mlessentials/Lab06/Old/Exercise6_11/Exercise6_11.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "V8UoTLWkigol"
   },
   "outputs": [],
   "source": [
    "# import libraries \n",
    "\n",
    "import pandas as pd \n",
    "\n",
    "from sklearn.model_selection import train_test_split \n",
    "\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": 203
    },
    "colab_type": "code",
    "id": "mxGIoM_5ilQF",
    "outputId": "e3bdf790-f9c5-4b87-e72e-9c68bb869517"
   },
   "outputs": [],
   "source": [
    "# data doesn't have headers, so let's create headers \n",
    "\n",
    "_headers = ['Age', 'Delivery_Nbr', 'Delivery_Time', 'Blood_Pressure', 'Heart_Problem', 'Caesarian'] \n",
    "\n",
    "# read in cars dataset \n",
    "\n",
    "df = pd.read_csv('../Dataset/caesarian.csv.arff', names=_headers, index_col=None, skiprows=15) \n",
    "\n",
    "df.head() \n",
    "\n",
    "# target column is 'Caesarian' "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "PxEvuaTJiojZ"
   },
   "outputs": [],
   "source": [
    "# target column is 'Caesarian' \n",
    "\n",
    "features = df.drop(['Caesarian'], axis=1).values \n",
    "\n",
    "labels = df[['Caesarian']].values \n",
    "\n",
    " \n",
    "\n",
    "# split 80% for training and 20% into an evaluation set \n",
    "\n",
    "X_train, X_eval, y_train, y_eval = train_test_split(features, labels, test_size=0.2, random_state=0) \n",
    "\n",
    " \n",
    "\n",
    "# further split the evaluation set into validation and test sets of 10% each \n",
    "\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": 157
    },
    "colab_type": "code",
    "id": "Ej6uIbezirCR",
    "outputId": "b0e201d2-d55f-4dbc-c21d-e05c2cf6935b"
   },
   "outputs": [],
   "source": [
    "model = LogisticRegression() \n",
    "\n",
    "model.fit(X_train, y_train) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "b7PyDlTRitfk"
   },
   "outputs": [],
   "source": [
    "y_proba = model.predict_proba(X_val) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "oaztmV1QjTYF"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import roc_curve\n",
    "from sklearn.metrics import auc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "DxAsnKfRiu0h"
   },
   "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": 34
    },
    "colab_type": "code",
    "id": "laUL4vKgjSNa",
    "outputId": "dcece431-2930-4cb7-fcbb-627f234cef94"
   },
   "outputs": [],
   "source": [
    "print(_false_positive) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "CWVZIRPFjlDN",
    "outputId": "40253e1c-782a-451d-ca2f-a1fe75bed8ea"
   },
   "outputs": [],
   "source": [
    "print(_true_positive) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "id": "87z9brVnjmht",
    "outputId": "7c8b8e45-ad81-411d-e7dc-316bd65c6d9d"
   },
   "outputs": [],
   "source": [
    "print(_thresholds) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 295
    },
    "colab_type": "code",
    "id": "6XgGwPzqjoV-",
    "outputId": "bf98a239-c612-4a66-ddc2-0a019307a4f6"
   },
   "outputs": [],
   "source": [
    "# Plot the RoC \n",
    "# Uncomment the following block of code to see the plot\n",
    "\n",
    "import matplotlib.pyplot as plt \n",
    "\n",
    "%matplotlib inline \n",
    "\n",
    " \n",
    "\n",
    "plt.plot(_false_positive, _true_positive, lw=2, label='Receiver Operating Characteristic') \n",
    "\n",
    "plt.xlim(0.0, 1.2) \n",
    "\n",
    "plt.ylim(0.0, 1.2) \n",
    "\n",
    "plt.xlabel('False Positive Rate') \n",
    "\n",
    "plt.ylabel('True Positive Rate') \n",
    "\n",
    "plt.title('Receiver Operating Characteristic') \n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise6.11.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
}