{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Demo of DBSCAN clustering algorithm\n\nFinds core samples of high density and expands clusters from them.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import numpy as np\n\nfrom sklearn.cluster import DBSCAN\nfrom sklearn import metrics\nfrom sklearn.datasets import make_blobs\nfrom sklearn.preprocessing import StandardScaler"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Generate sample data\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "centers = [[1, 1], [-1, -1], [1, -1]]\nX, labels_true = make_blobs(\n    n_samples=750, centers=centers, cluster_std=0.4, random_state=0\n)\n\nX = StandardScaler().fit_transform(X)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Compute DBSCAN\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "db = DBSCAN(eps=0.3, min_samples=10).fit(X)\ncore_samples_mask = np.zeros_like(db.labels_, dtype=bool)\ncore_samples_mask[db.core_sample_indices_] = True\nlabels = db.labels_\n\n# Number of clusters in labels, ignoring noise if present.\nn_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)\nn_noise_ = list(labels).count(-1)\n\nprint(\"Estimated number of clusters: %d\" % n_clusters_)\nprint(\"Estimated number of noise points: %d\" % n_noise_)\nprint(\"Homogeneity: %0.3f\" % metrics.homogeneity_score(labels_true, labels))\nprint(\"Completeness: %0.3f\" % metrics.completeness_score(labels_true, labels))\nprint(\"V-measure: %0.3f\" % metrics.v_measure_score(labels_true, labels))\nprint(\"Adjusted Rand Index: %0.3f\" % metrics.adjusted_rand_score(labels_true, labels))\nprint(\n    \"Adjusted Mutual Information: %0.3f\"\n    % metrics.adjusted_mutual_info_score(labels_true, labels)\n)\nprint(\"Silhouette Coefficient: %0.3f\" % metrics.silhouette_score(X, labels))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Plot result\n\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n\n# Black removed and is used for noise instead.\nunique_labels = set(labels)\ncolors = [plt.cm.Spectral(each) for each in np.linspace(0, 1, len(unique_labels))]\nfor k, col in zip(unique_labels, colors):\n    if k == -1:\n        # Black used for noise.\n        col = [0, 0, 0, 1]\n\n    class_member_mask = labels == k\n\n    xy = X[class_member_mask & core_samples_mask]\n    plt.plot(\n        xy[:, 0],\n        xy[:, 1],\n        \"o\",\n        markerfacecolor=tuple(col),\n        markeredgecolor=\"k\",\n        markersize=14,\n    )\n\n    xy = X[class_member_mask & ~core_samples_mask]\n    plt.plot(\n        xy[:, 0],\n        xy[:, 1],\n        \"o\",\n        markerfacecolor=tuple(col),\n        markeredgecolor=\"k\",\n        markersize=6,\n    )\n\nplt.title(\"Estimated number of clusters: %d\" % n_clusters_)\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
}