class sklearn.cluster.SpectralBiclustering(n_clusters=3, *, method='bistochastic', n_components=6, n_best=3, svd_method='randomized', n_svd_vecs=None, mini_batch=False, init='k-means++', n_init=10, random_state=None)[source]#

Spectral biclustering (Kluger, 2003).

Partitions rows and columns under the assumption that the data has an underlying checkerboard structure. For instance, if there are two row partitions and three column partitions, each row will belong to three biclusters, and each column will belong to two biclusters. The outer product of the corresponding row and column label vectors gives this checkerboard structure.

Read more in the User Guide.

n_clustersint or tuple (n_row_clusters, n_column_clusters), default=3

The number of row and column clusters in the checkerboard structure.

method{‘bistochastic’, ‘scale’, ‘log’}, default=’bistochastic’

Method of normalizing and converting singular vectors into biclusters. May be one of ‘scale’, ‘bistochastic’, or ‘log’. The authors recommend using ‘log’. If the data is sparse, however, log normalization will not work, which is why the default is ‘bistochastic’.


if method='log', the data must not be sparse.

n_componentsint, default=6

Number of singular vectors to check.

n_bestint, default=3

Number of best singular vectors to which to project the data for clustering.

svd_method{‘randomized’, ‘arpack’}, default=’randomized’

Selects the algorithm for finding singular vectors. May be ‘randomized’ or ‘arpack’. If ‘randomized’, uses randomized_svd, which may be faster for large matrices. If ‘arpack’, uses scipy.sparse.linalg.svds, which is more accurate, but possibly slower in some cases.

n_svd_vecsint, default=None

Number of vectors to use in calculating the SVD. Corresponds to ncv when svd_method=arpack and n_oversamples when svd_method is ‘randomized`.

mini_batchbool, default=False

Whether to use mini-batch k-means, which is faster but may get different results.

init{‘k-means++’, ‘random’} or ndarray of shape (n_clusters, n_features), default=’k-means++’

Method for initialization of k-means algorithm; defaults to ‘k-means++’.

n_initint, default=10

Number of random initializations that are tried with the k-means algorithm.

If mini-batch k-means is used, the best initialization is chosen and the algorithm runs once. Otherwise, the algorithm is run for each initialization and the best solution chosen.

random_stateint, RandomState instance, default=None

Used for randomizing the singular value decomposition and the k-means initialization. Use an int to make the randomness deterministic. See Glossary.

rows_array-like of shape (n_row_clusters, n_rows)

Results of the clustering. rows[i, r] is True if cluster i contains row r. Available only after calling fit.

columns_array-like of shape (n_column_clusters, n_columns)

Results of the clustering, like rows.

row_labels_array-like of shape (n_rows,)

Row partition labels.

column_labels_array-like of shape (n_cols,)

Column partition labels.

biclusters_tuple of two ndarrays

Convenient way to get row and column indicators together.


Number of features seen during fit.

Added in version 0.24.

feature_names_in_ndarray of shape (n_features_in_,)

Names of features seen during fit. Defined only when X has feature names that are all strings.

Added in version 1.0.

See also


Spectral Co-Clustering algorithm (Dhillon, 2001).



>>> from sklearn.cluster import SpectralBiclustering
>>> import numpy as np
>>> X = np.array([[1, 1], [2, 1], [1, 0],
...               [4, 7], [3, 5], [3, 6]])
>>> clustering = SpectralBiclustering(n_clusters=2, random_state=0).fit(X)
>>> clustering.row_labels_
array([1, 1, 1, 0, 0, 0], dtype=int32)
>>> clustering.column_labels_
array([1, 0], dtype=int32)
>>> clustering
SpectralBiclustering(n_clusters=2, random_state=0)
property biclusters_#

Convenient way to get row and column indicators together.

Returns the rows_ and columns_ members.

fit(X, y=None)[source]#

Create a biclustering for X.

Xarray-like of shape (n_samples, n_features)

Training data.


Not used, present for API consistency by convention.


SpectralBiclustering instance.


Row and column indices of the i’th bicluster.

Only works if rows_ and columns_ attributes exist.


The index of the cluster.

row_indndarray, dtype=np.intp

Indices of rows in the dataset that belong to the bicluster.

col_indndarray, dtype=np.intp

Indices of columns in the dataset that belong to the bicluster.


Get metadata routing of this object.

Please check User Guide on how the routing mechanism works.


A MetadataRequest encapsulating routing information.


Get parameters for this estimator.

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.


Parameter names mapped to their values.


Shape of the i’th bicluster.


The index of the cluster.


Number of rows in the bicluster.


Number of columns in the bicluster.

get_submatrix(i, data)[source]#

Return the submatrix corresponding to bicluster i.


The index of the cluster.

dataarray-like of shape (n_samples, n_features)

The data.

submatrixndarray of shape (n_rows, n_cols)

The submatrix corresponding to bicluster i.


Works with sparse matrices. Only works if rows_ and columns_ attributes exist.


Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.


Estimator parameters.

selfestimator instance

Estimator instance.