mlessentials/Lab06/Exercise6.12/Exercise6_12.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "wMcwTFr3IfLF"
   },
   "source": [
    "**Plotting ROC**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "pMbqUnILG4CX"
   },
   "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",
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.metrics import auc\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": "UUYqPslNHC5F",
    "outputId": "db56cc50-f1a7-403f-f43d-79751f378f3c"
   },
   "outputs": [],
   "source": [
    "# data doesn't have headers, so let's create headers\n",
    "_headers = ['Age', 'Delivery_Nbr', 'Delivery_Time', 'Blood_Pressure', 'Heart_Problem', 'Caesarian']\n",
    "# read in cars dataset\n",
    "df = pd.read_csv('../Dataset/caesarian.csv.arff', names=_headers, index_col=None, skiprows=15)\n",
    "df.head()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "NnYpB2dkHHNa"
   },
   "outputs": [],
   "source": [
    "# target column is 'Caesarian'\n",
    "features = df.drop(['Caesarian'], axis=1).values\n",
    "labels = df[['Caesarian']].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=0.2, 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)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 161
    },
    "colab_type": "code",
    "id": "A8E1Hc5RHI_5",
    "outputId": "d4ea2a9b-ef8b-4ad6-9e84-9d59ae23030b"
   },
   "outputs": [],
   "source": [
    "model = LogisticRegression()\n",
    "model.fit(X_train, y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "75B0f5oBHLVh"
   },
   "outputs": [],
   "source": [
    "y_proba = model.predict_proba(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ALurTbneHNQp"
   },
   "outputs": [],
   "source": [
    "_false_positive, _true_positive, _thresholds = roc_curve(y_val, y_proba[:, 0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "S1GrOAc-Hw4A",
    "outputId": "0977453a-c6dd-4eab-8210-9518147a64b5"
   },
   "outputs": [],
   "source": [
    "print(_false_positive)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "mTn94iOLH07c",
    "outputId": "6f7b1728-4be5-4176-def1-1a5f6e51c6e0"
   },
   "outputs": [],
   "source": [
    "print(_true_positive)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "OhQAm1sTH2Cp",
    "outputId": "4cc45cde-36d8-4850-f22b-c15e740b8d2e"
   },
   "outputs": [],
   "source": [
    "print(_thresholds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 313
    },
    "colab_type": "code",
    "id": "gdRsiwEqH5sM",
    "outputId": "26108706-1324-4229-dbd1-e80a40b21340"
   },
   "outputs": [],
   "source": [
    "# Plot the RoC\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "plt.plot(_false_positive, _true_positive, lw=2, label='Receiver Operating Characteristic')\n",
    "plt.xlim(0.0, 1.2)\n",
    "plt.ylim(0.0, 1.2)\n",
    "plt.xlabel('False Positive Rate')\n",
    "plt.ylabel('True Positive Rate')\n",
    "plt.title('Receiver Operating Characteristic')\n",
    "plt.show()\n",
    "y_proba = model.predict_proba(X_val)\n",
    "from sklearn.metrics import roc_auc_score\n",
    "_auc = roc_auc_score(y_val, y_proba[:, 0])\n",
    "print(_auc)\n"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise6_12.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
}