{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# An example of K-Means++ initialization\n\nAn example to show the output of the :func:`sklearn.cluster.kmeans_plusplus`\nfunction for generating initial seeds for clustering.\n\nK-Means++ is used as the default initialization for `k_means`.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn.cluster import kmeans_plusplus\nfrom sklearn.datasets import make_blobs\n\n# Generate sample data\nn_samples = 4000\nn_components = 4\n\nX, y_true = make_blobs(\n    n_samples=n_samples, centers=n_components, cluster_std=0.60, random_state=0\n)\nX = X[:, ::-1]\n\n# Calculate seeds from k-means++\ncenters_init, indices = kmeans_plusplus(X, n_clusters=4, random_state=0)\n\n# Plot init seeds along side sample data\nplt.figure(1)\ncolors = [\"#4EACC5\", \"#FF9C34\", \"#4E9A06\", \"m\"]\n\nfor k, col in enumerate(colors):\n    cluster_data = y_true == k\n    plt.scatter(X[cluster_data, 0], X[cluster_data, 1], c=col, marker=\".\", s=10)\n\nplt.scatter(centers_init[:, 0], centers_init[:, 1], c=\"b\", s=50)\nplt.title(\"K-Means++ Initialization\")\nplt.xticks([])\nplt.yticks([])\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": "3.11.14"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}