mlessentials/Lab08/Exercise8.01/Exercise_8_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8AgQ_HS9i40B"
   },
   "outputs": [],
   "source": [
    "from sklearn import neighbors, datasets, model_selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "TluW5qEojQHo"
   },
   "outputs": [],
   "source": [
    "# dataset\n",
    "cancer = datasets.load_breast_cancer()\n",
    "\n",
    "# target\n",
    "y = cancer.target\n",
    "\n",
    "# features\n",
    "X = cancer.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "NBmvMbQ1j6zQ"
   },
   "outputs": [],
   "source": [
    "# no arguments specified\n",
    "knn = neighbors.KNeighborsClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "tWS3Dqfgj30k",
    "outputId": "fcf0e80d-25d0-490a-ead1-2264528a3bc9"
   },
   "outputs": [],
   "source": [
    "# 10 folds, scored on precision\n",
    "cv = model_selection.cross_val_score(knn, X, y, cv=10, scoring='precision')\n",
    "\n",
    "# precision scores\n",
    "print(cv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "w_F9k2hdj_8V",
    "outputId": "d51240c4-c8a2-498c-86d5-3681adbc81a1"
   },
   "outputs": [],
   "source": [
    "# average over all folds\n",
    "print(round(cv.mean(), 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "mM_XnnNQkbrx",
    "outputId": "5dfaee9d-958c-4854-c270-47841c9853a6"
   },
   "outputs": [],
   "source": [
    "# k = 15\n",
    "knn = neighbors.KNeighborsClassifier(n_neighbors=15)\n",
    "\n",
    "cv = model_selection.cross_val_score(knn, X, y, cv=10, scoring='precision')\n",
    "\n",
    "print(round(cv.mean(), 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 70
    },
    "colab_type": "code",
    "id": "VSpsCUkYog-B",
    "outputId": "ae3ac9bf-83e9-4719-c76a-606f868abf5b"
   },
   "outputs": [],
   "source": [
    "def evaluate_knn(k):\n",
    "    knn = neighbors.KNeighborsClassifier(n_neighbors=k)\n",
    "    cv = model_selection.cross_val_score(knn, X, y, cv=10, scoring='precision')\n",
    "    print(round(cv.mean(), 2))\n",
    "\n",
    "evaluate_knn(k=7)\n",
    "evaluate_knn(k=3)\n",
    "evaluate_knn(k=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "oTu-nTHPsRfH",
    "outputId": "9f72c262-5ad1-497c-ab56-2db620f12669"
   },
   "outputs": [],
   "source": [
    "# k =5, weights evaluated using distance\n",
    "knn = neighbors.KNeighborsClassifier(n_neighbors=5, weights='distance')\n",
    "\n",
    "cv = model_selection.cross_val_score(knn, X, y, cv=10, scoring='precision')\n",
    "\n",
    "print(round(cv.mean(), 2))"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise_8_1.ipynb",
   "provenance": []
  },
  "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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}