{
  "nbformat_minor": 0, 
  "nbformat": 4, 
  "cells": [
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "%matplotlib inline"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "\n# Demo of DBSCAN clustering algorithm\n\n\nFinds core samples of high density and expands clusters from them.\n\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "print(__doc__)\n\nimport numpy as np\n\nfrom sklearn.cluster import DBSCAN\nfrom sklearn import metrics\nfrom sklearn.datasets.samples_generator import make_blobs\nfrom sklearn.preprocessing import StandardScaler"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "Generate sample data\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "source": [
        "centers = [[1, 1], [-1, -1], [1, -1]]\nX, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,\n                            random_state=0)\n\nX = StandardScaler().fit_transform(X)"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "Compute DBSCAN\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "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)\n\nprint('Estimated number of clusters: %d' % n_clusters_)\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\"\n      % metrics.adjusted_rand_score(labels_true, labels))\nprint(\"Adjusted Mutual Information: %0.3f\"\n      % metrics.adjusted_mutual_info_score(labels_true, labels))\nprint(\"Silhouette Coefficient: %0.3f\"\n      % metrics.silhouette_score(X, labels))"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }, 
    {
      "source": [
        "Plot result\n"
      ], 
      "cell_type": "markdown", 
      "metadata": {}
    }, 
    {
      "execution_count": null, 
      "cell_type": "code", 
      "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)\n          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(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=14)\n\n    xy = X[class_member_mask & ~core_samples_mask]\n    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),\n             markeredgecolor='k', markersize=6)\n\nplt.title('Estimated number of clusters: %d' % n_clusters_)\nplt.show()"
      ], 
      "outputs": [], 
      "metadata": {
        "collapsed": false
      }
    }
  ], 
  "metadata": {
    "kernelspec": {
      "display_name": "Python 2", 
      "name": "python2", 
      "language": "python"
    }, 
    "language_info": {
      "mimetype": "text/x-python", 
      "nbconvert_exporter": "python", 
      "name": "python", 
      "file_extension": ".py", 
      "version": "2.7.13", 
      "pygments_lexer": "ipython2", 
      "codemirror_mode": {
        "version": 2, 
        "name": "ipython"
      }
    }
  }
}