Upload 2 files
Browse files- GuardShield_CNNLSTM_v1.h5 +3 -0
- GuardShield_CNNLSTM_v1.ipynb +978 -0
GuardShield_CNNLSTM_v1.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a910a015674cbce9cd3bc9f140ca6f16a1f5a1e31237b56e7408538c4ae19db8
|
3 |
+
size 1006128
|
GuardShield_CNNLSTM_v1.ipynb
ADDED
@@ -0,0 +1,978 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"metadata": {},
|
6 |
+
"source": [
|
7 |
+
"# GUARDSHIELD_CNNLSTM \n",
|
8 |
+
"# Version 1.0"
|
9 |
+
]
|
10 |
+
},
|
11 |
+
{
|
12 |
+
"cell_type": "markdown",
|
13 |
+
"metadata": {},
|
14 |
+
"source": [
|
15 |
+
"## Loading Dataset"
|
16 |
+
]
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"cell_type": "code",
|
20 |
+
"execution_count": 1,
|
21 |
+
"metadata": {},
|
22 |
+
"outputs": [
|
23 |
+
{
|
24 |
+
"name": "stderr",
|
25 |
+
"output_type": "stream",
|
26 |
+
"text": [
|
27 |
+
"c:\\Users\\laksh\\anaconda3\\envs\\tf\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
28 |
+
" from .autonotebook import tqdm as notebook_tqdm\n",
|
29 |
+
"HTTP Error 502 thrown while requesting GET https://huggingface.co/datasets/racdroid/cicds-2017/resolve/main/cleaned_data.csv\n",
|
30 |
+
"Retrying in 1s [Retry 1/5].\n"
|
31 |
+
]
|
32 |
+
}
|
33 |
+
],
|
34 |
+
"source": [
|
35 |
+
"import pandas as pd\n",
|
36 |
+
"\n",
|
37 |
+
"df = pd.read_csv(\"hf://datasets/racdroid/cicds-2017/cleaned_data.csv\", engine='pyarrow')"
|
38 |
+
]
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"cell_type": "markdown",
|
42 |
+
"metadata": {},
|
43 |
+
"source": [
|
44 |
+
"## Dataset Enumeration"
|
45 |
+
]
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"cell_type": "code",
|
49 |
+
"execution_count": 2,
|
50 |
+
"metadata": {},
|
51 |
+
"outputs": [
|
52 |
+
{
|
53 |
+
"data": {
|
54 |
+
"text/html": [
|
55 |
+
"<div>\n",
|
56 |
+
"<style scoped>\n",
|
57 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
58 |
+
" vertical-align: middle;\n",
|
59 |
+
" }\n",
|
60 |
+
"\n",
|
61 |
+
" .dataframe tbody tr th {\n",
|
62 |
+
" vertical-align: top;\n",
|
63 |
+
" }\n",
|
64 |
+
"\n",
|
65 |
+
" .dataframe thead th {\n",
|
66 |
+
" text-align: right;\n",
|
67 |
+
" }\n",
|
68 |
+
"</style>\n",
|
69 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
70 |
+
" <thead>\n",
|
71 |
+
" <tr style=\"text-align: right;\">\n",
|
72 |
+
" <th></th>\n",
|
73 |
+
" <th>Destination Port</th>\n",
|
74 |
+
" <th>Flow Duration</th>\n",
|
75 |
+
" <th>Total Fwd Packets</th>\n",
|
76 |
+
" <th>Total Backward Packets</th>\n",
|
77 |
+
" <th>Total Length of Fwd Packets</th>\n",
|
78 |
+
" <th>Total Length of Bwd Packets</th>\n",
|
79 |
+
" <th>Fwd Packet Length Max</th>\n",
|
80 |
+
" <th>Fwd Packet Length Min</th>\n",
|
81 |
+
" <th>Fwd Packet Length Mean</th>\n",
|
82 |
+
" <th>Fwd Packet Length Std</th>\n",
|
83 |
+
" <th>...</th>\n",
|
84 |
+
" <th>min_seg_size_forward</th>\n",
|
85 |
+
" <th>Active Mean</th>\n",
|
86 |
+
" <th>Active Std</th>\n",
|
87 |
+
" <th>Active Max</th>\n",
|
88 |
+
" <th>Active Min</th>\n",
|
89 |
+
" <th>Idle Mean</th>\n",
|
90 |
+
" <th>Idle Std</th>\n",
|
91 |
+
" <th>Idle Max</th>\n",
|
92 |
+
" <th>Idle Min</th>\n",
|
93 |
+
" <th>Label</th>\n",
|
94 |
+
" </tr>\n",
|
95 |
+
" </thead>\n",
|
96 |
+
" <tbody>\n",
|
97 |
+
" <tr>\n",
|
98 |
+
" <th>0</th>\n",
|
99 |
+
" <td>49188</td>\n",
|
100 |
+
" <td>4</td>\n",
|
101 |
+
" <td>2</td>\n",
|
102 |
+
" <td>0</td>\n",
|
103 |
+
" <td>12</td>\n",
|
104 |
+
" <td>0</td>\n",
|
105 |
+
" <td>6</td>\n",
|
106 |
+
" <td>6</td>\n",
|
107 |
+
" <td>6.0</td>\n",
|
108 |
+
" <td>0.0</td>\n",
|
109 |
+
" <td>...</td>\n",
|
110 |
+
" <td>20</td>\n",
|
111 |
+
" <td>0.0</td>\n",
|
112 |
+
" <td>0.0</td>\n",
|
113 |
+
" <td>0</td>\n",
|
114 |
+
" <td>0</td>\n",
|
115 |
+
" <td>0.0</td>\n",
|
116 |
+
" <td>0.0</td>\n",
|
117 |
+
" <td>0</td>\n",
|
118 |
+
" <td>0</td>\n",
|
119 |
+
" <td>BENIGN</td>\n",
|
120 |
+
" </tr>\n",
|
121 |
+
" <tr>\n",
|
122 |
+
" <th>1</th>\n",
|
123 |
+
" <td>49188</td>\n",
|
124 |
+
" <td>1</td>\n",
|
125 |
+
" <td>2</td>\n",
|
126 |
+
" <td>0</td>\n",
|
127 |
+
" <td>12</td>\n",
|
128 |
+
" <td>0</td>\n",
|
129 |
+
" <td>6</td>\n",
|
130 |
+
" <td>6</td>\n",
|
131 |
+
" <td>6.0</td>\n",
|
132 |
+
" <td>0.0</td>\n",
|
133 |
+
" <td>...</td>\n",
|
134 |
+
" <td>20</td>\n",
|
135 |
+
" <td>0.0</td>\n",
|
136 |
+
" <td>0.0</td>\n",
|
137 |
+
" <td>0</td>\n",
|
138 |
+
" <td>0</td>\n",
|
139 |
+
" <td>0.0</td>\n",
|
140 |
+
" <td>0.0</td>\n",
|
141 |
+
" <td>0</td>\n",
|
142 |
+
" <td>0</td>\n",
|
143 |
+
" <td>BENIGN</td>\n",
|
144 |
+
" </tr>\n",
|
145 |
+
" <tr>\n",
|
146 |
+
" <th>2</th>\n",
|
147 |
+
" <td>49188</td>\n",
|
148 |
+
" <td>1</td>\n",
|
149 |
+
" <td>2</td>\n",
|
150 |
+
" <td>0</td>\n",
|
151 |
+
" <td>12</td>\n",
|
152 |
+
" <td>0</td>\n",
|
153 |
+
" <td>6</td>\n",
|
154 |
+
" <td>6</td>\n",
|
155 |
+
" <td>6.0</td>\n",
|
156 |
+
" <td>0.0</td>\n",
|
157 |
+
" <td>...</td>\n",
|
158 |
+
" <td>20</td>\n",
|
159 |
+
" <td>0.0</td>\n",
|
160 |
+
" <td>0.0</td>\n",
|
161 |
+
" <td>0</td>\n",
|
162 |
+
" <td>0</td>\n",
|
163 |
+
" <td>0.0</td>\n",
|
164 |
+
" <td>0.0</td>\n",
|
165 |
+
" <td>0</td>\n",
|
166 |
+
" <td>0</td>\n",
|
167 |
+
" <td>BENIGN</td>\n",
|
168 |
+
" </tr>\n",
|
169 |
+
" <tr>\n",
|
170 |
+
" <th>3</th>\n",
|
171 |
+
" <td>49188</td>\n",
|
172 |
+
" <td>1</td>\n",
|
173 |
+
" <td>2</td>\n",
|
174 |
+
" <td>0</td>\n",
|
175 |
+
" <td>12</td>\n",
|
176 |
+
" <td>0</td>\n",
|
177 |
+
" <td>6</td>\n",
|
178 |
+
" <td>6</td>\n",
|
179 |
+
" <td>6.0</td>\n",
|
180 |
+
" <td>0.0</td>\n",
|
181 |
+
" <td>...</td>\n",
|
182 |
+
" <td>20</td>\n",
|
183 |
+
" <td>0.0</td>\n",
|
184 |
+
" <td>0.0</td>\n",
|
185 |
+
" <td>0</td>\n",
|
186 |
+
" <td>0</td>\n",
|
187 |
+
" <td>0.0</td>\n",
|
188 |
+
" <td>0.0</td>\n",
|
189 |
+
" <td>0</td>\n",
|
190 |
+
" <td>0</td>\n",
|
191 |
+
" <td>BENIGN</td>\n",
|
192 |
+
" </tr>\n",
|
193 |
+
" <tr>\n",
|
194 |
+
" <th>4</th>\n",
|
195 |
+
" <td>49486</td>\n",
|
196 |
+
" <td>3</td>\n",
|
197 |
+
" <td>2</td>\n",
|
198 |
+
" <td>0</td>\n",
|
199 |
+
" <td>12</td>\n",
|
200 |
+
" <td>0</td>\n",
|
201 |
+
" <td>6</td>\n",
|
202 |
+
" <td>6</td>\n",
|
203 |
+
" <td>6.0</td>\n",
|
204 |
+
" <td>0.0</td>\n",
|
205 |
+
" <td>...</td>\n",
|
206 |
+
" <td>20</td>\n",
|
207 |
+
" <td>0.0</td>\n",
|
208 |
+
" <td>0.0</td>\n",
|
209 |
+
" <td>0</td>\n",
|
210 |
+
" <td>0</td>\n",
|
211 |
+
" <td>0.0</td>\n",
|
212 |
+
" <td>0.0</td>\n",
|
213 |
+
" <td>0</td>\n",
|
214 |
+
" <td>0</td>\n",
|
215 |
+
" <td>BENIGN</td>\n",
|
216 |
+
" </tr>\n",
|
217 |
+
" </tbody>\n",
|
218 |
+
"</table>\n",
|
219 |
+
"<p>5 rows × 67 columns</p>\n",
|
220 |
+
"</div>"
|
221 |
+
],
|
222 |
+
"text/plain": [
|
223 |
+
" Destination Port Flow Duration Total Fwd Packets \\\n",
|
224 |
+
"0 49188 4 2 \n",
|
225 |
+
"1 49188 1 2 \n",
|
226 |
+
"2 49188 1 2 \n",
|
227 |
+
"3 49188 1 2 \n",
|
228 |
+
"4 49486 3 2 \n",
|
229 |
+
"\n",
|
230 |
+
" Total Backward Packets Total Length of Fwd Packets \\\n",
|
231 |
+
"0 0 12 \n",
|
232 |
+
"1 0 12 \n",
|
233 |
+
"2 0 12 \n",
|
234 |
+
"3 0 12 \n",
|
235 |
+
"4 0 12 \n",
|
236 |
+
"\n",
|
237 |
+
" Total Length of Bwd Packets Fwd Packet Length Max \\\n",
|
238 |
+
"0 0 6 \n",
|
239 |
+
"1 0 6 \n",
|
240 |
+
"2 0 6 \n",
|
241 |
+
"3 0 6 \n",
|
242 |
+
"4 0 6 \n",
|
243 |
+
"\n",
|
244 |
+
" Fwd Packet Length Min Fwd Packet Length Mean Fwd Packet Length Std \\\n",
|
245 |
+
"0 6 6.0 0.0 \n",
|
246 |
+
"1 6 6.0 0.0 \n",
|
247 |
+
"2 6 6.0 0.0 \n",
|
248 |
+
"3 6 6.0 0.0 \n",
|
249 |
+
"4 6 6.0 0.0 \n",
|
250 |
+
"\n",
|
251 |
+
" ... min_seg_size_forward Active Mean Active Std Active Max \\\n",
|
252 |
+
"0 ... 20 0.0 0.0 0 \n",
|
253 |
+
"1 ... 20 0.0 0.0 0 \n",
|
254 |
+
"2 ... 20 0.0 0.0 0 \n",
|
255 |
+
"3 ... 20 0.0 0.0 0 \n",
|
256 |
+
"4 ... 20 0.0 0.0 0 \n",
|
257 |
+
"\n",
|
258 |
+
" Active Min Idle Mean Idle Std Idle Max Idle Min Label \n",
|
259 |
+
"0 0 0.0 0.0 0 0 BENIGN \n",
|
260 |
+
"1 0 0.0 0.0 0 0 BENIGN \n",
|
261 |
+
"2 0 0.0 0.0 0 0 BENIGN \n",
|
262 |
+
"3 0 0.0 0.0 0 0 BENIGN \n",
|
263 |
+
"4 0 0.0 0.0 0 0 BENIGN \n",
|
264 |
+
"\n",
|
265 |
+
"[5 rows x 67 columns]"
|
266 |
+
]
|
267 |
+
},
|
268 |
+
"execution_count": 2,
|
269 |
+
"metadata": {},
|
270 |
+
"output_type": "execute_result"
|
271 |
+
}
|
272 |
+
],
|
273 |
+
"source": [
|
274 |
+
"df.head()"
|
275 |
+
]
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"cell_type": "code",
|
279 |
+
"execution_count": 3,
|
280 |
+
"metadata": {},
|
281 |
+
"outputs": [
|
282 |
+
{
|
283 |
+
"data": {
|
284 |
+
"text/plain": [
|
285 |
+
"(2827876, 67)"
|
286 |
+
]
|
287 |
+
},
|
288 |
+
"execution_count": 3,
|
289 |
+
"metadata": {},
|
290 |
+
"output_type": "execute_result"
|
291 |
+
}
|
292 |
+
],
|
293 |
+
"source": [
|
294 |
+
"df.shape"
|
295 |
+
]
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"cell_type": "code",
|
299 |
+
"execution_count": 4,
|
300 |
+
"metadata": {},
|
301 |
+
"outputs": [
|
302 |
+
{
|
303 |
+
"data": {
|
304 |
+
"text/plain": [
|
305 |
+
" Destination Port int64\n",
|
306 |
+
" Flow Duration int64\n",
|
307 |
+
" Total Fwd Packets int64\n",
|
308 |
+
" Total Backward Packets int64\n",
|
309 |
+
"Total Length of Fwd Packets int64\n",
|
310 |
+
" ... \n",
|
311 |
+
"Idle Mean float64\n",
|
312 |
+
" Idle Std float64\n",
|
313 |
+
" Idle Max int64\n",
|
314 |
+
" Idle Min int64\n",
|
315 |
+
" Label object\n",
|
316 |
+
"Length: 67, dtype: object"
|
317 |
+
]
|
318 |
+
},
|
319 |
+
"execution_count": 4,
|
320 |
+
"metadata": {},
|
321 |
+
"output_type": "execute_result"
|
322 |
+
}
|
323 |
+
],
|
324 |
+
"source": [
|
325 |
+
"df.dtypes"
|
326 |
+
]
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"cell_type": "code",
|
330 |
+
"execution_count": 5,
|
331 |
+
"metadata": {},
|
332 |
+
"outputs": [
|
333 |
+
{
|
334 |
+
"data": {
|
335 |
+
"text/html": [
|
336 |
+
"<div>\n",
|
337 |
+
"<style scoped>\n",
|
338 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
339 |
+
" vertical-align: middle;\n",
|
340 |
+
" }\n",
|
341 |
+
"\n",
|
342 |
+
" .dataframe tbody tr th {\n",
|
343 |
+
" vertical-align: top;\n",
|
344 |
+
" }\n",
|
345 |
+
"\n",
|
346 |
+
" .dataframe thead th {\n",
|
347 |
+
" text-align: right;\n",
|
348 |
+
" }\n",
|
349 |
+
"</style>\n",
|
350 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
351 |
+
" <thead>\n",
|
352 |
+
" <tr style=\"text-align: right;\">\n",
|
353 |
+
" <th></th>\n",
|
354 |
+
" <th>Destination Port</th>\n",
|
355 |
+
" <th>Flow Duration</th>\n",
|
356 |
+
" <th>Total Fwd Packets</th>\n",
|
357 |
+
" <th>Total Backward Packets</th>\n",
|
358 |
+
" <th>Total Length of Fwd Packets</th>\n",
|
359 |
+
" <th>Total Length of Bwd Packets</th>\n",
|
360 |
+
" <th>Fwd Packet Length Max</th>\n",
|
361 |
+
" <th>Fwd Packet Length Min</th>\n",
|
362 |
+
" <th>Fwd Packet Length Mean</th>\n",
|
363 |
+
" <th>Fwd Packet Length Std</th>\n",
|
364 |
+
" <th>...</th>\n",
|
365 |
+
" <th>act_data_pkt_fwd</th>\n",
|
366 |
+
" <th>min_seg_size_forward</th>\n",
|
367 |
+
" <th>Active Mean</th>\n",
|
368 |
+
" <th>Active Std</th>\n",
|
369 |
+
" <th>Active Max</th>\n",
|
370 |
+
" <th>Active Min</th>\n",
|
371 |
+
" <th>Idle Mean</th>\n",
|
372 |
+
" <th>Idle Std</th>\n",
|
373 |
+
" <th>Idle Max</th>\n",
|
374 |
+
" <th>Idle Min</th>\n",
|
375 |
+
" </tr>\n",
|
376 |
+
" </thead>\n",
|
377 |
+
" <tbody>\n",
|
378 |
+
" <tr>\n",
|
379 |
+
" <th>count</th>\n",
|
380 |
+
" <td>2.827876e+06</td>\n",
|
381 |
+
" <td>2.827876e+06</td>\n",
|
382 |
+
" <td>2.827876e+06</td>\n",
|
383 |
+
" <td>2.827876e+06</td>\n",
|
384 |
+
" <td>2.827876e+06</td>\n",
|
385 |
+
" <td>2.827876e+06</td>\n",
|
386 |
+
" <td>2.827876e+06</td>\n",
|
387 |
+
" <td>2.827876e+06</td>\n",
|
388 |
+
" <td>2.827876e+06</td>\n",
|
389 |
+
" <td>2.827876e+06</td>\n",
|
390 |
+
" <td>...</td>\n",
|
391 |
+
" <td>2.827876e+06</td>\n",
|
392 |
+
" <td>2.827876e+06</td>\n",
|
393 |
+
" <td>2.827876e+06</td>\n",
|
394 |
+
" <td>2.827876e+06</td>\n",
|
395 |
+
" <td>2.827876e+06</td>\n",
|
396 |
+
" <td>2.827876e+06</td>\n",
|
397 |
+
" <td>2.827876e+06</td>\n",
|
398 |
+
" <td>2.827876e+06</td>\n",
|
399 |
+
" <td>2.827876e+06</td>\n",
|
400 |
+
" <td>2.827876e+06</td>\n",
|
401 |
+
" </tr>\n",
|
402 |
+
" <tr>\n",
|
403 |
+
" <th>mean</th>\n",
|
404 |
+
" <td>8.061534e+03</td>\n",
|
405 |
+
" <td>1.480065e+07</td>\n",
|
406 |
+
" <td>9.368972e+00</td>\n",
|
407 |
+
" <td>1.040396e+01</td>\n",
|
408 |
+
" <td>5.498522e+02</td>\n",
|
409 |
+
" <td>1.617903e+04</td>\n",
|
410 |
+
" <td>2.078044e+02</td>\n",
|
411 |
+
" <td>1.872929e+01</td>\n",
|
412 |
+
" <td>5.825628e+01</td>\n",
|
413 |
+
" <td>6.897811e+01</td>\n",
|
414 |
+
" <td>...</td>\n",
|
415 |
+
" <td>5.423519e+00</td>\n",
|
416 |
+
" <td>-2.744494e+03</td>\n",
|
417 |
+
" <td>8.163400e+04</td>\n",
|
418 |
+
" <td>4.117582e+04</td>\n",
|
419 |
+
" <td>1.533378e+05</td>\n",
|
420 |
+
" <td>5.835492e+04</td>\n",
|
421 |
+
" <td>8.324468e+06</td>\n",
|
422 |
+
" <td>5.043548e+05</td>\n",
|
423 |
+
" <td>8.704568e+06</td>\n",
|
424 |
+
" <td>7.928061e+06</td>\n",
|
425 |
+
" </tr>\n",
|
426 |
+
" <tr>\n",
|
427 |
+
" <th>std</th>\n",
|
428 |
+
" <td>1.827432e+04</td>\n",
|
429 |
+
" <td>3.366750e+07</td>\n",
|
430 |
+
" <td>7.500527e+02</td>\n",
|
431 |
+
" <td>9.978937e+02</td>\n",
|
432 |
+
" <td>9.998639e+03</td>\n",
|
433 |
+
" <td>2.264235e+06</td>\n",
|
434 |
+
" <td>7.175183e+02</td>\n",
|
435 |
+
" <td>6.035533e+01</td>\n",
|
436 |
+
" <td>1.861733e+02</td>\n",
|
437 |
+
" <td>2.813212e+02</td>\n",
|
438 |
+
" <td>...</td>\n",
|
439 |
+
" <td>6.367482e+02</td>\n",
|
440 |
+
" <td>1.085539e+06</td>\n",
|
441 |
+
" <td>6.489234e+05</td>\n",
|
442 |
+
" <td>3.935787e+05</td>\n",
|
443 |
+
" <td>1.026333e+06</td>\n",
|
444 |
+
" <td>5.773818e+05</td>\n",
|
445 |
+
" <td>2.364057e+07</td>\n",
|
446 |
+
" <td>4.605289e+06</td>\n",
|
447 |
+
" <td>2.437766e+07</td>\n",
|
448 |
+
" <td>2.337390e+07</td>\n",
|
449 |
+
" </tr>\n",
|
450 |
+
" <tr>\n",
|
451 |
+
" <th>min</th>\n",
|
452 |
+
" <td>0.000000e+00</td>\n",
|
453 |
+
" <td>-1.300000e+01</td>\n",
|
454 |
+
" <td>1.000000e+00</td>\n",
|
455 |
+
" <td>0.000000e+00</td>\n",
|
456 |
+
" <td>0.000000e+00</td>\n",
|
457 |
+
" <td>0.000000e+00</td>\n",
|
458 |
+
" <td>0.000000e+00</td>\n",
|
459 |
+
" <td>0.000000e+00</td>\n",
|
460 |
+
" <td>0.000000e+00</td>\n",
|
461 |
+
" <td>0.000000e+00</td>\n",
|
462 |
+
" <td>...</td>\n",
|
463 |
+
" <td>0.000000e+00</td>\n",
|
464 |
+
" <td>-5.368707e+08</td>\n",
|
465 |
+
" <td>0.000000e+00</td>\n",
|
466 |
+
" <td>0.000000e+00</td>\n",
|
467 |
+
" <td>0.000000e+00</td>\n",
|
468 |
+
" <td>0.000000e+00</td>\n",
|
469 |
+
" <td>0.000000e+00</td>\n",
|
470 |
+
" <td>0.000000e+00</td>\n",
|
471 |
+
" <td>0.000000e+00</td>\n",
|
472 |
+
" <td>0.000000e+00</td>\n",
|
473 |
+
" </tr>\n",
|
474 |
+
" <tr>\n",
|
475 |
+
" <th>25%</th>\n",
|
476 |
+
" <td>5.300000e+01</td>\n",
|
477 |
+
" <td>1.550000e+02</td>\n",
|
478 |
+
" <td>2.000000e+00</td>\n",
|
479 |
+
" <td>1.000000e+00</td>\n",
|
480 |
+
" <td>1.200000e+01</td>\n",
|
481 |
+
" <td>2.000000e+00</td>\n",
|
482 |
+
" <td>6.000000e+00</td>\n",
|
483 |
+
" <td>0.000000e+00</td>\n",
|
484 |
+
" <td>6.000000e+00</td>\n",
|
485 |
+
" <td>0.000000e+00</td>\n",
|
486 |
+
" <td>...</td>\n",
|
487 |
+
" <td>0.000000e+00</td>\n",
|
488 |
+
" <td>2.000000e+01</td>\n",
|
489 |
+
" <td>0.000000e+00</td>\n",
|
490 |
+
" <td>0.000000e+00</td>\n",
|
491 |
+
" <td>0.000000e+00</td>\n",
|
492 |
+
" <td>0.000000e+00</td>\n",
|
493 |
+
" <td>0.000000e+00</td>\n",
|
494 |
+
" <td>0.000000e+00</td>\n",
|
495 |
+
" <td>0.000000e+00</td>\n",
|
496 |
+
" <td>0.000000e+00</td>\n",
|
497 |
+
" </tr>\n",
|
498 |
+
" <tr>\n",
|
499 |
+
" <th>50%</th>\n",
|
500 |
+
" <td>8.000000e+01</td>\n",
|
501 |
+
" <td>3.133800e+04</td>\n",
|
502 |
+
" <td>2.000000e+00</td>\n",
|
503 |
+
" <td>2.000000e+00</td>\n",
|
504 |
+
" <td>6.200000e+01</td>\n",
|
505 |
+
" <td>1.230000e+02</td>\n",
|
506 |
+
" <td>3.700000e+01</td>\n",
|
507 |
+
" <td>2.000000e+00</td>\n",
|
508 |
+
" <td>3.400000e+01</td>\n",
|
509 |
+
" <td>0.000000e+00</td>\n",
|
510 |
+
" <td>...</td>\n",
|
511 |
+
" <td>1.000000e+00</td>\n",
|
512 |
+
" <td>2.400000e+01</td>\n",
|
513 |
+
" <td>0.000000e+00</td>\n",
|
514 |
+
" <td>0.000000e+00</td>\n",
|
515 |
+
" <td>0.000000e+00</td>\n",
|
516 |
+
" <td>0.000000e+00</td>\n",
|
517 |
+
" <td>0.000000e+00</td>\n",
|
518 |
+
" <td>0.000000e+00</td>\n",
|
519 |
+
" <td>0.000000e+00</td>\n",
|
520 |
+
" <td>0.000000e+00</td>\n",
|
521 |
+
" </tr>\n",
|
522 |
+
" <tr>\n",
|
523 |
+
" <th>75%</th>\n",
|
524 |
+
" <td>4.430000e+02</td>\n",
|
525 |
+
" <td>3.239368e+06</td>\n",
|
526 |
+
" <td>5.000000e+00</td>\n",
|
527 |
+
" <td>4.000000e+00</td>\n",
|
528 |
+
" <td>1.880000e+02</td>\n",
|
529 |
+
" <td>4.840000e+02</td>\n",
|
530 |
+
" <td>8.100000e+01</td>\n",
|
531 |
+
" <td>3.600000e+01</td>\n",
|
532 |
+
" <td>5.000000e+01</td>\n",
|
533 |
+
" <td>2.616295e+01</td>\n",
|
534 |
+
" <td>...</td>\n",
|
535 |
+
" <td>2.000000e+00</td>\n",
|
536 |
+
" <td>3.200000e+01</td>\n",
|
537 |
+
" <td>0.000000e+00</td>\n",
|
538 |
+
" <td>0.000000e+00</td>\n",
|
539 |
+
" <td>0.000000e+00</td>\n",
|
540 |
+
" <td>0.000000e+00</td>\n",
|
541 |
+
" <td>0.000000e+00</td>\n",
|
542 |
+
" <td>0.000000e+00</td>\n",
|
543 |
+
" <td>0.000000e+00</td>\n",
|
544 |
+
" <td>0.000000e+00</td>\n",
|
545 |
+
" </tr>\n",
|
546 |
+
" <tr>\n",
|
547 |
+
" <th>max</th>\n",
|
548 |
+
" <td>6.553500e+04</td>\n",
|
549 |
+
" <td>1.200000e+08</td>\n",
|
550 |
+
" <td>2.197590e+05</td>\n",
|
551 |
+
" <td>2.919220e+05</td>\n",
|
552 |
+
" <td>1.290000e+07</td>\n",
|
553 |
+
" <td>6.554530e+08</td>\n",
|
554 |
+
" <td>2.482000e+04</td>\n",
|
555 |
+
" <td>2.325000e+03</td>\n",
|
556 |
+
" <td>5.940857e+03</td>\n",
|
557 |
+
" <td>7.125597e+03</td>\n",
|
558 |
+
" <td>...</td>\n",
|
559 |
+
" <td>2.135570e+05</td>\n",
|
560 |
+
" <td>1.380000e+02</td>\n",
|
561 |
+
" <td>1.100000e+08</td>\n",
|
562 |
+
" <td>7.420000e+07</td>\n",
|
563 |
+
" <td>1.100000e+08</td>\n",
|
564 |
+
" <td>1.100000e+08</td>\n",
|
565 |
+
" <td>1.200000e+08</td>\n",
|
566 |
+
" <td>7.690000e+07</td>\n",
|
567 |
+
" <td>1.200000e+08</td>\n",
|
568 |
+
" <td>1.200000e+08</td>\n",
|
569 |
+
" </tr>\n",
|
570 |
+
" </tbody>\n",
|
571 |
+
"</table>\n",
|
572 |
+
"<p>8 rows × 66 columns</p>\n",
|
573 |
+
"</div>"
|
574 |
+
],
|
575 |
+
"text/plain": [
|
576 |
+
" Destination Port Flow Duration Total Fwd Packets \\\n",
|
577 |
+
"count 2.827876e+06 2.827876e+06 2.827876e+06 \n",
|
578 |
+
"mean 8.061534e+03 1.480065e+07 9.368972e+00 \n",
|
579 |
+
"std 1.827432e+04 3.366750e+07 7.500527e+02 \n",
|
580 |
+
"min 0.000000e+00 -1.300000e+01 1.000000e+00 \n",
|
581 |
+
"25% 5.300000e+01 1.550000e+02 2.000000e+00 \n",
|
582 |
+
"50% 8.000000e+01 3.133800e+04 2.000000e+00 \n",
|
583 |
+
"75% 4.430000e+02 3.239368e+06 5.000000e+00 \n",
|
584 |
+
"max 6.553500e+04 1.200000e+08 2.197590e+05 \n",
|
585 |
+
"\n",
|
586 |
+
" Total Backward Packets Total Length of Fwd Packets \\\n",
|
587 |
+
"count 2.827876e+06 2.827876e+06 \n",
|
588 |
+
"mean 1.040396e+01 5.498522e+02 \n",
|
589 |
+
"std 9.978937e+02 9.998639e+03 \n",
|
590 |
+
"min 0.000000e+00 0.000000e+00 \n",
|
591 |
+
"25% 1.000000e+00 1.200000e+01 \n",
|
592 |
+
"50% 2.000000e+00 6.200000e+01 \n",
|
593 |
+
"75% 4.000000e+00 1.880000e+02 \n",
|
594 |
+
"max 2.919220e+05 1.290000e+07 \n",
|
595 |
+
"\n",
|
596 |
+
" Total Length of Bwd Packets Fwd Packet Length Max \\\n",
|
597 |
+
"count 2.827876e+06 2.827876e+06 \n",
|
598 |
+
"mean 1.617903e+04 2.078044e+02 \n",
|
599 |
+
"std 2.264235e+06 7.175183e+02 \n",
|
600 |
+
"min 0.000000e+00 0.000000e+00 \n",
|
601 |
+
"25% 2.000000e+00 6.000000e+00 \n",
|
602 |
+
"50% 1.230000e+02 3.700000e+01 \n",
|
603 |
+
"75% 4.840000e+02 8.100000e+01 \n",
|
604 |
+
"max 6.554530e+08 2.482000e+04 \n",
|
605 |
+
"\n",
|
606 |
+
" Fwd Packet Length Min Fwd Packet Length Mean \\\n",
|
607 |
+
"count 2.827876e+06 2.827876e+06 \n",
|
608 |
+
"mean 1.872929e+01 5.825628e+01 \n",
|
609 |
+
"std 6.035533e+01 1.861733e+02 \n",
|
610 |
+
"min 0.000000e+00 0.000000e+00 \n",
|
611 |
+
"25% 0.000000e+00 6.000000e+00 \n",
|
612 |
+
"50% 2.000000e+00 3.400000e+01 \n",
|
613 |
+
"75% 3.600000e+01 5.000000e+01 \n",
|
614 |
+
"max 2.325000e+03 5.940857e+03 \n",
|
615 |
+
"\n",
|
616 |
+
" Fwd Packet Length Std ... act_data_pkt_fwd min_seg_size_forward \\\n",
|
617 |
+
"count 2.827876e+06 ... 2.827876e+06 2.827876e+06 \n",
|
618 |
+
"mean 6.897811e+01 ... 5.423519e+00 -2.744494e+03 \n",
|
619 |
+
"std 2.813212e+02 ... 6.367482e+02 1.085539e+06 \n",
|
620 |
+
"min 0.000000e+00 ... 0.000000e+00 -5.368707e+08 \n",
|
621 |
+
"25% 0.000000e+00 ... 0.000000e+00 2.000000e+01 \n",
|
622 |
+
"50% 0.000000e+00 ... 1.000000e+00 2.400000e+01 \n",
|
623 |
+
"75% 2.616295e+01 ... 2.000000e+00 3.200000e+01 \n",
|
624 |
+
"max 7.125597e+03 ... 2.135570e+05 1.380000e+02 \n",
|
625 |
+
"\n",
|
626 |
+
" Active Mean Active Std Active Max Active Min Idle Mean \\\n",
|
627 |
+
"count 2.827876e+06 2.827876e+06 2.827876e+06 2.827876e+06 2.827876e+06 \n",
|
628 |
+
"mean 8.163400e+04 4.117582e+04 1.533378e+05 5.835492e+04 8.324468e+06 \n",
|
629 |
+
"std 6.489234e+05 3.935787e+05 1.026333e+06 5.773818e+05 2.364057e+07 \n",
|
630 |
+
"min 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
631 |
+
"25% 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
632 |
+
"50% 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
633 |
+
"75% 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
634 |
+
"max 1.100000e+08 7.420000e+07 1.100000e+08 1.100000e+08 1.200000e+08 \n",
|
635 |
+
"\n",
|
636 |
+
" Idle Std Idle Max Idle Min \n",
|
637 |
+
"count 2.827876e+06 2.827876e+06 2.827876e+06 \n",
|
638 |
+
"mean 5.043548e+05 8.704568e+06 7.928061e+06 \n",
|
639 |
+
"std 4.605289e+06 2.437766e+07 2.337390e+07 \n",
|
640 |
+
"min 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
641 |
+
"25% 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
642 |
+
"50% 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
643 |
+
"75% 0.000000e+00 0.000000e+00 0.000000e+00 \n",
|
644 |
+
"max 7.690000e+07 1.200000e+08 1.200000e+08 \n",
|
645 |
+
"\n",
|
646 |
+
"[8 rows x 66 columns]"
|
647 |
+
]
|
648 |
+
},
|
649 |
+
"execution_count": 5,
|
650 |
+
"metadata": {},
|
651 |
+
"output_type": "execute_result"
|
652 |
+
}
|
653 |
+
],
|
654 |
+
"source": [
|
655 |
+
"df.describe()"
|
656 |
+
]
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"cell_type": "code",
|
660 |
+
"execution_count": 6,
|
661 |
+
"metadata": {},
|
662 |
+
"outputs": [
|
663 |
+
{
|
664 |
+
"name": "stdout",
|
665 |
+
"output_type": "stream",
|
666 |
+
"text": [
|
667 |
+
"<class 'pandas.core.frame.DataFrame'>\n",
|
668 |
+
"RangeIndex: 2827876 entries, 0 to 2827875\n",
|
669 |
+
"Data columns (total 67 columns):\n",
|
670 |
+
" # Column Dtype \n",
|
671 |
+
"--- ------ ----- \n",
|
672 |
+
" 0 Destination Port int64 \n",
|
673 |
+
" 1 Flow Duration int64 \n",
|
674 |
+
" 2 Total Fwd Packets int64 \n",
|
675 |
+
" 3 Total Backward Packets int64 \n",
|
676 |
+
" 4 Total Length of Fwd Packets int64 \n",
|
677 |
+
" 5 Total Length of Bwd Packets int64 \n",
|
678 |
+
" 6 Fwd Packet Length Max int64 \n",
|
679 |
+
" 7 Fwd Packet Length Min int64 \n",
|
680 |
+
" 8 Fwd Packet Length Mean float64\n",
|
681 |
+
" 9 Fwd Packet Length Std float64\n",
|
682 |
+
" 10 Bwd Packet Length Max int64 \n",
|
683 |
+
" 11 Bwd Packet Length Min int64 \n",
|
684 |
+
" 12 Bwd Packet Length Mean float64\n",
|
685 |
+
" 13 Bwd Packet Length Std float64\n",
|
686 |
+
" 14 Flow Bytes/s float64\n",
|
687 |
+
" 15 Flow Packets/s float64\n",
|
688 |
+
" 16 Flow IAT Mean float64\n",
|
689 |
+
" 17 Flow IAT Std float64\n",
|
690 |
+
" 18 Flow IAT Max int64 \n",
|
691 |
+
" 19 Flow IAT Min int64 \n",
|
692 |
+
" 20 Fwd IAT Total int64 \n",
|
693 |
+
" 21 Fwd IAT Mean float64\n",
|
694 |
+
" 22 Fwd IAT Std float64\n",
|
695 |
+
" 23 Fwd IAT Max int64 \n",
|
696 |
+
" 24 Fwd IAT Min int64 \n",
|
697 |
+
" 25 Bwd IAT Total int64 \n",
|
698 |
+
" 26 Bwd IAT Mean float64\n",
|
699 |
+
" 27 Bwd IAT Std float64\n",
|
700 |
+
" 28 Bwd IAT Max int64 \n",
|
701 |
+
" 29 Bwd IAT Min int64 \n",
|
702 |
+
" 30 Fwd PSH Flags int64 \n",
|
703 |
+
" 31 Fwd Header Length int64 \n",
|
704 |
+
" 32 Bwd Header Length int64 \n",
|
705 |
+
" 33 Fwd Packets/s float64\n",
|
706 |
+
" 34 Bwd Packets/s float64\n",
|
707 |
+
" 35 Min Packet Length int64 \n",
|
708 |
+
" 36 Max Packet Length int64 \n",
|
709 |
+
" 37 Packet Length Mean float64\n",
|
710 |
+
" 38 Packet Length Std float64\n",
|
711 |
+
" 39 Packet Length Variance float64\n",
|
712 |
+
" 40 FIN Flag Count int64 \n",
|
713 |
+
" 41 SYN Flag Count int64 \n",
|
714 |
+
" 42 PSH Flag Count int64 \n",
|
715 |
+
" 43 ACK Flag Count int64 \n",
|
716 |
+
" 44 URG Flag Count int64 \n",
|
717 |
+
" 45 Down/Up Ratio int64 \n",
|
718 |
+
" 46 Average Packet Size float64\n",
|
719 |
+
" 47 Avg Fwd Segment Size float64\n",
|
720 |
+
" 48 Avg Bwd Segment Size float64\n",
|
721 |
+
" 49 Fwd Header Length.1 int64 \n",
|
722 |
+
" 50 Subflow Fwd Packets int64 \n",
|
723 |
+
" 51 Subflow Fwd Bytes int64 \n",
|
724 |
+
" 52 Subflow Bwd Packets int64 \n",
|
725 |
+
" 53 Subflow Bwd Bytes int64 \n",
|
726 |
+
" 54 Init_Win_bytes_forward int64 \n",
|
727 |
+
" 55 Init_Win_bytes_backward int64 \n",
|
728 |
+
" 56 act_data_pkt_fwd int64 \n",
|
729 |
+
" 57 min_seg_size_forward int64 \n",
|
730 |
+
" 58 Active Mean float64\n",
|
731 |
+
" 59 Active Std float64\n",
|
732 |
+
" 60 Active Max int64 \n",
|
733 |
+
" 61 Active Min int64 \n",
|
734 |
+
" 62 Idle Mean float64\n",
|
735 |
+
" 63 Idle Std float64\n",
|
736 |
+
" 64 Idle Max int64 \n",
|
737 |
+
" 65 Idle Min int64 \n",
|
738 |
+
" 66 Label object \n",
|
739 |
+
"dtypes: float64(24), int64(42), object(1)\n",
|
740 |
+
"memory usage: 1.4+ GB\n"
|
741 |
+
]
|
742 |
+
}
|
743 |
+
],
|
744 |
+
"source": [
|
745 |
+
"df.info()"
|
746 |
+
]
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"cell_type": "code",
|
750 |
+
"execution_count": 7,
|
751 |
+
"metadata": {},
|
752 |
+
"outputs": [
|
753 |
+
{
|
754 |
+
"data": {
|
755 |
+
"text/plain": [
|
756 |
+
"Index([' Destination Port', ' Flow Duration', ' Total Fwd Packets',\n",
|
757 |
+
" ' Total Backward Packets', 'Total Length of Fwd Packets',\n",
|
758 |
+
" ' Total Length of Bwd Packets', ' Fwd Packet Length Max',\n",
|
759 |
+
" ' Fwd Packet Length Min', ' Fwd Packet Length Mean',\n",
|
760 |
+
" ' Fwd Packet Length Std', 'Bwd Packet Length Max',\n",
|
761 |
+
" ' Bwd Packet Length Min', ' Bwd Packet Length Mean',\n",
|
762 |
+
" ' Bwd Packet Length Std', 'Flow Bytes/s', ' Flow Packets/s',\n",
|
763 |
+
" ' Flow IAT Mean', ' Flow IAT Std', ' Flow IAT Max', ' Flow IAT Min',\n",
|
764 |
+
" 'Fwd IAT Total', ' Fwd IAT Mean', ' Fwd IAT Std', ' Fwd IAT Max',\n",
|
765 |
+
" ' Fwd IAT Min', 'Bwd IAT Total', ' Bwd IAT Mean', ' Bwd IAT Std',\n",
|
766 |
+
" ' Bwd IAT Max', ' Bwd IAT Min', 'Fwd PSH Flags', ' Fwd Header Length',\n",
|
767 |
+
" ' Bwd Header Length', 'Fwd Packets/s', ' Bwd Packets/s',\n",
|
768 |
+
" ' Min Packet Length', ' Max Packet Length', ' Packet Length Mean',\n",
|
769 |
+
" ' Packet Length Std', ' Packet Length Variance', 'FIN Flag Count',\n",
|
770 |
+
" ' SYN Flag Count', ' PSH Flag Count', ' ACK Flag Count',\n",
|
771 |
+
" ' URG Flag Count', ' Down/Up Ratio', ' Average Packet Size',\n",
|
772 |
+
" ' Avg Fwd Segment Size', ' Avg Bwd Segment Size',\n",
|
773 |
+
" ' Fwd Header Length.1', 'Subflow Fwd Packets', ' Subflow Fwd Bytes',\n",
|
774 |
+
" ' Subflow Bwd Packets', ' Subflow Bwd Bytes', 'Init_Win_bytes_forward',\n",
|
775 |
+
" ' Init_Win_bytes_backward', ' act_data_pkt_fwd',\n",
|
776 |
+
" ' min_seg_size_forward', 'Active Mean', ' Active Std', ' Active Max',\n",
|
777 |
+
" ' Active Min', 'Idle Mean', ' Idle Std', ' Idle Max', ' Idle Min',\n",
|
778 |
+
" ' Label'],\n",
|
779 |
+
" dtype='object')"
|
780 |
+
]
|
781 |
+
},
|
782 |
+
"execution_count": 7,
|
783 |
+
"metadata": {},
|
784 |
+
"output_type": "execute_result"
|
785 |
+
}
|
786 |
+
],
|
787 |
+
"source": [
|
788 |
+
"df.columns"
|
789 |
+
]
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"cell_type": "markdown",
|
793 |
+
"metadata": {},
|
794 |
+
"source": [
|
795 |
+
"## Data Preprocessing"
|
796 |
+
]
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"cell_type": "code",
|
800 |
+
"execution_count": 8,
|
801 |
+
"metadata": {},
|
802 |
+
"outputs": [
|
803 |
+
{
|
804 |
+
"name": "stdout",
|
805 |
+
"output_type": "stream",
|
806 |
+
"text": [
|
807 |
+
"X_train_shape: (2262296, 5, 66), Y_train_shape: (2262296,), X_test_shape:(565575, 5, 66), Y_test_shape: (565575,)\n"
|
808 |
+
]
|
809 |
+
}
|
810 |
+
],
|
811 |
+
"source": [
|
812 |
+
"import numpy as np\n",
|
813 |
+
"from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
|
814 |
+
"from sklearn.model_selection import train_test_split\n",
|
815 |
+
"\n",
|
816 |
+
"# Filling missing numerical values with median\n",
|
817 |
+
"df.dropna()\n",
|
818 |
+
"\n",
|
819 |
+
"\n",
|
820 |
+
"# Encoding labels using LabelEncoder for classification\n",
|
821 |
+
"label_encoder = LabelEncoder()\n",
|
822 |
+
"df['Label'] = label_encoder.fit_transform(df[' Label'])\n",
|
823 |
+
"\n",
|
824 |
+
"# Dropping irrelevant columns\n",
|
825 |
+
"df.drop(columns=[' Label'], inplace=True)\n",
|
826 |
+
"\n",
|
827 |
+
"\n",
|
828 |
+
"# Seperating features and target\n",
|
829 |
+
"X = df.drop(columns=['Label']).values\n",
|
830 |
+
"Y = df['Label'].values\n",
|
831 |
+
"\n",
|
832 |
+
"\n",
|
833 |
+
"# Normalize feature set using StandardScaler\n",
|
834 |
+
"scaler=StandardScaler()\n",
|
835 |
+
"X=scaler.fit_transform(X)\n",
|
836 |
+
"\n",
|
837 |
+
"# Preparing sequences for LSTM\n",
|
838 |
+
"def create_sequences(X, Y, time_steps=5):\n",
|
839 |
+
" Xs, Ys = [],[]\n",
|
840 |
+
" for i in range(len(X) - time_steps):\n",
|
841 |
+
" Xs.append(X[i:i + time_steps])\n",
|
842 |
+
" Ys.append(Y[i+time_steps])\n",
|
843 |
+
" return np.array(Xs), np.array(Ys)\n",
|
844 |
+
"\n",
|
845 |
+
"time_steps = 5\n",
|
846 |
+
"X_seq, Y_seq = create_sequences(X,Y, time_steps)\n",
|
847 |
+
"\n",
|
848 |
+
"# Splitting data into training and testing sets\n",
|
849 |
+
"X_train, X_test, Y_train, Y_test = train_test_split(X_seq, Y_seq, test_size=0.2, random_state=42)\n",
|
850 |
+
"\n",
|
851 |
+
"# Printing\n",
|
852 |
+
"print(f'X_train_shape: {X_train.shape}, Y_train_shape: {Y_train.shape}, X_test_shape:{X_test.shape}, Y_test_shape: {Y_test.shape}')"
|
853 |
+
]
|
854 |
+
},
|
855 |
+
{
|
856 |
+
"cell_type": "markdown",
|
857 |
+
"metadata": {},
|
858 |
+
"source": [
|
859 |
+
"## Model Building"
|
860 |
+
]
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"cell_type": "code",
|
864 |
+
"execution_count": 20,
|
865 |
+
"metadata": {},
|
866 |
+
"outputs": [
|
867 |
+
{
|
868 |
+
"name": "stdout",
|
869 |
+
"output_type": "stream",
|
870 |
+
"text": [
|
871 |
+
"Epoch 1/20\n",
|
872 |
+
"28279/28279 [==============================] - 108s 4ms/step - loss: 0.1723 - accuracy: 0.9611 - val_loss: 0.1224 - val_accuracy: 0.9714\n",
|
873 |
+
"Epoch 2/20\n",
|
874 |
+
"28279/28279 [==============================] - 109s 4ms/step - loss: 0.1266 - accuracy: 0.9708 - val_loss: 0.1142 - val_accuracy: 0.9729\n",
|
875 |
+
"Epoch 3/20\n",
|
876 |
+
"28279/28279 [==============================] - 109s 4ms/step - loss: 0.1203 - accuracy: 0.9726 - val_loss: 0.1101 - val_accuracy: 0.9752\n",
|
877 |
+
"Epoch 4/20\n",
|
878 |
+
"28279/28279 [==============================] - 95s 3ms/step - loss: 0.1164 - accuracy: 0.9736 - val_loss: 0.1076 - val_accuracy: 0.9760\n",
|
879 |
+
"Epoch 5/20\n",
|
880 |
+
"28279/28279 [==============================] - 103s 4ms/step - loss: 0.1141 - accuracy: 0.9744 - val_loss: 0.1062 - val_accuracy: 0.9762\n",
|
881 |
+
"Epoch 6/20\n",
|
882 |
+
"28279/28279 [==============================] - 112s 4ms/step - loss: 0.1124 - accuracy: 0.9748 - val_loss: 0.1049 - val_accuracy: 0.9765\n",
|
883 |
+
"Epoch 7/20\n",
|
884 |
+
"28279/28279 [==============================] - 126s 4ms/step - loss: 0.1108 - accuracy: 0.9754 - val_loss: 0.1038 - val_accuracy: 0.9773\n",
|
885 |
+
"Epoch 8/20\n",
|
886 |
+
"28279/28279 [==============================] - 128s 5ms/step - loss: 0.1092 - accuracy: 0.9760 - val_loss: 0.1024 - val_accuracy: 0.9781\n",
|
887 |
+
"Epoch 9/20\n",
|
888 |
+
"28279/28279 [==============================] - 123s 4ms/step - loss: 0.1077 - accuracy: 0.9769 - val_loss: 0.1000 - val_accuracy: 0.9789\n",
|
889 |
+
"Epoch 10/20\n",
|
890 |
+
"28279/28279 [==============================] - 131s 5ms/step - loss: 0.1055 - accuracy: 0.9781 - val_loss: 0.0983 - val_accuracy: 0.9800\n",
|
891 |
+
"Epoch 11/20\n",
|
892 |
+
"28279/28279 [==============================] - 131s 5ms/step - loss: 0.1042 - accuracy: 0.9788 - val_loss: 0.0962 - val_accuracy: 0.9814\n",
|
893 |
+
"Epoch 12/20\n",
|
894 |
+
"28279/28279 [==============================] - 115s 4ms/step - loss: 0.1020 - accuracy: 0.9798 - val_loss: 0.0937 - val_accuracy: 0.9821\n",
|
895 |
+
"Epoch 13/20\n",
|
896 |
+
"28279/28279 [==============================] - 123s 4ms/step - loss: 0.1010 - accuracy: 0.9800 - val_loss: 0.0944 - val_accuracy: 0.9815\n",
|
897 |
+
"Epoch 14/20\n",
|
898 |
+
"28279/28279 [==============================] - 128s 5ms/step - loss: 0.1009 - accuracy: 0.9799 - val_loss: 0.0961 - val_accuracy: 0.9809\n",
|
899 |
+
"Epoch 15/20\n",
|
900 |
+
"28279/28279 [==============================] - 131s 5ms/step - loss: 0.1021 - accuracy: 0.9792 - val_loss: 0.0951 - val_accuracy: 0.9813\n",
|
901 |
+
"Epoch 16/20\n",
|
902 |
+
"28279/28279 [==============================] - 110s 4ms/step - loss: 0.1002 - accuracy: 0.9801 - val_loss: 0.0928 - val_accuracy: 0.9826\n",
|
903 |
+
"Epoch 17/20\n",
|
904 |
+
"28279/28279 [==============================] - 118s 4ms/step - loss: 0.0992 - accuracy: 0.9804 - val_loss: 0.0909 - val_accuracy: 0.9826\n",
|
905 |
+
"Epoch 18/20\n",
|
906 |
+
"28279/28279 [==============================] - 116s 4ms/step - loss: 0.0980 - accuracy: 0.9808 - val_loss: 0.0907 - val_accuracy: 0.9827\n",
|
907 |
+
"Epoch 19/20\n",
|
908 |
+
"28279/28279 [==============================] - 112s 4ms/step - loss: 0.0975 - accuracy: 0.9808 - val_loss: 0.0910 - val_accuracy: 0.9828\n",
|
909 |
+
"Epoch 20/20\n",
|
910 |
+
"28279/28279 [==============================] - 140s 5ms/step - loss: 0.0980 - accuracy: 0.9804 - val_loss: 0.0898 - val_accuracy: 0.9827\n",
|
911 |
+
"17675/17675 [==============================] - 34s 2ms/step - loss: 0.9803 - accuracy: 0.9270\n",
|
912 |
+
"Test Loss : 0.9802790284156799, Test Accuracy: 0.9269522428512573\n"
|
913 |
+
]
|
914 |
+
}
|
915 |
+
],
|
916 |
+
"source": [
|
917 |
+
"from tensorflow.keras.models import Sequential\n",
|
918 |
+
"from tensorflow.keras.layers import Conv1D, MaxPooling1D, LSTM, Dropout, Dense\n",
|
919 |
+
"from tensorflow.keras.optimizers import Adam\n",
|
920 |
+
"from tensorflow.keras.utils import to_categorical\n",
|
921 |
+
"import tensorflow as tf\n",
|
922 |
+
"\n",
|
923 |
+
"Y_train = to_categorical(Y_train, num_classes=15)\n",
|
924 |
+
"Y_test = to_categorical(Y_test, num_classes=15)\n",
|
925 |
+
"\n",
|
926 |
+
"\n",
|
927 |
+
"model=Sequential() \n",
|
928 |
+
"\n",
|
929 |
+
"# CNN Layer\n",
|
930 |
+
"model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(X_train.shape[1], X_train.shape[2])))\n",
|
931 |
+
"model.add(MaxPooling1D(pool_size=2))\n",
|
932 |
+
"model.add(Dropout(0.3))\n",
|
933 |
+
"\n",
|
934 |
+
"# LSTM Layer\n",
|
935 |
+
"model.add(LSTM(100, return_sequences=False))\n",
|
936 |
+
"model.add(Dropout(0.3))\n",
|
937 |
+
"model.add(Dense(15, activation='sigmoid'))\n",
|
938 |
+
"\n",
|
939 |
+
"model.compile(optimizer=Adam(learning_rate=1e-4), loss='categorical_crossentropy', metrics=['accuracy'])\n",
|
940 |
+
"\n",
|
941 |
+
"history=model.fit(X_train,Y_train, epochs=20, batch_size=64, validation_split=0.2)\n",
|
942 |
+
"\n",
|
943 |
+
"loss,accuracy = model.evaluate(X_test, Y_test)\n",
|
944 |
+
"print(f'Test Loss : {loss}, Test Accuracy: {accuracy}')"
|
945 |
+
]
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"cell_type": "code",
|
949 |
+
"execution_count": 21,
|
950 |
+
"metadata": {},
|
951 |
+
"outputs": [],
|
952 |
+
"source": [
|
953 |
+
"model.save('GuardShield_CNNLSTM_v1.h5')"
|
954 |
+
]
|
955 |
+
}
|
956 |
+
],
|
957 |
+
"metadata": {
|
958 |
+
"kernelspec": {
|
959 |
+
"display_name": "base",
|
960 |
+
"language": "python",
|
961 |
+
"name": "python3"
|
962 |
+
},
|
963 |
+
"language_info": {
|
964 |
+
"codemirror_mode": {
|
965 |
+
"name": "ipython",
|
966 |
+
"version": 3
|
967 |
+
},
|
968 |
+
"file_extension": ".py",
|
969 |
+
"mimetype": "text/x-python",
|
970 |
+
"name": "python",
|
971 |
+
"nbconvert_exporter": "python",
|
972 |
+
"pygments_lexer": "ipython3",
|
973 |
+
"version": "3.10.13"
|
974 |
+
}
|
975 |
+
},
|
976 |
+
"nbformat": 4,
|
977 |
+
"nbformat_minor": 2
|
978 |
+
}
|