labs/Module-4/2.Spam_Detection_SVMs.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#!pip install mlxtend"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "tXKmqh2JP1Io"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load data & split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "tXKmqh2JP1Io"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv('datasets-1/sms_spam_svm.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "1K8dyw4eP_08"
   },
   "outputs": [],
   "source": [
    "y = df.iloc[:, 0].values\n",
    "y = np.where(y == 'spam', -1, 1)\n",
    "\n",
    "x = df.iloc[:, [1, 2]].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "dCPECPPgQLPq"
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "         x, y, test_size=0.3, random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Training using SVC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "SIxi3X0BQpyG"
   },
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "\n",
    "# linear, poly, rbf, sigmoid\n",
    "svm = SVC(kernel='rbf', gamma='auto', random_state=1)\n",
    "svm.fit(X_train, y_train)\n",
    "\n",
    "y_pred = svm.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 384
    },
    "id": "_PZ3efgQR8K8",
    "outputId": "45df8ea2-5e8e-4fe1-bb10-6932aa900ca1"
   },
   "outputs": [],
   "source": [
    "from mlxtend.plotting import plot_decision_regions\n",
    "\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "X_combined = np.vstack((X_train, X_test))\n",
    "y_combined = np.hstack((y_train, y_test))\n",
    "\n",
    "\n",
    "\n",
    "plot_decision_regions(X_combined, y_combined, clf=svm)\n",
    "\n",
    "plt.xlabel('suspect words')\n",
    "plt.ylabel('spam or ham')\n",
    "plt.legend(loc='upper right')\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-Q5Ue3AETWrn",
    "outputId": "b0aa724e-828f-4b93-b6b5-e5e60a166b15"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "print('Misclassified samples: %d' % (y_test != y_pred).sum())\n",
    "print('Accuracy: %.2f' % accuracy_score(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report , confusion_matrix\n",
    "\n",
    "print(\"Confusion Matrix:\")\n",
    "print(confusion_matrix(y_test, y_pred))\n",
    "\n",
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(y_test, y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Spam detection with SVMs.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": "3.8.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}