From e844632c06ab64fbc993035cd3d469c7e1000fab Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=EC=A7=80=EC=88=98?=
<75234139+JisooKinn@users.noreply.github.com>
Date: Thu, 2 Dec 2021 15:26:55 +0900
Subject: [PATCH] Add Accuracy ect..
---
[DM]_Naive_Bayes.ipynb | 294 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 294 insertions(+)
create mode 100644 [DM]_Naive_Bayes.ipynb
diff --git a/[DM]_Naive_Bayes.ipynb b/[DM]_Naive_Bayes.ipynb
new file mode 100644
index 0000000..4d5c8d4
--- /dev/null
+++ b/[DM]_Naive_Bayes.ipynb
@@ -0,0 +1,294 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "name": "[DM] Naive_Bayes.ipynb",
+ "provenance": [],
+ "collapsed_sections": [],
+ "authorship_tag": "ABX9TyNy7hmbNOzoRjiOM4Rat/n0",
+ "include_colab_link": true
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "view-in-github",
+ "colab_type": "text"
+ },
+ "source": [
+ "<a href=\"https://colab.research.google.com/github/lani009/IDS-DataMining/blob/main/%5BDM%5D_Naive_Bayes.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "p_S1iryH1NBB"
+ },
+ "source": [
+ "import os\n",
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import seaborn as sns\n",
+ "import time"
+ ],
+ "execution_count": 1,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "S3PZhNLC1daY",
+ "outputId": "8c764462-6538-4e2e-c11e-b2bffad1a612"
+ },
+ "source": [
+ "data = pd.read_csv('DM_data.csv')\n",
+ "data.info()"
+ ],
+ "execution_count": 2,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "<class 'pandas.core.frame.DataFrame'>\n",
+ "RangeIndex: 25192 entries, 0 to 25191\n",
+ "Data columns (total 40 columns):\n",
+ " # Column Non-Null Count Dtype \n",
+ "--- ------ -------------- ----- \n",
+ " 0 duration 25192 non-null int64 \n",
+ " 1 protocol_type 25192 non-null int64 \n",
+ " 2 service 25192 non-null int64 \n",
+ " 3 flag 25192 non-null int64 \n",
+ " 4 src_bytes 25192 non-null int64 \n",
+ " 5 dst_bytes 25192 non-null int64 \n",
+ " 6 land 25192 non-null int64 \n",
+ " 7 wrong_fragment 25192 non-null int64 \n",
+ " 8 hot 25192 non-null int64 \n",
+ " 9 num_failed_logins 25192 non-null int64 \n",
+ " 10 logged_in 25192 non-null int64 \n",
+ " 11 num_compromised 25192 non-null int64 \n",
+ " 12 root_shell 25192 non-null int64 \n",
+ " 13 su_attempted 25192 non-null int64 \n",
+ " 14 num_root 25192 non-null int64 \n",
+ " 15 num_file_creations 25192 non-null int64 \n",
+ " 16 num_shells 25192 non-null int64 \n",
+ " 17 num_access_files 25192 non-null int64 \n",
+ " 18 is_guest_login 25192 non-null int64 \n",
+ " 19 count 25192 non-null int64 \n",
+ " 20 srv_count 25192 non-null int64 \n",
+ " 21 serror_rate 25192 non-null float64\n",
+ " 22 srv_serror_rate 25192 non-null float64\n",
+ " 23 rerror_rate 25192 non-null float64\n",
+ " 24 srv_rerror_rate 25192 non-null float64\n",
+ " 25 same_srv_rate 25192 non-null float64\n",
+ " 26 diff_srv_rate 25192 non-null float64\n",
+ " 27 srv_diff_host_rate 25192 non-null float64\n",
+ " 28 dst_host_count 25192 non-null int64 \n",
+ " 29 dst_host_srv_count 25192 non-null int64 \n",
+ " 30 dst_host_same_srv_rate 25192 non-null float64\n",
+ " 31 dst_host_diff_srv_rate 25192 non-null float64\n",
+ " 32 dst_host_same_src_port_rate 25192 non-null float64\n",
+ " 33 dst_host_srv_diff_host_rate 25192 non-null float64\n",
+ " 34 dst_host_serror_rate 25192 non-null float64\n",
+ " 35 dst_host_srv_serror_rate 25192 non-null float64\n",
+ " 36 dst_host_rerror_rate 25192 non-null float64\n",
+ " 37 dst_host_srv_rerror_rate 25192 non-null float64\n",
+ " 38 class 25192 non-null int64 \n",
+ " 39 index_num 25192 non-null int64 \n",
+ "dtypes: float64(15), int64(25)\n",
+ "memory usage: 7.7 MB\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "vzo6lf_G3QFN"
+ },
+ "source": [
+ "from sklearn.model_selection import train_test_split\n",
+ "from sklearn.preprocessing import MinMaxScaler, StandardScaler"
+ ],
+ "execution_count": 3,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "ioY_BhsQ3Suc"
+ },
+ "source": [
+ "data_y = data[\"class\"]\n",
+ "data_X = data.drop(columns = [\"class\",\"index_num\"])"
+ ],
+ "execution_count": 4,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "Aoz6AkZa3_rU"
+ },
+ "source": [
+ "sc = MinMaxScaler()\n",
+ "_X = sc.fit_transform(data_X)"
+ ],
+ "execution_count": 46,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "LffojJ-C1tEY",
+ "outputId": "2b81d88e-4810-4479-e668-ce1ecc4f377c"
+ },
+ "source": [
+ "X_train, X_test, Y_train, Y_test = train_test_split(_X, data_y, test_size=0.3, random_state=42)\n",
+ "print(X_train.shape, X_test.shape)\n",
+ "print(Y_train.shape, Y_test.shape)"
+ ],
+ "execution_count": 47,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "(17634, 38) (7558, 38)\n",
+ "(17634,) (7558,)\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "R1X0zCyN4qNT"
+ },
+ "source": [
+ "## **Naive Bayes**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "xupFriQx2n6T"
+ },
+ "source": [
+ "from sklearn.naive_bayes import GaussianNB"
+ ],
+ "execution_count": 59,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "bTXaZ-jf4Slk"
+ },
+ "source": [
+ "nb = GaussianNB()"
+ ],
+ "execution_count": 60,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "N8lbZQaE4UD8",
+ "outputId": "977a4c01-5f90-45d4-f590-3e7a8f3283b6"
+ },
+ "source": [
+ "nb.fit(X_train, Y_train.values.ravel())"
+ ],
+ "execution_count": 61,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "GaussianNB()"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 61
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "Kf7YGTRd4WyR"
+ },
+ "source": [
+ "Y_test_pred = nb.predict(X_test)"
+ ],
+ "execution_count": 62,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "aqMM4cqwvXQt",
+ "outputId": "dcc7cda0-81ef-46a8-fbf5-97c7a805e851"
+ },
+ "source": [
+ "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score\n",
+ "\n",
+ "\n",
+ "print(\"Accuracy : \", accuracy_score(Y_test,Y_test_pred)) \n",
+ "\n",
+ "print(\"Precision : \", precision_score(Y_test,Y_test_pred))\n",
+ "\n",
+ "print(\"Recall : \", recall_score(Y_test,Y_test_pred))\n",
+ "\n",
+ "print(\"F1 Score : \",f1_score(Y_test,Y_test_pred))"
+ ],
+ "execution_count": 65,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Accuracy : 0.9053982535062186\n",
+ "Precision : 0.8777987591043971\n",
+ "Recall : 0.9254835039817975\n",
+ "F1 Score : 0.9010106603904195\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "metadata": {
+ "id": "IYDovkMfwr-X"
+ },
+ "source": [
+ ""
+ ],
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
--
GitLab