{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "o1E-avoFxNcn"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn import *\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "XviNmJlcxbem"
   },
   "outputs": [],
   "source": [
    "phishing_dataset = np.genfromtxt('datasets-2/phishing_dataset.csv', delimiter=',', dtype=np.int32)\n",
    "samples = phishing_dataset[:,:-1]\n",
    "targets = phishing_dataset[:, -1]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "do33z7f7xz8I"
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import  train_test_split\n",
    "training_samples, testing_samples, training_targets, testing_targets = train_test_split(samples, targets, test_size = 0.2, random_state= 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "5Q3Z13wVyFjM",
    "outputId": "96f7d9e9-fd88-4a1a-f8dc-381f785fc588"
   },
   "outputs": [],
   "source": [
    "from sklearn import tree\n",
    "tree_classifier = tree.DecisionTreeClassifier()\n",
    "tree_classifier.fit(training_samples, training_targets)\n",
    "predictions = tree_classifier.predict(testing_samples)\n",
    "accuracy = 100.0* accuracy_score(testing_targets, predictions)\n",
    "print(\"Decision Tree accuracy: \"+ str(accuracy))"
   ]
  },
  {
   "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(testing_targets, predictions))\n",
    "\n",
    "print(\"\\nClassification Report:\")\n",
    "print(classification_report(testing_targets, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Phishing detection with decision trees.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
}