{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "EiRcuZEgBUSr"
   },
   "source": [
    "# Grid Search with Cross Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2B25z9iTBUSx"
   },
   "outputs": [],
   "source": [
    "# import libraries\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 266
    },
    "colab_type": "code",
    "id": "3hi2YJ1YBUS6",
    "outputId": "f6e6d95a-4e9c-4bb4-9441-86eaaf0d1fb5"
   },
   "outputs": [],
   "source": [
    "# data doesn't have headers, so let's create headers\n",
    "_headers = ['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety', 'car']\n",
    "# read in cars dataset\n",
    "df = pd.read_csv('../Dataset/car.data', names=_headers, index_col=None)\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 214
    },
    "colab_type": "code",
    "id": "Y4wiYrMdBUTI",
    "outputId": "32726b67-d1fe-4feb-e0fd-85546b621abb"
   },
   "outputs": [],
   "source": [
    "# encode categorical variables\n",
    "_df = pd.get_dummies(df, columns=['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety'])\n",
    "_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "V8nt2KJZBUTS"
   },
   "outputs": [],
   "source": [
    "# separate features and labels DataFrames\n",
    "features = _df.drop(['car'], axis=1).values\n",
    "labels = _df[['car']].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "85aKwASjBUTa"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "rTR2pG1aBUTo"
   },
   "outputs": [],
   "source": [
    "clf = DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "nKGE6HIRBUTt"
   },
   "outputs": [],
   "source": [
    "params = {'max_depth': np.arange(1, 8)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "wrrJQttkBUT5"
   },
   "outputs": [],
   "source": [
    "clf_cv = GridSearchCV(clf, param_grid=params, cv=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 319
    },
    "colab_type": "code",
    "id": "tjkKzynOBUT_",
    "outputId": "d03ac1a0-c96e-48cb-c8da-ec73f604182c"
   },
   "outputs": [],
   "source": [
    "clf_cv.fit(features, labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "LN-GZzdoBUUO",
    "outputId": "9900ce91-6df3-4bfe-bb0e-23a3dd29dc95"
   },
   "outputs": [],
   "source": [
    "print(\"Tuned Decision Tree Parameters: {}\".format(clf_cv.best_params_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "1vZftcIMBUUd",
    "outputId": "cd468b70-0008-440f-c2d4-23d52e53995a"
   },
   "outputs": [],
   "source": [
    "print(\"Best score is {}\".format(clf_cv.best_score_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 124
    },
    "colab_type": "code",
    "id": "9prZ_aBxBUUp",
    "outputId": "755e6818-ab48-4490-c0a2-4d5b67dcfd1b"
   },
   "outputs": [],
   "source": [
    "model = clf_cv.best_estimator_\n",
    "model"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise7.07.ipynb",
   "provenance": []
  },
  "file_extension": ".py",
  "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"
  },
  "mimetype": "text/x-python",
  "name": "python",
  "npconvert_exporter": "python",
  "pygments_lexer": "ipython3",
  "version": 3
 },
 "nbformat": 4,
 "nbformat_minor": 1
}