.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/cluster/plot_linkage_comparison.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. or to run this example in your browser via JupyterLite or Binder .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_cluster_plot_linkage_comparison.py: ================================================================ Comparing different hierarchical linkage methods on toy datasets ================================================================ This example shows characteristics of different linkage methods for hierarchical clustering on datasets that are "interesting" but still in 2D. The main observations to make are: - single linkage is fast, and can perform well on non-globular data, but it performs poorly in the presence of noise. - average and complete linkage perform well on cleanly separated globular clusters, but have mixed results otherwise. - Ward is the most effective method for noisy data. While these examples give some intuition about the algorithms, this intuition might not apply to very high dimensional data. .. GENERATED FROM PYTHON SOURCE LINES 25-39 .. code-block:: Python # Authors: The scikit-learn developers # SPDX-License-Identifier: BSD-3-Clause import time import warnings from itertools import cycle, islice import matplotlib.pyplot as plt import numpy as np from sklearn import cluster, datasets from sklearn.preprocessing import StandardScaler .. GENERATED FROM PYTHON SOURCE LINES 40-42 Generate datasets. We choose the size big enough to see the scalability of the algorithms, but not too big to avoid too long running times .. GENERATED FROM PYTHON SOURCE LINES 42-63 .. code-block:: Python n_samples = 1500 noisy_circles = datasets.make_circles( n_samples=n_samples, factor=0.5, noise=0.05, random_state=170 ) noisy_moons = datasets.make_moons(n_samples=n_samples, noise=0.05, random_state=170) blobs = datasets.make_blobs(n_samples=n_samples, random_state=170) rng = np.random.RandomState(170) no_structure = rng.rand(n_samples, 2), None # Anisotropicly distributed data X, y = datasets.make_blobs(n_samples=n_samples, random_state=170) transformation = [[0.6, -0.6], [-0.4, 0.8]] X_aniso = np.dot(X, transformation) aniso = (X_aniso, y) # blobs with varied variances varied = datasets.make_blobs( n_samples=n_samples, cluster_std=[1.0, 2.5, 0.5], random_state=170 ) .. GENERATED FROM PYTHON SOURCE LINES 64-65 Run the clustering and plot .. GENERATED FROM PYTHON SOURCE LINES 65-179 .. code-block:: Python # Set up cluster parameters plt.figure(figsize=(9 * 1.3 + 2, 14.5)) plt.subplots_adjust( left=0.02, right=0.98, bottom=0.001, top=0.96, wspace=0.05, hspace=0.01 ) plot_num = 1 default_base = {"n_neighbors": 10, "n_clusters": 3} datasets = [ (noisy_circles, {"n_clusters": 2}), (noisy_moons, {"n_clusters": 2}), (varied, {"n_neighbors": 2}), (aniso, {"n_neighbors": 2}), (blobs, {}), (no_structure, {}), ] for i_dataset, (dataset, algo_params) in enumerate(datasets): # update parameters with dataset-specific values params = default_base.copy() params.update(algo_params) X, y = dataset # normalize dataset for easier parameter selection X = StandardScaler().fit_transform(X) # ============ # Create cluster objects # ============ ward = cluster.AgglomerativeClustering( n_clusters=params["n_clusters"], linkage="ward" ) complete = cluster.AgglomerativeClustering( n_clusters=params["n_clusters"], linkage="complete" ) average = cluster.AgglomerativeClustering( n_clusters=params["n_clusters"], linkage="average" ) single = cluster.AgglomerativeClustering( n_clusters=params["n_clusters"], linkage="single" ) clustering_algorithms = ( ("Single Linkage", single), ("Average Linkage", average), ("Complete Linkage", complete), ("Ward Linkage", ward), ) for name, algorithm in clustering_algorithms: t0 = time.time() # catch warnings related to kneighbors_graph with warnings.catch_warnings(): warnings.filterwarnings( "ignore", message="the number of connected components of the " + "connectivity matrix is [0-9]{1,2}" + " > 1. Completing it to avoid stopping the tree early.", category=UserWarning, ) algorithm.fit(X) t1 = time.time() if hasattr(algorithm, "labels_"): y_pred = algorithm.labels_.astype(int) else: y_pred = algorithm.predict(X) plt.subplot(len(datasets), len(clustering_algorithms), plot_num) if i_dataset == 0: plt.title(name, size=18) colors = np.array( list( islice( cycle( [ "#377eb8", "#ff7f00", "#4daf4a", "#f781bf", "#a65628", "#984ea3", "#999999", "#e41a1c", "#dede00", ] ), int(max(y_pred) + 1), ) ) ) plt.scatter(X[:, 0], X[:, 1], s=10, color=colors[y_pred]) plt.xlim(-2.5, 2.5) plt.ylim(-2.5, 2.5) plt.xticks(()) plt.yticks(()) plt.text( 0.99, 0.01, ("%.2fs" % (t1 - t0)).lstrip("0"), transform=plt.gca().transAxes, size=15, horizontalalignment="right", ) plot_num += 1 plt.show() .. image-sg:: /auto_examples/cluster/images/sphx_glr_plot_linkage_comparison_001.png :alt: Single Linkage, Average Linkage, Complete Linkage, Ward Linkage :srcset: /auto_examples/cluster/images/sphx_glr_plot_linkage_comparison_001.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 1.821 seconds) .. _sphx_glr_download_auto_examples_cluster_plot_linkage_comparison.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: binder-badge .. image:: images/binder_badge_logo.svg :target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/1.6.X?urlpath=lab/tree/notebooks/auto_examples/cluster/plot_linkage_comparison.ipynb :alt: Launch binder :width: 150 px .. container:: lite-badge .. image:: images/jupyterlite_badge_logo.svg :target: ../../lite/lab/index.html?path=auto_examples/cluster/plot_linkage_comparison.ipynb :alt: Launch JupyterLite :width: 150 px .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_linkage_comparison.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_linkage_comparison.py ` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: plot_linkage_comparison.zip ` .. include:: plot_linkage_comparison.recommendations .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_