{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Y8oDtb1a1soZ"
   },
   "source": [
    "# Compute Confusion Matrix for a Classification Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "j6OMqdIo1soc"
   },
   "outputs": [],
   "source": [
    "# import libraries\n",
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 194
    },
    "colab_type": "code",
    "id": "oxPjA6Hg1sol",
    "outputId": "88062841-e158-49df-b0e7-807bed63d4de"
   },
   "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.head()\n",
    "\n",
    "# target column is 'car'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 214
    },
    "colab_type": "code",
    "id": "RRfKF7uZ1sor",
    "outputId": "166bcd32-aa0f-44a0-f694-fb9bddd0eac0"
   },
   "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": "tPTFi0ge1sov"
   },
   "outputs": [],
   "source": [
    "# target column is 'car'\n",
    "\n",
    "features = _df.drop(['car'], axis=1).values\n",
    "labels = _df[['car']].values\n",
    "\n",
    "# split 80% for training and 20% into an evaluation set\n",
    "X_train, X_eval, y_train, y_eval = train_test_split(features, labels, test_size=0.3, random_state=0)\n",
    "\n",
    "# further split the evaluation set into validation and test sets of 10% each\n",
    "X_val, X_test, y_val, y_test = train_test_split(X_eval, y_eval, test_size=0.5, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 161
    },
    "colab_type": "code",
    "id": "I3lTUzJd1so4",
    "outputId": "fb0d0f99-6f2b-4012-8878-ba3eb40b7210"
   },
   "outputs": [],
   "source": [
    "# train a Logistic Regression model\n",
    "model = LogisticRegression()\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tYjPIag91so8"
   },
   "outputs": [],
   "source": [
    "# make predictions for the validation dataset\n",
    "y_pred = model.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "R-YmhMlL1spA"
   },
   "outputs": [],
   "source": [
    "#import libraries\n",
    "from sklearn.metrics import confusion_matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 88
    },
    "colab_type": "code",
    "id": "7qEjfjQ51spH",
    "outputId": "b6b6c598-a0fc-487a-f5b2-77e9b7c512d6"
   },
   "outputs": [],
   "source": [
    "confusion_matrix(y_val, y_pred)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise6_06.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
}