Pushing the docs to dev/ for branch: main, commit 0822851f5cb17827939a7d7b4f8c84f43184ae89

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -0,0 +1,54 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "%matplotlib inline"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n# Bisecting K-Means and Regular K-Means Performance Comparison\n\nThis example shows differences between Regular K-Means algorithm and Bisecting K-Means.\n\nWhile K-Means clusterings are different when with increasing n_clusters,\nBisecting K-Means clustering build on top of the previous ones.\n\nThis difference can visually be observed.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "import matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_blobs\nfrom sklearn.cluster import BisectingKMeans, KMeans\n\n\nprint(__doc__)\n\n\n# Generate sample data\nn_samples = 1000\nrandom_state = 0\n\nX, _ = make_blobs(n_samples=n_samples, centers=2, random_state=random_state)\n\n# Number of cluster centers for KMeans and BisectingKMeans\nn_clusters_list = [2, 3, 4, 5]\n\n# Algorithms to compare\nclustering_algorithms = {\n    \"Bisecting K-Means\": BisectingKMeans,\n    \"K-Means\": KMeans,\n}\n\n# Make subplots for each variant\nfig, axs = plt.subplots(\n    len(clustering_algorithms), len(n_clusters_list), figsize=(15, 5)\n)\n\naxs = axs.T\n\nfor i, (algorithm_name, Algorithm) in enumerate(clustering_algorithms.items()):\n    for j, n_clusters in enumerate(n_clusters_list):\n        algo = Algorithm(n_clusters=n_clusters, random_state=random_state)\n        algo.fit(X)\n        centers = algo.cluster_centers_\n\n        axs[j, i].scatter(X[:, 0], X[:, 1], s=10, c=algo.labels_)\n        axs[j, i].scatter(centers[:, 0], centers[:, 1], c=\"r\", s=20)\n\n        axs[j, i].set_title(f\"{algorithm_name} : {n_clusters} clusters\")\n\n\n# Hide x labels and tick labels for top plots and y ticks for right plots.\nfor ax in axs.flat:\n    ax.label_outer()\n    ax.set_xticks([])\n    ax.set_yticks([])\n\nplt.show()"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.9.12"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

dev/_downloads/13db5212719118ea59532c291af3a8f9/plot_bisect_kmeans.ipynb

@@ -0,0 +1,63 @@
+"""
+=============================================================
+Bisecting K-Means and Regular K-Means Performance Comparison
+=============================================================
+
+This example shows differences between Regular K-Means algorithm and Bisecting K-Means.
+
+While K-Means clusterings are different when with increasing n_clusters,
+Bisecting K-Means clustering build on top of the previous ones.
+
+This difference can visually be observed.
+
+"""
+import matplotlib.pyplot as plt
+
+from sklearn.datasets import make_blobs
+from sklearn.cluster import BisectingKMeans, KMeans
+
+
+print(__doc__)
+
+
+# Generate sample data
+n_samples = 1000
+random_state = 0
+
+X, _ = make_blobs(n_samples=n_samples, centers=2, random_state=random_state)
+
+# Number of cluster centers for KMeans and BisectingKMeans
+n_clusters_list = [2, 3, 4, 5]
+
+# Algorithms to compare
+clustering_algorithms = {
+    "Bisecting K-Means": BisectingKMeans,
+    "K-Means": KMeans,
+}
+
+# Make subplots for each variant
+fig, axs = plt.subplots(
+    len(clustering_algorithms), len(n_clusters_list), figsize=(15, 5)
+)
+
+axs = axs.T
+
+for i, (algorithm_name, Algorithm) in enumerate(clustering_algorithms.items()):
+    for j, n_clusters in enumerate(n_clusters_list):
+        algo = Algorithm(n_clusters=n_clusters, random_state=random_state)
+        algo.fit(X)
+        centers = algo.cluster_centers_
+
+        axs[j, i].scatter(X[:, 0], X[:, 1], s=10, c=algo.labels_)
+        axs[j, i].scatter(centers[:, 0], centers[:, 1], c="r", s=20)
+
+        axs[j, i].set_title(f"{algorithm_name} : {n_clusters} clusters")
+
+
+# Hide x labels and tick labels for top plots and y ticks for right plots.
+for ax in axs.flat:
+    ax.label_outer()
+    ax.set_xticks([])
+    ax.set_yticks([])
+
+plt.show()