{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Comparing Nearest Neighbors with and without Neighborhood Components Analysis\n\nAn example comparing nearest neighbors classification with and without\nNeighborhood Components Analysis.\n\nIt will plot the class decision boundaries given by a Nearest Neighbors\nclassifier when using the Euclidean distance on the original features, versus\nusing the Euclidean distance after the transformation learned by Neighborhood\nComponents Analysis. The latter aims to find a linear transformation that\nmaximises the (stochastic) nearest neighbor classification accuracy on the\ntraining set.\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\nfrom matplotlib.colors import ListedColormap\n\nfrom sklearn import datasets\nfrom sklearn.inspection import DecisionBoundaryDisplay\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.neighbors import KNeighborsClassifier, NeighborhoodComponentsAnalysis\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler\n\nn_neighbors = 1\n\ndataset = datasets.load_iris()\nX, y = dataset.data, dataset.target\n\n# we only take two features. We could avoid this ugly\n# slicing by using a two-dim dataset\nX = X[:, [0, 2]]\n\nX_train, X_test, y_train, y_test = train_test_split(\n    X, y, stratify=y, test_size=0.7, random_state=42\n)\n\nh = 0.05  # step size in the mesh\n\n# Create color maps\ncmap_light = ListedColormap([\"#FFAAAA\", \"#AAFFAA\", \"#AAAAFF\"])\ncmap_bold = ListedColormap([\"#FF0000\", \"#00FF00\", \"#0000FF\"])\n\nnames = [\"KNN\", \"NCA, KNN\"]\n\nclassifiers = [\n    Pipeline(\n        [\n            (\"scaler\", StandardScaler()),\n            (\"knn\", KNeighborsClassifier(n_neighbors=n_neighbors)),\n        ]\n    ),\n    Pipeline(\n        [\n            (\"scaler\", StandardScaler()),\n            (\"nca\", NeighborhoodComponentsAnalysis()),\n            (\"knn\", KNeighborsClassifier(n_neighbors=n_neighbors)),\n        ]\n    ),\n]\n\nfor name, clf in zip(names, classifiers):\n    clf.fit(X_train, y_train)\n    score = clf.score(X_test, y_test)\n\n    _, ax = plt.subplots()\n    DecisionBoundaryDisplay.from_estimator(\n        clf,\n        X,\n        cmap=cmap_light,\n        alpha=0.8,\n        ax=ax,\n        response_method=\"predict\",\n        plot_method=\"pcolormesh\",\n        shading=\"auto\",\n    )\n\n    # Plot also the training and testing points\n    plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold, edgecolor=\"k\", s=20)\n    plt.title(\"{} (k = {})\".format(name, n_neighbors))\n    plt.text(\n        0.9,\n        0.1,\n        \"{:.2f}\".format(score),\n        size=15,\n        ha=\"center\",\n        va=\"center\",\n        transform=plt.gca().transAxes,\n    )\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": "3.9.21"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}