mlessentials/Lab06/Old/Exercise6_12/Exercise6_12.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "QWyZQ1u8DuI_"
   },
   "source": [
    "# Computing the ROC AUC for the Caesarian Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "p89bSWY_DuJD"
   },
   "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"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "id": "vW0hhGg3DuJI",
    "outputId": "a79179c0-dedd-41dc-f13e-93c1e2120617"
   },
   "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",
    "\n",
    "# target column is 'Caesarian'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "MGk_0UmkDuJN"
   },
   "outputs": [],
   "source": [
    "# target column is 'Caesarian'\n",
    "\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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 136
    },
    "colab_type": "code",
    "id": "3qwJP9sEDuJQ",
    "outputId": "de02ebb1-fb71-4283-f90c-1623e14af1f4"
   },
   "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": "v3vFYHI7DuJU"
   },
   "outputs": [],
   "source": [
    "# make predictions for the validation dataset\n",
    "y_proba = model.predict_proba(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "s2mk5XKxDuJY",
    "outputId": "28e3e3db-3e8f-42ea-da67-5febd5cae99b"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import roc_auc_score\n",
    "_auc = roc_auc_score(y_val, y_proba[:, 0])\n",
    "print(_auc)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise6.12.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
}