class sklearn.cluster.AgglomerativeClustering(n_clusters=2, *, metric='euclidean', memory=None, connectivity=None, compute_full_tree='auto', linkage='ward', distance_threshold=None, compute_distances=False)[source]#

Agglomerative Clustering.

Recursively merges pair of clusters of sample data; uses linkage distance.

Read more in the User Guide.

n_clustersint or None, default=2

The number of clusters to find. It must be None if distance_threshold is not None.

metricstr or callable, default=”euclidean”

Metric used to compute the linkage. Can be “euclidean”, “l1”, “l2”, “manhattan”, “cosine”, or “precomputed”. If linkage is “ward”, only “euclidean” is accepted. If “precomputed”, a distance matrix is needed as input for the fit method.

Added in version 1.2.

Deprecated since version 1.4: metric=None is deprecated in 1.4 and will be removed in 1.6. Let metric be the default value (i.e. "euclidean") instead.

memorystr or object with the joblib.Memory interface, default=None

Used to cache the output of the computation of the tree. By default, no caching is done. If a string is given, it is the path to the caching directory.

connectivityarray-like, sparse matrix, or callable, default=None

Connectivity matrix. Defines for each sample the neighboring samples following a given structure of the data. This can be a connectivity matrix itself or a callable that transforms the data into a connectivity matrix, such as derived from kneighbors_graph. Default is None, i.e, the hierarchical clustering algorithm is unstructured.

For an example of connectivity matrix using kneighbors_graph, see Agglomerative clustering with and without structure.

compute_full_tree‘auto’ or bool, default=’auto’

Stop early the construction of the tree at n_clusters. This is useful to decrease computation time if the number of clusters is not small compared to the number of samples. This option is useful only when specifying a connectivity matrix. Note also that when varying the number of clusters and using caching, it may be advantageous to compute the full tree. It must be True if distance_threshold is not None. By default compute_full_tree is “auto”, which is equivalent to True when distance_threshold is not None or that n_clusters is inferior to the maximum between 100 or 0.02 * n_samples. Otherwise, “auto” is equivalent to False.

linkage{‘ward’, ‘complete’, ‘average’, ‘single’}, default=’ward’

Which linkage criterion to use. The linkage criterion determines which distance to use between sets of observation. The algorithm will merge the pairs of cluster that minimize this criterion.

  • ‘ward’ minimizes the variance of the clusters being merged.

  • ‘average’ uses the average of the distances of each observation of the two sets.

  • ‘complete’ or ‘maximum’ linkage uses the maximum distances between all observations of the two sets.

  • ‘single’ uses the minimum of the distances between all observations of the two sets.

Added in version 0.20: Added the ‘single’ option

For examples comparing different linkage criteria, see Comparing different hierarchical linkage methods on toy datasets.

distance_thresholdfloat, default=None

The linkage distance threshold at or above which clusters will not be merged. If not None, n_clusters must be None and compute_full_tree must be True.

Added in version 0.21.

compute_distancesbool, default=False

Computes distances between clusters even if distance_threshold is not used. This can be used to make dendrogram visualization, but introduces a computational and memory overhead.

Added in version 0.24.

For an example of dendrogram visualization, see Plot Hierarchical Clustering Dendrogram.


The number of clusters found by the algorithm. If distance_threshold=None, it will be equal to the given n_clusters.

labels_ndarray of shape (n_samples)

Cluster labels for each point.


Number of leaves in the hierarchical tree.


The estimated number of connected components in the graph.

Added in version 0.21: n_connected_components_ was added to replace n_components_.


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.

children_array-like of shape (n_samples-1, 2)

The children of each non-leaf node. Values less than n_samples correspond to leaves of the tree which are the original samples. A node i greater than or equal to n_samples is a non-leaf node and has children children_[i - n_samples]. Alternatively at the i-th iteration, children[i][0] and children[i][1] are merged to form node n_samples + i.

distances_array-like of shape (n_nodes-1,)

Distances between nodes in the corresponding place in children_. Only computed if distance_threshold is used or compute_distances is set to True.

See also


Agglomerative clustering but for features instead of samples.


Hierarchical clustering with ward linkage.


>>> from sklearn.cluster import AgglomerativeClustering
>>> import numpy as np
>>> X = np.array([[1, 2], [1, 4], [1, 0],
...               [4, 2], [4, 4], [4, 0]])
>>> clustering = AgglomerativeClustering().fit(X)
>>> clustering
>>> clustering.labels_
array([1, 1, 1, 0, 0, 0])
fit(X, y=None)[source]#

Fit the hierarchical clustering from features, or distance matrix.

Xarray-like, shape (n_samples, n_features) or (n_samples, n_samples)

Training instances to cluster, or distances between instances if metric='precomputed'.


Not used, present here for API consistency by convention.


Returns the fitted instance.

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

Fit and return the result of each sample’s clustering assignment.

In addition to fitting, this method also return the result of the clustering assignment for each sample in the training set.

Xarray-like of shape (n_samples, n_features) or (n_samples, n_samples)

Training instances to cluster, or distances between instances if affinity='precomputed'.


Not used, present here for API consistency by convention.

labelsndarray of shape (n_samples,)

Cluster labels.


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.


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.