convergence tolerance --skl_tol Float ≥ 0 None tol

DBSCAN

Scikit-Learn module documentation: DBSCAN

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Maximum distance between neighborhood samples --skl_eps Float > 0 None eps
Minimum samples in a neighborhood --skl_min_samples Integer ≥ 1 None min_samples
Distance metric --skl_metric String; see sklearn docs None metric

FeatureAgglomeration

Scikit-Learn module documentation: FeatureAgglomeration

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Distance metric for linkage --skl_metric String; see sklearn docs None metric
Linkage criterion --skl_linkage ward | complete | average | single None linkage

HDBSCAN

Scikit-Learn module documentation: HDBSCAN

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of CPU cores to use --cpus_per_task Integer ≥ 1 None n_jobs
Minimum number of samples in a cluster --skl_min_cluster_size Integer ≥ 2 None min_cluster_size
Minimum samples in a neighborhood --skl_min_samples Integer ≥ 1 None min_samples
Distance metric --skl_metric String; see sklearn docs None metric

KMeans

Scikit-Learn module documentation: KMeans

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Number of centroid initializations --skl_n_init Integer ≥ 1 None n_init
Maximum number of iterations --skl_max_iter Integer ≥ 1 None max_iter
Convergence tolerance --skl_tol Float ≥ 0 None tol

MeanShift

Scikit-Learn module documentation: MeanShift

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of CPU cores to use --cpus_per_task Integer ≥ 1 None n_jobs
Bandwidth for kernel density estimation --skl_bandwidth Float > 0 None bandwidth
Maximum number of iterations --skl_max_iter Integer ≥ 1 None max_iter

MiniBatchKMeans

Scikit-Learn module documentation: MiniBatchKMeans

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Number of centroid initializations --skl_n_init Integer ≥ 1 None n_init
Maximum number of iterations --skl_max_iter Integer ≥ 1 None max_iter
Number of samples per mini-batch --skl_batch_size Integer ≥ 1 None batch_size
Convergence tolerance --skl_tol Float ≥ 0 None tol

SpectralBiclustering

Scikit-Learn module documentation: SpectralBiclustering

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of biclusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Number of singular vectors to use --skl_n_components Integer ≥ 1 None n_components
Number of k-means initializations --skl_n_init Integer ≥ 1 None n_init

SpectralClustering

Scikit-Learn module documentation: SpectralClustering

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of clusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Number of eigenvectors to use --skl_n_components Integer ≥ 1 None n_components
Number of k-means initializations --skl_n_init Integer ≥ 1 None n_init

SpectralCoclustering

Scikit-Learn module documentation: SpectralCoclustering

Arguments

Description Zero2Neuro Argument Possible Values Default Value Scikit-Learn Parameter
Number of biclusters to find --skl_n_clusters Integer ≥ 1 None n_clusters
Number of k-means initializations --skl_n_init Integer ≥ 1 None n_init


This site uses Just the Docs, a documentation theme for Jekyll.